Review article: Deep learning for potential landslide identification: data, models, applications, challenges, and opportunities

As global climate change and human activities escalate, the frequency and severity of landslide hazards have been increasing. Early identification, as an important prerequisite for monitoring, evaluation, and prevention, has become increasingly critical. Deep learning, as a powerful tool for data interpretation, has demonstrated remarkable potential in advancing landslide identification, particularly through the automated analysis of remote sensing, geological, and topographic data. This review systematically examines and synthesizes over 400 studies, with a primary focus on literature from the last six years (2020–2025), alongside key foundational works. It provides a comprehensive overview of recent advancements in the utilization of deep learning for potential landslide identification. First, the sources and characteristics of landslide-related data are summarized, including satellite observation data, airborne remote sensing data, and ground-based observation data. Next, commonly used deep learning models are classified based on their roles in potential landslide identification, such as image analysis and time series analysis. Then, the role of deep learning in identifying rainfall-induced landslides, earthquake-induced landslides, human activity-induced landslides, and multi-factor-induced landslides is summarized. Although deep learning has achieved considerable success in landslide identification, it still faces several challenges, including data imbalance, limited model generalization, and the inherent complexity of landslide mechanisms. Finally, future research directions in this field are discussed. It is suggested that integrating knowledge-driven and data-driven approaches for potential landslide identification will further enhance the applicability of deep learning, offering broad prospects for future research and practice.