Landslide susceptibility modeling by interpretable neural network

Abstract Landslides are notoriously difficult to predict because numerous spatially and temporally varying factors contribute slope stability. Artificial neural networks (ANN) have been shown improve prediction accuracy but largely uninterpretable. Here we introduce an additive ANN optimization framework assess landslide susceptibility, as well dataset division outcome interpretation techniques. We refer our approach, which features full interpretability, high accuracy, generalizability low model complexity, superposable network (SNN) optimization. validate approach by training models on inventories from three different easternmost Himalaya regions. Our SNN outperformed physically-based statistical achieved similar performance state-of-the-art deep networks. The found the product of precipitation hillslope aspect be important primary contributors highlights importance strong slope-climate couplings, along with microclimates, occurrences.