Department of Arid Zone Management, Gorgan University of Agricultural Sciences and Natural Resources, Gorgan, Iran.
Department of Natural Resources and Environmental Engineering, College of Agriculture, Shiraz University, Shiraz, Iran.
PLoS One. 2024 Oct 31;19(10):e0308854. doi: 10.1371/journal.pone.0308854. eCollection 2024.
Preventing wind erosion and dust storms has always been a major concern in arid and semi-arid areas because of their negative effects on the environment. This study aims to utilize remote sensing and machine learning techniques to model, monitor, and predict the risk of wind erosion in Northeast Iran. Through an examination of relevant studies, a comprehensive review was conducted, leading to the identification of eight remote sensing indicators that exhibited the highest correlation with field data. These indicators were subsequently employed to model the risk of wind erosion in the study area. Various methods including Random Forest (RF), Support Vector Machine (SVM), Gradient Boosting Machine (GBM), and Generalized Linear Models (GLM) were employed to carry out the modeling process. The final method utilized a weighted average of the model, and the SDM statistical package was used to combine different approaches to decrease uncertainty when modeling and monitoring wind erosion in the area. The modeling results indicated that in 2008, the RF model performed the best (AUC = 0.92, TSS = 0.82, and Kappa = 0.96), while in 2023, the GBM model showed superior performance (AUC = 0.95, TSS = 0.79, and Kappa = 0.95). Therefore, the utilization of an ensemble model emerged as an effective approach to reduce uncertainty during the modeling process. By employing the ensemble model, the outcomes obtained accurately depicted an elevated intensity of wind erosion in the northeastern regions of the study area by 2023. Furthermore, considering the climatic scenarios and projected land use changes, it is anticipated that wind erosion intensity will experience a 23% increase in the central and southern parts of the study area by 2038. By taking into account the reliable results of the ensemble model, which offers reduced uncertainty, it becomes feasible to implement effective planning, optimal management, and appropriate measures to mitigate the progression of wind erosion.
防治风蚀和沙尘暴一直是干旱和半干旱地区的主要关注点，因为它们会对环境产生负面影响。本研究旨在利用遥感和机器学习技术对伊朗东北部的风蚀风险进行建模、监测和预测。通过对相关研究的考察，进行了全面的综述，确定了与实地数据相关性最高的 8 个遥感指标。这些指标随后被用于对研究区域的风蚀风险进行建模。采用随机森林 (RF)、支持向量机 (SVM)、梯度提升机 (GBM) 和广义线性模型 (GLM) 等多种方法进行建模。最终采用模型的加权平均值，使用 SDM 统计包将不同方法结合起来，以减少建模和监测该区域风蚀时的不确定性。建模结果表明，2008 年 RF 模型的性能最佳 (AUC=0.92，TSS=0.82，Kappa=0.96)，而 2023 年 GBM 模型的性能最优 (AUC=0.95，TSS=0.79，Kappa=0.95)。因此，采用集成模型是减少建模过程不确定性的有效方法。通过采用集成模型，可以准确地描绘出研究区东北部到 2023 年风蚀强度的增加。此外，考虑到气候情景和预测的土地利用变化，预计到 2038 年研究区中部和南部的风蚀强度将增加 23%。考虑到集成模型可靠的结果，降低了不确定性，可以实施有效的规划、优化管理和适当的措施来减缓风蚀的发展。
