Work

Rockfall Forecasting Using Ensemble Deep Learning and Temporal Gradient-Based Explanations

Year: 2025

Type: conference-paper

Abstract: Rockfalls pose a significant risk for infrastructures and human activities. Accurate forecasting is therefore crucial for prevention. While current methods rely on expert hypotheses, AI models, particularly explainable ones, offer a promising way to improve the accuracy of forecasts and provide transparent, trustworthy results. In this paper, an ensemble of multisource neural networks based on InceptionTime modules whose forecasts are explained using a temporal Grad-CAM approach is being developed for the Mont Saint-Eynard cliff, showcasing the potential of AI in this area.

Source: IEEE ... International Conference on Data Mining workshops

DOI: 10.1109/icdmw69685.2025.00034

Authors: Sabrine Bouaziz, Christophe Lin-Kwong-Chon, Nicolas Méger, David Amitrano

Institutions: Université Savoie Mont Blanc, Institut des Sciences de la Terre, Centre National de la Recherche Scientifique, Institut de Recherche pour le Développement, Université Grenoble Alpes

Language: English

Topic: Landslides and related hazards

Subfield: Management, Monitoring, Policy and Law

Field: Environmental Science

Domain: Physical Sciences

Open Access status: green

Funder: Agence Nationale de la Recherche

Award: Rockfall risk: the use of Artificial Intelligence for the operational management of the risk