All

Predicting Weathering Indices Using FTIR Spectra

The main goal of this study was to analyze the weathering conditions of the most representative soils of West Azerbaijan, Northern Iran, using chemical indices, and to demonstrate the suitability of FTIR spectra and RF to predict these weathering indices and to identify the major soil components related to soil weathering.

Determining the contribution of environmental factors in controlling dust pollution during cold and warm months of western Iran using different data mining algorithms and game theory

A methodology framework was proposed for identifying the environmental controls of dust pollution in western Iran using game theory and different machine-learning models. Here, we observed that the DNN model was most effective in predicting DSI in the cold and warm months of western Iran when compared to the MLR, GPR, XGB, and RF models.

Environmental Factors in Controlling Dust Pollution

A methodology framework was proposed for identifying the environmental controls of dust pollution in western Iran using game theory and different machine-learning models. Here, we observed that the DNN model was most effective in predicting DSI in the cold and warm months of western Iran when compared to the MLR, GPR, XGB, and RF models.

SOC Prediction in Rangelands

Remote sensing indices obtained from Sentinel-2 satellite images are closely related to SOCS changes in the study area. Therefore, using environmental variables with high spatial resolution greatly increases the accuracy of predicting the target variable, while saving costs and time for researches.

Spatial prediction of soil organic carbon stocks in an arid rangeland using machine learning algorithms

Remote sensing indices obtained from Sentinel-2 satellite images are closely related to SOCS changes in the study area. Therefore, using environmental variables with high spatial resolution greatly increases the accuracy of predicting the target variable, while saving costs and time for researches.

Accuracy, uncertainty, and interpretability assessments of ANFIS models to predict dust concentration in semi-arid regions

The present study investigated the accuracy and the uncertainty of ANFIS and ANFIS+BAT models to predict DC in the cold and warm months across semi-arid regions. The interpretability of the hybrid ANFIS model has also been examined using the permutation importance metric.

ANFIS Models to Predict Dust Concentration

The present study investigated the accuracy and the uncertainty of ANFIS and ANFIS+BAT models to predict DC in the cold and warm months across semi-arid regions. The interpretability of the hybrid ANFIS model has also been examined using the permutation importance metric.

Assessing agricultural salt-affected land using digital soil mapping and hybridized random forests

Digital soil maps that identify areas of high risk to the salinization and alkalization processes can be used to facilitate better land management and soil management practices. This study assessed spatial variability of soil salinity and sodicity on agriculturally intensive regions of the Kurdistan province, Iran.

Assessing Salty Land Using Hybridized RF

Digital soil maps that identify areas of high risk to the salinization and alkalization processes can be used to facilitate better land management and soil management practices. This study assessed spatial variability of soil salinity and sodicity on agriculturally intensive regions of the Kurdistan province, Iran.

High resolution middle eastern soil attributes mapping via open data and cloud computing

We obtained accurate predictions of clay, silt, sand, OC, pH and CCE for the middle eastern topsoils, with correct pedological correspondences, realistic spatial representations, and satisfactory levels of uncertainties.