Search

Ecological restoration of rare earth element (REE) mining areas has become a key component in the sustainable development of the ion-adsorption-type REE industry. Current studies on ecological restoration assessments are mainly based on a comparison of REE mining ranges conducted over two or more periods, therefore, the dynamic evolution of spatial patterns for REE mining and vegetation recovery remains to be elucidated. Rapid advances in remote sensing techniques, along with the cloud-based Google Earth Engine (GEE), can provide an effective and convenient observation strategy for monitoring the environment in mining areas. In this study, we propose a hybrid method consisting of a random forest (RF) classifier and Landsat-based detection of trends in disturbance and recovery (LandTrendr) to identify and monitor the disturbance of REE mining and vegetation recovery in REE mining areas in the southern Jiangxi Province of China from 1988 to 2021 based on the GEE platform. The results reveal that REE mining activities were widespread in the study area, and the spatial distribution of REE mining areas was highly dispersed. The total area of REE mining in the study region was 93.14 km2, and the greatest REE mining activity was observed in the year 2006. As of 2021, the vegetation coverage area in the REE mining zone reached 47.44 km2, with a recovery rate of 50.93%. Among the seven counties in the study area, Longnan county had the lowest level of vegetation recovery in REE mining areas. A total of 95% of the vegetation recovery events in REE mining areas lasted between 1 and 18 years. These observations suggest that LandTrendr efficiently captured REE mining-induced disturbances and vegetation recovery and offers important reference data for the formulation of mining area restoration strategies. The results can provide a referable basis for the ecological restoration of southern Jiangxi Province, China. [ABSTRACT FROM AUTHOR]

For shallow lakes, the most dramatic ecosystem shift is that from a clear-water, macrophyte-dominated regime to a turbid, phytoplankton-dominated regime. Whereas many studies have focussed on the factors that trigger such shifts, it is still unclear how these changes shape fish diversity. In the present study, we characterised the fish communities taxonomically and functionally in Lake Taihu, China, along a spatial gradient of habitat types, i.e. algal-dominated, macrophyte-dominated, open-lake and aquaculture conversion zones. Random Forests regression was then applied to examine how fish diversities were related to environmental conditions. Our results showed that the taxonomic and functional composition of the fish community varied among different habitat regimes. Macrophyte and water quality were identified as the most important factors affecting the fish diversity indices. Habitats with a high macrophyte biomass and low nutrient concentration supported higher functional diversity. Moreover, our analysis revealed that although functional diversity indices were strongly correlated with species richness, they appeared more sensitive to changes in habitat conditions. Overall, our study highlights the importance of macrophyte-dominated state in maintaining fish diversity in freshwater ecosystems and provides new insight into how functional diversity can improve our understanding of the response of biodiversity to ecological processes. [ABSTRACT FROM AUTHOR]

Precise and timely prediction of crop yields is crucial for food security and the development of agricultural policies. However, crop yield is influenced by multiple factors within complex growth environments. Previous research has paid relatively little attention to the interference of environmental factors and drought on the growth of winter wheat. Therefore, there is an urgent need for more effective methods to explore the inherent relationship between these factors and crop yield, making precise yield prediction increasingly important. This study was based on four type of indicators including meteorological, crop growth status, environmental, and drought index, from October 2003 to June 2019 in Henan Province as the basic data for predicting winter wheat yield. Using the sparrow search algorithm combined with random forest (SSA-RF) under different input indicators, accuracy of winter wheat yield estimation was calculated. The estimation accuracy of SSA-RF was compared with partial least squares regression (PLSR), extreme gradient boosting (XG-Boost), and random forest (RF) models. Finally, the determined optimal yield estimation method was used to predict winter wheat yield in three typical years. Following are the findings: 1) the SSA-RF demonstrates superior performance in estimating winter wheat yield compared to other algorithms. The best yield estimation method is achieved by four types indicators' composition with SSA-RF) (R2 = 0.805, RRMSE = 9.9%. 2) Crops growth status and environmental indicators play significant roles in wheat yield estimation, accounting for 46% and 22% of the yield importance among all indicators, respectively. 3) Selecting indicators from October to April of the following year yielded the highest accuracy in winter wheat yield estimation, with an R2 of 0.826 and an RAISE of 9.0%. Yield estimates can be completed two months before the winter wheat harvest in June. 4) The predicted performance will be slightly affected by severe drought. Compared with severe drought year (2011) (R2 = 0.680) and normal year (2017) (R2 = 0.790), the SSA-RF model has higher prediction accuracy for wet year (2018) (R2 = 0.820). This study could provide an innovative approach for remote sensing estimation of winter wheat yield, yield. [ABSTRACT FROM AUTHOR]

Reference crop evapotranspiration (ETO) is a basic component of the hydrological cycle and its estimation is critical for agricultural water resource management and scheduling. In this study, three tree-based machine learning algorithms (random forest [RF], gradient boosting decision tree [GBDT], and extreme gradient boosting [XGBoost]) were adopted to determine the essential factors for ETO prediction. The tree-based models were optimized using the Bayesian optimization (BO) algorithm and were compared with three standalone models in terms of daily ETO and monthly mean ETO estimations in North China, with different input combinations of essential variables. The results indicated that solar radiation (Rs) and air temperature (Ts), including the maximum, minimum, and average temperatures, in daily ETO were the key variables affecting model prediction accuracy. Rs was the most influential factor in the monthly average ETO model followed by Ts. Both relative humidity (RH) and wind speed at 2 m (U2) had little impact on ETO prediction at different scales, although their importance differed. Compared with the GBDT and RF models, the XGBoost model exhibited the best performance for daily ETO and monthly mean ETO estimations. The hybrid tree-based models with the BO algorithm outperformed standalone tree-based models. Overall, compared with the other inputs, the model with three inputs (Rs, Ts, and RH/U2) had the highest accuracy. The BO-XGBoost model exhibited superior performance in terms of the global performance index (GPI) for daily ETO and monthly mean ETO predictions and is recommended as a more accurate model for predicting daily ETO and monthly mean ETO in North China or areas with a similar climate. [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]

Identifying the current pollution status, future trends, and driving factors is a crucial prerequisite for protecting and managing soil environmental quality in light of the challenging soil heavy metal pollution situation. In this study, a typical industrial city in southeast China was selected as the study area. The environmental capacity of 12 heavy metals was first measured for the evaluation of soil heavy metal pollution, and then spatiotemporal change was simulated using indicator Kriging to warn the pollution risk. Finally, the driving factors of heavy metal pollution were analyzed using random forest and geographical detectors. The results revealed that the average environmental capacity index was 0.768, at a medium capacity level. The environmental capacity of each heavy metal showed a decreasing trend from 2016 to 2035. In 2035, the dynamic environmental capacity of each heavy metal element will have decreased by more than 75% if no preventative and remedial measures are taken. The distance from rivers, fine particulate matter, organic matter content, population density, and distance from industrial enterprises were the main factors contributing to heavy metal pollution in soil. The interaction effect of two environmental factors will mostly lead to the intensification of pollution. Based on the results, this study discussed strategies for controlling and remediating the polluted land. These findings could support the source investigation and early warning of soil heavy metal pollution, which are crucial to manag soil pollution and alleviating environmental quality issues. [ABSTRACT FROM AUTHOR]

Topographic variables derived from digital elevation models (DEM) are the most commonly used predictor in soil organic carbon (SOC) prediction. The predictability of these variates for the spatial heterogenity of SOC is influenced by the size of DEM resolution. This paper aimed to investigate the resolution effect of the topography at multiple DEM resolutions and select the most important predictors and the optimal resolution for SOC prediction in a large-scale and morphologically complex area. The study area, covering 15 600 km2, was located in a mountainous province in China. A total of 3901 soil samples and three machine learning algorithms including random forest, gradient boosted regression tree, and artificial neural network were used to construct the SOC predictive models at resolutions of 30, 90, 150, 210, 270, 330, and 390 m. Topographic factors were derived from the DEM with an original resolution of 30 m and were subsequently resampled to varying resolutions by using the bilinear interpolation algorithm. The importance of each variate in each predictive model was computed for the most important predictor selection, and the determination coefficient (R2) and Root Mean Square Error (RMSE) of each predictive model were computed for the accuracy evaluation. Comparative analysis on point-based topographic representation, the accuracy of predictive models, and the variable importance was conducted among different resolutions to investigate the resolution effect on the SOC prediction and to select the optimal resolution for this study area. The results showed that topography was the key factor influencing the SOC distribution in this large-scale area due to the region's mountainous nature, and the relative contribution of the topography to predict SOC distribution varied with DEM resolutions. Elevation was the most important topographic factor at all DEM resolutions. Accuracies of predictive models built on the three machine learning algorithms were all dependent on DEM resolution, indicating that DEM resolution had an important effect on SOC prediction. Overall, the random forest predictive models outperformed the other two algorithms, and its most accurate result was obtained at the 210-m resolution with an R2 of 0.25 and an RMSE of 4.77 g kg–1. In conclusion, we found that finer resolutions did not necessarily produce more accurate SOC predictions even in a large-scale and morphologically complex area. Therefore, investigating the resolution effect is suggested to select an optimal resolution for the SOC prediction in other regions characterized by similar geomorphological conditions as this study area. [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]

Exploring the value of multi-source information fusion to predict small and medium-sized enterprises' (SMEs) credit risk in supply chain finance (SCF) is a popular yet challenging task, as two issues of key variable selection and imbalanced class must be addressed simultaneously. To this end, we develop new forecast models adopting an imbalance sampling strategy based on machine learning techniques and apply these new models to predict credit risk of SMEs in China, using financial information, operation information, innovation information, and negative events as predictors. The empirical results show that the financial-based information, such as TOC, NIR, is most useful in predicting SMEs' credit risk in SCF, and multi-source information fusion is meaningful in better predicting the credit risk. In addition, based on the preferred CSL-RF model, which extends cost-sensitive learning to a random forest, we also present the varying mechanisms of key predictors for SMEs' credit risk by using partial dependency analysis. The strategic insights obtained may be helpful for market participants, such as SMEs' managers, investors, and market regulators. [ABSTRACT FROM AUTHOR]

The mechanism of coal and gas outburst disasters is perplexing, and the evaluation methods of outburst disasters based on various sensitive indicators often have some imprecision and fuzziness. With the concept of accurate and intelligent mining in coal mines proposed in China, selecting quantifiable parameters for machine learning risk prediction can avoid the deviation caused by human subjectivity, and improve the accuracy of coal and gas outburst prediction. Aiming at the shortcomings of the support vector machine (SVM) such as low noise resistance and being prone to be influenced by parameters easily, this research proposed a prediction method based on a grey wolf optimizer to optimize the support vector machine (GWO-SVM). To coordinate the global and local optimization ability of the GWO, Tent Chaotic Mapping and DLH strategies were introduced to improve the optimization ability of the GWO and reduce the local optimal probability. The improved prediction model IGWO-SVM was used to predict the coal and gas outburst. The results showed that this model has faster training speed and higher classification prediction accuracy than the SVM and GWO-SVM models, which the accuracy rate reaching 100%. Finally, to obtain the correlation between the parameters of the coal and gas outburst prediction parameters, the random forest algorithm was used for training, and the three parameters with the highest feature importance were selected to rebuild the data set for machine learning. The accuracy of the IGWO-SVM outburst prediction model based on Random Forest was still 100%. Therefore, even if some prediction parameters are missing, the outburst can still be effectively predicted by using the RF-IGWO-SVM model, which is beneficial for the model application and underground safety management. [ABSTRACT FROM AUTHOR]

This work is based on an analysis of the spatial trends and drivers of soil C, N, and P contents and their stocks in relation to latitude, longitude, and altitude. For this purpose, the coniferous forests of Qinghai spruce (Picea crassifolia (Pc)) and Qilian juniper (Juniperus przewalskii (Jp)) within the Qilian Mountains in northwest China were selected as the objects of research. It was found that at the regional scale, the C and N contents in soil from the Pc forests were 1.34 and 1.17 folds higher than those of the Jp forests, respectively, whereas the P content was 0.92 fold lower than that of the Jp forests. Interestingly, the stock of soil C and N in the two forests was consistent, indicating an equivalent role of both in maintaining the regional C and N stocks. Secondly, the soil C and N stocks of Jp were the highest at a low altitude (< 2800 m), which indicated that the Jp forest trees retained high amounts of C and N at an altitude < 2800 m. In addition, the stocks of soil C and N correlated negatively with the latitude and positively with the longitude (P < 0.05). A partial redundancy analysis and random forests regression models showed that the stocks of soil C, N, and P were primarily controlled by the soil properties, particularly the bulk density and nutrient contents. Overall, these results provide insights into the effects of soil and terrain factors on soil C, N, and P stock, thereby providing a foundation for targeted forest conservation and rehabilitation in the Qilian Mountains in the future. [ABSTRACT FROM AUTHOR]

Mineral prospectivity mapping (MPM) is a fundamental task in mineral exploration. In recent years, the random forest (RF), which is recognized as a significant model for ensemble machine learning algorithms, has been widely used in MPM due to its advantages of high performance and robustness. Nevertheless, the RF method does not fully consider the correlation between variables. In this regard, a hybrid model, namely, the projection pursuit RF (PPRF), has been proposed. In this study, for validation and comparison purposes, the PPRF and ordinary RF methods were employed for the MPM of porphyry Cu–Mo deposits in the Eastern Tianshan orogenic belt, northwestern China, under the same conditions. In the case study, the performance of these two methods was critically investigated. The overall prediction accuracies of the PPRF and RF methods were evaluated by the area under the receiver operating characteristic curve and prediction–area plot approaches. To analyze the sensitivity of the PPRF and RF methods to unbalanced data caused by the limited number of known deposits in the study area, the synthetic minority oversampling technique was used to generate a balanced dataset. The results demonstrated that the PPRF method not only outperforms the ordinary RF method in the overall accuracy of MPM but is also less sensitive to unbalanced data than the RF method. Therefore, the PPRF method provides a novel and useful data-driven method with excellent performance for MPM. It utilizes the combination of predictor variables in the projection feature space rather than the variables themselves to identify the inherent characteristics of a given dataset and may thus discover deep hidden features that the ordinary RF method cannot find. [ABSTRACT FROM AUTHOR]

The mechanism of coal and gas outburst disasters is perplexing, and the evaluation methods of outburst disasters based on various sensitive indicators often have some imprecision and fuzziness. With the concept of accurate and intelligent mining in coal mines proposed in China, selecting quantifiable parameters for machine learning risk prediction can avoid the deviation caused by human subjectivity, and improve the accuracy of coal and gas outburst prediction. Aiming at the shortcomings of the support vector machine (SVM) such as low noise resistance and being prone to be influenced by parameters easily, this research proposed a prediction method based on a grey wolf optimizer to optimize the support vector machine (GWO-SVM). To coordinate the global and local optimization ability of the GWO, Tent Chaotic Mapping and DLH strategies were introduced to improve the optimization ability of the GWO and reduce the local optimal probability. The improved prediction model IGWO-SVM was used to predict the coal and gas outburst. The results showed that this model has faster training speed and higher classification prediction accuracy than the SVM and GWO-SVM models, which the accuracy rate reaching 100%. Finally, to obtain the correlation between the parameters of the coal and gas outburst prediction parameters, the random forest algorithm was used for training, and the three parameters with the highest feature importance were selected to rebuild the data set for machine learning. The accuracy of the IGWO-SVM outburst prediction model based on Random Forest was still 100%. Therefore, even if some prediction parameters are missing, the outburst can still be effectively predicted by using the RF-IGWO-SVM model, which is beneficial for the model application and underground safety management. [ABSTRACT FROM AUTHOR]

Purpose: As a huge natural carbon storage, wetlands play an important role in the global carbon cycle. However, the spatial pattern and storage of soil organic carbon (SOC) in wetland ecosystems remain largely uncertain due to large spatial heterogeneity and insufficient field observations. Methods: In this study, we predict the spatial pattern of SOC density and estimated SOC storage in wetlands of Northeast China based on 819 field samples and multiple geospatial data using random forest algorithm. Results: The SOC density of wetlands at different depths was affected differently by environmental factors and the SOC density in the surface layer (0–30 cm) was more susceptible to climatic change. The correlation coefficients (r) between the SOC density predicted by the random forest model and the measured SOC density were 0.86, 0.77 and 0.73 in 0–30, 30–60 and 60–100 cm soil depths, respectively. Our estimation showed that Northeast China holds huge wetland SOC storage in the amount of 3.40 ± 0.13 Pg C. The average wetland SOC density was 44.30 ± 1.72 kg C m−2, which decreased gradually from north to south in the study area. Conclusion: The wetland SOC density in Northeast China decreased with soil depth, and the influence of environmental factors on wetland SOC gradually decreased. Surface wetland SOC may be more sensitive to global climate change. Our results examined the relationship between wetland SOC and environmental factors, which benefits the understanding of the responses of wetland SOC to climate change. [ABSTRACT FROM AUTHOR]

Runoff prediction with high accuracy is vital to protect people's properties and lives. In this study, a Short-Term Streamflow Forecasting Framework combining Long Short-Term Memory (LSTM) with Self-Organizing Map (SOM) is proposed, which clusters hydro-meteorological factors through SOM network to cluster the streamflow into several flow modes with different physical characteristics, converting complex global modeling into local modeling. The framework also considers the temporal characteristics of the streamflow, so the data of different flow modes are fitted with multiple LSTM separately. Besides, Random Forest is used in the framework for feature selection. The model is used for streamflow forecasting 1 to 3 day(s) ahead in the Qingxi River Basin in China, and the performance is compared with those of SVR, ANN, LSTM, SOM-SVR, SOM-ANN, FCM-LSTM, and K-means-LSTM. In addition, SOM-LSTM with three and four clusters were compared. The results show that (1) the sub-processes obtained by SOM clustering show some physical characteristics consistent with the actual process. (2) SOM-LSTM significantly improves the prediction accuracy of short-term streamflow forecasting. (3) All the integrated models using different clustering methods can improve the prediction accuracy of a single LSTM, and SOM-LSTM has the most reliable prediction when the lead time is 1–2 day(s). (4) The number of clusters being set to 4 is more suitable for the proposed prediction framework. The overall results show that the SOM-LSTM provides an efficient method for short-term streamflow forecasting. [ABSTRACT FROM AUTHOR]

In recent years, the development of machine learning, especially deep learning, has provided new methods and ideas for current climate research. Stacked auto-encoder based on deep learning are used to perform nonlinear down-scaling to compress the degree of freedom of climate variables in the early stage. And climate predictors features are extracted from the summer precipitation in four regions in eastern China, from which key climate predictors affecting summer precipitation in each region are identified. On this basis, a variety of regression methods including random forest in machine learning method were used to construct prediction models for key climate predictors in each region. The best model parameters were determined by the sensitivity test of model parameters to forecast results. Several years of predictions suggest that the method for the forecast of precipitation in eastern China has a very high skill, especially in southern China. The results show that the anomaly consistency of the proposed model in regional prediction is better than that of the model. Compared with the mainstream model, the prediction results in South China can be improved by more than 10%. The method has a good application prospect for summer precipitation prediction in eastern China. [ABSTRACT FROM AUTHOR]

It is difficult to accurately estimate the incidence rate of intimate partner violence (IPV) using traditional social survey methods because IPV victims are often reluctant to disclose their experiences, leading to an underestimation of the incidence rate. To address this issue, we applied machine learning algorithms to predict the incidence rate of IPV in China based on data from the Third Wave Survey on the Social Status of Women in China (TWSSSCW 2010). Specifically, we examined five unbalanced sample-processing methods and six machine learning algorithms, choosing the random under-sampling ensemble method and the random forest algorithm to impute the missing data. Analysis of the complete data showed that the incidence rates of physical violence, verbal violence, and cold violence were 7.10%, 13.74%, and 21.35%, respectively, which were higher than the incidence rates in the original dataset (4.05%, 11.21%, and 17.95%, respectively). The robustness of our findings was further confirmed by analysis using different training sets. Overall, this study demonstrates that better tools need to be developed to accurately estimate the incidence rates of IPV. It also serves as a useful guide for future research that imputes missing data using machine learning. [ABSTRACT FROM AUTHOR]

The Ms 8.0 Wenchuan earthquake of 2008 dramatically changed the terrain surface and caused long-term increases in the scale and frequency of landslides and debris flows. The changing trend of landslides in the earthquake-affected area over the decade since the earthquake remains largely unknown. In this study, we were able to address this issue using supervised classification methods and multitemporal remote sensing images to study landslide evolution in the worst-affected area (Mianyuan River Basin) over a period of ten years. Satellite images were processed using the maximum likelihood method and random forest algorithm to automatically map landslide occurrence from 2007 to 2018. The principal findings are as follows: (1) when compared with visual image analysis, the random forest algorithm had a good average accuracy rate of 87% for landslide identification; (2) postevent landslide occurrence has generally decreased with time, but heavy monsoonal seasons have caused temporary spikes in activity; and (3) the postearthquake landslide activity in the Mianyuan River Basin can be divided into a strong activity period (2008 to 2011), medium activity period (2012 to 2016), and weak activity period (post 2017). Landslide activity remains above the prequake level, with damaging events being rare but continuing to occur. Long-term remote sensing and on-site monitoring are required to understand the evolution of landslide activity after strong earthquakes. [ABSTRACT FROM AUTHOR]

The identification of multivariate geochemical anomalies is critical in mineral exploration. Machine learning algorithms have been successfully employed in the recognition of multivariate geochemical anomalies in support of mineral exploration, owing to their strong ability to learn the complex relationship between geochemical characteristics and mineralization. However, applications of machine learning algorithms suffer from data redundancy and the curse of dimensionality. In this study, a hybrid model combining t-distributed stochastic neighbor embedding (t-SNE) and random forest (RF) was used to solve the aforementioned problems in geochemical mapping for gold exploration in the northwestern Hubei Province of China. Specifically, t-SNE was used for dimension reduction and feature extraction from the major and trace elements of geochemical survey data, and RF was used for probabilistic classification of geochemical patterns related to gold deposits. A comparative study demonstrated that the hybrid model of t-SNE + RF possesses stronger generalization ability than that of PCA + RF and pure RF. Specifically, after 15 experiments, the mean area under the receiver operator characteristic curve (AUC) values of t-SNE + RF, PCA + RF, and pure RF were 0.83, 0.65, and 0.75, respectively. These results suggest that the hybrid model combining t-SNE and RF can more efficiently recognize geochemical anomalies associated with gold mineralization. Compared with PCA, t-SNE can more effectively identify hidden information in complex and nonlinear geochemical survey data. In addition, it can reduce information redundancy and further improve the efficiency of RF for processing multidimensional geochemical survey data. The high-probability areas obtained by t-SNE + RF showed a strong spatial correlation with known gold deposits, which can provide critical clues for further prospecting in the study area. [ABSTRACT FROM AUTHOR]

A rapid identification method for flue-cured tobacco quality was proposed based on Raman spectroscopy. Considering the critical quality factors of flue-cured tobacco-like oil content, softness, and glossiness, four statistical methods, random forest, K-nearest neighbor, logistic regression, and partial least squares, can effectively improve the accuracy of quality identification. We randomly collected 149 flue-cured tobacco samples from multiple producing areas in China. After Raman spectroscopy analysis, Savitzky–Golay convolution smoothing and multi-scatter correction were done. The functional groups were analyzed to select characteristic peaks as features for discriminant analysis. The results show that the Raman spectroscopic information can distinguish the quality of flue-cured tobacco with an accuracy greater than 95%, whereas the partial least-squares approach delivers an accuracy of 100%. We conclude that Raman spectroscopy can be considered a vital avenue for identifying the quality of flue-cured tobacco. [ABSTRACT FROM AUTHOR]

Purpose: Plant-associated microbes enhance nutrient access and stress tolerance of the host species, and therefore, are crucial for plant traits and resource strategies. However, the links between aboveground plant traits and belowground microbes related to plant resource strategies under stressful conditions remain poorly understood. Methods: We tested the relationships between leaf traits linked to water (carbon isotopic composition, δ13C) and nutrient use (elemental concentrations and stoichiometry) with microbial compositions in roots and rhizospheres of two dominant species (Artemisia ordosica and Leymus secalinus) in the Mu Us Desert, northern China. Results: L. secalinus exhibited higher Mg and Mn concentrations, N:P ratios, stoichiometric flexibility, and root fungi:bacteria ratios, but lower foliar K and Ca concentrations and δ13C values than A. ordosica. The leaf N:P of L. secalinus increased with the root fungi:bacteria ratios, whereas the leaf N:P of A. ordosica decreased with the root fungi:bacteria ratios. The plant elemental levels (P, N, K, Ca, Mn, and δ13C) of L. secalinus but not A. ordosica were significantly related to their root fungal composition. Additionally, the random forest model identified four key fungal families in predicting leaf elemental traits for both plant species. Conclusion: The results suggested tight coupling and coordination between leaf elemental traits and root microbial compositions (especially fungal communities) related to plant resource acquisition strategies. By regulating aboveground and belowground feedback loops through trait flexibility and root microbial compositions, the studied plant species can sustain their resource strategies under stressful environmental conditions. [ABSTRACT FROM AUTHOR]

Accurately identifying and quantifying the factors influencing PM2.5 pollution is of great significance for the prevention and control of pollution. However, the redundancy among potential factors of PM2.5 may be overlooked. Meanwhile, the inconsistent spatial distribution of the natural and socioeconomic conditions brings unique implications for the cities within a region, which may lead to an uncertain understanding of the relationship between pollution and environmental factors. This study focused on the Beijing-Tianjin-Hebei (BTH) Region, China, which presents complex and varied background conditions. Potential impact factors on PM2.5 were firstly screened by combining systematic cluster analysis with a random forest recursive feature elimination algorithm. Then, the representative multi-factor responsible for PM2.5 pollution in the region during the key period of 2014–2018 (when the strict national air pollution control policy was implemented). The results showed that the key driving factors of PM2.5 pollution in the BTH cities are different, indicating that the uniqueness of a city will have an impact on the leading causes of pollution. Further discussion shows that air control policy provides an effective way to improve air quality. This study aims to deepen the understanding of the risk drivers of air pollution within the BTH Region. In the future, it is recommended that more attention should be paid to the specific differences between the cities when formulating PM2.5 concentration control measures. [ABSTRACT FROM AUTHOR]

The functional group (FG) system sensu Colin S. Reynolds of freshwater phytoplankton has been widely applied in many aspects of freshwater ecological assessments. However, there is no current consensus as to how and to why some functional coda shows multiple habitat templates in different water bodies. To test whether there are multiple habitat templates for some functional coda in the FG system, we used two mesotrophic deep reservoirs in China as examples, analysing phytoplankton taxonomic and environmental data collected in 4 seasons over two years. Results showed that a large proportion of the indicators had similar habitat templates within the FG system, whilst some species had multiple or different habitat templates according to their niche differentiation. The random forest (RF) model filtered a minimum set of environmental conditions and provided two potential habitat templates for Oocystis lacustris. One explanatory habitat template of clear water provided by the FG system was verified in the Nanwan Reservoir, and the other habitat template of high dissolved inorganic nitrogen (DIN) was found in the Nianyushan Reservoir. Further studies of the potential multiple habitat templates for some functional coda are recommended for its proper use. [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]

Wetland vegetation classification using deep learning algorithm and unmanned aerial vehicle (UAV) images have attracted increased attentions. However, there exist several challenges in mapping karst wetland vegetation due to its fragmentation, intersection, and high heterogeneity of vegetation patches. This study proposed a novel approach to classify karst vegetation in Huixian National Wetland Park, the largest karst wetland in China by fusing single-class SegNet classification using the maximum probability algorithm. A new optimized post-classification algorithm was developed to eliminate the stitching traces caused by SegNet model prediction. This paper evaluated the effect of multi-class and fusion of multiple single-class SegNet models with different EPOCH values on mapping karst vegetation using UAV images. Finally, this paper carried out a comparison of classification accuracies between object-based Random Forest (RF) and fusion of single-class SegNet models. The specific conclusions of this paper include the followings: (1) fusion of four single-class SegNet models produced better classification for karst wetland vegetation than multi-class SegNet model, and achieved the highest overall accuracy of 87.34%; (2) the optimized post-classification algorithm improved classification accuracy of SegNet model by eliminating splicing traces; (3) classification performance of single-class SegNet model outperformed multi-class SegNet model, and improved classification accuracy (F1-Score) ranging from 10 to 25%; (4) Fusion of single-class SegNet models and object-based RF classifier both produced good classifications for karst wetland vegetation, and achieved over 87% overall accuracy. [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]

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]

The brain seems to be the most complex organ in the human body and operates as the central part of the nervous system. The classification of brain tumors is the most complicated problem which medical experts face. In our proposed work, the novelty is that we have adopted the hybridization of feature exaction techniques and a conglomerate of classification methods. The hybrid features are extracted from the tumor region using the Gray Level Co-occurrence Matrix technique and shape-based features. There are three different types of brain magnetic resonance imaging datasets used in work. For the segmentation, the Marker-controlled watershed segmentation strategy is implemented in this work. In this work, the hybrid classifier, which includes the Random Forest (RF) classifier, K-Nearest Neighbour classifier, and Decision Tree classifier, is implemented. Dataset 1 (China Hospital data) shows a better overall accuracy of 98.75%; for dataset 2, accuracy is 98.99%; and for dataset 3, the achieved accuracy is 98.92%. The other parameters that prove the overall work's efficacy include sensitivity, precision, specificity, F1-score, Cohen's kappa value, Dice coefficient, Jaccard Index, and area under the curve (AUC). The proposed work is also compared with the state-of-the-art methods and observed better one. [ABSTRACT FROM AUTHOR]

With less than ten years left to meet its pledge to peak carbon dioxide emissions (peak emissions hereafter) by 2030, China has entered a critical emissions reduction stage. How to meet this commitment in a context in which GDP per capita will double from 2020 by 2035 is a major decision-making issue for the Chinese government and people and one which warrants further study. To reveal the relationships between the GDP growth rate, the rate of decrease of carbon intensity and the time to reach peak emissions, this study translates the question as to "when China's carbon emissions peak will occur" into "how can one control the rate of carbon intensity decrease at a given GDP growth rate". In the light of the results of a random forest algorithm used to identify and project the key drivers of carbon intensity in China, a mathematical model was developed to simulate different scenarios relating to decreases in carbon intensity. The date at which Chinese carbon emissions will peak is predicted by comparing the rate of decrease of carbon intensity with the GDP growth rate. The results show that the time to peak emissions depends on the relationship between the rate of decrease of carbon intensity and the GDP growth rate, where the former depends mainly on the energy structure and policy. If China's annual GDP growth rate were 5.0% during the 15th Five-Year Plan, and if the share of non-fossil energy in total energy consumption were 23.0% or above, China's carbon emissions will peak before 2030. If the share of non-fossil fuels were 20.0% or less, China might not be able to reach its 2030 target. In this latter case an acceleration in the pace of energy restructuring would be required to reach peak emissions before 2030. The projected peak emissions scenarios suggest that the carbon peak will occur between 2025 to 2029, with average peak emissions of 11.2 billion tons and a distribution ranging from a minimum of 10.5 billion and a maximum of 11.9 billion tons. If the GDP growth rate were 4.5%, 5.5% or 6.0% during the 15th Five-year Plan, the share of non-fossil energy must reach 23.0%, 25.0% or 27.0%, respectively, to ensure that emissions peak by 2030. The results of this study provide a series of reference points for China's pursuit of feasible pathways to peak carbon emissions by 2030. [ABSTRACT FROM AUTHOR]

Displacement prediction plays a significant role in the landslide disaster early warning. However, landslide deformation is a complex nonlinear dynamic process, posing difficulties in the displacement prediction especially for the commonly used static models. This study applies an advanced deep machine learning method called gated recurrent unit (GRU) to the displacement prediction of the Jiuxianping landslide, which is a typical reservoir landslide located in the Yunyang County of Chongqing, China. Results show that the GRU-based approach is able to portray the variation of the periodic displacement in the testing dataset with fewer outliers. Although both the artificial neural network (ANN) and random forest regression (RFR) can capture the variation tendency of data points in the training dataset, they are unable to predict the local peaks well in the testing dataset. For the multivariate adaptive regression splines (MARS), the deformation characteristics of the periodic displacement curve cannot be well captured, and the overall predictive performance is unsatisfactory. Different from the three static models, the GRU model is essentially a dynamic model making full use of the historical information, which can portray the deformation characteristics of the Jiuxianping landslide rationally. [ABSTRACT FROM AUTHOR]

Rockburst is a severe geological hazard that restricts deep mine operations and tunnel constructions. To overcome the shortcomings of widely used algorithms in rockburst prediction, this study investigates the ensemble trees, i.e., random forest (RF), extremely randomized tree (ET), adaptive boosting machine (AdaBoost), gradient boosting machine, extreme gradient boosting machine (XGBoost), light gradient boosting machine, and category gradient boosting machine, for rockburst estimation based on 314 real rockburst cases. Additionally, Bayesian optimization is utilized to optimize these ensemble trees. To improve performance, three combination strategies, voting, bagging, and stacking, are adopted to combine multiple models according to training accuracy. ET and XGBoost receive the best capabilities (85.71% testing accuracy) in single models, and except for AdaBoost, six ensemble trees have high accuracy and can effectively foretell strong rockburst to prevent large-scale underground disasters. The combination models generated by voting, bagging, and stacking perform better than single models, and the voting 2 model that combines XGBoost, ET, and RF with simple soft voting, is the most outstanding (88.89% testing accuracy). The performed sensitivity analysis confirms that the voting 2 model has better robustness than single models and has remarkable adaptation and superiority when input parameters vary or miss, and it has more power to deal with complex and variable engineering environments. Eventually, the rockburst cases in Sanshandao Gold Mine, China, were investigated, and these data verify the practicability of voting 2 in field rockburst prediction. [ABSTRACT FROM AUTHOR]

Using modern census and environmental factor data, this study first identified the environmental factors that significantly affect the population distribution through Geodetector analysis and then constructed a population spatial distribution model based on the random forest regression algorithm. Finally, with this model and historical population data that were examined and corrected by historians, gridded population distributions with a spatial resolution of 10 km by 10 km in the traditional cultivated region of China (TCRC, hereafter) were reconstructed for six time slices from 1776 to 1953. Using the reconstruction dataset, the spatiotemporal characteristics of the population distribution were depicted. The results showed that (1) the environmental factors that significantly affected the population density differences among counties in the TCRC mainly consisted of elevation, slope, relief amplitude, distances to the nearest prefectural and provincial capitals, distance to the nearest river and the climatology moisture index. (2) Using the census data of 1934 counties in the TCRC in 2000 and the above-mentioned environmental factor data, a random forest regression algorithm-based population spatial distribution model was constructed. Its determination coefficient (R2) is 0.81. In 88.4% of the counties (districts), the relative errors of the model predictions were less than 50%. (3) From 1776 to 1953, the total population in the study area showed an uptrend. Prior to 1851, the population increased mainly in the Yangtze River Delta. During this period, the number of grid cells in which the population densities were greater than 500 persons per km2 increased from 292 to 683. From 1851 to 1953, the population increased extensively across the study area. In the North China Plain and the Pearl River Delta, the number of grid cells in which the population densities were greater than 500 persons per km2 increased from 36 to 88 and from 4 to 35, respectively. The spatial clustering pattern of the population distribution varied temporally. The potential reasons included the shifts in economic development hot spots, traditional beliefs, wars, famine, and immigration policies. (4) Between our reconstructions and the HYDE dataset, there are large differences in the data sources, selected environmental factors and modeling methods. As a consequence, in comparison to our reconstructions, there were fewer populations in the eastern area and more populations in the western area from 1776 to 1851 and more populations in urban areas and fewer populations in rural areas after 1851 in the HYDE dataset. [ABSTRACT FROM AUTHOR]

Artificial intelligence has been increasingly employed to improve operations for various firms and industries. In this study, we construct a box office revenue prediction system for a film at its early stage of production, which can help management overcome resource allocation challenges considering the significant investment and risk for the whole film production. In this research, we focus on China's film market, the second-largest box office in the world. Our model is based on data regarding the nature of a film itself without word-of-mouth data from social platforms. Combining extreme gradient boosting, random forest, light gradient boosting machine, k-nearest neighbor algorithm, and stacking model fusion theory, we establish a stacking model for film box office prediction. Our empirical results show that the model exhibits good prediction accuracy, with its 1-Away accuracy being 86.46%. Moreover, our results show that star influence has the strongest predictive power in this model. [ABSTRACT FROM AUTHOR]

Multisource geoscience data can provide significant information for mineral exploration in a variety of ways. For example, remote-sensing images record the spectral characteristics of objects, and geochemical data represent the enrichment or depletion of geochemical elements, which reflect the physical and chemical attributes of geological features. In this study, a hybrid model comprising data fusion and machine learning was applied for lithological mapping. This process is illustrated through a case study of mapping several lithological units in the Cuonadong Dome, in the northeastern part of the Himalayas, China. In this process, multisource data fusion technology is first used to provide more abundant information by integrating geochemical data and Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) remote-sensing images, retaining both the geochemical patterns and the textural structure of the remote-sensing images. Then, a random forest metric learning (RFML) approach is employed to achieve a high classification performance based on the fused data. RFML adopts metric learning in the classification process of each decision tree calculation, making full use of the advantages of random forest and metric learning. Seven target lithological units were discriminated with 93.0% overall accuracy. This excellent performance demonstrates the effectiveness of the hybrid method in the geological exploration of areas in poor environments that have undergone limited geological research. [ABSTRACT FROM AUTHOR]

A novel machine learning ensemble model that is a hybridization of Bagging and random subspace–based naïve Bayes tree (RSNBtree), named as BRSNBtree, was used to prepare a landslide susceptibility map for Zigui County of the Three Gorges Reservoir Area, China. The proposed method is implemented by using the Bagging scheme to integrate the base-level RSNBtree model. To predict landslide susceptibility for the study area, a spatial database consisted of 807 landslides and 11 conditioning factors has been prepared. Evaluation of conditioning factors was conducted using the Pearson correlation coefficient and Relief-F method. The results indicate that all factors except the topographic wetness index can be accepted as modeling inputs. Particularly, the distance to rivers is the most important factor in landslide susceptibility prediction. The performance of landslide models was evaluated using statistical indices and areas under the receiver operatic characteristic curve (AUC). The support vector machines (SVM) and random forest (RF) were adopted for the comparison with our methods. Results show that the BRSNBtree (AUC = 0.968) achieves the highest prediction performance, which successfully refines the RSNBtree (AUC = 0.938) and outperforms the RF (AUC = 0.949) and SVM (AUC = 0.895). Therefore, the proposed BRSNBtree presents advantages in targeting landslide susceptible areas and provides a promising method for landslide susceptibility assessment. The developed susceptibility maps could facilitate effective landslide risk management for this landslide-prone area. [ABSTRACT FROM AUTHOR]

The built environment can contribute to the spread of the novel coronavirus disease (COVID-19) by facilitating human mobility and social contacts between infected and uninfected individuals. However, mobility data capturing detailed interpersonal transmission at a large scale are not available. In this study, we aimed to objectively assess the influence of key built environment factors, which create spaces for activities—"inferred activity" rather than "actually observed activity"—on the spread of COVID-19 across townships in China at its initial stage through a random forest approach. Taking data for 2994 township-level administrative units, the spread is measured by two indicators: the ratio of cumulative infection cases (RCIC), and the coefficient of variation of infection cases (CVIC) that reflects the policy effect in the initial stage of the spread. Accordingly, we selected 19 explanatory variables covering built environment factors (urban facilities, land use, and transportation infrastructure), the level of nighttime activities, and the inter-city population flow (from Hubei Province). We investigated the spatial agglomerations based on an analysis of bivariate local indicators of spatial association between RCIC and CVIC. We found spatial agglomeration (or positive spatial autocorrelations) of RCIC and CVIC in about 20% of all townships under study. The density of convenience shops, supermarkets and shopping malls (DoCSS), and the inter-city population flow (from Hubei Province) are the two most important variables to explain RCIC, while the population flow is the most important factor in measuring policy effects (CVIC). When the DoCSS gets to 21/km2, the density of comprehensive hospitals to 0.7/km2, the density of road intersections to 72/km2, and the density of gyms and sports centers to 2/km2, their impacts on RCIC reach their maximum and remain constant with further increases in the density values. Stricter policy measures should be taken at townships with a density of colleges and universities higher than 0.5/km2 or a density of comprehensive hospitals higher than 0.25/km2 in order to effectively control the spread of COVID-19. [ABSTRACT FROM AUTHOR]

We focus on the causes of fluctuations in wintertime PM10 in nine regional core cities of China using two machine learning models, Random Forest (RF) and Recurrent Neural Network (RNN). RF and RNN both show high performance in predicting hourly PM10 using only gaseous air pollutants (SO2, NO2 and CO) as inputs, showing the predominance of the secondary inorganic aerosol and implying the existence of thermodynamic equilibrium between gaseous air pollutants and PM10. Also, we find the following results. The correlation of gaseous air pollutants and PM10 were more relevant than that of meteorological conditions and PM10. CO was the predominant factor for PM10 in the Beijing-Tianjin-Hebei Plain and the Yangtze River Delta while SO2 and NO2 were also important features for PM10 in the Pearl River Delta and Sichuan Basin. The spatial heterogeneity and temporal homogeneity of PM10 in China are revealed. The long-range transported PM10 was substantiated to be insignificant, except in the sandstorms. The severity of PM10 was attributable to the lopsided shift of thermodynamic equilibrium and the phenology of indigenous flora. [ABSTRACT FROM AUTHOR]

Air pollution has emerged as one of the most urgent problems worldwide over the past few years. Especially, fine particulate matter with a diameter smaller than 2.5 micrometres (PM2.5) has seriously endangered the human life and health worldwide. Thus, monitoring accurate and spatio-temporal continuously PM2.5 concentrations is essential for controlling air pollution. The key to accurately estimating PM2.5 concentrations is to build a reliable aerosol optical depth (AOD)–PM2.5 model, which is mainly determined by the AOD remotely sensed products, meteorological parameters, and estimating methods. However, no systematic evaluation and analysis of the influence of these three variables on AOD–PM2.5 model has yet been reported. Based on Terra and Aqua Moderate Resolution Imaging Spectroradiometer AOD products, reanalysis meteorological data, and ground-based PM2.5 data during 2014–2015 in eastern China, we analyzed the influence of above mentioned variables on the accuracy of the AOD–PM2.5 model. The four modeling methods investigated are stepwise multiple linear regression (SMLR), backpropagation neural network (BPNN), classification and regression tree (CART), and random forest (RF). Adjusted R2, mean absolute error (MAE), product index (PI), spatial resolution index (SRI), and Taylor diagrams are used to assess the accuracy of models. The results show that adding meteorological elements that vary with time and height can improve the accuracy by 4.97% over eastern China. The average PI of Terra AOD products increased by 0.15 compared with that of Aqua AOD products. Most SRIs have positive values, suggesting that AOD products with a spatial resolution of 10 km can lead to a more accurate AOD–PM2.5 model. The Taylor diagram indicates that RF model > BPNN model > CART model > SMLR model in terms of performance. Therefore, Terra AOD products with spatial resolution of 10 km and RF are more suitable for use with the AOD–PM2.5 model in eastern China. [ABSTRACT FROM AUTHOR]

To improve students' performance effectively, many Chinese universities are establishing systems to predict student's academic performance and sending student's academic early alerts. With student's population of over 600,000, Chinese-foreign cooperation in running schools (CFCRS) has become one of the booming higher education forms in China. Compared with students in the non-cooperatively running programs, CFCRS students' academic performances are weaker on average. To predict the academic-at-risk students and provide efficient supports to the students, a precise and prompt academic prediction is in great need. Therefore, this research aims at representing a more efficient and accurate model to predict academic performance of CFCRS students which will be based on graph convolutional network. In this research, student's similarity is measured on academic performance by Pearson correlation coefficient. An undirected graph in which similar students are connected is conducted. Feature matrix is composed of students' previous grades. In addition, graph convolutional network is trained based on the undirected graph and feature matrix. In the experiment, it shows that this model predicts certain student's performance on certain course from the final exam results in previous semesters, which might improve learning efficiency and teaching quality. With an average accuracy of 81.5%, graph convolutional network outperforms support vector machine and random forest models. [ABSTRACT FROM AUTHOR]

Numerous researches have been published on the application of landslide susceptibility assessment models; however, they were only applied in the same areas as the models were originated, the effect of applying the models to other areas than the origin of the models has not been explored. This study is purposed to develop an optimized random forest (RF) model with best ratios of positive-to-negative cells and 10-fold cross-validation for landslide susceptibility mapping (LSM), and then explore its generalization ability not only in the area where the model is originated but also in area other than the origin of the model. Two typical counties (Fengjie County and Wushan County) in the Three Gorges Reservoir area, China, which have the same terrain and geological conditions, were selected as an example. To begin with, landslide inventory was prepared based on field investigations, satellite images, and historical records, and 1 522 landslides were then identified in Fengjie County. 22 landslide-conditioning factors under the influence of topography, geology, environmental conditions, and human activities were prepared. Then, combined with 10-fold cross-validation, three typical ratios of positive-to-negative cells, i.e., 1:1, 1:5, and 1:10, were adopted for comparative analyses. An optimized RF model (Fengjie-based model) with the best ratios of positive-to-negative cells and 10-fold cross-validation was constructed. Finally, the Fengjie-based model was applied to Fengjie County and Wushan County, and the confusion matrix and area under the receiver operating characteristic (ROC) curve value (AUC) were used to estimate the accuracy. The Fengjie-based model delivered high stability and predictive capability in Fengjie County, indicating a great generalization ability of the model to the area where the model is originated. The LSM in Wushan County generated by the Fengjie-based model had a reasonable reference value, indicating the Fengjie-based model had a great generalization ability in area other than the origin of the model. The Fengjie-based model in this study could be applied in other similar areas/countries with the same terrain and geological conditions, and a LSM may be generated without collecting landslide information for modeling, so as to reduce workload and improve efficiency in practice. [ABSTRACT FROM AUTHOR]

Lake ecosystems are exposed to a range of anthropogenic pressures, particularly eutrophication, and in some cases also stocking and/or overfishing of top-predator fish species, all factors that have implications for the food web structure and which could lead to dominance of nuisance cyanobacteria. Restoration of degraded lakes demands insight into the relative role of top-down for bottom-up regulating forces. While knowledge about these forces in temperate lakes is extensive, comparatively little is known of their role in subtropical lakes where the importance of herbivorous and benthic feeding fish is higher. Here, we analyzed a long-term monitoring data set on subtropical, shallow Lake Taihu, China, and applied random forests regression to examine how phytoplankton was related to environmental variables and biotic assemblages. Our results indicate that the biomass and density of phytoplankton increased with increasing biomass of benthivorous and zooplanktivorous fish and decreased with increases in ammonium concentrations, the nitrogen to phosphorus ratio, and zooplankton biomass, while the response to climate fluctuations and changes in the biomass of piscivores was weak. Effects of higher trophic levels explained as much of the variance in phytoplankton biomass as did nutrients and climatic factors. Moreover, the remarkably reduced ratio of zooplankton to phytoplankton biomass and the decline in cladoceran individual biomass emphasized the increasing importance of top-down control in regulating the phytoplankton following extensive stocking. Our findings offer insight into how fish management may be combined with catchment-level restoration measures to conserve and enhance water quality. [ABSTRACT FROM AUTHOR]

In order to improve the prediction accuracy and modeling speed of railway freight volume, this paper combines the cargo floating price prediction model with the neural network algorithm (hereinafter referred to as NNA) to establish a prediction model. The railway cargo floating price based on neural network (hereinafter referred to as PMBCFP) relies on the random forest regression algorithm (hereinafter referred to as RFRA). Through the neural network operator in the prediction model of the floating price of goods, the randomness of the original sequence is weakened, and the implicit rules in the series are mined. The characteristics of neural networks are computationally very simple. In addition, a random forest regression algorithm is applied to the optimization, RFRA's choice. Case studies of China's rail freight volume show that RMSE and other indicators are faster. The MAE, MPE and Tell inequality coefficients obtained from this model were 0.0628, 0.0523, 0.0162 and 0.0107, respectively. This model has good prediction results. The time to search for the best parameters of RFRA using the NNA algorithm is 55.656 s, which is 10.462 s less than the time required for traditional cross-validation methods. Therefore, it is suitable for short-term forecasting of railway freight volume. [ABSTRACT FROM AUTHOR]

Landslide susceptibility mapping (LSM) is a critical tool for mitigating the damages caused by geologic disasters. The selection of map units and mathematical models greatly affects the efficiency of LSM. To obtain the most appropriate combination of map units and mathematical models, four scales of catchment map units (CMUs) were analyzed and random forest (RF) and multivariate adaptive regression spline (MARSpline) models were applied in Gero City, Japan. The percentage of correctly identified landslides and the areas under the relative operating characteristic (ROC) curve were used to evaluate the model performances. The results indicate that the RF model had higher prediction accuracy than the MARSpline model, especially when the size of the CMU was 0.09 km2. A relatively high percentage of landslides fell into the high and very high landslide susceptibility classes (73%) and the lowest percentage of landslides fell into the very low landslide susceptibility classes (0.82%). The prediction-area (P-A) plots indicated that the prediction rates were higher for the RF model than the MARSpline model. The results of this study also suggest that the model accuracy can be increased if the appropriate CMU size is used. Therefore, the potential benefits of using the RF model in combination with the appropriate CMU size should be further explored using additional landslide-conditioning factors and other models. [ABSTRACT FROM AUTHOR]

Coal-floor water-inrush incidents account for a large proportion of coal mine disasters in northern China, and accurate risk assessment is crucial for safe coal production. A novel and promising assessment model for water inrush is proposed based on random forest (RF), which is a powerful intelligent machine-learning algorithm. RF has considerable advantages, including high classification accuracy and the capability to evaluate the importance of variables; in particularly, it is robust in dealing with the complicated and non-linear problems inherent in risk assessment. In this study, the proposed model is applied to Panjiayao Coal Mine, northern China. Eight factors were selected as evaluation indices according to systematic analysis of the geological conditions and a field survey of the study area. Risk assessment maps were generated based on RF, and the probabilistic neural network (PNN) model was also used for risk assessment as a comparison. The results demonstrate that the two methods are consistent in the risk assessment of water inrush at the mine, and RF shows a better performance compared to PNN with an overall accuracy higher by 6.67%. It is concluded that RF is more practicable to assess the water-inrush risk than PNN. The presented method will be helpful in avoiding water inrush and also can be extended to various engineering applications. [ABSTRACT FROM AUTHOR]

The main objective of the current study is to apply a random forest (RF) data-driven model and prioritization of landslide conditioning factors according to this method and its comparison to a multivariate adaptive regression spline (MARS) model for landslide susceptibility mapping in China. For this purpose, at first, landslide locations were identified by earlier reports, aerial photographs, and field surveys and a total of 348 landslides were mapped from various sources in GIS. Then, the landslide inventory was randomly split into a training dataset (70% = 244 landslides) and the remaining (30% = 104 landslides) were used for validation. In this study, 12 landslide conditioning factors were applied to detect the most susceptible areas. These factors were slope aspect, altitude, distance to faults, lithology, normalized difference vegetation index, plan curvature, profile curvature, distance to rivers, distance to roads, slope angle, stream power index, and topographic wetness index. The relationship between each conditioning factor and landslide was finalized using a frequency ration (FR) model. Subsequently, landslide-susceptible areas were mapped using the MARS and RF models. The results revealed that the most important conditioning factors according to the accuracy measure (mean decrease) of the RF model are lithology (23.47%), distance to faults (22.21%), and altitude (19.58%). We also notice that altitude (19.04%), distance to faults (18.83%), and distance to roads (15.29%) have the highest importance according to the Gini measure. Finally, the accuracy of the landslide susceptibility maps produced from the two models was verified using a receiver operating characteristics curve. The results showed that the landslide susceptibility map produced using the MARS model has a higher prediction rate than RF by area under the curve values of 87.51 and 77.32%, respectively. According to the validation results, the map produced by the MARS model exhibits the better accuracy and could be proposed for land-use planning in the study area. [ABSTRACT FROM AUTHOR]

The main objective of the present study was to produce a landslide susceptibility map by implementing a novel methodology that combines Information Theory and GIS-based methods for the Nancheng County, China, an area with numerous reported landslide events. Specifically, the information coefficient that is estimated from Shannon's entropy index was used to determine the number of classes of each landslide-related variable that maximizes the information coefficient, while three methods, logistic regression, weight of evidence, and random forest algorithm, were implemented to produce the landslide susceptibility map. The comparison of the various models was based on the assessment of a database of 112 past landslide events, which were divided randomly into a training dataset (70 %) and a validation dataset (30 %). The identification of the areas affected was established by analyzing airborne imagery, extensive field investigation, and the examination of previous research studies, while the morphometric variables were derived using remote sensing technology. The geo-environmental conditions in those locations were analyzed regarding their susceptibility to slide. In particular, 11 variables were analyzed: lithology, altitude, slope, aspect, topographic wetness index, sediment transport index, profile curvature, plan curvature, distance to rivers, distance to faults, and distance to roads. The comparison and validation of the outcomes of each model were achieved using statistical evaluation measures, the receiving operating characteristic, and the area under the success and predictive rate curves. Each model gave similar outcomes; however, the random forest model had a slightly higher predictive performance in terms of area under the curve (0.9220) against the ones estimated for the weight of evidence (0.9090) and the logistic regression model (0.8940). The same pattern of performance was reported when the success power of the models was calculated. Random forest was slightly better than the other two models in terms of area under the curve (0.9350) in comparison with the weight of evidence (0.9255) and logistic regression (0.9097). The predictive performance was estimated by using the validation dataset, while the success power of the models was estimated by using the training dataset. From the visual inspection of the produced landslide susceptibility maps, the most susceptible areas are located at the west and east mountainous areas, while moderate to low susceptibility values characterize the central area. [ABSTRACT FROM AUTHOR]

Introduction: Urbanization is associated with major changes in environmental and lifestyle exposures that may influence metabolic signatures. Objectives: We investigated cross-sectional urban and rural differences in plasma metabolome analyzed by liquid chromatography/mass spectrometry platform in 500 Chinese adults aged 25–68 years from two neighboring southern Chinese provinces. Methods: We first examined the overall metabolome differences by urban and rural residential location, using Orthogonal Partial Least Squares Discriminant Analysis (OPLS-DA) and random forest classification. We then tested the association between urbanization status and individual metabolites using a linear regression adjusting for age, sex, and province and conducted pathway analysis (Fisher's exact test) to identify metabolic pathways differed by urbanization status. Results: We observed distinct overall metabolome by urbanization status in OPLS-DA and random forest classification. Using linear regression, out of a total of 1108 unique metabolite features identified in this sample, we found that 266 metabolites were differed by urbanization status (positive false discovery rate-adjusted p-value, q-value < 0.05). For example, the following metabolites were positively associated with urbanization status: caffeine metabolites from xanthine metabolism, hazardous pollutants like 4-hydroxychlorothalonil and perfluorooctanesulfonate, and metabolites implicated in cardiometabolic diseases, such as branched-chain amino acids. In pathway analysis, we found that xanthine metabolism pathways differed by urbanization status (q-value = 1.64E−04). Conclusion: We detected profound differences in host metabolites by urbanization status. Urban residents were characterized by metabolites signaling caffeine metabolism and toxic pollutants and metabolites on known pathways to cardiometabolic disease risks, compared to their rural counterparts. Our findings highlight the importance of considering urbanization in metabolomics analysis. [ABSTRACT FROM AUTHOR]

This study investigated the diarrhoea seasonality and its potential drivers as well as potential opportunities for future diarrhoea control and prevention in China. Data on weekly infectious diarrhoea cases in 31 provinces of China from 2005 to 2012, and data on demographic and geographic characteristics, as well as climatic factors, were complied. A cosinor function combined with a Poisson regression was used to calculate the three seasonal parameters of diarrhoea in different provinces. Regression tree analysis was used to identify the predictors of diarrhoea seasonality. Diarrhoea cases in China showed a bimodal distribution. Diarrhoea in children <5 years was more likely to peak in fall-winter seasons, while diarrhoea in persons > = 5 years peaked in summer. Latitude was significantly associated with spatial pattern of diarrhoea seasonality, with peak and trough times occurring earlier at high latitudes (northern areas), and later at low latitudes (southern areas). The annual amplitudes of diarrhoea in persons > = 5 years increased with latitude (r = 0.62, P<0.001). Latitude 27.8° N and 38.65° N were the latitudinal thresholds for diarrhoea seasonality in China. Regional-specific diarrhoea control and prevention strategies may be optimal for China. More attention should be paid to diarrhoea in children <5 years during fall-winter seasons. [ABSTRACT FROM AUTHOR]