Using multivariate adaptive regression splines and extremely randomized trees algorithms to predict dust events frequency around an international wetland and prioritize its drivers.

This study aimed to evaluate the performance of multivariate adaptive regression splines (MARS) and extremely randomized trees (ERT) models for predicting the internal and external dust events frequencies (DEF) across the northeastern and southwestern regions of the Gavkhouni International Wetland. These models were also evaluated to model the internal DEF (IDEF) across the northwestern, southeastern, northern, and western regions around the wetland. Furthermore, the main factors controlling DEF and IDEF were identified based on the importance value (IV) of predictors in the best model. The results showed that the ERT model increased the prediction accuracies by an average of 40%, compared to the MARS model. According to the IV obtained from the ERT model, aerosol optical depth (IV = 0.28), wetland discharge (IV = 0.25), near-surface wind speed (IV = 0.08), and erosive winds frequency (IV = 0.07) were identified as the most important factors controlling DEF across the northeastern and southwestern regions of the wetland. However, the erosive wind speed was detected as the major factor affecting the IDEF in the northern (IV = 0.16), western (IV = 0.18), and southeastern (IV = 0.65) regions of study wetland. It was also found that vapor pressure with IV of 0.32 had the greatest effect on IDEF variations across the northwestern region of the wetland. Overall, the results demonstrate the effectiveness of the ERT model in modeling the factors affecting DEF and IDEF, and the results may be used to mitigate dust events hazards around the Gavkhouni Wetland, in central Iran.