AUTHOR=Gholami Hamid , Mohammadifar Aliakbar , Fitzsimmons Kathryn E. , Li Yue , Kaskaoutis Dimitris G. TITLE=Modeling land susceptibility to wind erosion hazards using LASSO regression and graph convolutional networks JOURNAL=Frontiers in Environmental Science VOLUME=Volume 11 - 2023 YEAR=2023 URL=https://www.frontiersin.org/journals/environmental-science/articles/10.3389/fenvs.2023.1187658 DOI=10.3389/fenvs.2023.1187658 ISSN=2296-665X ABSTRACT=Predicting land susceptibility to wind erosion is necessary to mitigate the negative impacts of erosion on soil fertility, ecosystems and human health. This study is a first attempt to model wind erosion hazards through the application of novel graph convolutional networks (GCNs), as deep learning models with Monte Carlo dropout. We apply this approach to the Semnan province in arid Central Iran, an area vulnerable to dust storms and climate change. We mapped 15 potential factors controlling wind erosion, including climatic variables, soil characteristics, lithology, vegetation cover, land use and a digital elevation model (DEM), and then applied the least absolute shrinkage and selection operator (LASSO) regression to discriminate the most important factors. We constructed a predictive model by randomly selecting 70% and 30% of the pixels, as training and validation datasets respectively, focusing on locations with severe wind erosion on the inventory map. The current LASSO regression identified eight out of the 15 features (four soil property categories, vegetation cover, land use, wind speed and evaporation) as the most important factors controlling wind erosion in Semnan province. These factors were adopted into the GCNs model, which estimated that 15.5%, 19.8%, 33.2% and 31.4% of the total area is characterized by low, moderate, high and very high susceptibility to wind erosion, respectively. The area under curve (AUC) and SHapley Additive exPlanations (SHAP) of game theory were applied to assess the performance and interpretability of GCNs output, respectively. The AUC values for training and validation datasets were estimated at 97.2% and 97.25%, respectively, indicating excellent model prediction. SHAP values ranged between -0.3 to 0.4; SHAP analyses revealed that the coarse clastic component, vegetation cover and land use were the most effective features of the GCNs output. Our results suggest that this novel suite of methods is highly recommended for future spatial prediction of wind erosion hazards in other regions.