Mapping of dust source susceptibility by remote sensing and machine learning techniques (case study: Iran-Iraq border)

Pourhashemi, Sima; Asadi, Mohammad Ali Zangane; Boroughani, Mahdi; Azadi, Hossein

doi:10.1007/s11356-022-23982-x

Cited by 6 publications

(1 citation statement)

References 81 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The frequency of dust storms has increased substantially across Iran over the last 20 years, exacerbated by prolonged dry conditions during 2000-2002and 2008(Akoglu et al, 2015Duniway et al, 2019;Hamzeh et al, 2021;Rashki et al, 2021). In order to mitigate the effects of wind erosion and associated dust storms on the atmosphere, geosphere, and biosphere, the prediction and mapping of land susceptibility to wind erosion are essential (Gholami et al, 2020c;Jafari et al, 2022;Pourhashemi et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

Modeling land susceptibility to wind erosion hazards using LASSO regression and graph convolutional networks

Gholami

Mohammadifar

Fitzsimmons

et al. 2023

Front. Environ. Sci.

View full text Add to dashboard Cite

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 the first attempt to model wind erosion hazards through the application of a novel approach, the graph convolutional networks (GCNs), as deep learning models with Monte Carlo dropout. This approach is applied to 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 GCN 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 GCN 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 and 0.4, while SHAP analyses revealed that the coarse clastic component, vegetation cover, and land use were the most effective features of the GCN output. Our results suggest that this novel suite of methods is highly recommended for future spatial prediction of wind erosion hazards in other arid environments around the globe.

show abstract