Search Results (47)

Semiconductors play a crucial role in a wide range of applications and are integral to essential infrastructures. Manufacturers of these semiconductors must meet specific quality and lifetime targets. To estimate the lifetime of semiconductors, accelerated stress tests are conducted. This paper introduces a novel approach to modeling drift in discrete electrical parameters within stress test devices. It incorporates a machine learning (ML) approach for arbitrary panel data sets of electrical parameters from accelerated stress tests. The proposed model involves an expert-in-the-loop MLOps decision process, allowing experts to choose between an interpretable model and a robust ML algorithm for regularization and fine-tuning. The model addresses the issue of outliers influencing statistical models by employing regularization techniques. This ensures that the model’s accuracy is not compromised by outliers. The model uses interpretable statistically calculated limits for lifetime drift and uncertainty as input data. It then predicts these limits for new lifetime stress test data of electrical parameters from the same technology. The effectiveness of the model is demonstrated using anonymized real data from Infineon technologies. The model’s output can help prioritize parameters by the level of significance for indication of degradation over time, providing valuable insights for the analysis and improvement of electrical devices. The combination of explainable statistical algorithms and ML approaches enables the regularization of quality control limit calculations and the detection of lifetime drift in stress test parameters. This information can be used to enhance production quality by identifying significant parameters that indicate degradation and detecting deviations in production processes. Full article

Considering the demand for the optimization of the technical factors of spraying for a greater area coverage and minimal drift, field tests were carried out to determine the interaction between the area coverage, number of droplets per cm², droplet diameter, and drift. The studies were conducted with two different types of sprayers (axial and radial fan) in an apple orchard and a vineyard. The technical factors of the spraying interactions were nozzle type (ISO code 015, code 02, and code 03), working speed (6 and 8 km h⁻¹), and spraying norm (250–400 L h⁻¹). The airflow of both sprayers was adjusted to the plantation leaf mass and the working pressure was set for each repetition separately. A method using water-sensitive paper and a digital image analysis was used to collect data on coverage factors. The data from the field research were processed using four machine learning models: quantile random forest (QRF), support vector regression with radial basis function kernel (SVR), Bayesian Regularization for Feed-Forward Neural Networks (BRNN), and Ensemble Machine Learning (ENS). Nozzle type had the highest predictive value for the properties of number of droplets per cm² (axial = 69.1%; radial = 66.0%), droplet diameter (axial = 30.6%; radial = 38.2%), and area coverage (axial = 24.6%; radial = 34.8%). Spraying norm had the greatest predictive value for area coverage (axial = 43.3%; radial = 26.9%) and drift (axial = 72.4%; radial = 62.3%). Greater coverage of the treated area and a greater number of droplets were achieved with the radial sprayer, as well as less drift. The accuracy of the machine learning model for the prediction of the treated surface showed a satisfactory accuracy for most properties (R² = 0.694–0.984), except for the estimation of the droplet diameter for an axial sprayer (R² = 0.437–0.503). Full article

The main source of electricity worldwide stems from fossil fuels, contributing to air pollution, global warming, and associated adverse effects. This study explores wind energy as a potential alternative. Nevertheless, the variable nature of wind introduces uncertainty in its reliability. Thus, it is necessary to identify an appropriate machine learning model capable of reliably forecasting wind speed under various environmental conditions. This research compares the effectiveness of Dynamic Architecture for Artificial Neural Networks (DAN2), convolutional neural networks (CNN), random forest and XGBOOST in predicting wind speed across three locations in South Africa, characterised by different weather patterns. The forecasts from the four models were then combined using quantile regression averaging models, generalised additive quantile regression (GAQR) and quantile regression neural networks (QRNN). Empirical results show that CNN outperforms DAN2 in accurately forecasting wind speed under different weather conditions. This superiority is likely due to the inherent architectural attributes of CNNs, including feature extraction capabilities, spatial hierarchy learning, and resilience to spatial variability. The results from the combined forecasts were comparable with those from the QRNN, which was slightly better than those from the GAQR model. However, the combined forecasts were more accurate than the individual models. These results could be useful to decision-makers in the energy sector. Full article

Gully erosion is a serious environmental threat, compromising soil health, damaging agricultural lands, and destroying vital infrastructure. Pinpointing regions prone to gully erosion demands careful selection of an appropriate machine learning algorithm. This choice is crucial, as the complex interplay of various environmental factors contributing to gully formation requires a nuanced analytical approach. To develop the most accurate Gully Erosion Susceptibility Map (GESM) for India’s Raiboni River basin, researchers harnessed the power of two cutting-edge machine learning algorithm: Extreme Gradient Boosting (XGBoost) and Random Forest (RF). For a comprehensive analysis, this study integrated 24 potential control factors. We meticulously investigated a dataset of 200 samples, ensuring an even balance between non-gullied and gullied locations. To assess multicollinearity among the 24 variables, we employed two techniques: the Information Gain Ratio (IGR) test and Variance Inflation Factors (VIF). Elevation, land use, river proximity, and rainfall most influenced the basin’s GESM. Rigorous tests validated XGBoost and RF model performance. XGBoost surpassed RF (ROC 86% vs. 83.1%). Quantile classification yielded a GESM with five levels: very high to very low. Our findings reveal that roughly 12% of the basin area is severely affected by gully erosion. These findings underscore the critical need for targeted interventions in these highly susceptible areas. Furthermore, our analysis of gully characteristics unveiled a predominance of V-shaped gullies, likely in an active developmental stage, supported by an average Shape Index (SI) value of 0.26 and a mean Erosivness Index (EI) of 0.33. This research demonstrates the potential of machine learning to pinpoint areas susceptible to gully erosion. By providing these valuable insights, policymakers can make informed decisions regarding sustainable land management practices. Full article

A rational landslide susceptibility mapping (LSM) can minimize the losses caused by landslides and enhance the efficiency of disaster prevention and reduction. At present, frequency ratio (FR), information value (IV), and certainty factor (CF) are widely used to quantify the relationships between landslides and their causative factors; however, it remains unclear which method is the most effective. Moreover, existing landslide susceptibility zoning methods lack full automation; thus, the results are full of uncertainties. To address this, the FR, IV, and CF were used to analyze the relationship between landslides and causative factors. Subsequently, three distinct sets of models were developed, namely random forest models (RF_FR, RF_IV, and RF_CF), support vector machine models (SVM_FR, SVM_IV, and SVM_CF), and logistic regression models (LR_FR, LR_IV, and LR_CF) using the analysis results as inputs. A Gaussian mixture model (GMM) was introduced as a new method for landslide susceptibility zoning, classifying the LSM into five distinct levels. An accuracy evaluation of the models and a rationality analysis of the LSM indicated that the FR is superior to the IV and CF in quantifying the relationship between landslides and causative factors. Additionally, the quantile method was employed as a comparative approach to the GMM, further validating the effectiveness of the GMM. This research contributes to more effective and efficient LSM, ultimately enhancing landslide prevention measures. Full article

The investigation of a potential correlation between the filtered-out vegetation index and forest aboveground biomass (AGB) using the conventional variables screening method is crucial for enhancing the estimation accuracy. In this study, we examined the Pinus densata forests in Shangri-La and utilized 31 variables to establish quantile regression models for the AGB across 19 quantiles. The key variables associated with biomass were based on their significant correlation with the AGB in different quantiles, and the QRNN and QRF models were constructed accordingly. Furthermore, the optimal quartile models yielding the minimum mean error were combined as the best QRF (QRFb) and QRNN (QRNNb). The results were as follows: (1) certain bands exhibited significant relationships with the AGB in specific quantiles, highlighting the importance of band selection. (2) The vegetation index involving the band of blue and SWIR was more suitable for estimating the Pinus densata. (3) Both the QRNN and QRF models demonstrated their optimal performance in the 0.5 quantiles, with respective R² values of 0.68 and 0.7. Moreover, the QRNNb achieved a high R² value of 0.93, while the QRFb attained an R² value of 0.86, effectively reducing the underestimation and overestimation. Overall, this research provides valuable insights into the variable screening methods that enhance estimation accuracy and mitigate underestimation and overestimation issues. Full article

Soil moisture is a key environmental variable. There is a lack of software to facilitate non-specialists in estimating and analyzing soil moisture at the field scale. This study presents a new open-sourced R package mlhrsm, which can be used to generate Machine Learning-based high-resolution (30 to 500 m, daily to monthly) soil moisture maps and uncertainty estimates at selected sites across the contiguous USA at 0–5 cm and 0–1 m. The model is based on the quantile random forest algorithm, integrating in situ soil sensors, satellite-derived land surface parameters (vegetation, terrain, and soil), and satellite-based models of surface and rootzone soil moisture. It also provides functions for spatial and temporal analysis of the produced soil moisture maps. A case study is provided to demonstrate the functionality to generate 30 m daily to weekly soil moisture maps across a 70-ha crop field, followed by a spatial–temporal analysis. Full article

Photovoltaic (PV) power generation has brought about enormous economic and environmental benefits, promoting sustainable development. However, due to the intermittency and volatility of PV power, the high penetration rate of PV power generation may pose challenges to the planning and operation of power systems. Accurate PV power forecasting is crucial for the safe and stable operation of the power grid. This paper proposes a short-term PV power forecasting method using K-means clustering, ensemble learning (EL), a feature rise-dimensional (FRD) approach, and quantile regression (QR) to improve the accuracy of deterministic and probabilistic forecasting of PV power. The K-means clustering algorithm was used to construct weather categories. The EL method was used to construct a two-layer ensemble learning (TLEL) model based on the eXtreme gradient boosting (XGBoost), random forest (RF), CatBoost, and long short-term memory (LSTM) models. The FRD approach was used to optimize the TLEL model, construct the FRD-XGBoost-LSTM (R-XGBL), FRD-RF-LSTM (R-RFL), and FRD-CatBoost-LSTM (R-CatBL) models, and combine them with the results of the TLEL model using the reciprocal error method, in order to obtain the deterministic forecasting results of the FRD-TLEL model. The QR was used to obtain probability forecasting results with different confidence intervals. The experiments were conducted with data at a time level of 15 min from the Desert Knowledge Australia Solar Center (DKASC) to forecast the PV power of a certain day. Compared to other models, the proposed FRD-TLEL model has the lowest root mean square error (RMSE) and mean absolute percentage error (MAPE) in different seasons and weather types. In probability interval forecasting, the 95%, 75%, and 50% confidence intervals all have good forecasting intervals. The results indicate that the proposed PV power forecasting method exhibits a superior performance in forecasting accuracy compared to other methods. Full article

Crown width (CW) is an important indicator for assessing tree health, vitality, and stability, as well as being used to predict forestry models and evaluate forest dynamics. However, acquiring CW data is laborious and time-consuming, making it crucial to establish a convenient and accurate CW prediction model for forest management. In this study, we developed three models capable of conducting calibration: generalized models (GM), quantile regression models (QR), and mixed-effects models (MIXED). The aim was to effectively improve the prediction accuracy of CW using data from Dahurian larch (Larix gmelinii Rupr.) in Northeastern China. Different sampling designs were applied, including selecting the thickest, thinnest, intermediate, and random trees, with 1 to 10 sample trees for each design. The results showed that all models achieved accurate CW predictions. MIXED displayed the most superior fitting statistics than GM and QR. In model validation, with the increase in the number of sample trees, the model prediction accuracy gradually improved and the model differences gradually reduced. MIXED produced the smallest RMSE, MAE, and MAPE across all sampling designs. The intermediate tree sampling design with the best validation statistics for the given sample size was selected as the final sampling design. Under intermediate tree sampling design, MIXED required a minimum of five sample trees, while GM and QR required at least five and six sample trees for calibration, respectively. Generally, we suggested selecting MIXED as the final CW prediction model and using the intermediate tree sampling design of five trees per plot. This study could provide ideas and support for forest managers to accurately and efficiently predict CW. Full article

Comparing algorithms are crucial for enhancing the accuracy of remote sensing estimations of forest biomass in regions with high heterogeneity. Herein, Sentinel 2A, Sentinel 1A, Landsat 8 OLI, and Digital Elevation Model (DEM) were selected as data sources. A total of 12 algorithms, including 7 types of learners, were utilized for estimating the aboveground biomass (AGB) of Pinus yunnanensis forest. The results showed that: (1) The optimal algorithm (Extreme Gradient Boosting, XGBoost) was selected as the meta-model (referred to as XGBoost-stacking) of the stacking ensemble algorithm, which integrated 11 other algorithms. The R² value was improved by 0.12 up to 0.61, and RMSE was decreased by 4.53 Mg/ha down to 39.34 Mg/ha compared to the XGBoost. All algorithms consistently showed severe underestimation of AGB in the Pinus yunnanensis forest of Yunnan Province when AGB exceeded 100 Mg/ha. (2) XGBoost-Stacking, XGBoost, BRNN (Bayesian Regularized Neural Network), RF (Random Forest), and QRF (Quantile Random Forest) have good sensitivity to forest AGB. QRNN (Quantile Regression Neural Network), GP (Gaussian Process), and EN (Elastic Network) have more outlier data and their robustness was poor. SVM-RBF (Radial Basis Function Kernel Support Vector Machine), k-NN (K Nearest Neighbors), and SGB (Stochastic Gradient Boosting) algorithms have good robustness, but their sensitivity was poor, and QRF algorithms and BRNN algorithm can estimate low values with higher accuracy. In conclusion, the XGBoost-stacking, XGBoost, and BRNN algorithms have shown promising application prospects in remote sensing estimation of forest biomass. This study could provide a reference for selecting the suitable algorithm for forest AGB estimation. Full article

It is important to improve the accuracy of models estimating aboveground biomass (AGB) in large areas with complex geography and high forest heterogeneity. In this study, k-nearest neighbors (k-NN), gradient boosting machine (GBM), random forest (RF), quantile random forest (QRF), regularized random forest (RRF), and Bayesian regularization neural network (BRNN) machine learning algorithms were constructed to estimate the AGB of four forest types based on environmental factors and the variables selected by the Boruta algorithm in Yunnan Province and using integrated Landsat 8 OLI and Sentinel 2A images. The results showed that (1) DEM was the most important variable for estimating the AGB of coniferous forests, evergreen broadleaved forests, deciduous broadleaved forests, and mixed forests; while the vegetation index was the most important variable for estimating deciduous broadleaved forests, the climatic factors had a higher variable importance for estimating coniferous and mixed forests, and texture features and vegetation index had a higher variable importance for estimating evergreen broadleaved forests. (2) In terms of specific model performance for the four forest types, RRF was the best model both in estimating the AGB of coniferous forests and mixed forests; the R² and RMSE for coniferous forests were 0.63 and 43.23 Mg ha⁻¹, respectively, and the R² and RMSE for mixed forests were 0.56 and 47.79 Mg ha⁻¹, respectively. BRNN performed the best in estimating the AGB of evergreen broadleaved forests; the R² was 0.53 and the RMSE was 68.16 Mg ha⁻¹. QRF was the best in estimating the AGB of deciduous broadleaved forests, with R² of 0.43 and RMSE of 45.09 Mg ha⁻¹. (3) RRF was the best model for the four forest types according to the mean values, with R² and RMSE of 0.503 and 52.335 Mg ha⁻¹, respectively. In conclusion, different variables and suitable models should be considered when estimating the AGB of different forest types. This study could provide a reference for the estimation of forest AGB based on remote sensing in complex terrain areas with a high degree of forest heterogeneity. Full article

Satellite-based soil organic carbon content (SOC) mapping over wide regions is generally hampered by the low soil sampling density and the diversity of soil sampling periods. Some unfavorable topsoil conditions, such as high moisture, rugosity, the presence of crop residues, the limited amplitude of SOC values and the limited area of bare soil when a single image is used, are also among the influencing factors. To generate a reliable SOC map, this study addresses the use of Sentinel-2 (S2) temporal mosaics of bare soil (S2Bsoil) over 6 years jointly with soil moisture products (SMPs) derived from Sentinel 1 and 2 images, SOC measurement data and other environmental covariates derived from digital elevation models, lithology maps and airborne gamma-ray data. In this study, we explore (i) the dates and periods that are preferable to construct temporal mosaics of bare soils while accounting for soil moisture and soil management; (ii) which set of covariates is more relevant to explain the SOC variability. From four sets of covariates, the best contributing set was selected, and the median SOC content along with uncertainty at 90% prediction intervals were mapped at a 25-m resolution from quantile regression forest models. The accuracy of predictions was assessed by 10-fold cross-validation, repeated five times. The models using all the covariates had the best model performance. Airborne gamma-ray thorium, slope and S2 bands (e.g., bands 6, 7, 8, 8a) and indices (e.g., calcareous sedimentary rocks, “calcl”) from the “late winter–spring” time series were the most important covariates in this model. Our results also indicated the important role of neighboring topographic distances and oblique geographic coordinates between remote sensing data and parent material. These data contributed not only to optimizing SOC mapping performance but also provided information related to long-range gradients of SOC spatial variability, which makes sense from a pedological point of view. Full article

We use a quantile machine learning (random forests) approach to analyse the predictive ability of newspapers-based macroeconomic attention indexes (MAIs) on eight major fundamentals of the United States on the realized volatility of a major commodity-exporting emerging stock market, namely South Africa. We compare the performance of the MAIs with the performance of a news sentiment index (NSI) of the US. We find that both fundamentals and sentiment improve predictive performance, but the relative impact of the former is stronger. We document how the impact of fundamentals and sentiment on predictive performance varies across the quantiles of the conditional distribution of realized volatility, and across different prediction horizons. Specifically, fundamentals matter more at the extreme quantiles at short horizons, and at the median in the long-run. In addition, we report several robustness checks (involving sample period and alternative definitions of realized volatility), and indicate that the obtained results for South Africa also tend to carry over to other emerging countries such as, Brazil, China, India, and Russia. Our results have important implications for investors with volatility being an input for portfolio allocation decisions. In addition, with stock market variability also capturing financial uncertainty, its accurate prediction based on US fundamentals and sentiment also has a role in policy design to prevent possible collapse. Full article

The uncertainty from the under-estimation and over-estimation of forest aboveground biomass (AGB) is an urgent problem in optical remote sensing estimation. In order to more accurately estimate the AGB of Pinus densata forests in Shangri-La City, we mainly discuss three non-parametric models—the artificial neural network (ANN), random forests (RFs), and the quantile regression neural network (QRNN) based on 146 sample plots and Sentinel-2 images in Shangri-La City, China. Moreover, we selected the corresponding optical quartile models with the lowest mean error at each AGB segment to combine as the best QRNN (QRNNb). The results showed that: (1) for the whole biomass segment, the QRNNb has the best fitting performance compared with the ANN and RFs, the ANN has the lowest R² (0.602) and the highest RMSE (48.180 Mg/ha), and the difference between the QRNNb and RFs is not apparent. (2) For the different biomass segments, the QRNNb has a better performance. Especially when AGB is lower than 40 Mg/ha, the QRNNb has the highest R² of 0.961 and the lowest RMSE of 1.733 (Mg/ha). Meanwhile, when AGB is larger than 160 Mg/ha, the QRNNb has the highest R² of 0.867 and the lowest RMSE of 18.203 Mg/ha. This indicates that the QRNNb is more robust and can improve the over-estimation and under-estimation in AGB estimation. This means that the QRNNb combined with the optimal quantile model of each biomass segment provides a method with more potential for reducing the uncertainties in AGB estimation using optical remote sensing images. Full article

Solar-power-generation forecasting tools are essential for microgrid stability, operation, and planning. The prediction of solar irradiance (SI) usually relies on the time series of SI and other meteorological data. In this study, the considered microgrid was a combined cold- and power-generation system, located in Tahiti. Point forecasts were obtained using a particle swarm optimization (PSO) algorithm combined with three stand-alone models: XGboost (PSO-XGboost), the long short-term memory neural network (PSO-LSTM), and the gradient boosting regression algorithm (PSO-GBRT). The implemented daily SI forecasts relied on an hourly time-step. The input data were composed of outputs from the numerical forecasting model AROME (Météo France) combined with historical meteorological data. Our three hybrid models were compared with other stand-alone models, namely, artificial neural network (ANN), convolutional neural network (CNN), random forest (RF), LSTM, GBRT, and XGboost. The probabilistic forecasts were obtained by mapping the quantiles of the hourly residuals, which enabled the computation of 38%, 68%, 95%, and 99% prediction intervals (PIs). The experimental results showed that PSO-LSTM had the best accuracy for day-ahead solar irradiance forecasting compared with the other benchmark models, through overall deterministic and probabilistic metrics. Full article