Wind erosion is a serious environmental issue caused by the interaction between various climatic and terrestrial factors. Using the ridge regression (RR) method, the present study aimed to investigate the relationship between these parameters and dust storm index (DSI) in arid regions of Central Iran during 2000–2014. The removal area of soil particles in the dustiest season was further detected via sand and dust roses. The results showed that the highest activity of wind erosion occurred in spring (DSI > 1). The RR analysis indicated that only the air temperature changes had a significant positive effect on DSI variations during the first period (β = +0.38; p < .05). For the second period, decreased precipitation and increased wind velocity were identified as the most important factors influencing the DSI variations. The estimated regression coefficients concerning precipitation and wind speed at 95% confidence level were (−1.02) and (+0.51), respectively. Based on the R² value, 27% of the DSI changes could be explained by the air temperature variations in the first period. However, approximately 50% of the DSI variations were explained by the rainfall and wind speed changes in the second period. These results illustrate the effective application of RR to elucidate the relationship of climatic and terrestrial factors with DSI. It was further observed that the removal area of soil particles in the northeastern, southeastern, and western parts of Central Iran was easterly, northerly, and westerly, respectively.

Estimating sediment load of rivers is one of the major problems in river engineering that has been using various data mining algorithms and variables. It is desirable to obtain accurate estimates of sediment load while using techniques that limit computational intensity when datasets are large. This study investigates the usefulness of geo-morphometric factors and machine learning (ML) models for predicting suspended sediment load (SSL) in several river basins in Lorestan and Gilan, Iran. Six ML models, namely, multiple linear regression (MLR), artificial neural networks (ANN), K-nearest neighbor (KNN), Gaussian processes (GP), support vector machines (SVM), and evolutionary support vector machines (ESVM), were evaluated for estimating minimum and average SSL for the study regions. Geo-morphometric parameters and river discharge data were utilized as the main predictors in modeling process. In addition, an attribute reduction technique was applied to decrease the algorithm complexity and computational resources used. The results showed that all models estimated both target variables well. However, the optimal models for predicting average sediment load and minimum sediment load were the GP and ESVM models, respectively.