Search

Shear slowness data are crucial data in rock physics analysis and seismic reservoir characterization. In petrophysical formation evaluation, the use of sonic data is limited, and hence, sonic data, especially shear sonic, are not considered as critical. In many deep-water wells to save the cost of operations, shear sonic data are not recorded. In these scenarios for rock physics analysis, it becomes necessary to predict shear sonic data from other available datasets. Conventional techniques for shear slowness predictions rely on empirical relations and rock physics modeling. However, these approaches require extensive information as input and additionally carry assumptions and multiple prerequisites. Presently with the advancement of computing power Machine learning (ML) emerges as a robust and optimized technique for predicting precise DTS in quick time and with fewer input datasets. In this study, wells located in the deep-waters of the East Coast of India and penetrated siliciclastic reservoirs of both compacted sand and soft high porosity sands were used as input to train the ML algorithm. Random Forest machine learning algorithm is best used for both classification and regression tasks, and this algorithm is used here for the data prediction. As a comparison, the convolutional LSTM method is also used for data prediction. To comply with the geological variability in the prediction and to enhance the prediction accuracy, rock physics understandings were used as a guide in feature engineering. The RF prediction shows a good match of ~ 93%, and the LSTM model prediction shows ~ 94% correlation at validation well. Both the model predicted data show good agreement with the rock physics modeling interpretations at the target well. [ABSTRACT FROM AUTHOR]

Machine learning (ML) approaches have been developed to predict materials' corrosion inhibition efficiency, particularly pyrimidine compounds. Notably, the virtual sample generation (VSG) technique enhances prediction accuracy, a novel approach for handling small datasets in this context. The random forest model, the best-performing nonlinear algorithm, showed substantial accuracy improvement based on the increase in R2 value from 0.05 to 0.99 and the decrease in RMSE value from 5.60 to 0.42, after applying VSG. These results underscore the efficacy of the VSG technique in boosting the predictive performance of ML models, particularly in scenarios constrained by limited data availability. [ABSTRACT FROM AUTHOR]

Purpose: Public debt forecasts represent a key policy issue. Many methodologies have been employed to predict debt sustainability, including dynamic stochastic general equilibrium models, the stock flow consistent method, the structural vector autoregressive model and, more recently, the neuro-fuzzy method. Despite their widespread application in the empirical literature, all of these approaches exhibit shortcomings that limit their utility. The present research adopts a different approach to public debt forecasts, that is, the random forest, an ensemble of machine learning. Design/methodology/approach: Using quarterly observations over the period 2000–2021, the present research tests the reliability of the random forest technique for forecasting the Italian public debt. Findings: The results show the large predictive power of this method to forecast debt-to-GDP fluctuations, with no need to model the underlying structure of the economy. Originality/value: Compared to other methodologies, the random forest method has a predictive capacity that is granted by the algorithm itself. The use of repeated learning, training and validation stages provides well-defined parameters that are not conditional to strong theoretical restrictions This allows to overcome the shortcomings arising from the traditional techniques which are generally adopted in the empirical literature to forecast public debt. [ABSTRACT FROM AUTHOR]

Malaria is a deadly disease that can take a person's life if not predicted or cured correctly. Numerous factors like temperature, humidity, precipitation, etc., impact India's increasing cases of malaria diseases. This research presents an advanced machine learning regression technique recently developed to anticipate the prevalence of malaria in Tripura using a real-world data. The proposed structure uses nine different regression methods, such as multilayer perceptron (MLP), random forest, support vector regressor, gradient boosting regressor, Bayesian ridge, kernel ridge, extreme gradient boost regressor (XGB), light gradient boosting machine (LGBM regressor and linear regression, to predict malaria using the most affecting factors of malaria diseases, namely temperature, humidity, precipitation, month, and years as input. Furthermore, to opt out the best suited technology for malaria cases prediction, the range of value method (ROVM)–multi-criteria decision methods (MCDM) technique has been applied, considering various statistical measurements as criteria. Ultimately, a comparison of various MCDM techniques reveals that MLP, XGB, and RF emerge as the top three choices. MLP regression, with root-mean-square error (RMSE) value of 0.03357, yields the lowest RMSE value, and the coefficient of determination (R2) is 0.97616, yielding the maximum among other regressions. To effectively battle the illness in Tripura, it could be useful for continuing intervention tactics by governmental, profit and nonprofit organizations. [ABSTRACT FROM AUTHOR]

Land Surface Temperature (LST) is a crucial parameter in Earth observation and environmental studies due to its significance in various fields. The purpose of this study is to investigate the effects of including spatial information into the Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) models for forecasting LST. The significance and impact of each input parameter on the models’ predictive capabilities are assessed using the SHAP (SHapley Additive exPlanations) approach and the model intercomparisons were done using the error evaluation metrices. The predictions were further validated using the Pearson correlation, independent samples t-test and potential geographic anomalies in the predictions are examined by spatial comparison of predicted errors using classification maps and error envelopes. The projected errors are within the acceptable range and range from − 2.267 ◦C to 1.292 ◦C for the spatially enhanced RF model and from − 1.675 ◦C to 1.439 ◦C for the spatially enhanced XGBoost model. These error ranges closely align with the training data’s quality flag of ±2 ◦C, demonstrating the models’ capability to predict LST accurately and within a reasonable error range. The findings show the significance of adding spatial information for precise LST prediction and draw attention to possible uses for such models in environmental monitoring and management. The work advances our understanding of spatial modelling strategies and offers practical guidelines for enhancing LST forecasts. [ABSTRACT FROM AUTHOR]

The current research is dedicated to harnessing cutting-edge technologies within the paradigm of Industry 5.0. The objective is to capitalize on advancements in Machine and Deep Learning techniques. This research endeavors to construct robust predictive models, utilizing historical data, for precise real-time predictions in estimating material quantities within a cement workshop. Machine Learning regressors evaluated based on several metrics, SVR (R-squared 0.9739, MAE 0.0403), Random Forest (R-squared 0.9990, MAE 0.0026), MLP (R-squared 0.9890, MAE 0.0255), Gradient Boosting (R-squared 0.9989, MAE 0.0042). The time series models LSTM and GRU yielded R-squared 0.9978, MAE 0.0100, and R-squared 0.9980, MAE 0.0099, respectively. The ultimate outcomes include improved and efficient production, optimization of production processes, streamlined operations, reduced downtime, mitigation of potential disruptions, and the facilitation of the factory's evolution towards intelligent manufacturing processes embedded within the framework of Industry 5.0. These achievements underscore the potential impact of leveraging advanced machine learning techniques for enhancing the operational dynamics and overall efficiency of manufacturing facilities [ABSTRACT FROM AUTHOR]

The paper explores the possibilities of using data classification methods when forecasting time series of the geomagnetic Kp-index by machine learning methods. To classify categories of the Kp-index based on the degree of disturbance, linear and logistic regression, random forest, gradient boosting on top of decision trees, and artificial neural networks of various architectures are used. The results of these methods are compared with a trivial inertial forecast (the statistical indicators of which for problems of this type are always high) at horizons from 3 h to 1 day in 3-h increments. The problem of choosing a cross-validation scheme for selecting the model hyperparameters, ways to overcome the imbalance of categories, the relative importance of input features, as well as the dependence of the results on the test sample (beginning of the 25th solar activity cycle) on inclusion in the training sample of data from the 23rd and 24th cycles or only the 24th cycles are studied. Based on the results, conclusions are drawn about the preferred methods for classifying values of the Kp-index based on the level of geomagnetic disturbance. Ways for further research and possible improvement of the classification quality are outlined, including for determining the characteristic hidden states of Earth's magnetosphere as a dynamic system in order to improve the quality of forecasting geomagnetic indices. [ABSTRACT FROM AUTHOR]

Execution of a marine operation (MO) requires coordinated actions of several vessels conducting simultaneous and sequential offshore activities. These activities have their operational limits given in terms of environmental parameters. Wave parameters are important because of their high energetic level. During the execution of a MO, forecast wave spectral parameters, i.e., significant wave height (Hs), peak period (Tp), and peak direction, are used to make an on-board decision. For critical operations, the use of forecasts can be complemented with buoy measurements. This paper proposes to use synthetic statistics of vessel dynamic responses to predict "real-time" wave spectral parameters using multi-output machine learning (ML) regression algorithms. For a case study of a vessel with no forward speed, it is observed that the random forest model predicts accurate Hs and Tp parameters. The prediction of wave direction is not very accurate but it can be corrected with on-board observations. The random forest model has good performance; it is efficient, useful for practical purposes, and comparable with other deep learning models reported in the scientific literature. Findings from this research can be valuable for real-time assessment of wave spectral parameters, which are necessary to support decision-making during the execution of MOs. [ABSTRACT FROM AUTHOR]

Predicting electricity production from renewable energy sources, such as solar photovoltaic installations, is crucial for effective grid management and energy planning in the transition towards a sustainable future. This study proposes machine learning approaches for predicting electricity production from solar photovoltaic installations at a regional level in Italy, not using data on individual installations. Addressing the challenge of diverse data availability between pinpoint meteorological inputs and aggregated power data for entire regions, we propose leveraging meteorological data from the centroid of each Italian province within each region. Particular attention is given to the selection of the best input features, which leads to augmenting the input with 1-hour-lagged meteorological data and previous-hour power data. Several ML approaches were compared and examined, optimizing the hyperparameters through five-fold cross-validation. The hourly predictions encompass a time horizon ranging from 1 to 24 h. Among tested methods, Kernel Ridge Regression and Random Forest Regression emerge as the most effective models for our specific application. We also performed experiments to assess how frequently the models should be retrained and how frequently the hyperparameters should be optimized in order to comprise between accuracy and computational costs. Our results indicate that once trained, the model can provide accurate predictions for extended periods without frequent retraining, highlighting its long-term reliability. [ABSTRACT FROM AUTHOR]

Introduction: Prediction of outcomes following allogeneic hematopoietic cell transplantation (HCT) remains a major challenge. Machine learning (ML) is a computational procedure that may facilitate the generation of HCT prediction models. We sought to investigate the prognostic potential of multiple ML algorithms when applied to a large single-center allogeneic HCT database. Methods: Our registry included 2,697 patients that underwent allogeneic HCT from January 1976 to December 2017. 45 pretransplant baseline variables were included in the predictive assessment of each ML algorithm on overall survival (OS) as determined by area under the curve (AUC). Pretransplant variables used in the EBMT ML study (Shouval et al., 2015) were used as a benchmark for comparison. Results: On the entire dataset, the random forest (RF) algorithm performed best (AUC 0.71 ± 0.04) compared to the second-best model, logistic regression (LR) (AUC = 0.69 ± 0.04) (p < 0.001). Both algorithms demonstrated improved AUC scores using all 45 variables compared to the limited variables examined by the EBMT study. Survival at 100 days post-HCT using RF on the full dataset discriminated patients into different prognostic groups with different 2-year OS (p < 0.0001). We then examined the ML methods that allow for significant individual variable identification, including LR and RF, and identified matched related donors (HR = 0.49, p < 0.0001), increasing TBI dose (HR = 1.60, p = 0.006), increasing recipient age (HR = 1.92, p < 0.0001), higher baseline Hb (HR = 0.59, p = 0.0002), and increased baseline FEV1 (HR = 0.73, p = 0.02), among others. Conclusion: The application of multiple ML techniques on single-center allogeneic HCT databases warrants further investigation and may provide a useful tool to identify variables with prognostic potential. [ABSTRACT FROM AUTHOR]

The article proposes to use machine learning as one of the areas of artificial intelligence to forecast the volume of biogas production from household organic waste. The use of five regression algorithms (Linear Regression, Ridge Regression, Lasso Regression, Random Forest Regression, and Gradient Boosting Regression) to create an effective model for forecasting the volume of biogas production from household organic waste is considered. Based on the comparison of these algorithms by MSE and MAE indicators, the quality of training and their accuracy during forecasting are evaluated. The proposed algorithm for creating a model for forecasting biogas production volumes from household organic waste involves the implementation of 10 main and 3 auxiliary steps. Their advantage is that they aid in the performance of component data analysis, which is carried out based on the method of reducing the dimensionality of the data set, increasing interpretability, and minimizing the risk of data loss. An analysis of 2433 data is was carried out, which characterizes the formation of biogas from food (FW) and yard waste (YW) according to four features. Data preparation is performed using the Jupyter Notebook environment in Python. We select five machine learning algorithms to substantiate an effective model for forecasting volumes of biogas production from household organic waste. On the basis of the conducted research, the main advantages and disadvantages of the used algorithms for building forecasting models of biogas production volumes from household organic waste are determined. It is found that two models, "Random Forest Regressor" and "Gradient Boosting Regressor", show the best accuracy indicators. The other three models (Linear Regression, Ridge Regression, Lasso Regression) are inferior in accuracy and were not considered further. To determine the accuracy of the "Random Forest Regressor" and "Gradient Boosting Regressor" models, we choose the MSE and MAE indicators. The Random Forest Regressor model is found to be a more accurate model compared to the Gradient Boosting Regressor. This is confirmed by the fact that the MSE of the "Random Forest Regressor" model on the training data set is 7.14 times smaller than that of the "Gradient Boosting Regressor" model. At the same time, MAE is 2.67 times smaller in the "Random Forest Regressor" model than in the "Gradient Boosting Regressor" model. The MSE and MAE of both models are worse on the test data set, which indicates overtraining tendencies. The Gradient Boosting Regressor model has worse MSE and MAE than the Random Forest Regressor model on both the training and test data sets. It is established that the model based on the "Random Forest Regressor" algorithm is the most effective for forecasting the volume of biogas production from household organic waste. It provides MAE = 0.088 on test data and the smallest absolute errors in predictions. Further systematic improvement of the "Random Forest Regressor" model for forecasting biogas production volumes from household organic waste based on new data will ensure its accuracy and maintain competitive advantages. [ABSTRACT FROM AUTHOR]

Uncertainty presents unfamiliar circumstances or incomplete information that may be difficult to handle with a single model of a traditional machine learning algorithm. They are possibly limited by inadequate data, an ambiguous model, and learning performance to make a prediction. Therefore, ensemble modeling is proposed as a powerful model for enhancing predictive capabilities and robustness. This study aims to apply Bayesian prediction to ensemble modeling because it can encode conditional dependencies between variables and present the reasoning model using the BMIC model. The BMIC has clarified knowledge in the model which is ready for learning. Then, it was selected as the base model to be integrated with well-known algorithms such as logistic regression, K-nearest neighbors, decision trees, random forests, support vector machines (SVMs), neural networks, naive Bayes, and XGBoost classifiers. Also, the Bayesian neural network (BNN) and the probabilistic Bayesian neural network (PBN) were considered to compare their performance as a single model. The findings of this study indicate that the ensemble model of the BMIC with some traditional algorithms, which are SVM, random forest, neural networks, and XGBoost classifiers, returns 96.3% model accuracy in prediction. It provides a more reliable model and a versatile approach to support decision-making. [ABSTRACT FROM AUTHOR]

This study aims to forecast New York and Los Angeles gasoline spot prices on a daily frequency. The dataset includes gasoline prices and a big set of 128 other relevant variables spanning the period from 17 February 2004 to 26 March 2022. These variables were fed to three tree-based machine learning algorithms: decision trees, random forest, and XGBoost. Furthermore, a variable importance measure (VIM) technique was applied to identify and rank the most important explanatory variables. The optimal model, a trained random forest, achieves a mean absolute percent error (MAPE) in the out-of-sample of 3.23% for the New York and 3.78% for the Los Angeles gasoline spot prices. The first lag, AR (1), of gasoline is the most important variable in both markets; the top five variables are all energy-related. This paper can strengthen the understanding of price determinants and has the potential to inform strategic decisions and policy directions within the energy sector, making it a valuable asset for both industry practitioners and policymakers. [ABSTRACT FROM AUTHOR]

This study aims to predict the significant duration (D5-75, D5-95) of seismic motion by employing machine learning algorithms. Based on three parameters (moment magnitude, fault distance, and average shear wave velocity), two additional parameters(fault top depth and epicenter mechanism parameters) were introduced in this study. The XGBoost algorithm is utilized for characteristic parameter optimization analysis to obtain the optimal combination of four parameters. We compare the prediction results of four machine learning algorithms (random forest, XGBoost, BP neural network, and SVM) and develop a new method of significant duration prediction by constructing two fusion models (stacking and weighted averaging). The fusion model demonstrates an improvement in prediction accuracy and generalization ability of the significant duration when compared to single algorithm models based on evaluation indicators and residual values. The accuracy and rationality of the fusion model are validated through comparison with existing research. [ABSTRACT FROM AUTHOR]

Because of the complex nonlinear relationship between working conditions, the prediction of tribological properties has become a difficult problem in the field of tribology. In this study, we employed three distinct machine learning (ML) models, namely random forest regression (RFR), gradient boosting regression (GBR), and extreme gradient boosting (XGBoost), to predict the tribological properties of polytetrafluoroethylene (PTFE) composites under high-speed and high-temperature conditions. Firstly, PTFE composites were successfully prepared, and tribological properties under different temperature, speed, and load conditions were studied in order to explore wear mechanisms. Then, the investigation focused on establishing correlations between the friction and wear of PTFE composites by testing these parameters through the prediction of the friction coefficient and wear rate. Importantly, the correlation results illustrated that the friction coefficient and wear rate gradually decreased with the increase in speed, which was also proven by the correlation coefficient. In addition, the GBR model could effectively predict the tribological properties of the PTFE composites. Furthermore, an analysis of relative importance revealed that both load and speed exerted a greater influence on the prediction of the friction coefficient and wear rate. [ABSTRACT FROM AUTHOR]

As an indicator of the optical characteristics of perovskite materials, the band gap is a crucial parameter that impacts the functionality of a wide range of optoelectronic devices. Obtaining the band gap of a material via a labor-intensive, time-consuming, and inefficient high-throughput calculation based on first principles is possible. However, it does not yield the most accurate results. Machine learning techniques emerge as a viable and effective substitute for conventional approaches in band gap prediction. This paper collected 201 pieces of data through the literature and open-source databases. By separating the features related to bits A, B, and X, a dataset of 1208 pieces of data containing 30 feature descriptors was established. The dataset underwent preprocessing, and the Pearson correlation coefficient method was employed to eliminate non-essential features as a subset of features. The band gap was predicted using the GBR algorithm, the random forest algorithm, the LightGBM algorithm, and the XGBoost algorithm, in that order, to construct a prediction model for organic–inorganic hybrid perovskites. The outcomes demonstrate that the XGBoost algorithm yielded an MAE value of 0.0901, an MSE value of 0.0173, and an R2 value of 0.991310. These values suggest that, compared to the other two models, the XGBoost model exhibits the lowest prediction error, suggesting that the input features may better fit the prediction model. Finally, analysis of the XGBoost-based prediction model's prediction results using the SHAP model interpretation method reveals that the occupancy rate of the A-position ion has the greatest impact on the prediction of the band gap and has an A-negative correlation with the prediction results of the band gap. The findings provide valuable insights into the relationship between the prediction of band gaps and significant characteristics of organic–inorganic hybrid perovskites. [ABSTRACT FROM AUTHOR]

Accurate prediction of carbon price is of great value for production, operation, investment decisions and the establishment of carbon pricing mechanism. However, the large amount of data often limits the application of learning model with good predictive performance in carbon price prediction. Therefore, the development of learning algorithms with low computational complexity has become a research hotspot. Among them, subsampling integration technology is an effective method to reduce the computational complexity. However, lack of data representativeness in subsamples and ignorance of differences among submodels inhibit the prediction performance of the subsampled ensemble model. This project proposes an optimal weight random forest ensemble model with cluster-based subsampling (FCM-OWSRFE) for carbon price forecasting. Firstly, Fuzzy C-means cluster-based subsampling to ensure the data representativeness of subsamples. Secondly, a series of sub-random forest models are built based on subsamples with data representativeness. Finally, an optimal weight ensemble model from these sub-models is derived. To verify the validity of the model, we test FCM-OWSRFE model with the carbon price of Guangzhou Emission Exchange and the carbon price of Hubei Carbon Emission Exchange, respectively. Experimental results show that Fuzzy C-means cluster-based subsampling and the optimal weight scheme can efficiently improve the prediction performance of the subsampled random forest ensemble model. [ABSTRACT FROM AUTHOR]

Forest fire risk prediction is essential for building a forest fire defense system. Ensemble learning methods can avoid the problem of difficult model selection for disaster susceptibility prediction and can significantly improve modeling accuracy. This study introduces a stacking ensemble learning model for predicting forest fire risks in Yunnan Province by integrating various data types, such as meteorological, topographic, vegetation, and human activity factors. A total of 70,274 fire points and an equal number of randomly selected nonfire points were used to develop the model, with 70% of the data allocated for training and the remaining 30% for testing. The stacking model combined four diverse machine learning methods: random forest (RF), extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), and multilayer perceptron (MLP). We evaluated the model's predictive performance using metrics like accuracy, area under the characteristic curve (AUC), and fire density (FD). The results demonstrated that the stacking fusion model exhibited remarkable accuracy with an AUC of 0.970 on the test set, significantly surpassing the performance of individual machine learning models, which had AUC values ranging from 0.935 to 0.953. Furthermore, the stacking fusion model effectively captured the maximum fire density in extremely high susceptibility areas, demonstrating enhanced generalization capabilities. [ABSTRACT FROM AUTHOR]

An in-depth understanding of a key element such as lake evaporation is particularly beneficial in developing the optimal management approach for reservoirs. In this study, we first aim to evaluate the applicability of regressors Random Forest (RF), Gradient Booting (GB), and Decision Tree (DT), K Nearest Neighbor (kNN), and XGBoost architectures to predict daily lake evaporation of five reservoirs in the Awash River basin, Ethiopia. The best performing models, Gradient Boosting and XGBoost, are then explained through an explanatory framework using daily climate datasets. The interpretability of the models was evaluated using the Shapley Additive explanations (SHAP). The GB model performed better with (RMSE = 0.045, MSE = 0.031, MAE = 0.002, NSE = 0.997, KGF = 0.991, RRMSE = 0.011) for Metehara Station, (RMSE = 0.032, MSE = 0.024, MAE = 0.001, NSE = 0.998, KGF = 0.999, RRMSE = 0.008) at Melkasa Station, and Dubti Station (RMSE = 0.13, MSE = 0.09, MAE = 0.017, NSE = 0.982, KGF = 0.977,RRMSE = 0.022) as the same as of XGBoost. The factors with the greatest overall impact on the daily evaporation for GB and XGboost Architecture were the SH, month, Tmax, and Tmin for Metehara and Melkasa, and Tmax, Tmin, and month had the greatest impact on the daily evaporation for Dubti. Furthermore, the interpretability of the models showed good agreement between the MLAs simulations and the actual hydro-climatic evaporation process. This result allows decision makers to not only rely on the results of an algorithm, but to make more informed decisions by using interpretable results for better control of the basin reservoir operating rules. [ABSTRACT FROM AUTHOR]

This study presented a novel paradigm for forecasting 12-step-ahead monthly precipitation at 126 California gauge stations. First, the satellite-based precipitation time series from Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS), TerraClimate, ECMWF Reanalysis V5 (ERA5), and Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks-Climate Data Record (PERSIANN-CDR) products were bias-corrected using historical precipitation data. Four methods were tested, and quantile mapping (QM) was the best. After pre-processing data, 19 machine-learning models were developed. random forest, Extreme Gradient Boosting (XGBoost), extreme gradient boosting, support vector machine, multi-layer perceptron, and K-nearest-neighbours were chosen as the best models based on Complex Proportional Assessment (COPRAS) measurement. After hyperparameter adjustment, the Bayesian back-propagation regularization algorithm fused the results. The superior models' predictions were considered inputs, and the target's initial step was labeled. The next 11 steps at each station followed this approach, and the fusion models accurately predicted all steps. The 12th step's average Nash-Sutcliffe efficiency (NSE), mean square error (MSE), coefficient of determination (R2), correlation coefficient (R) were 0.937, 52.136, 0.880, and 0.869, respectively, demonstrating the framework's effectiveness at high forecasting horizons to help policymakers manage water resources. [ABSTRACT FROM AUTHOR]

The study aimed to identify critical factors associated with the surgical stability of pogonion (Pog) by applying machine learning (ML) to predict relapse following two-jaw orthognathic surgery (2 J-OGJ). The sample set comprised 227 patients (110 males and 117 females, 207 training and 20 test sets). Using lateral cephalograms taken at the initial evaluation (T0), pretreatment (T1), after (T2) 2 J-OGS, and post treatment (T3), 55 linear and angular skeletal and dental surgical movements (T2-T1) were measured. Six ML modes were utilized, including classification and regression trees (CART), conditional inference tree (CTREE), and random forest (RF). The training samples were classified into three groups; highly significant (HS) (≥ 4), significant (S) (≥ 2 and < 4), and insignificant (N), depending on Pog relapse. RF indicated that the most important variable that affected relapse rank prediction was ramus inclination (RI), CTREE and CART revealed that a clockwise rotation of more than 3.7 and 1.8 degrees of RI was a risk factor for HS and S groups, respectively. RF, CTREE, and CART were practical tools for predicting surgical stability. More than 1.8 degrees of CW rotation of the ramus during surgery would lead to significant Pog relapse. [ABSTRACT FROM AUTHOR]

Machine learning (ML) is being applied in an increasing volume of geographical research. However, the aspects of spatial autocorrelation (SAC) in the residuals produced by ML models have been understudied compared to the benefit of ML, namely, reduction of prediction errors. In this study, we examined the relationship between predictive accuracy and the reduction in the residual SAC for 597 variables from 25 geographical socio‐economic data sets using spatial and nonspatial cross‐validation of three ML algorithms such as random forests, support vector machine, and artificial neural network (ANN) to provide an extensive empirical diagnosis—but not a definitive theory—of the relationship between SAC and ML. Our results highlighted that the ML algorithms with tuned hyperparameters yielded marginal predictive accuracy gains and the minimal decreases in residual SAC. ANN revealed lower accuracy and higher reduction in the residual SAC than others. This implies ML algorithms in geographical research in socio‐economic domains would not always result in higher prediction accuracy. We suggest that ML in geographical research should be cautiously employed when the main objective is related to the residual SAC. We also showed that spatial cross‐validation neither improves predictive accuracy substantially nor reduce the residual SAC effectively. [ABSTRACT FROM AUTHOR]

In recent years, there has been a growing emphasis on combining intelligent prospecting algorithms, such as random forest, with extensive geological and mineral data for the purpose of quantitatively predicting exploration geochemistry. This approach holds significant importance for enhancing the accuracy of target delineation. The central Kunlun area in Xinjiang possesses highly favorable ore-forming geological conditions, offering excellent prospects for mineral exploration. However, the depletion of shallow deposits coupled with a decade-long gap in geological exploration have presented increasing challenges in the quest to discover substantial metal resources. Consequently, there is now a severe shortage of reserve assets in the region, prompting an urgent need for the implementation of new theories, methods, and technologies in mineral resource investigation and evaluation efforts. The researchers used geological and regional geochemical data to construct a random forest metallogenic discriminant model for predicting the mineralization of gold polymetallic minerals in the central Kunlun area of Xinjiang and delineating the metallogenic target area. Two different sampling methods were compared to quantitatively predict gold polymetallic mineral resources. The results indicate that the selected training samples offer higher prediction accuracy and reliability by fully capturing the complex information of the original data. The random forest model using select training samples has valuable applications in metallogenic prospect prediction and potential division due to its ability to consider the actual exploration cost and identify small areas with high potential and a high proportion of ore. This study significantly improves prediction accuracy, reduces exploration risk, and expands the use of machine learning algorithms in mathematical geology in the central Kunlun area of Xinjiang. [ABSTRACT FROM AUTHOR]

It is indisputable that power systems are being transformed around the world to increase the use of RES and reduce the use of fossil fuels in overall electricity production. This year, the EU Parliament adopted the Fit for 55 package, which should significantly reduce the use of fossil fuels in the energy balance of EU countries while increasing the use of RES. At the end of 2022, the total number of prosumer installations in Poland amounted to about one million two hundred thousand. Such a high saturation of prosumer micro-installations in the power system causes many threats resulting from their operation. These threats result, among others, from the fact that photovoltaics are classified as unstable sources and the expected production of electricity from such installations is primarily associated with highly variable weather conditions and is only dependent on people to a minor extent. Currently, there is a rapid development of topics related to forecasting the volume of energy production from unstable sources such as wind and photovoltaic power plants. This issue is being actively developed by research units around the world. Scientists use a whole range of tools and models related to forecasting techniques, from physical models to artificial intelligence. According to our findings, the use of machine learning models has the greatest chance of obtaining positive prognostic effects for small, widely distributed prosumer installations. The present paper presents the research results of two energy balance prediction algorithms based on machine learning models. For forecasting, we proposed two regression models, i.e., regularized LASSO regression and random forests. The work analyzed scenarios taking into account both endogenous and exogenous variables as well as direct multi-step forecasting and recursive multi-step forecasting. The training was carried out on real data obtained from a prosumer micro-installation. Finally, it was found that the best forecasting results are obtained with the use of a random forest model trained using a recursive multi-step method and an exogenous scenario. [ABSTRACT FROM AUTHOR]

Batteries are the most expensive component of battery electric vehicles (BEVs), but they degrade over time and battery operation. State of health (SOH) forecasting models learn how battery operation over long-time periods of weeks or months influences battery aging. Currently, existing methods for SOH forecasting of lithium-ion batteries based on deep neural network (DNN) models lack explainability of their forecasts due to their inherent black box character. However, the explainability of forecasts is essential to build user trust into the forecasting models. In this work, we address this problem from two perspectives: First, we compared four machine learning (ML) models like decision tree and random forest, which are inherently transparent, to two new DNN architectures with a more inherent black box character. Second, we proposed a new method using Gaussian-filtered saliency maps to visualize battery operational states that are relevant to DNN models. This method is applied to the best DNN models previously trained. We used an extensive data corpus consisting of five public data sets with different operational conditions, battery types, and aging trajectories. Furthermore, we show that the Gaussian-filtered saliency maps meaningfully visualize battery operational states that are consistent with findings from controlled laboratory aging experiments. Thus, this work was able to add transparency and interpretability to the SOH forecasting results of two state-of-the-art DNNs, while maintaining their superior performance compared to transparent ML models, while mitigating their inherent black box character. [ABSTRACT FROM AUTHOR]

The popularity of cutting‐edge machine learning ensemble approaches has solved many climate change research and prediction issues. The six top‐performing GCMs obtained from Technique for Order Preference by Similarity to an Ideal Solution were ensembled using seven machine learning ensemble methods such as Random Forest Regressor (RFR), Support Vector Regressor (SVR), Linear Regression (LR), Adaptive Boosting Regressor (AdaBoost), Extreme Gradient Boosting Regressor (XGBR), Extra Tree Regressor (ETR), Multi‐Layer Perceptron neural network (MLP) and simple Arithmetic Mean (AM) over the diverse geo‐climatic basins. Precipitation is best simulated by EC‐Earth3 and BCC‐CSM2‐MR. Maximum temperature by MPI‐ESM1‐2‐HR, EC‐Earth3‐Veg, INM‐CM5‐0 and MPI‐ESM1‐2‐LR. Minimum temperature by INM‐CM5‐0 and MPI‐ESM1‐2‐LR model. The MME of XGBR and RFR stand out for their superior performance across all six basins, with exceptional performance over the per‐humid basins, while AdaBoost, SVR and the AM underperform. Examining the interseasonal variability of the simulated MMEs over the basins highlights the reliability of these MME models. The anticipated change in maximum and minimum temperature in the SSP245 and SSP585 in the future horizon corroborates the undeniable rise in temperature by all the MMEs with a dramatic change in future temperature in AM and AdaBoost in precipitation with a factor of two rises in the far future over the recent past. Though climate change is expected to increase precipitation, atmospheric stabilization over the Ghats will affect the spatiotemporal distribution of precipitation. We recommend a comprehensive testing and validation approach to generate ensembles in regional investigations involving complicated and diverse precipitation mechanisms. [ABSTRACT FROM AUTHOR]

Tight reservoirs around the world contain a significant volume of hydrocarbons; however, the heterogeneity of these reservoirs limits the recovery of the original oil in place to less than 20%. Accurate characterization is therefore needed to understand variations in reservoir properties and their effects on production. Water saturation (Sw) has always been challenging to estimate in ultra-tight reservoirs such as the Bakken Formation due to the inaccuracy of resistivity-based methods. While machine learning (ML) has proven to be a powerful tool for predicting rock properties in many tight formations, few studies have been conducted in reservoirs of similar complexity to the Bakken Formation, which is an ultra-tight, multimineral, low-resistivity reservoir. This study presents a workflow for Sw prediction using well logs, core data, and ML algorithms. Logs and core data were gathered from 29 wells drilled in the Bakken Formation. Due to the inaccuracy and lack of robustness of the tried and tested regression models (e.g., linear regression, random forest regression) in predicting Sw as a continuous variable, the problem was reformulated as a classification task. Instead of exact values, the Sw predictions were made in intervals of 10% increments representing 10 classes from 0% to 100%. Gradient boosting and random forest classifiers scored the best classification accuracy, and these two models were used to construct a voting classifier that achieved the best accuracy of 85.53%. The ML model achieved much better accuracy than conventional resistivity-based methods. By conducting this study, we aim to develop a new workflow to improve the prediction of Sw in reservoirs where conventional methods have poor performance. [ABSTRACT FROM AUTHOR]

Drug property prediction, especially toxicity, helps reduce risks in a range of real-world applications. In this paper, we aim to apply various machine-learning models for solving the drug toxicity prediction problem. Among various machine-learning approaches, we select five suitable representatives: random forest, multi-layer perceptron, logistic regression, graph convolutional neural network, and graph isomorphism network (GIN) for conducting experiments on six datasets for toxicity prediction, including Tox 21, ClinTox, ToxCast, SIDER, HIV, and BACE. We design the GIN with four hidden layers and select the Adam optimizer with the learning rate 1 0 − 4 and the batch size 2 5 6. Furthermore, we use a batch norm layer inside each of the GIN hidden layers. Experimental results show that the designed GIN model is most efficient in distinguishing between safe and toxic drugs and outperforms the others under the supervision of ROC AUC score and recall. [ABSTRACT FROM AUTHOR]

Accurate wind power forecasting plays a crucial role in the planning of unit commitments, maintenance scheduling, and maximizing profits for power traders. Uncertainty and changes in wind speeds pose challenges to the integration of wind power into the power system. Therefore, the reliable prediction of wind power output is a complex task with significant implications for the efficient operation of electricity grids. Developing effective and precise wind power prediction systems is essential for the cost-efficient operation and maintenance of modern wind turbines. This article focuses on the development of a very-short-term forecasting model using machine learning algorithms. The forecasting model is evaluated using LightGBM, random forest, CatBoost, and XGBoost machine learning algorithms with 16 selected parameters from the wind energy system. The performance of the machine learning-based wind energy forecasting is assessed using metrics such as mean absolute error (MAE), mean-squared error (MSE), root-mean-squared error (RMSE), and R-squared. The results indicate that the random forest algorithm performs well during training, while the CatBoost algorithm demonstrates superior performance, with an RMSE of 13.84 for the test set, as determined by 10-fold cross-validation. [ABSTRACT FROM AUTHOR]

Antisense oligonucleotide (ASO)-mediated exon skipping has become a valuable tool for investigating gene function and developing gene therapy. Machine-learning-based computational methods, such as eSkip-Finder, have been developed to predict the efficacy of ASOs via exon skipping. However, these methods are computationally demanding, and the accuracy of predictions remains suboptimal. In this study, we propose a new approach to reduce the computational burden and improve the prediction performance by using feature selection within machine-learning algorithms and ensemble-learning techniques. We evaluated our approach using a dataset of experimentally validated exon-skipping events, dividing it into training and testing sets. Our results demonstrate that using a three-way-voting approach with random forest, gradient boosting, and XGBoost can significantly reduce the computation time to under ten seconds while improving prediction performance, as measured by R2 for both 2′-O-methyl nucleotides (2OMe) and phosphorodiamidate morpholino oligomers (PMOs). Additionally, the feature importance ranking derived from our approach is in good agreement with previously published results. Our findings suggest that our approach has the potential to enhance the accuracy and efficiency of predicting ASO efficacy via exon skipping. It could also facilitate the development of novel therapeutic strategies. This study could contribute to the ongoing efforts to improve ASO design and optimize gene therapy approaches. [ABSTRACT FROM AUTHOR]

The advances made in wireless communication technology have led to efforts to improve the quality of reception, prevent poor connections and avoid disconnections between wireless and cellular devices. One of the most important steps toward preventing communication failures is to correctly estimate the received signal strength indicator (RSSI) of a wireless device. RSSI prediction is important for addressing various challenges such as localization, power control, link quality estimation, terminal connectivity estimation, and handover decisions. In this study, we compare different machine learning (ML) techniques that can be used to predict the received signal strength values of a device, given the received signal strength values of other devices in the region. We consider various ML methods, such as multi-layer ANN, K nearest neighbors, decision trees, random forest, and the K-means based method, for the prediction challenge. We checked the accuracy level of the learning process using a real dataset provided by a major national cellular operator. Our results show that the weighted K nearest neighbors algorithm, for K = 3 neighbors, achieved, on average, the most accurate RSSI predictions. We conclude that in environments where the size of data is relatively small, and data of close geographical points is available, a method that predicts the coverage of a point using the coverage near geographical points can be more successful and more accurate compared with other ML methods. [ABSTRACT FROM AUTHOR]

Rampant terrorism poses a serious threat to the national security of many countries worldwide, particularly due to separatism and extreme nationalism. This paper focuses on the development and application of a temporal self-exciting point process model to the terror data of three countries: the US, Turkey, and the Philippines. To account for occurrences with the same time-stamp, this paper introduces the order mark and reward term in parameter selection. The reward term considers the triggering effect between events in the same time-stamp but different order. Additionally, this paper provides comparisons between the self-exciting models generated by day-based and month-based arrival times. Another highlight of this paper is the development of a model to predict the number of terror events using a combination of simulation and machine learning, specifically the random forest method, to achieve better predictions. This research offers an insightful approach to discover terror event patterns and forecast future occurrences of terror events, which may have practical application towards national security strategies. [ABSTRACT FROM AUTHOR]

Particulate matter (PM) in the air can cause various health problems and diseases in humans. In particular, the smaller size of PM 2.5 enable them to penetrate deep into the lungs, causing severe health impacts. Exposure to PM 2.5 can result in respiratory, cardiovascular, and allergic diseases, and prolonged exposure has also been linked to an increased risk of cancer, including lung cancer. Therefore, forecasting the PM 2.5 concentration in the surrounding is crucial for preventing these adverse health effects. This paper proposes a method for forecasting the PM 2.5 concentration after 1 h using bidirectional long short-term memory (Bi-LSTM). The proposed method involves selecting input variables based on the feature importance calculated by random forest, classifying the data to assign weight variables to reduce bias, and forecasting the PM 2.5 concentration using Bi-LSTM. To compare the performance of the proposed method, two case studies were conducted. First, a comparison of forecasting performance according to preprocessing. Second, forecasting performance between deep learning (long short-term memory, gated recurrent unit, and Bi-LSTM) and conventional machine learning models (multi-layer perceptron, support vector machine, decision tree, and random forest). In case study 1, The proposed method shows that the performance indices (RMSE: 3.98%p, MAE: 5.87%p, RRMSE: 3.96%p, and R 2 :0.72%p) are improved because weights are given according to the input variables before the forecasting is performed. In case study 2, we show that Bi-LSTM, which considers both directions (forward and backward), can effectively forecast when compared to conventional models (RMSE: 2.70, MAE: 0.84, RRMSE: 1.97, R 2 : 0.16). Therefore, it is shown that the proposed method can effectively forecast PM 2.5 even if the data in the high-concentration section is insufficient. [ABSTRACT FROM AUTHOR]

Electricity load forecasting is one of the important tasks of the power marketing department, and accurate load forecasting is extremely important to ensure real-time dispatch and security of the power system. In order to obtain accurate and reliable load forecasting results, an ultra-short-term power load forecasting model based on an improved random forest regression algorithm is proposed in this paper. First, data pre-processing is performed on the original dataset. Then the pre-processed time data and historical load data are used as inputs to the model, and optimization of the model using the Gaussian mixture-based tree-structured Parzen estimator algorithm is carried out. Finally, the final prediction results were derived. Experimental analysis was conducted with real load data from a region of China, and the experimental results show that the method has better prediction accuracy than the original random forest algorithm and other traditional machine learning algorithms. [ABSTRACT FROM AUTHOR]

Background: Increasing access and better allocation of organs in the field of transplantation is a critical problem in clinical care. Limitations exist in accurately predicting allograft discard. Potential exists for machine learning to provide a balanced assessment of the potential for an organ to be used in a transplantation procedure. Methods: We accessed and utilized all available deceased donor United Network for Organ Sharing data from 1987 to 2020. With these data, we evaluated the performance of multiple machine learning methods for predicting organ use. The machine learning methods trialed included XGBoost, random forest, Naïve Bayes (NB), logistic regression, and fully connected feedforward neural network classifier methods. The top two methods, XGBoost and random forest, were fully developed using 10‐fold cross‐validation and Bayesian optimization of hyperparameters. Results: The top performing model at predicting liver organ use was an XGBoost model which achieved an AUC‐ROC of.925, an AUC‐PR of.868, and an F1 statistic of.756. The top performing model for predicting kidney organ use classification was an XGBoost model which achieved an AUC‐ROC of.952, and AUC‐PR of.883, and an F1 statistic of.786. Conclusions: The XGBoost method demonstrated a significant improvement in predicting donor allograft discard for both kidney and livers in solid organ transplantation procedures. Machine learning methods are well suited to be incorporated into the clinical workflow; they can provide robust quantitative predictions and meaningful data insights for clinician consideration and transplantation decision‐making. [ABSTRACT FROM AUTHOR]

Incorporating machine learning into automatic performance analysis and tuning tools is a promising path to tackle the increasing heterogeneity of current HPC applications. However, this introduces the need for generating balanced datasets of parallel applications' executions and for dealing with natural imbalances for optimizing performance parameters. This work proposes a holistic approach that integrates a methodology for building balanced datasets of OpenMP code-region patterns and a way to use such datasets for tuning performance parameters. The methodology uses hardware performance counters to characterize the execution of a given region and correlation analysis to determine whether it covers an unique part of the pattern input space. Nevertheless, a balanced dataset of region patterns may become naturally imbalanced when used for training a model for tuning any specific performance parameter. For this reason, we have explored several methods for dealing with naturally imbalanced datasets for finding the appropriated way of using them for tuning purposes. Experimentation shows that the proposed methodology can be used to build balanced datasets and that such datasets, plus a combination of Random Forest and binary classification, can be used to train a model able to accurately tune the number of threads of OpenMP parallel regions. [ABSTRACT FROM AUTHOR]

In this study, a novel general multi-step ahead strategy is developed for forecasting time series of air pollutants. The values of the predictors at future moments are gathered from official weather forecast sites as independent ex-ante data. They are updated with new forecasted values every day. Each new sample is used to build- a separate single model that simultaneously predicts future pollution levels. The sought forecasts were estimated by averaging the actual predictions of the single models. The strategy was applied to three pollutants—PM10, SO2, and NO2—in the city of Pernik, Bulgaria. Random forest (RF) and arcing (Arc-x4) machine learning algorithms were applied to the modeling. Although there are many highly changing day-to-day predictors, the proposed averaging strategy shows a promising alternative to single models. In most cases, the root mean squared errors (RMSE) of the averaging models (aRF and aAR) for the last 10 horizons are lower than those of the single models. In particular, for PM10, the aRF's RMSE is 13.1 vs. 13.8 micrograms per cubic meter for the single model; for the NO2 model, the aRF exhibits 21.5 vs. 23.8; for SO2, the aAR has 17.3 vs. 17.4; for NO2, the aAR's RMSE is 22.7 vs. 27.5, respectively. Fractional bias is within the same limits of (−0.65, 0.7) for all constructed models. [ABSTRACT FROM AUTHOR]

A robust short-term significant wave height (Hs) modelling framework based on an ensemble local mean decomposition method integrated with random forest (i.e. , En-RLMD-RF) is developed. The robust local mean decomposition (RLMD) decomposed the Hs data series into three subseries; amplitude modulation, frequency modulation and the low-frequency product function (PFs). The partial autocorrelation function was employed to determine the correlation-based significant predictor signals between the PFs at t 0 and t 1. Then the statistically significant PFs were incorporated into the random forest (RF) to construct the RLMD-RF model. The RLMD-RF based forecasted PFs were used again in the RF model as input predictors resulting in an ensemble-based RLMD-RF (i.e. , En-RLMD-RF) model for forecasting short-term Hs. The En-RLMD-RF model is validated and compared with RF, extreme learning machine (ELM) and multiple linear regression (MLR) models and their hybrids RLMD-RF, RLMD-ELM, RLMD-MLR, En-RLMD-ELM and En-RLMD-MLR counterparts using a set of performance metrics. The results demonstrated that the En-RLMD-RF model generates better forecasting accuracy against the benchmarking models. This study is beneficial for the application and optimization of more clean energy resources worldwide for sustained energy generation. [ABSTRACT FROM AUTHOR]

Nowadays, time series data are applied in many fields, such as economics, medicine, biology, science, society, nature, environment, or typically in weather forecasting. Time series is a tool that includes methodological formulas and models to help us analyze time series data, extract potentially valuable information, capture historical fluctuations, present and support forecasts of the value of the research object in future. There are many models and methods of time series analysis that have been researched and improved these days for trend analysis and forecasts. Techniques related to time series data processing include linear regression with time series with two features unique to time series lags and time steps, the trend for model long-term changes with moving averages and time dummy, seasonality to create indicators, Fourier features to capture periodic change, and time series as features to predict the future from the pass with a lag embedding. In this article, we build a new hybrid model called Lucy Hybrid that provides full steps in the machine learning process including data pre-processing, training model, evaluation model with Mean Square Error (MSE), Root-Mean-Square Error (RMSE) and Mean Absolute Error (MAE) to compare and get the best model quality. The model also provides functions like storage and loading model to support researchers to reuse and save time on training model. In the Lucy hybrid, we also support the trend and forecast function for time series data. We experiment with a large dataset of more than 3,000,000 records from a large Ecuadorian-based grocery retailer, and we used Linear Regression, Elastic Net, Lasso, Ridge and Extra Trees Regressor, Random Forest Regressor, K-Neighbors Regressor, MLP Regressor, XGB Regressor to experiment and create 20 Lucy hybrid sample models and publish a full source code for researchers to use to expand the model. [ABSTRACT FROM AUTHOR]

Background: Acute oral toxicity of drug candidates can lead to drug development failure; thus, predicting the acute oral toxicity of small compounds is important for successful drug development. However, evaluation of the acute oral toxicity of small compounds considered in the early stages of drug discovery is limited because of cost and time. Here, we developed a computational framework, PredAOT, that predicts the acute oral toxicity of small compounds in mice and rats. Methods: PredAOT is based on multiple random forest models for the accurate prediction of acute oral toxicity. A total of 6226 and 6238 compounds evaluated in mice and rats, respectively, were used to train the models. Results: PredAOT has the advantage of predicting acute oral toxicity in mice and rats simultaneously, and its prediction performance is similar to or better than that of existing tools. Conclusion: PredAOT will be a useful tool for the quick and accurate prediction of the acute oral toxicity of small compounds in mice and rats during drug development. [ABSTRACT FROM AUTHOR]

Implementing impedance control in Cartesian task space or directly at the joint level is a popular option for achieving desired compliance behavior for robotic manipulators performing tasks. The damping ratio is an important control criterion for modulating the dynamic response; however, tuning or selecting this parameter is not easy, and can be even more complicated in cases where the system cannot be directly solved at the joint space level. Our study proposes a novel methodology for calculating the local optimal damping ratio value and supports it with results obtained from five different scenarios. We carried out 162 different experiments and obtained the values of the inertia, stiffness, and damping matrices for each experiment. Then, data preprocessing was carried out to select the most significant variables using different criteria, reducing the seventeen initial variables to only three. Finally, the damping ratio values were calculated (predicted) using automatic regression tools. In particular, five-fold cross-validation was used to obtain a more generalized model and to assess the forecasting performance. The results show a promising methodology capable of calculating and predicting control parameters for robotic manipulation tasks. [ABSTRACT FROM AUTHOR]

Solar power forecasting is of high interest in managing any power system based on solar energy. In the case of photovoltaic (PV) systems, and building integrated PV (BIPV) in particular, it may help to better operate the power grid and to manage the power load and storage. Power forecasting directly based on PV time series has some advantages over solar irradiance forecasting first and PV power modeling afterwards. In this paper, the power forecasting for BIPV systems in a vertical façade is studied using machine learning algorithms based on decision trees. The forecasting scheme employs the skforecast library from the Python environment, which facilitates the implementation of different schemes for both deterministic and probabilistic forecasting applications. Firstly, deterministic forecasting of hourly BIPV power was performed with XGBoost and Random Forest algorithms for different cases, showing an improvement in forecasting accuracy when some exogenous variables were used. Secondly, probabilistic forecasting was performed with XGBoost combined with the Bootstrap method. The results of this paper show the capabilities of Random Forest and gradient boosting algorithms, such as XGBoost, to work as regressors in time series forecasting of BIPV power. Mean absolute error in the deterministic forecast, using the most influencing exogenous variables, were around 40% and close below 30% for the south and east array, respectively. [ABSTRACT FROM AUTHOR]

Predicting the behaviour of wildfires can help save lives and reduce health, socioeconomic, and environmental impacts. Because wildfire behaviour is highly dependent on fuel type and distribution, their accurate estimation is paramount for accurate prediction of the fire propagation dynamics. This paper studies the effect of combining automated hyperparameter tuning with Bayesian optimisation and recursive feature elimination on the accuracy of three boosting (AdaB, XGB, CatB), two bagging (Random Forest, Extremely Randomised Trees), and three stacking ensemble models with respect to their ability to estimate the vegetation cover type from cartographic data. The models are trained on the University of California Irvine (UCI) cover type dataset using five-fold cross-validation. Feature importance scores are calculated and used in recursive feature elimination analysis to study the sensitivity of model accuracy to the different feature combinations. Our results indicate that the implemented fine-tuning procedure significantly affects the accuracy of all models investigated, with XGB achieving an overall accuracy of 97.1% slightly outperforming the others. [ABSTRACT FROM AUTHOR]

Small-incision lenticule extraction (SMILE) is a safe and effective surgical procedure for refractive correction. However, the nomogram from the VisuMax femtosecond laser system often overestimates the achieved lenticule thickness (LT), leading to inaccurate estimation of residual central corneal thickness in some patients. In order to improve the accuracy of predicting achieved LT, we used machine learning models to make predictions of LT and analyze the influencing factors of LT estimation in this study. We collected nine variables of 302 eyes and their LT results as input variables. The input variables included age, sex, mean K reading of anterior corneal surface, lenticule diameter, preoperative CCT, axial length, the eccentricity of the anterior corneal surface (E), diopter of spherical, and diopter of the cylinder. Multiple linear regression and several machine learning algorithms were employed in developing the models for predicting LT. According to the evaluation results, the Random Forest (RF) model achieved the highest performance in predicting the LT with an R2 of 0.95 and found the importance of CCT and E in predicting LT. To validate the effectiveness of the RF model, we selected additional 50 eyes for testing. Results showed that the nomogram overestimated LT by 19.59% on average, while the RF model underestimated LT by −0.15%. In conclusion, this study can provide efficient technical support for the accurate estimation of LT in SMILE. [ABSTRACT FROM AUTHOR]

Assessment of spatiotemporal dynamics of meteorological variables and their forecast is essential in the context of climate change. Such analysis can help suggest possible solutions for flora and fauna in protected areas and adaptation strategies to make forests and communities more resilient. The present study attempts to analyze climate variability, trend and forecast of temperature and rainfall in the Valmiki Tiger Reserve, India. We utilized rainfall and temperature gridded data obtained from the Indian Meteorological Department during 1981–2020. The Mann–Kendall test and Sen's slope estimator were employed to examine the time series trend and magnitude of change at the annual, monthly and seasonal levels. Random forest machine learning algorithm was used to estimate seasonal prediction and forecasting of rainfall and temperature trend for the next ten years (2021–2030). The predictive capacity of the model was evaluated by statistical performance assessors of coefficient of correlation, mean absolute error, mean absolute percentage error and root mean squared error. The findings revealed a significant decreasing trend in rainfall and an increasing trend in temperature. However, a declining trend for maximum temperature has been observed for winter and post-monsoon seasons. The results of seasonal forecasting exhibited a considerable decrease in rainfall and temperature across the Reserve during all the seasons. However, the temperature will increase during the summer season. The random forest machine learning algorithm has shown its effectiveness in forecasting the temperature and rainfall variables. The findings suggest that these approaches may be used at various spatial scales in different geographical locations. [ABSTRACT FROM AUTHOR]

We examined the prediction accuracies of genomic best linear unbiased prediction (GBLUP), various weighted GBLUP according to the degrees of marker effects (WGBLUP) and machine learning (ML) methods, and compared them with traditional BLUP for age at first calving (AFC), calving difficulty (CD), and gestation length in Japanese Black cattle. For WGBLUP, firstly, BayesC and FarmCPU were used to estimate marker effects. Then, we constructed three weighted genomic relationship matrices from information of estimated marker effects in the first step: absolute value of the estimated marker‐effect WGBLUP, estimated marker‐variance WGBLUP, and genomic‐feature WGBLUP. For ML, we applied Gaussian kernel, random forest, extreme gradient boost, and support vector regression. We collected a total of 2583 animals having both phenotypic records and genotypes with 30,105 markers and 16,406 pedigree records. For AFC, prediction accuracies of WGBLUP methods using FarmCPU exceeded BLUP by 25.7%–39.5%. For CD, estimated marker‐variance WGBLUP using BayesC achieved the highest prediction accuracy. Among ML methods, extreme gradient boost, support vector regression, and Gaussian kernel increased prediction accuracies by 28.4%, 19.0%, and 36.4% for AFC, CD, and gestation length compared with BLUP, respectively. Thus, prediction performance could be improved using suitable WGBLUP and ML methods according to target reproductive traits for the population used. [ABSTRACT FROM AUTHOR]

Producing an accurate and calibrated probabilistic forecast has high social and economic value. Systematic errors or biases in the ensemble weather forecast can be corrected by postprocessing models whose development is an urgent challenge. Traditionally, the bias correction is done by employing linear regression models that estimate the conditional probability distribution of the forecast. Although this model framework works well, it is restricted to a prespecified model form that often relies on a limited set of predictors only. Most machine learning (ML) methods can tackle these problems with a point prediction, but only a few of them can be applied effectively in a probabilistic manner. The tree-based ML techniques, namely, natural gradient boosting (NGB), quantile random forests (QRF), and distributional regression forests (DRF), are used to adjust hourly 2-m temperature ensemble prediction at lead times of 1–10 days. The ensemble model output statistics (EMOS) and its boosting version are used as benchmark models. The model forecast is based on the European Centre for Medium-Range Weather Forecasts (ECMWF) for the Czech Republic domain. Two training periods 2015–18 and 2018 only were used to learn the models, and their prediction skill was evaluated in 2019. The results show that the QRF and NGB methods provide the best performance for 1–2-day forecasts, while the EMOS method outperforms other methods for 8–10-day forecasts. Key components to improving short-term forecasting are additional atmospheric/surface state predictors and the 4-yr training sample size. Significance Statement: Machine learning methods have great potential and are beginning to be widely applied in meteorology in recent years. A new technique called natural gradient boosting (NGB) has been released and used in this paper to refine the probabilistic forecast of surface temperature. It was found that the NGB has better prediction skills than the traditional ensemble model output statistics in forecasting 1 and 2 days in advance. The NGB has similar prediction skills with lower computational demands compared to other advanced machine learning methods such as the quantile random forests. We showed a path to employ the NGB method in this task, which can be followed for refining other and more challenging meteorological variables such as wind speed or precipitation. [ABSTRACT FROM AUTHOR]

In the Caribbean basin, particulate matter lower or equal to 10 μm in diameter (PM10) has a huge impact on human mortality and morbidity due to the African dust. For the first time in this geographical area, the theoretical framework of artificial intelligence is applied to forecast PM10 concentrations. The aim of this study is to forecast PM10 concentrations using six machine learning (ML) models: support vector regression (SVR), k-nearest neighbor regression (kNN), random forest regression (RFR), gradient boosting regression (GBR), Tweedie regression (TR), and Bayesian ridge regression (BRR). Overall, with MBEmax = −2.8139, the results showed that all the models tend to slightly underestimate PM10 empirical data. GBR is the model that gives the best performance (r = 0.7831, R2 = 0.6132, MAE = 6.8479, RMSE = 10.4400, and IOA = 0.7368). By comparing our results to other PM10 ML studies in megacities, we found similar performance using only three input variables, whereas previous studies use many input variables with Artificial Neural Network (ANN) models. All these results showed the features of PM10 concentrations in the Caribbean area. [ABSTRACT FROM AUTHOR]

This study, which aims to make predictions using a previously unused deep hybrid Convolutional Neural Network-Support Vector Regression approach for hydropower generation, was carried out using a unique meteorological data set as input data. The unique dataset was collected from Kaman Meteorology Directorate and Hirfanlı HEPP in Turkey, from 2007 to 2021, to estimate the HEPP's Net Head and Hydroelectric Power Generation on a daily basis. The performances of the prediction models were benchmarked in addition to the used CNN-SVR model with Machine Learning (ML) models (Boosting Random Forest Regression (BRFR) and Weighted K-Nearest Neighbor Regression (WKNNR)) and Deep Learning (DL) models (Long-Short Term Memory (LSTM) and Deep Belief Network (DBN)). The comparison results of the used CNN-SVR model with other alternative models showed that CNN-SVR performed effectively with the highest correlation coefficient of 0.971 for NH and 0.968 for PP. [ABSTRACT FROM AUTHOR]

Metaplastic breast cancer (MpBC) is a rare and aggressive subtype of breast cancer, with data emerging on prognostic factors and survival prediction. This study aimed to develop machine learning models to predict breast cancer-specific survival (BCSS) in MpBC patients, utilizing a dataset of 160 patients with clinical, pathological, and biological variables. An in-depth variable selection process was carried out using gain ratio and correlation-based methods, resulting in 10 variables for model estimation. Five models (decision tree with bagging; logistic regression; multilayer perceptron; naïve Bayes; and, random forest algorithms) were evaluated using 10-fold cross-validation. Despite the constraints posed by the absence of therapeutic information, the random forest model exhibited the highest performance in predicting BCSS, with an ROC area of 0.808. This study emphasizes the potential of machine learning algorithms in predicting prognosis for complex and heterogeneous cancer subtypes using clinical datasets, and their potential to contribute to patient management. Further research that incorporates additional variables, such as treatment response, and more advanced machine learning techniques will likely enhance the predictive power of MpBC prognostic models. [ABSTRACT FROM AUTHOR]