Spatial characterization of dust emission prone arid regions using feature extraction and predictive algorithms

Abstract

Abstract Aeolian dust emission is a serious environmental hazard in central Iran. We attempted to map the dust emission prone (DEP) areas in this region of Iran using the most accurate model among the random forest (RF), conditional RF (CRF), parallel RF (PRF), and extremely randomized trees (ERT) models. These models were evaluated using the Taylor diagram, Nash Sutcliffe coefficient, and Kling–Gupta efficiency. The generated map of DEP areas was also validated based on an aerosols optical depth (AOD) dataset. The Shapely values were used to determine the contribution of factors controlling dust events in DEP areas. The high performance and reliability of the ERT model for mapping DEP territories were confirmed by both error assessment statistics and reclassified AOD map. Using the ERT-generated map, five dust generation susceptibility classes including very low (20.16%), low (19.99%), moderate (19.82%), high (24.11%), and very high (15.92%) were identified in the study region. Drought severity, solar radiation, soil moisture, geology, soil sand content, bulk density, vegetation cover, land use, and slope were detected as the key features controlling dust emissions in central Iran. These results are useful for developing programs to reduce dust emissions hazards in DEP areas, particularly in central Iran.