An improved spatial case-based reasoning considering multiple spatial drivers of geographic events and its application in landslide susceptibility mapping

Traditional case-based reasoning methods overlook non-stationary spatial drivers of geographical events such as heterogeneity, dependence, and accumulation in case representation, and directly obtain the solution of the most similar cases in case reuse instead of considering the interference of fake similar cases to eliminate the contin-gency of reasoning, which leads to poor interpretations and low efficiency decisions in complex and heteroge-neous geographical environments. This study proposes an improved spatial case-based reasoning (SCBR) considering multiple spatial drivers to overcome above problems and uses landslide susceptibility mapping as an example. Specifically, these spatial drivers were captured, extracted, and integrated into case representation by using geographic self-organizing mapping algorithm, spatial statistic, and spatial adjacent matrix, respectively. Additionally, the K-nearest neighbor method as case retrieval was introduced to retrieve the K similar cases based on the local and global similarity reasoning. Finally, the Gaussian process regression as case reuse method was generated to landslide susceptibility index under the assumption that K similar cases follows Gaussian distri-bution. Our experimental results show that the precision, F1, recall, and kappa of the proposed SCBR method are 0.974, 0.976, 0.979, and 0.953 which are higher than those of the traditional case-based reasoning (0.931, 0.941, 0.953, and 0.881), long short-term memory (0.951, 0.933, 0.915, and 0.870), and extreme gradient boosting decision tree (0.963, 0.967, 0.972, and 0.945), respectively. In general, the novel approach with better predictive performance can help decision makers to develop policies that reduce the loess of landslides and apply to similar geological events.