Search

Purpose: To identify the key risk factors for venous thromboembolism (VTE) in urological inpatients based on the Caprini scale using an interpretable machine learning method. Methods: VTE risk data of urological inpatients were obtained based on the Caprini scale in the case hospital. Based on the data, the Boruta method was used to further select the key variables from the 37 variables in the Caprini scale. Furthermore, decision rules corresponding to each risk level were generated using the rough set (RS) method. Finally, random forest (RF), support vector machine (SVM), and backpropagation artificial neural network (BPANN) were used to verify the data accuracy and were compared with the RS method. Results: Following the screening, the key risk factors for VTE in urology were "(C1) Age," "(C2) Minor Surgery planned," "(C3) Obesity (BMI > 25)," "(C8) Varicose veins," "(C9) Sepsis (< 1 month)," (C10) "Serious lung disease incl. pneumonia (< 1month) " (C11) COPD," "(C16) Other risk," "(C18) Major surgery (> 45 min)," "(C19) Laparoscopic surgery (> 45 min)," "(C20) Patient confined to bed (> 72 h)," "(C18) Malignancy (present or previous)," "(C23) Central venous access," "(C31) History of DVT/PE," "(C32) Other congenital or acquired thrombophilia," and "(C34) Stroke (< 1 month." According to the decision rules of different risk levels obtained using the RS method, "(C1) Age," "(C18) Major surgery (> 45 minutes)," and "(C21) Malignancy (present or previous)" were the main factors influencing mid- and high-risk levels, and some suggestions on VTE prevention were indicated based on these three factors. The average accuracies of the RS, RF, SVM, and BPANN models were 79.5%, 87.9%, 92.6%, and 97.2%, respectively. In addition, BPANN had the highest accuracy, recall, F1-score, and precision. Conclusions: The RS model achieved poorer accuracy than the other three common machine learning models. However, the RS model provides strong interpretability and allows for the identification of high-risk factors and decision rules influencing high-risk assessments of VTE in urology. This transparency is very important for clinicians in the risk assessment process. [ABSTRACT FROM AUTHOR]

Horizontal principal stress is a fundamental parameter for reservoir reconstruction. For improving single well productivity, accurate evaluation of reservoir stress characteristics is of great importance. One of the main challenges in predicting the magnitude of the in situ stress is how to obtain the rock mechanical parameters accurately. An intelligent fusion model was proposed to predict rock mechanical parameters to address the issue that traditional approaches are not very reliable at predicting the rock mechanical parameters of complex lithology reservoirs, using transitional shale reservoir rocks as the research object. Machine learning algorithms such as nearest neighbor regression, support vector machine, and random forest were selected to construct intelligent fusion models of different rock mechanics parameters based on the laboratory test data. Finally, the logging profile of transitional shale reservoir horizontal principal stress in the study area was obtained under the constraints of the empirical physical model and measured in situ stress data. The results showed that the fusion models outperformed the single model on rock mechanics parameters and had higher accuracy in both training and test sets, meeting the engineering requirements for predicting the horizontal principal stress in the study area. [ABSTRACT FROM AUTHOR]

Background: Nosocomial infections with heavy disease burden are becoming a major threat to the health care system around the world. Through long-term, systematic, continuous data collection and analysis, Nosocomial infection surveillance (NIS) systems are constructed in each hospital; while these data are only used as real-time surveillance but fail to realize the prediction and early warning function. Study is to screen effective predictors from the routine NIS data, through integrating the multiple risk factors and Machine learning (ML) methods, and eventually realize the trend prediction and risk threshold of Incidence of Nosocomial infection (INI). Methods: We selected two representative hospitals in southern and northern China, and collected NIS data from 2014 to 2021. Thirty-nine factors including hospital operation volume, nosocomial infection, antibacterial drug use and outdoor temperature data, etc. Five ML methods were used to fit the INI prediction model respectively, and to evaluate and compare their performance. Results: Compared with other models, Random Forest showed the best performance (5-fold AUC = 0.983) in both hospitals, followed by Support Vector Machine. Among all the factors, 12 indicators were significantly different between high-risk and low-risk groups for INI (P < 0.05). After screening the effective predictors through importance analysis, prediction model of the time trend was successfully constructed (R2 = 0.473 and 0.780, BIC = -1.537 and -0.731). Conclusions: The number of surgeries, antibiotics use density, critical disease rate and unreasonable prescription rate and other key indicators could be fitted to be the threshold predictions of INI and quantitative early warning. [ABSTRACT FROM AUTHOR]

A timely and accurately predicted grain yield can ensure regional and global food security. The scientific community is gradually advancing the prediction of regional-scale maize yield. However, the combination of various datasets while predicting the regional-scale maize yield using simple and accurate methods is still relatively rare. Here, we have used multi-source datasets (climate dataset, satellite dataset, and soil dataset), lasso algorithm, and machine learning methods (random forest, support vector, extreme gradient boosting, BP neural network, long short-term memory network, and K-nearest neighbor regression) to predict China's county-level maize yield. The use of multi-sourced datasets advanced the predicting accuracy of maize yield significantly compared to the single-sourced dataset. We found that the machine learning methods were superior to the lasso algorithm, while random forest, extreme gradient boosting, and support vector machine represented the most preferable methods for maize yield prediction in China (R2 ≥ 0.75, RMSE = 824–875 kg/ha, MAE = 626–651 kg/ha). The climate dataset contributed more to the prediction of maize yield, while the satellite dataset contributed to tracking the maize growth process. However, the methods' accuracies and the dominant variables affecting maize growth varied with agricultural regions across different geographic locations. Our research serves as an important effort to examine the feasibility of multi-source datasets and machine learning techniques for regional-scale maize yield prediction. In addition, the methodology we have proposed here provides guidance for reliable yield prediction of different crops. [ABSTRACT FROM AUTHOR]

Machine learning models are widely used for landslide susceptibility prediction (LSP). To better develop a landslide susceptibility prediction model for the Loess Plateau, this study compared different machine-learning models (Logistic regression (LR), support vector machines (SVM), random forests (RF), Naïve Bayes (NB), and multilayer perceptron (MLP)). Using Xunyi County, China as the study area, 1096 landslides were collected and divided into a training set (70%) and a test set (30%). Significant influencing factors were selected from 20 landslide factors using GeoDetector. The relationships between these factors and landslides were determined by normalized frequency ratios. Five trained machine learning models calculated landslide susceptibility indices and generated landslide susceptibility maps. Additionally, the accuracy (ACC), precision (PRE), recall (REC), F1 score, AUC values, LSI distribution characteristics, and overlay analysis of historical landslides with LSM were used to evaluate the performance of the models. The results show that the LSP results of the five models are generally reasonable. The results further indicated that the use of GeoDetector was able to filter out the main factors of eolian landslides, improving the predictive performance of the model and obtaining better LSMs. The RF model had the best overall performance, followed by the SVM, and the MLP model created LSM high susceptibility zones that could contain the highest number of historical landslides. The q-values of factor contributions indicate that elevation, NDVI, rainfall, POI kernel density, and RDLS are the main factors controlling landslides, which need to be paid attention to for landslide control in the Loess Plateau region. The results of this study can provide a reference for the follow-up study of landslide prevention and control, especially landslide susceptibility modeling in the Loess Plateau. [ABSTRACT FROM AUTHOR]

Objectives: We aim to develop a deep learning model based on a convolutional neural network (CNN) combined with a classification algorithm (CA) to assist dentists in quickly and accurately diagnosing the stage of periodontitis. Materials and methods: Periapical radiographs (PERs) and clinical data were collected. The CNNs including Alexnet, VGG16, and ResNet18 were trained on PER to establish the PER-CNN models for no periodontal bone loss (PBL) and PBL. The CAs including random forest (RF), support vector machine (SVM), naive Bayes (NB), logistic regression (LR), and k-nearest neighbor (KNN) were added to the PER-CNN model for control, stage I, stage II and stage III/IV periodontitis. Heat map was produced using a gradient-weighted class activation mapping method to visualize the regions of interest of the PER-Alexnet model. Clustering analysis was performed based on the ten PER-CNN scores and the clinical characteristics. Results: The accuracy of the PER-Alexnet and PER-VGG16 models with the higher performance was 0.872 and 0.853, respectively. The accuracy of the PER-Alexnet + RF model with the highest performance for control, stage I, stage II and stage III/IV was 0.968, 0.960, 0.835 and 0.842, respectively. Heat map showed that the regions of interest predicted by the model were periodontitis bone lesions. We found that age and smoking were significantly related to periodontitis based on the PER-Alexnet scores. Conclusion: The PER-Alexnet + RF model has reached high performance for whole-case periodontal diagnosis. The CNN models combined with CA can assist dentists in quickly and accurately diagnosing the stage of periodontitis. [ABSTRACT FROM AUTHOR]

Landslides are widely distributed mountainous geological hazards that threaten economic development and people's daily lives. Interferometric synthetic aperture radar (InSAR) with comprehensive coverage and high‐precision ground displacement monitoring abilities are frequently utilized for regional‐scale active slope detection. Moreover, InSAR measurements that characterize ground dynamics are integrated with conventional topographic, hydrological, and geological landslide conditioning factors (LCFs) for landslide susceptibility mapping (LSM). Weining County in southwest China, with complex geological conditions, steep terrain, and frequent tectonic activities, is prone to catastrophic landslide failures. In this study, we refined the landslide inventory of Weining County using one ascending and one descending Sentinel‐1 dataset acquired during 2015–2021 through a small baseline subset InSAR (SBAS InSAR) analysis. We then combine the LOS measurements from both datasets using multidimensional SBAS to obtain time series two‐dimensional (2D) displacements to characterize the kinematics of active slopes. Hot spot and cluster analysis (HCA) was carried out on 2D displacement rate maps to highlight clustered deformed areas and suppress noisy signals that occurred on single pixels. Two hundred fifty‐eight landslides (including 71 active identified in this study) are used to construct 76,412 positive samples for LSM. In our study, the HCA maps, instead of the 2D displacement maps, are integrated with conventional LCFs to form an LCF_HCA set to feed support vector machine (SVM), Random Forest (RF), extreme Gradient Boosting (XGBoost) and Light Gradient‐Boosting Machine (LightGBM) models. A conventional LCF (LCF_CON) set and an integrated 2D displacement maps (LCF_2D) set have also been adapted for comparison. The performance of the tree‐based ensemble methods distinctly outperforms the SVM model. In the meantime, models' performances using the LCF_HCA set are superior to that of the other 2 LCF sets from all evaluation metrics. The ranks of HCA maps increased compared with 2D displacement maps from feature importance analysis, which might lead to the better performance of models using the LCF_HCA set. With the continuous accumulation of SAR images, ground dynamic characteristics from InSAR can offer us opportunities to understand landslide kinematics and enhance LSM. [ABSTRACT FROM AUTHOR]

Background: Traditional Chinese Medicine (TCM) defines constitutions which are relevant to corresponding diseases among people. As one of the common constitutions, Yin-deficiency constitution influences a number of Chinese population in the disease onset. Therefore, accurate Yin-deficiency constitution identification is significant for disease prevention and treatment. Methods: In this study, we collected participants with Yin-deficiency constitution and balanced constitution, separately. The least absolute shrinkage and selection operator (LASSO) and logistic regression were used to analyze genetic predictors. Four machine learning models for Yin-deficiency constitution classification with multiple combined genetic indicators were integrated to analyze and identify the optimal model and features. The Shapley Additive exPlanations (SHAP) interpretation was developed for model explanation. Results: The results showed that, NFKBIA, BCL2A1 and CCL4 were the most associated genetic indicators with Yin-deficiency constitution. Random forest with three genetic predictors including NFKBIA, BCL2A1 and CCL4 was the optimal model, area under curve (AUC): 0.937 (95% CI 0.844–1.000), sensitivity: 0.870, specificity: 0.900. The SHAP method provided an intuitive explanation of risk leading to individual predictions. Conclusion: We constructed a Yin-deficiency constitution classification model based on machine learning and explained it with the SHAP method, providing an objective Yin-deficiency constitution identification system in TCM and the guidance for clinicians. [ABSTRACT FROM AUTHOR]

Obtaining accurate and real-time spatial distribution information regarding crops is critical for enabling effective smart agricultural management. In this study, innovative decision fusion strategies, including Enhanced Overall Accuracy Index (E-OAI) voting and the Overall Accuracy Index-based Majority Voting (OAI-MV), were introduced to optimize the use of diverse remote sensing data and various classifiers, thereby improving the accuracy of crop/vegetation identification. These strategies were utilized to integrate crop/vegetation classification outcomes from distinct feature sets (including Gaofen-6 reflectance, Sentinel-2 time series of vegetation indices, Sentinel-2 time series of biophysical variables, Sentinel-1 time series of backscatter coefficients, and their combinations) using distinct classifiers (Random Forests (RFs), Support Vector Machines (SVMs), Maximum Likelihood (ML), and U-Net), taking two grain-producing areas (Site #1 and Site #2) in Haixi Prefecture, Qinghai Province, China, as the research area. The results indicate that employing U-Net on feature-combined sets yielded the highest overall accuracy (OA) of 81.23% and 91.49% for Site #1 and Site #2, respectively, in the single classifier experiments. The E-OAI strategy, compared to the original OAI strategy, boosted the OA by 0.17% to 6.28%. Furthermore, the OAI-MV strategy achieved the highest OA of 86.02% and 95.67% for the respective study sites. This study highlights the distinct strengths of various remote sensing features and classifiers in discerning different crop and vegetation types. Additionally, the proposed OAI-MV and E-OAI strategies effectively harness the benefits of diverse classifiers and multisource remote sensing features, significantly enhancing the accuracy of crop/vegetation classification. [ABSTRACT FROM AUTHOR]

Machine learning (ML) is increasingly utilized in Landslide Susceptibility Mapping (LSM), though challenges remain in interpreting the predictions of ML models. To reveal the response relationship between landslide susceptibility and evaluation factors, an interpretability model was constructed to analyze how the results of the ML model are realized. This study focuses on Zhenba County in Shaanxi Province, China, employing both Random Forest (RF) and Support Vector Machine (SVM) to develop LSM models optimized through Random Search (RS). To enhance interpretability, the study incorporates techniques such as Partial Dependence Plot (PDP), Local Interpretable Model-Agnostic Explanations (LIMEs), and Shapley Additive Explanations (SHAP). The RS-optimized RF model demonstrated superior performance, achieving an Area Under the Curve (AUC) of 0.965. The interpretability model identified the NDVI and distance from road as important factors influencing landslides occurrence. NDVI plays a positive role in the occurrence of landslides in this region, and the landslide-prone areas are within 500 m from the road. These analyses indicate the importance of improved hyperparameter selection in enhancing model accuracy and performance. The interpretability model provides valuable insights into LSM, facilitating a deeper understanding of landslide formation mechanisms and guiding the formulation of effective prevention and control strategies. [ABSTRACT FROM AUTHOR]

Southern China, one of the traditional rice production bases, has experienced significant declines in the area of rice paddy since the beginning of this century. Monitoring the rice cropping area is becoming an urgent need for food security policy decisions. One of the main challenges for mapping rice in this area is the quantity of cloud-free observations that are vulnerable to frequent cloud cover. Another relevant issue that needs to be addressed is determining how to select the appropriate classifier for mapping paddy rice based on the cloud-masked observations. Therefore, this study was organized to quickly find a strategy for rice mapping by evaluating cloud-mask algorithms and machine-learning methods for Sentinel-2 imagery. Specifically, we compared four GEE-embedded cloud-mask algorithms (QA60, S2cloudless, CloudScore, and CDI (Cloud Displacement Index)) and analyzed the appropriateness of widely accepted machine-learning classifiers (random forest, support vector machine, classification and regression tree, gradient tree boost) for cloud-masked imagery. The S2cloudless algorithm had a clear edge over the other three algorithms based on its overall accuracy in evaluation and visual inspection. The findings showed that the algorithm with a combination of S2cloudless and random forest showed the best performance when comparing mapping results with field survey data, referenced rice maps, and statistical yearbooks. In general, the research highlighted the potential of using Sentinel-2 imagery to map paddy rice with multiple combinations of cloud-mask algorithms and machine-learning methods in a cloud-prone area, which has the potential to broaden our rice mapping strategies. [ABSTRACT FROM AUTHOR]

Purpose: Immunohistochemistry (IHC) is the main method to detect human epidermal growth factor receptor 2 (HER2) expression levels. However, IHC is invasive and cannot reflect HER2 expression status in real time. The aim of this study was to construct and verify three types of radiomics models based on 18F-fuorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) imaging and to evaluate the predictive ability of these radiomics models for the expression status of HER2 in patients with gastric cancer (GC). Patients and Methods: A total of 118 patients with GC were enrolled in this study. 18F-FDG PET/CT imaging was performed prior to surgery. The LIFEx software package was applied to extract PET and CT radiomics features. The minimum absolute contraction and selection operator (least absolute shrinkage and selection operator [LASSO]) algorithm was used to select the best radiomics features. Three machine learning methods, logistic regression (LR), support vector machine (SVM), and random forest (RF) models, were constructed and verified. The Synthetic Minority Oversampling Technique (SMOTE) was applied to address data imbalance. Results: In the training and test sets, the area under the curve (AUC) values of the LR, SVM, and RF models were 0.809, 0.761, 0.861 and 0.628, 0.993, 0.717, respectively, and the Brier scores were 0.118, 0.214, and 0.143, respectively. Among the three models, the LR and RF models exhibited extremely good prediction performance. The AUC values of the three models significantly improved after SMOTE balanced the data. Conclusions:18F-FDG PET/CT-based radiomics models, especially LR and RF models, demonstrate good performance in predicting HER2 expression status in patients with GC and can be used to preselect patients who may benefit from HER2-targeted therapy. [ABSTRACT FROM AUTHOR]

The primary aim of this study is to explore the utility of machine learning algorithms for predicting personal PM2.5 exposures of elderly participants and to evaluate the effect of individual variables on model performance. Personal PM2.5 was measured on five consecutive days across seasons in 66 retired adults in Beijing (BJ) and Nanjing (NJ), China. The potential predictors were extracted from routine monitoring data (ambient PM2.5 concentrations and meteorological factors), basic questionnaires (personal and household characteristics), and time-activity diary (TAD). Prediction models were developed based on either traditional multiple linear regression (MLR) or five advanced machine learning methods. Our results revealed that personal PM2.5 exposures were well predicted by both MLR and machine learning models with predictors extracted from routine monitoring data, which was indicated by the high nested cross-validation (CV) R 2 ranging from 0.76 to 0.88. The addition of predictors from either the questionnaire or TAD did not improve predictive accuracy for all algorithms. The ambient PM2.5 concentrations were the most important predictor. Overall, the random forest, support vector machine, and extreme gradient boosting algorithms outperformed the reference MLR method. Compared with the traditional MLR approach, the CV R 2 of the RF model increased up to 7% (from 0.82 ± 0.13 to 0.88 ± 0.10), while the RMSE reduced up to 18% (from 19.8 ± 5.4 to 16.3 ± 4.5) in BJ. [ABSTRACT FROM AUTHOR]

Quickly and accurately obtaining information on rice planting areas is crucial for maintaining food security and social stability. Based on the time series of Sentinel-1A images, this study proposes an automatic rice mapping method called the Dynamic Threshold Time-Weighted Dynamic Time Warping method (DT-TWDTW). This method consists of two parts. First, rice samples are extracted automatically by a dynamic threshold method based on the unique flooding signal before and after rice transplanting. Then, the Time-Weighted Dynamic Time Warping (TWDTW) method is used for rice mapping based on the cumulative cost matrix between unknown pixels and rice samples. The results show that the DT-TWDTW method can achieve satisfactory mapping accuracy with an overall accuracy of 94.6%, higher than random forest (89.9%), and support vector machine (91.7%). This study provides a new approach and perspective for remote sensing monitoring of rice, especially for some regions without prior phenological knowledge and collection of the rice samples. [ABSTRACT FROM AUTHOR]

Rockburst is a frequent challenge during tunnel and other underground construction and is an extreme rock damage phenomenon. Therefore, it is very crucial to accurately estimate the damage potential of rockburst events. Microseismic (MS) monitoring can be used to obtain the relevant MS parameters for short-term rockburst prediction in real time that reflect the evolution of short-term rockburst. In this study, short-term rockburst potential data containing 7 MS parameters (cumulative number of events, cumulative released energy, cumulative apparent volume, event rate, energy rate, apparent volume rate, and incubation time) and 91 rockburst events (none rockburst, low rockburst, moderate rockburst, and high rockburst) were collected from the Jinping Hydropower Station diversion tunnel project in China. The objective of this paper is to propose an ensemble learning (EML) model based on the LévyFlight-Jaya optimization (LFJaya) and fivefold cross-validation (CV) method to achieve an accurate prediction of short-term rockburst damage potential using MS information. The EML consists of light gradient boosting machine (LGBM), extreme gradient boosting (XGBoost), random forest (RF), support vector machine (SVM), and logistic regression (LR), with seven MS parameters as the EML inputs and four rockburst levels as target variables. 70% and 30% of the cases were randomly selected for training and testing, respectively. Five metrics (accuracy, kappa, precision, recall, and F1-score) and nonparametric statistical tests were used to evaluate the performance of the model. It can be observed from the results of this study that the proposed EML has a higher test accuracy (89.29%) than the multiple base classifiers used in the study. With the use of the ensemble model, the decision boundary becomes more precise and overfitting is significantly improved. Additionally, the internal decision-making process of EML was elucidated through an analysis of the model parameters using SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME). It was discovered that the cumulative released energy, the number of MS events, and the cumulative apparent volume (which reflects the number and strength of rock fractures) exert a significant influence on the prediction of short-term rockburst potential. Finally, developed graphical user interface (GUI) accurately predicted six instances of rockburst in the deeply buried tunnel of Jinping. Verification results indicated that the proposed EML exhibits strong generalization and can effectively utilize MS information to achieve precise short-term rockburst potential predictions. [ABSTRACT FROM AUTHOR]

Background: Poverty contributes to the transmission of schistosomiasis via multiple pathways, with the insufficiency of appropriate interventions being a crucial factor. The aim of this article is to provide more economical and feasible intervention measures for endemic areas with varying levels of poverty. Methods: We collected and analyzed the prevalence patterns along with the cost of control measures in 11 counties over the last 20 years in China. Seven machine learning models, including XGBoost, support vector machine, generalized linear model, regression tree, random forest, gradient boosting machine and neural network, were used for developing model and calculate marginal benefits. Results: The XGBoost model had the highest prediction accuracy with an R2 of 0.7308. Results showed that risk surveillance, snail control with molluscicides and treatment were the most effective interventions in controlling schistosomiasis prevalence. The best combination of interventions was interlacing seven interventions, including risk surveillance, treatment, toilet construction, health education, snail control with molluscicides, cattle slaughter and animal chemotherapy. The marginal benefit of risk surveillance is the most effective intervention among nine interventions, which was influenced by the prevalence of schistosomiasis and cost. Conclusions: In the elimination phase of the national schistosomiasis program, emphasizing risk surveillance holds significant importance in terms of cost-saving. [ABSTRACT FROM AUTHOR]

Accurate delineation of debris-flow-endangered areas (e.g., the maximum runout distance) is a necessary prerequisite for the debris-flow risk assessment and countermeasures design. Recently, machine-learning models have been proved to be an effective tool in predicting debris-flow parameters. However, existing machine-learning models are generally developed based on a very limited number of observation data, which may result in the predictive model overfitting or underfitting. How to develop a robust model for accurate forecasting of debris-flow-endangered areas still remains a difficult task. This paper proposes a hybrid method for predicting debris-flow hazard zone by integrating machine-learning algorithms and an empirical regression model. The proposed method takes the calculated maximum runout distance obtained from the empirical model as supplementary inputs to increase the amount of training data to construct hybrid machine-learning models. Three commonly used machine-learning models (i.e., multivariate adaptive regression splines (MARS), random forest (RF), and support vector machine (SVM)) are developed based on the training datasets of a specific debris basin. Then, these three machine-learning models are combined with an empirical relationship developed using the same training datasets to generate corresponding hybrid models. Finally, the performance metrics (i.e., coefficient of determination (R2), root-mean-square error (RMSE), and mean absolute error (MAE)) of the proposed hybrid models are comprehensively investigated and compared with the single predictive model (i.e., MARS, RF, SVM, and the empirical model) under fivefold cross-validation. The proposed method is illustrated using 134 channelized debris-flow events in Sichuan province, China. Results show that compared with the three individual machine-learning models, hybridization of machine-learning algorithms and the empirical model results in R2, RMSE, and MAE improved by 70.5%, 32.9%, and 41.1%, respectively. In contrast to the empirical model, the R2, RMSE, and MAE value of the proposed hybrid models are improved by 29.6%, 22.3%, and 32.5%, respectively. The proposed hybrid models generally perform better than the single machine-learning and the empirical model, providing a promising tool for accurate forecasting of a debris-flow-endangered area. [ABSTRACT FROM AUTHOR]

Wildfire has extensive and profound impacts on forest structure and function. Therefore, it is important to study the spatial and temporal patterns of forest fire regimes and their drivers in order to better understand the feedbacks between climate change, fire disturbance, and forest ecosystems. Based on the Global Fire Atlas dataset, three forest fire regime components (fire occurrence density, burned rate, and median fire size) were extracted for China from 2003 to 2016. Three statistical models (Boosted Regression Tree, Random Forest, and Support Vector Machine) were used to systematically analyze the relationships between patterns of forest fire disturbance and climate, human activities, vegetation, and topography in China, as well as their spatial heterogeneity in different climatic regions. The results indicate that the spatial distribution of forest fires is heterogeneous, and different forest fire regime components are predicted by different factors. At the national level, the distribution of forest fire regimes mainly corresponds to climatic factors, although the relationship between median fire size and predictors is obscure. At the scale of each ecoregion, the main climate predictors of forest fire occurrence density and burned rate change from temperature in the north to temperature and precipitation in the south. Median fire size varies with elevation and temperature in the south. These results demonstrate that the spatial heterogeneity of predictors and scaling effects must be fully considered in the study of forest fire disturbance. [ABSTRACT FROM AUTHOR]

Among the critical global crises curbing world development and sustainability, air quality degradation has been a long-lasting and increasingly urgent one and it has been sufficiently proven to pose severe threats to human health and social welfare. A higher level of model prediction accuracy can play a fundamental role in air quality assessment and enhancing human well-being. In this paper, four types of machine learning models—random forest model, ridge regression model, support vector machine model, extremely randomized trees model—were adopted to predict PM2.5 concentration in ten cities in the Jing-Jin-Ji region of north China based on multi-sources spatiotemporal data including air quality and meteorological data in time series. Data were fed into the model by using the rolling prediction method which is proven to improve prediction accuracy in our experiments. Lastly, the comparative experiments show that at the city level, RF and ExtraTrees models have better predictive results with lower mean absolute error (MAE), root mean square error (RMSE), and higher index of agreement (IA) compared to other selected models. For seasonality, level four models all have the best prediction performances in winter time and the worst in summer time, and RF models have the best prediction performance with the IA ranging from 0.93 to 0.98 with an MAE of 5.91 to 11.68 μg/m3. Consequently, the demonstration of how each model performs differently in each city and each season is expected to shed light on environmental policy implications. [ABSTRACT FROM AUTHOR]

The current study aims at assessing the capabilities of five machine learning models in terms of mapping tungsten polymetallic prospectivity in the Gannan region, China. The five models include logistic regression (LR), support vector machine (SVM), random forest, convolutional neural network (CNN), and light gradient boosting machine (LGBM) models. Three types of data sets including geochemical data, lithostratigraphic contacts, and faults were employed to generate 16 evidential maps that were used to build the machine learning models. Tungsten polymetallic deposits were randomly separated into two parts: 80% for training and 20% for validating. Performance of the models was evaluated through receiver operating characteristic and K‐fold cross validation, with an emphasis on the variable influence within different machine learning methods. The results show that the models are especially sensitive to the chemical elements: Be, Bi, Pb, and Cd, implying that they are closely related to tungsten polymetallic mineralization. Compared to other models, the LGBM and CNN models performed best, while the LR model was the most stable. The results also indicated that the CNN model can predict the maximum number of tungsten polymetallic deposits within the minimum area based on the prediction‐area plot analysis, while the SVM model can capture the least amount of tungsten polymetallic deposits within the largest area. Finally, 18 prospective areas were delineated according to the prediction results of the machine learning models, which provided important guidance for tungsten polymetallic exploration in the study area. Key Points: Five machine learning models were used and compared for tungsten polymetallic prospectivity analysis in the Gannan region, ChinaPerformances of the machine learning models were evaluated through receiver operating characteristic, P‐A plot, and K‐fold cross validationConvolutional neural network model is most efficient in mapping favorable areas for tungsten polymetallic exploration [ABSTRACT FROM AUTHOR]

While geological data gathering expands and advances along with mineral exploration, there is still a need for more innovation and enrichment because there are few complete analytical tools for these data. The light gradient boosting machine (LightGBM) technique is used in this study to estimate the prospectivity for minerals in three dimensions. However, because of the LightGBM model's large number of hyper-parameters, it is difficult to manually configure and alter model hyper-parameters, which has a substantial impact on the trained model's accuracy and dependability. Therefore, to optimize the LightGBM hyper-parameters, we use genetic algorithm (GA), which has the resilience and global optimization searchability in addressing difficult optimization problems. The GA–LightGBM algorithm for 3D mineral prospectivity modeling is the name we give to this combined approach. This study compares the GA–LightGBM algorithm against the GA-optimized support vector machine (SVM) and random forest (RF) algorithms in order to assess its applicability and superiority. The training set accuracy, test set accuracy, and Kappa coefficient values for the GA–LightGBM algorithm model were 0.9763, 0.9651, and 0.9453, respectively. The GA–LightGBM model's receiver operating characteristic curve was quite close to the upper left corner of the graph. The findings show that in terms of application and predictability, the GA–LightGBM ensemble learning approach performs better than the GA-optimized SVM and GA-optimized RF models. The outcomes of this study offer fresh perspectives for 3D mineral prospectivity modeling. [ABSTRACT FROM AUTHOR]

Background: Having a reliable and feasible method to estimate whether an individual has reached 16 years of age would greatly benefit forensic analysis. The study of age using dental information has matured recently. In addition, machine learning (ML) is gradually being applied for dental age estimation. Aim: The purpose of this study was to evaluate the development of the third molar using the Demirjian method (Demirjian3M), measure the development index of the third molar (I3M) using the method by Cameriere, and assess the periodontal ligament development of the second molar (PL2M). This study aimed to predict whether Chinese adolescents have reached the age of criminal responsibility (16 years) by combining the above measurements with ML techniques. Subjects & methods: A total of 665 Chinese adolescents aged between 12 and 20 years were recruited for this study. The development of the second and third molars was evaluated by taking orthopantomographs. ML algorithms, including random forests (RF), decision trees (DT), support vector machines (SVM), K-nearest neighbours (KNN), Bernoulli Naive Bayes (BNB), and logistic regression (LR), were used for training and testing to determine the dental age. This is the first study to combine ML with an evaluation of periodontal ligament and tooth development to predict whether individuals are over 16 years of age. Results and conclusions: The study showed that SVM had the highest Bayesian posterior probability at 0.917 and a Youden index of 0.752. This finding provides an important reference for forensic identification, and the combination of traditional methods and ML is expected to improve the accuracy of age determination for this population, which is of substantial significance for criminal litigation. [ABSTRACT FROM AUTHOR]

Rice has always been one of the major food sources for human beings, and the monitoring and planning of cultivation areas to maintain food security and achieve sustainable development is critical for this crop. Traditional manual ground survey methods have been recognized as being laborious, while remote-sensing technology can perform the accurate mapping of paddy rice due to its unique data acquisition capabilities. The recently emerged Google Earth Engine (GEE) cloud-computing platform was found to be capable of storing and computing the resources required for the rapid processing of massive quantities of remote-sensing data, thereby revolutionizing traditional analysis patterns and offering unique advantages for large-scale crop mapping. Since the phenology of paddy rice depends on local climatic conditions, and considering the vast expanse of China with its outstanding geospatial heterogeneity, a zoning strategy was proposed in this study to separate the monsoon climate zone of China into two regions based on the Qinling Mountain–Huaihe River Line (Q-H Line), while discrepant basic data and algorithms have been adopted to separately map mid-season rice nationwide. For the northern regions, optical indices have been calculated based on Sentinel-2 images, growth spectral profiles have been constructed to identify phenological periods, and rice was mapped using One-Class Support Vector Machine (OCSVM); for the southern regions, microwave sequences have been constructed based on Sentinel-1 images, and rice was mapped using Random Forest (RF). By applying this methodological system, mid-season rice at 10 m spatial resolution was mapped on the GEE for the entire Chinese monsoon region in 2021. According to the accuracy evaluation coefficients and publicly released local statistical yearbook data, the relative error of the mapped areas in each province was limited to 10%, and the overall accuracy exceeded 85%. The results could indicate that mid-season rice can be mapped more accurately and efficiently on a China-wide scale with relatively few samples based on the proposed zoning strategy and mapping methods. By adjusting the parameters, the time interval for mapping could also be further extended. The powerful cloud-computing competence of the GEE platform was used to map rice on a large spatial scale, and the results can help governments to ascertain the distribution of mid-season rice across the country in a short-term period, which would be well suited to meeting the increasingly efficient and fine-grained decision-making and management requirements. [ABSTRACT FROM AUTHOR]

Objective: We aimed to develop a 5-year overall survival prediction model for patients with oral tongue squamous cell carcinoma based on machine learning methods. Subjects and methods: The data were obtained from electronic medical records of 224 OTSCC patients at the PLA General Hospital. A five-year overall survival prediction model was constructed using logistic regression, Support Vector Machines, Decision Tree, Random Forest, Extreme Gradient Boosting, and Light Gradient Boosting Machine. Model performance was evaluated according to the area under the curve (AUC) of the receiver operating characteristic curve. The output of the optimal model was explained using the Python package (SHapley Additive exPlanations, SHAP). Results: After passing through the grid search and secondary modeling, the Light Gradient Boosting Machine was the best prediction model (AUC = 0.860). As explained by SHapley Additive exPlanations, N-stage, age, systemic inflammation response index, positive lymph nodes, plasma fibrinogen, lymphocyte-to-monocyte ratio, neutrophil percentage, and T-stage could perform a 5-year overall survival prediction for OTSCC. The 5-year survival rate was 42%. Conclusion: The Light Gradient Boosting Machine prediction model predicted 5-year overall survival in OTSCC patients, and this predictive tool has potential prognostic implications for patients with OTSCC. [ABSTRACT FROM AUTHOR]

Accurate prediction of landslide susceptibility relies on effectively handling absence samples in data-driven models. This study investigates the influence of different absence sampling methods, including buffer control sampling (BCS), controlled target space exteriorization sampling (CTSES), information value (IV), and mini-batch k-medoids (MBKM), on landslide susceptibility mapping in Songyang County, China, using support vector machines and random forest algorithms. Various evaluation metrics are employed to compare the efficacy of these sampling methods for susceptibility zoning. The results demonstrate that CTSES, IV, and MBKM methods exhibit an expansion of the high susceptibility region (maximum susceptibility mean value reaching 0.87) and divergence in the susceptibility index when extreme absence samples are present, with MBKM showing a comparative advantage (lower susceptibility mean value) compared to the IV model. Building on the strengths of different sampling methods, a novel integrative sampling approach that incorporates multiple existing methods is proposed. The integrative sampling can mitigate negative effects caused by extreme absence samples (susceptibility mean value is approximately 0.5 in the same extreme samples and presence-absence ratio) and obtain significantly better prediction results (AUC = 0.92, KC = 0.73, POA = 2.46 in the best model). Additionally, the mean level of susceptibility is heavily influenced by the proportion of absent samples. [ABSTRACT FROM AUTHOR]

In-season crop-type maps are required for a variety of agricultural monitoring and decision-making applications. The earlier the crop type maps of the current growing season are obtained, the more beneficial it is for agricultural decision-making and management. With the availability of a large amount of high spatiotemporal resolution remote sensing data, different data sources are expected to increase the frequency of data acquisition, which can provide more information in the early season. To explore the potential of integrating different data sources, a Dual-1DCNN algorithm was built based on the CNN model in this study. Moreover, an incremental training method was used to attain the network on each data acquisition date and obtain the best detection date for each crop type in the early season. A case study for Hengshui City in China was conducted using time series of Sentinel-1A (S1A) and Sentinel-2 (S2) attained in 2019. To verify this method, the classical methods support vector machine (SVM), random forest (RF), and Mono-1DCNN were implemented. The input for SVM and RF was S1A and S2 data, and the input for Mono-1DCNN was S2 data. The results demonstrated the following: (1) Dual-1DCNN achieved an overall accuracy above 85% at the earliest time.; (2) all four types of models achieved high accuracy (F1s were greater than 90%) on summer maize after sowing one month later; (3) for cotton and common yam rhizomes, Dual-1DCNN performed best, with its F1 reaching 85% within 2 months after cotton sowing, 15 days, 20 days, and 45 days ahead of Mono-1DCNN, SVM, and RF, respectively, and its extraction of the common yam rhizome was achieved 1–2 months earlier than other methods within the acceptable accuracy. These results confirmed that Dual-1DCNN offered significant potential in the in-season detection of crop types. [ABSTRACT FROM AUTHOR]

The glass relics are precious material evidence of the early trade and cultural exchange between the East and the West. To explore the cultural differences and trade development between early China and foreign countries, it is extremely important to classify glass cultural relics. Despite their similar appearances, Chinese glass contains more lead, while foreign glass contains more potassium. In view of this, this paper proposes a joint Daen-LR, ARIMA-LSTM, and MLR machine learning algorithm (JMLA) for the analysis and identification of the chemical composition of ancient glass. We separate the sampling points of ancient glass into two systems: lead-barium glass and high-potassium glass. Firstly, an improved logistic regression model based on a double adaptive elastic network (Daen-LR) is used to select variables with both Oracle and adaptive classification characteristics. Secondly, the ARIMA-LSTM model was used to establish the correlation curve of chemical composition before and after weathering and to predict the change in chemical composition with weathering. Thirdly, combining the data processed by the above two methods, a multiple linear regression model (MLR) is used to classify unknown glass products. It was shown that the sample obtained by this processing method has a very good fit. In comparison with other similar types of models like Decision Trees (DT), Random Forests (RF), Support Vector Machines (SVM), and Random Forests based on classification and regression trees (CART-RF), the classification accuracy of JMLA is 97.9% on the train set. The accuracy rate on the test set reached 97.6%. The results of the research demonstrate that JMLA can improve the accuracy of the glass type classification problem, greatly enhance the research efficiency of archaeological staff, and gain a more reliable result. [ABSTRACT FROM AUTHOR]

Landslide susceptibility mapping of mountain roads is frequently confronted by insufficient historical landslide sample data, multicollinearity of existing evaluation index factors, and inconsistency of evaluation factors due to regional environmental variations. Then, a single machine learning model can easily become overfitting, thus reducing the accuracy and robustness of the evaluation model. This paper proposes a combined machine-learning model to address the issues. The landslide susceptibility in mountain roads were mapped by using factor analysis to normalize and reduce the dimensionality of the initial condition factor and generating six new combination factors as evaluation indexes. The mountain roads in the Youxi County, Fujian Province, China were used for the landslide susceptibility mapping. Three most frequently used machine learning techniques, support vector machine (SVM), random forest (RF), and artificial neural network (ANN) models, were used to model the landslide susceptibility of the study area and validate the accuracy of this evaluation index system. The global minimum variance portfolio was utilized to construct a machine learning combined model. 5-fold cross-validation, statistical indexes, and AUC (Area Under Curve) values were implemented to evaluate the predictive accuracy of the landslide susceptibility model. The mean AUC values for the SVM, RF, and ANN models in the training stage were 89.2%, 88.5%, and 87.9%, respectively, and 78.0%, 73.7%, and 76.7%, respectively, in the validating stage. In the training and validation stages, the mean AUC values of the combined model were 92.4% and 87.1%, respectively. The combined model provides greater prediction accuracy and model robustness than one single model. [ABSTRACT FROM AUTHOR]

Flash floods are a frequent and highly destructive natural hazard in China. In order to prevent and manage these disasters, it is crucial for decision-makers to create GIS-based flash flood susceptibility maps. In this study, we present an improved Blending approach, RF-Blending (Reserve Feature Blending), which differs from the Blending approach in that it preserves the original feature dataset during meta-learner training. Our objectives were to demonstrate the performance improvement of the RF-Blending approach and to produce flash flood susceptibility maps for all catchments in Jiangxi Province using the RF-Blending approach. The Blending approach employs a double-layer structure consisting of support vector machine (SVM), K-nearest neighbor (KNN), and random forest (RF) as base learners for level-0, and the output of level-0 is utilized as the meta-feature dataset for the meta-learner in level-1, which is logistic regression (LR). RF-Blending employs the output of level-0 along with the original feature dataset for meta-learner training. To develop flood susceptibility maps, we utilized these approaches in conjunction with historical flash flood points and catchment-based factors. Our results indicate that the RF-Blending approach outperformed the other approaches. These can significantly aid catchment-based flash flood susceptibility mapping and assist managers in controlling and remediating induced damages. [ABSTRACT FROM AUTHOR]

Purpose: Despite rising incomes and reduction of extreme poverty, the feeling of being poor remains widespread. Support programs can improve well-being, but they first require identifying who are the households that judge their income is insufficient to meet their basic needs, and what factors are associated with subjective poverty. Design/methodology/approach: Households report the income level they judge is sufficient to make ends meet. Then, they are classified as being subjectively poor if their own monetary income is inferior to the level they indicated. Second, the study compares the performance of three machine learning algorithms, the random forest, support vector machines and least absolute shrinkage and selection operator (LASSO) regression, applied to a set of socioeconomic variables to predict subjective poverty status. Findings: The random forest generates 85.29% of correct predictions using a range of income and non-income predictors, closely followed by the other two techniques. For the middle-income group, the LASSO regression outperforms random forest. Subjective poverty is mostly associated with monetary income for low-income households. However, a combination of low income, low endowment (land, consumption assets) and unusual large expenditure (medical, gifts) constitutes the key predictors of feeling poor for the middle-income households. Practical implications: To reduce the feeling of poverty, policy intervention should continue to focus on increasing incomes. However, improvements in nonincome domains such as health expenditure, education and family demographics can also relieve the feeling of income inadequacy. Methodologically, better performance of either algorithm depends on the data at hand. Originality/value: For the first time, the authors show that prediction techniques are reliable to identify subjective poverty prevalence, with example from rural China. The analysis offers specific attention to the modest-income households, who may feel poor but not be identified as such by objective poverty lines, and is relevant when policy-makers seek to address the "next step" after ending extreme poverty. Prediction performance and mechanisms for three machine learning algorithms are compared. [ABSTRACT FROM AUTHOR]

Accurately identifying groundwater contamination sites is vital for groundwater protection and restoration. This study aims to use a machine learning (ML) approach to identify groundwater contamination sites with total petroleum hydrocarbons (TPH) as target contaminants in a case study of gas stations in China. Firstly, six classical ML algorithms, including logistic regression, decision tree, gradient boosting decision tree (GBDT), random forest, multi-layer perceptron, and support vector machine, were applied to develop the identification models of TPH-contaminated groundwater with 40 features and the performances were compared. The comparison results showed that the GBDT model achieves the best prediction performance, with F1 score of 1 and AUC value of 1. Next, Bayesian optimization optimized GBDT (BO-GBDT) was conducted to further decrease the training time from 19,125 s to 513 s while maintaining the same prediction performance (F1 score = 1, AUC = 1). Finally, Shapley additive explanations (SHAP) analysis was performed on the BO-GBDT model. The SHAP results displayed that the critical feature variables in the BO-GBDT model include wind, population, evaporation, total potassium in the soil, precipitation, and leakage accident. This study demonstrated that BO-GBDT is one satisfactory model to identify groundwater TPH-contamination at gas stations. The method proposed in this study has the potential to be applied to other types of groundwater contamination sites. [ABSTRACT FROM AUTHOR]

Lithofacies identification and classification are critical for characterizing the hydrocarbon potential of unconventional resources. Although extensive applications of machine learning models in predicting lithofacies have been applied to conventional reservoir systems, the effectiveness of machine learning models in predicting clay-rich, lacustrine shale lithofacies has yet to be tackled. Here, we apply machine learning models to conventional well log data to automatically identify the shale lithofacies of Gulong Shale in the Songliao Basin. The shale lithofacies were classified into six types based on total organic carbon and mineral composition data from core analysis and geochemical logs. We compared the accuracy of Multilayer Perceptron (MLP), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), and Random Forest models. We mitigated the bias of imbalanced data by applying oversampling algorithms. Our results show that ensemble methods (XGBoost and Random Forest) have a better performance in shale lithofacies identification than the other models do, with accuracies of 0.868 and 0.884, respectively. The organic siliceous shale proposed to have the best hydrocarbon potential in Gulong Shale can be identified with F1 scores of 0.853 by XGBoost and 0.877 by Random Forest. Our study suggests that ensemble machine learning models can effectively identify the lithofacies of clay-rich shale from conventional well logs, providing insight into the sweet spot prediction of unconventional reservoirs. Further improvements in model performances can be achieved by adding domain knowledge and employing advanced well log data. [ABSTRACT FROM AUTHOR]

Selecting the best planting area for blueberries is an essential issue in agriculture. To better improve the effectiveness of blueberry cultivation, a machine learning-based classification model for blueberry ecological suitability was proposed for the first time and its validation was conducted by using multi-source environmental features data in this paper. The sparrow search algorithm (SSA) was adopted to optimize the CatBoost model and classify the ecological suitability of blueberries based on the selection of data features. Firstly, the Borderline-SMOTE algorithm was used to balance the number of positive and negative samples. The Variance Inflation Factor and information gain methods were applied to filter out the factors affecting the growth of blueberries. Subsequently, the processed data were fed into the CatBoost for training, and the parameters of the CatBoost were optimized to obtain the optimal model using SSA. Finally, the SSA-CatBoost model was adopted to classify the ecological suitability of blueberries and output the suitability types. Taking a study on a blueberry plantation in Majiang County, Guizhou Province, China as an example, the findings demonstrate that the AUC value of the SSA-CatBoost-based blueberry ecological suitability model is 0.921, which is 2.68% higher than that of the CatBoost (AUC = 0.897) and is significantly higher than Logistic Regression (AUC = 0.855), Support Vector Machine (AUC = 0.864), and Random Forest (AUC = 0.875). Furthermore, the ecological suitability of blueberries in Majiang County is mapped according to the classification results of different models. When comparing the actual blueberry cultivation situation in Majiang County, the classification results of the SSA-CatBoost model proposed in this paper matches best with the real blueberry cultivation situation in Majiang County, which is of a high reference value for the selection of blueberry cultivation sites. [ABSTRACT FROM AUTHOR]

Pine wilt disease (PWD) has caused huge economic and environmental losses since it invaded China. Although early monitoring is an effective way to control this hazard, the monitoring window for the early stage is hard to identify, and varies in different hosts and environments. We used UAV-based multispectral images of Pinus thunbergii forest in East China to identify the change in the number of infected trees in each month of the growing season. We built classification models to detect different PWD infection stages by testing three machine learning algorithms—random forest, support vector machine, and linear discriminant analysis—and identified the best monitoring period for each infection stage (namely, green attack, early, middle, and late). From the obtained results, the early monitoring window period was determined to be in late July, whereas the monitoring window for middle and late PWD stages ranged from mid-August to early September. We also identified four important vegetation indices to monitor each infection stage. In conclusion, this study demonstrated the effectiveness of using machine learning algorithms to analyze multitemporal multispectral data to establish a window for early monitoring of pine wilt disease infestation. The results could provide a reference for future research and guidance for the control of pine wilt disease. [ABSTRACT FROM AUTHOR]

Deep learning has drawn great attention in the financial field due to its powerful ability in nonlinear fitting, especially in the studies of asset pricing. In this paper, we proposed a long short-term memory option pricing model with realized skewness by fully considering the asymmetry of asset return in emerging markets. It was applied to price the ETF50 options of China. In order to emphasize the improvement of this model, a comparison with a parametric method, such as Black-Scholes (BS), and machine learning methods, such as support vector machine (SVM), random forests and recurrent neural network (RNN), was conducted. Moreover, we also took the characteristic of heavy tail into consideration and studied the effect of realized kurtosis on pricing to prove the robustness of the skewness. The empirical results indicate that realized skewness significantly improves the pricing performance of LSTM among moneyness states except for in-the-money call options. Specifically, the LSTM model with realized skewness outperforms the classical method and other machine learning methods in all metrics. [ABSTRACT FROM AUTHOR]

Earth history is punctuated by voluminous magmatism and the formation of large igneous provinces (LIPs). Although anomalous mantle temperatures are known to be involved in many LIPs formation, the potentially critical role of fluids remains elusive. Here we apply machine learning methods (e.g., random forest, deep neural network, and support vector machines) to train models based on global datasets of basalts associated with different settings. The trained models predict that the basalts of Tarim LIP in northwestern China show a spatial decrease in their island arc affinity from northeast to southwest, which can be correlated to fluids released from earlier southward oceanic subduction. Temporally, the fluid activity declined from 290 Ma basalts to 270 Ma mafic dykes, suggesting that the fusible components in the mantle source were waning over time and ultimately a strengthened lithosphere was generated. Our study provides new insights into the crucial role of fluids in the generation of LIPs, particularly those related to ancient subducted slabs. Plain Language Summary: Large igneous provinces (LIPs) represent enormous volume of magmas (>0.1 MKm3) produced within a short duration (∼1–5 Ma). The involvement of fluids in generating LIPs remains equivocal. Some studies suggest that water plays an important role, whereas the others argue against this model, based on the typical anhydrous mineralogy and oceanic island basalt‐like geochemical signatures displayed by the basalts in LIPs. In this study, we apply machine learning methods to investigate how the LIP basalts were influenced by fluids. Training data were extracted from database to establish the predictive models. The trained models are in turn applied to examine the fluid influence on the Tarim LIP basalts in NW China. The results show that the Tarim LIP basalts have variable IAB‐affinity up to 37%, suggesting that the source domains of Tarim LIP were affected by fluids. Spatially, the fluid activity decreases from northeast to southwest, which we correlate to southward subduction events. Temporally, the fluid activity declined over time from 290 to 270 Ma, suggesting that the mantle was dehydrated during the plume‐lithosphere interaction, which may induce a strengthened lithosphere. These observations suggest that the fluids played a crucial role in the generation of Tarim LIP. Key Points: Machine learning methods were employed to evaluate the fluid activity in Tarim large igneous provinceA spatial decrease in the fluid activity from northeast to southwest is observedSubducted slab‐derived fluids play a crucial role in the generation of large igneous provinces [ABSTRACT FROM AUTHOR]

Our aim was to explore the possibility of using machine learning (ML) in predicting the onset and trajectories of depressive symptom in home-based older adults over a 7-year period. Depressive symptom data (collected in the year 2011, 2013, 2015 and 2018) of home-based older Chinese (n = 2650) recruited in the China Health and Retirement Longitudinal Study (CHARLS) were included in the current analysis. The latent class growth modeling (LCGM) and growth mixture modeling (GMM) were used to classify different trajectory classes. Based on the identified trajectory patterns, three ML classification algorithms (i.e. gradient boosting decision tree, support vector machine and random forest) were evaluated with a 10-fold cross-validation procedure and a metric of the area under the receiver operating characteristic curve (AUC). Four trajectories were identified for the depressive symptoms: no symptoms (63.9%), depressive symptoms onset {incident increasing symptoms [new-onset increasing (16.8%)], chronic symptoms [slowly decreasing (12.5%), persistent high (6.8%)]}. Among the analyzed baseline variables, the 10-item Center for Epidemiologic Studies Depression Scale (CESD-10) score, cognition, sleep time, self-reported memory were the top five important predictors across all trajectories. The mean AUCs of the three predictive models had a range from 0.661 to 0.892. ML techniques can be robust in predicting depressive symptom onset and trajectories over a 7-year period with easily accessible sociodemographic and health information. Supplemental data for this article is available online at http://dx.doi.org/10.1080/13607863.2022.2031868 [ABSTRACT FROM AUTHOR]

The past landslides from landslide inventory are essential for machine learning (ML)-based landslide susceptibility assessment (LSA). They determine not only the positive samples (characterized by the past landslides) but also the negative samples (randomly generated based on past landslides) for training and validating the ML models. However, the number of past landslides is often limited because of the constraints of time, budget, and resources available, etc. In other words, the available data for establishing landslide susceptibility ML models are limited, which indicates that the accuracy and reliability of the corresponding models are insufficient. This article, therefore, proposes using a new landslide susceptibility index-based sampling strategy to enhance the positive and negative samples for model training and validation to reach an improved ML-based LSA. To realize this idea, landslide susceptibility analysis based on initial datasets compiled from landslide inventory by using three ML models, i.e., random forest (RF), gradient boosting decision tree (GBDT) and support vector machine (SVM), are first conducted to obtain the initial landslide susceptibility indices at different space locations. Then, the landslide susceptibility indices are analyzed with the proposed sampling strategy which considers directly the grid units with very high and very low landslide susceptibility indices as potential positive and negative samples, respectively, to enrich the initial dataset; and the number of these positive/negative samples is determined by a Bayesian optimization algorithm. Thereafter, the ML models are updated with the enriched datasets. Finally, to verify the effectiveness of the proposed strategy, the improved models are applied to assess the landslide susceptibility of Taojiang County, China, and the results are compared with those from initial corresponding models without updating. The results show that compared with the initial RF, GBDT and SVM models, the corresponding improved models have a better performance in accuracy, precision, recall rate, and specificity. In particular, the AUC values of the three models are increased by 11.94%, 10.72% and 0.57%, respectively. [ABSTRACT FROM AUTHOR]

China's landslide disasters are serious, and regional landslide disaster early-warning is one of the important means of disaster prevention and mitigation. The traditional regional landslide disaster early-warning model, however, is limited by the complex landslide induction mechanism, limited data accumulation, and insufficient big data analysis methods, and has problems such as limited early-warning accuracy and insufficient refinement. In this paper, a machine learning method was introduced into the field of regional landslide disaster warning. From the model construction process of training sample-set construction, sample learning and training, model parameter optimization, model preservation, warning output, and so on, a method for constructing a regional landslide early-warning model based on machine learning was systematically proposed. In the sample learning and training, 80% of the training sample-set was used as the training set, and 20% was used as the test set for five-fold cross validation. The Bayesian Optimization algorithm was used to optimize the model parameters, and the accuracy, ROC curve, and AUC value were used to verify the model accuracy and model generalization ability. With China's Fujian province as an example, based on nine years of geological and meteorological data (2010–2018), geological environment factors, factors of hazard-affected bodies and historical disaster situations, and rainfall-induced factors in four categories, a total of 26 indicators were used as input characteristic parameters. Six machine learning algorithms were adopted to improve model training; the results showed that the Random Forest algorithm performed the best, giving an accuracy of 92.3%, and was the model with the best generalization ability (AUC was 0.955). The second best was the Artificial Neural Network model, with an accuracy of 0.937 and an AUC of 0.935. Next were the Nearest Neighbor model, the Logistic Regression model, and the Support Vector Machine; the poorest results were from the Decision Tree model. Finally, the typical rainfall-type landslide disaster process in Fujian Province was selected as an example to verify the Random Forest algorithm model. The results showed that compared with the early-warning results of the original explicit statistical model, the hit rate of the new model was 6 times, or equal to that of the original model, and the landslide density in the early-warning area of the new model was 1.6–1.7 times that of the original model. Preliminary verification showed that the new model based on the Random Forest method has obvious advantages, a higher hit rate and a smaller warning area, and can achieve more accurate warnings. The follow-up will continue to track the new landslide disaster situation in the study area and carry out model verification and correction. [ABSTRACT FROM AUTHOR]

Due to concealed initial symptoms, many diabetic patients are not diagnosed in time, which delays treatment. Machine learning methods have been applied to increase the diagnosis rate, but most of them are black boxes lacking interpretability. Rule extraction is usually used to turn on the black box. As the number of diabetic patients is far less than that of healthy people, the rules obtained by the existing rule extraction methods tend to identify healthy people rather than diabetic patients. To address the problem, a method for extracting reduced rules based on biased random forest and fuzzy support vector machine is proposed. Biased random forest uses the k-nearest neighbor (k-NN) algorithm to identify critical samples and generates more trees that tend to diagnose diabetes based on critical samples to improve the tendency of the generated rules for diabetic patients. In addition, the conditions and rules are reduced based on the error rate and coverage rate to enhance interpretability. Experiments on the Diabetes Medical Examination Data collected by Beijing Hospital (DMED-BH) dataset demonstrate that the proposed approach has outstanding results (MCC = 0.8802) when the rules are similar in number. Moreover, experiments on the Pima Indian Diabetes (PID) and China Health and Nutrition Survey (CHNS) datasets prove the generalization of the proposed method. [ABSTRACT FROM AUTHOR]

In order to quickly and accurately predict the slope stability, an intelligent evaluation method of slope stability based on machine learning was proposed. Based on the characteristics of 618 slopes in China, 6 typical slope parameters, including gravity (γ), cohesion (C), internal friction angle (φ), slope angle (β), slope height (H) and pore water pressure (P), were selected to establish the slope stability evaluation dataset. Slope stability prediction models were established using gradient boosting machine (GBM), support vector machine (SVM), artificial neural network (ANN) and random forest (RF) in the machine learning algorithm. The models were trained and learned using the training set. The model parameters were adjusted using the 5-fold cross validation and grid-search. The ability of the model to classify the slope stability was tested through the test set, and the optimal model was determined. The results show that by comparing the area under the receiver operating characteristic curve (AUC) and F1Score of GBM, SVM, ANN and RF algorithms, the AUC value and F1Score of RF algorithm are 0.969 and 0.904, respectively; RF algorithm has the best evaluation index and is more suitable for analyzing slope stability. Based on the different slope stability prediction models established by deleting different characteristic variables of RF algorithm, the characteristic parameters in descending order of sensitivity are γ, β, H, φ, P, C. According to the different sensitivity factors, the slope protection measures are proposed based on the sensitivity of the characteristic parameters. [ABSTRACT FROM AUTHOR]

Objective To explore the risk factors for the prognosis of patients with aneurysmal subarachnoid hemorrhage (aSAH) after clipping, and to construct a predictive model based on machine learning algorithms to guide early identification of high risk patients. Methods A total of 182 patients with aSAH who underwent clipping in Tianjin Huanhu Hospital from October 2020 to July 2021 were reviewed. According to the ratio of 7:3, all the data were randomly divided into training set (to construct the prediction model) and test set (to evaluate the prediction model). Synthetic minority oversampling technique (SMOTE) was used to deal with imbalance data. Recursive feature elimination method, Spearman rank correlation analysis and XGBoost feature importance analysis were used to select the optimal variables. Logistic regression (LR), random forest (RF), support vector machine (SVM), decision tree (DT), K near neighbor (KNN) and naive Bayesian (NB) algorithms based on machine learning were used to construct a prediction model. Receiver operating characteristic (ROC) curve was plotted and the area under the curve (AUC) was calculated, as well as accuracy, precision, recall and F1 values. Results All 182 patients were randomly divided into a training set of 127 cases according to the ratio of 7:3, including 103 cases with good prognosis [Glasgow Outcome Scale (GOS) grade 4-5] and 24 cases with poor prognosis (GOS grade 1-3). The data was balanced by generating 79 cases of poor prognosis by SMOTE technique (103 cases of good prognosis and 103 cases of poor prognosis). The test set consisted of 55 cases, including 44 cases with good prognosis and 11 cases with poor prognosis. A total of 17 optimal features were obtained by feature selection and feature importance analysis, the number of aneurysms, alkaline phosphatase, creatinine, application of lysine, sodium heparin and nitroglycerin tend to be positive correlated with good prognosis, while age, Hunt-Hess score, mature neutrophil count, serum sodium, uric acid, total bilirubin, basophilic granulocyte basophil count, creatine kinase, application of furosemide, human albumin, and length of hospital stay tend to be negative correlated with good prognosis. The AUC of LR model was 0.75 ± 0.08 (95%CI: 0.615-0.857, P = 0.001), an accuracy of 0.764, a precision of 0.919, a recall of 0.773, and an F1 value of 0.840; the RF model was 0.57 ± 0.08 (95%CI: 0.428-0.701, P = 0.283), an accuracy of 0.745, a precision of 0.826, a recall of 0.864, and an F1 value of 0.845; the SVM model was 0.65 ± 0.08 (95%CI: 0.507-0.772, P = 0.034), an accuracy of 0.764, a precision of 0.860, a recall of 0.841, an F1 value of 0.850; the DT model was 0.61 ± 0.09 (95%CI: 0.473-0.742, P = 0.135), an accuracy of 0.709, a precision of 0.850, a recall of 0.773, an F1 value of 0.810; the KNN model was 0.66 ± 0.08 (95%CI: 0.519-0.782, P = 0.060), an accuracy of 0.618, a precision of 0.897, a recall of 0.591, and F1 value of 0.712; and the NB model was 0.56 ± 0.08 (95%CI: 0.417-0.691, P = 0.458), an accuracy of 0.673, a precision of 0.825, a recall of 0.750, and an F1 value of 0.786. In particular, the LR model has the best prediction performance (P < 0.05, for all). Conclusions Machine learning algorithms performed well in predicting the prognosis of aSAH clipping, among which the LR model had the best prediction performance and could be used for preoperative prediction to help neurosurgeons make better clinical decisions. [ABSTRACT FROM AUTHOR]

Background: Cardiac surgery-associated acute kidney injury (CSA-AKI) is a major complication that increases morbidity and mortality after cardiac surgery. Most established predictive models are limited to the analysis of nonlinear relationships and do not adequately consider intraoperative variables and early postoperative variables. Nonextracorporeal circulation coronary artery bypass grafting (off-pump CABG) remains the procedure of choice for most coronary surgeries, and refined CSA-AKI predictive models for off-pump CABG are notably lacking. Therefore, this study used an artificial intelligence-based machine learning approach to predict CSA-AKI from comprehensive perioperative data. Methods: In total, 293 variables were analysed in the clinical data of patients undergoing off-pump CABG in the Department of Cardiac Surgery at the First Affiliated Hospital of Guangxi Medical University between 2012 and 2021. According to the KDIGO criteria, postoperative AKI was defined by an elevation of at least 50% within 7 days, or 0.3 mg/dL within 48 hours, with respect to the reference serum creatinine level. Five machine learning algorithms--a simple decision tree, random forest, support vector machine, extreme gradient boosting and gradient boosting decision tree (GBDT)--were used to construct the CSA-AKI predictive model. The performance of these models was evaluated with the area under the receiver operating characteristic curve (AUC). Shapley additive explanation (SHAP) values were used to explain the predictive model. Results: The three most influential features in the importance matrix plot were 1-day postoperative serum potassium concentration, 1-day postoperative serum magnesium ion concentration, and 1-day postoperative serum creatine phosphokinase concentration. Conclusion: GBDT exhibited the largest AUC (0.87) and can be used to predict the risk of AKI development after surgery, thus enabling clinicians to optimise treatment strategies and minimise postoperative complications. [ABSTRACT FROM AUTHOR]

To develop and externally validate a machine learning–based fall prediction model for ambulatory nursing home residents. The focus is on predicting fall occurrences within 6 months after baseline assessment through a binary classification task, aiming to provide staff with an effective and user-friendly fall-risk assessment tool. Prospective cohort study. A total of 864 older residents living in 4 nursing homes between May 2022 and March 2023 in China. Potential fall-risk predictors were collected through in-person interviews and assessments of anthropometric and physical function. Participants were followed for 6 months, with falls recorded by trained nurses. Seven machine learning algorithms, including Logistic Regression (LR), Gradient Boosting Machine (GBM), eXtreme Gradient Boosting (XGBoost), Random Forest (RF), Support Vector Machine (SVM), Neural Networks (NN), and Decision Tree (DT), were used to develop prediction models. Performance was evaluated using the area under the receiver operating characteristic curve (ROC-AUC) and Precision-Recall curve (PR-AUC), with calibration assessed via a calibration curve. Feature importance was visualized using SHapley Additive exPlanations (SHAP). The 6 selected predictors were balance, grip strength, fatigue, fall history, age, and comorbidity. The ROC-AUC for the models ranged from 0.710 to 0.750, PR-AUC from 0.415 to 0.473, sensitivity from 0.704 to 0.914, and specificity from 0.511 to 0.687 in the validation cohort. The LR model was converted into a nomogram. The machine learning–based fall-prediction models effectively identified nursing home residents at high risk of falls. The developed nomogram can be integrated into clinical practice to enhance fall risk assessment protocols, ultimately improving patient safety and care in nursing homes. [ABSTRACT FROM AUTHOR]

How to promote air traveler repurchasing has become an important marketing strategy in airlines. However, because of the growing concern over user privacy, effectively and accurately delivering advertising to promote repurchasing has become more difficult. Here, we propose an effective framework based on machine learning to model the air traveler repurchasing and furthermore employ a field experiment to test the utility of a model framework. Specifically, we collected that this model framework is based on the random forest algorithm and compared with the conclusions of the other four algorithms, K-nearest neighbor, decision tree, support vector machine, and ExtraTree algorithms. The results show that the proposed model framework is better than the prediction results of the other algorithms. In addition, the proposed model framework was verified through a real case of an airline in China. This study will serve as a guide to analyze the repurchase behaviors of an air traveler and help airlines build a loyal air traveler base. [ABSTRACT FROM AUTHOR]

Drowning is a major public health problem and a leading cause of death in children living in developing countries. We seek better machine learning (ML) algorithms to provide a novel risk-assessment insight on non-fatal drowning prediction. The data on non-fatal drowning were collected in Qingyuan city, Guangdong Province, China. We developed four ML models to predict the non-fatal drowning risk, including a logistic regression model (LR), random forest model (RF), support vector machine model (SVM), and stacking-based model, on three primary learners (LR, RF, SVM). The area under the curve (AUC), F1 value, accuracy, sensitivity, and specificity were calculated to evaluate the predictive ability of the different learning algorithms. This study included a total of 8390 children. Of those, 12.07% (1013) had experienced non-fatal drowning. We found the following risk factors are closely associated with the risk of non-fatal drowning: the frequency of swimming in open water, distance between the school and the surrounding open waters, swimming skills, personality (introvert) and relationality with family members. Compared to the other three base models, the stacking generalization model achieved a superior performance in the non-fatal drowning dataset (AUC = 0.741, sensitivity = 0.625, F1 value = 0.359, accuracy = 0.739 and specificity = 0.754). This study indicates that applying stacking ensemble algorithms in the non-fatal drowning dataset may outperform other ML models. [ABSTRACT FROM AUTHOR]

Annual monitoring of the spatial distribution of cultivated land is important for maintaining the ecological environment, achieving a status quo of land resource management, and guaranteeing agricultural production. With the gradual development of remote sensing technology, it has become a common practice to obtain cultivated land boundary information on a large scale with the help of satellite Earth observation images. Traditional land use classification methods are affected by multiple types of land cover, which leads to a decrease in the accuracy of cultivated land mapping. In contrast, although the current advanced methods (such as deep learning) can obtain more accurate cultivated land mapping results than traditional methods, such methods often require the use of a massive amount of training samples, large computing power, and highly complex model tuning processes, increasing the cost of mapping and requiring the involvement of more professionals. This has hindered the promotion of related methods in mapping institutions. This paper proposes a method based on time series vector features (MTVF), which uses vector thinking to establish the features. The advantage of this method is that the introduction of vector features enlarges the differences between the different land cover types, which overcomes the loss of mapping accuracy caused by the influences of the spectra of different ground objects and ensures the calculation efficiency. Moreover, the MTVF uses a traditional method (random forest) as the classification core, which makes the MTVF less demanding than advanced methods in terms of the number of training samples. Sentinel-2 satellite images were used to carry out cultivated land mapping for 2020 in northern Henan Province, China. The results show that the MTVF has the potential to accurately identify cultivated land. Furthermore, the overall accuracy, producer accuracy, and user accuracy of the overall study area and four sub-study areas were all greater than 90%. In addition, the cultivated land mapping accuracy of the MTVF is significantly better than that of the maximum likelihood, support vector machine, and artificial neural network methods. [ABSTRACT FROM AUTHOR]

Melia azedarach L. is an important economic tree widely distributed in tropical and subtropical regions of China and some other countries. However, it is unclear how the species' suitable habitat will respond to future climate changes. We aimed to select the most accurate one among seven data mining models to predict the current and future suitable habitats for M. azedarach in China. These models include: maximum entropy (MaxEnt), support vector machine (SVM), generalized linear model (GLM), random forest (RF), naive bayesian model (NBM), extreme gradient boosting (XGBoost), and gradient boosting machine (GBM). A total of 906 M. azedarach locations were identified, and sixteen climate predictors were used for model building. The models' validity was assessed using three measures (Area Under the Curves (AUC), kappa, and overall accuracy (OA)). We found that the RF provided the most outstanding performance in prediction power and generalization capacity. The top climate factors affecting the species' suitable habitats were mean coldest month temperature (MCMT), followed by the number of frost-free days (NFFD), degree-days above 18 °C (DD > 18), temperature difference between MWMT and MCMT, or continentality (TD), mean annual precipitation (MAP), and degree-days below 18 °C (DD < 18). We projected that future suitable habitat of this species would increase under both the RCP4.5 and RCP8.5 scenarios for the 2011–2040 (2020s), 2041–2070 (2050s), and 2071–2100 (2080s). Our findings are expected to assist in better understanding the impact of climate change on the species and provide scientific basis for its planting and conservation. [ABSTRACT FROM AUTHOR]

The convolutional neural networks used widely in mineral prospectivity prediction usually perform mixed feature extraction for multichannel inputs. This results in redundant features and impacts further improvement of predictive performance. To solve this limitation, this paper utilized convolutional autoencoder networks to mine latent high-level features for each predictor variable in parallel to prevent the mixing of features and to enhance the feature mapping outcomes of each channel. Convolutional autoencoder networks, as unsupervised learning methods, can handle input images with high-dimensional features. They can train samples without differences such that the reconstructed outputs can restore inputs as accurately as possible to reduce the extraction of irrelevant feature information. Moreover, convolutional autoencoder networks focus on finding the fewest features for representing all inputs, and the extracted features express internal spatial relations at a high level. It is helpful to improve the performance of metallogenic prediction. Hence, this paper arranged these obtained features into one-dimensional vectors to establish the inputs of classifiers. Through modeling with four classifiers (logistic regression, support vector machine, artificial neural network, and random forest), we achieved different models for mineral prospectivity prediction. According to the comprehensive evaluations, the random forest model outperformed the other models. Taking the prediction of gold deposits in the Fengxian region of Southern Qinling in China as an example, the predictive capability of the proposed integrated method was shown to be effective and reliable. The predicted high-potential areas can provide significant guidance for gold deposit exploration in the study area. [ABSTRACT FROM AUTHOR]