“…Benefiting from the rapid development of earth observation technology and computer performance, the data‐driven approaches, represented by machine learning, have become the dominant approaches for LSE (Akgun & Erkan, 2016; Huang et al, 2020; Wu et al, 2021; Zhu et al, 2020). The frequently used machine learning models in the LSE field are support vector machines (SVM) (Chen et al, 2016; Hong et al, 2015; Pourghasemi et al, 2013; Tien Bui et al, 2016), random forests (RF) (Achour et al, 2021; Chen et al, 2018; Drid et al, 2022; Pourghasemi & Kerle, 2016), and artificial neural networks (ANN) (Chen et al, 2017; de Oliveira et al, 2019; Polykretis et al, 2015). These methods do not require specific expert knowledge and have little manual intervention, are end‐to‐end, and easy to use.…”