Knowledge-infused Deep Learning Enables Interpretable Landslide Forecasting

TL;DR

This paper introduces a transformer-based deep learning pipeline that integrates prior knowledge to produce interpretable and holistic landslide forecasts, improving understanding of landslide evolution and influencing factors.

Contribution

The study presents LFIT, a novel transformer-based model that incorporates prior knowledge for interpretable, nonlinear landslide forecasting across different regions.

Findings

Incorporating prior knowledge improves forecast accuracy.

The model identifies key influencing factors for landslide behavior.

Interpretable forecasts elucidate local responses to various factors.

Abstract

Forecasting how landslides will evolve over time or whether they will fail is a challenging task due to a variety of factors, both internal and external. Despite their considerable potential to address these challenges, deep learning techniques lack interpretability, undermining the credibility of the forecasts they produce. The recent development of transformer-based deep learning offers untapped possibilities for forecasting landslides with unprecedented interpretability and nonlinear feature learning capabilities. Here, we present a deep learning pipeline that is capable of predicting landslide behavior holistically, which employs a transformer-based network called LFIT to learn complex nonlinear relationships from prior knowledge and multiple source data, identifying the most relevant variables, and demonstrating a comprehensive understanding of landslide evolution and temporal patterns. By integrating prior knowledge, we provide improvement in holistic landslide forecasting, enabling us to capture diverse responses to various influencing factors in different local landslide areas. Using deformation observations as proxies for measuring the kinetics of landslides, we validate our approach by training models to forecast reservoir landslides in the Three Gorges Reservoir and creeping landslides on the Tibetan Plateau. When prior knowledge is incorporated, we show that interpretable landslide forecasting effectively identifies influential factors across various landslides. It further elucidates how local areas respond to these factors, making landslide behavior and trends more interpretable and predictable. The findings from this study will contribute to understanding landslide behavior in a new way and make the proposed approach applicable to other complex disasters influenced by internal and external factors in the future.