A Wasserstein GAN-based climate scenario generator for risk management and insurance: the case of soil subsidence

This paper introduces an AI framework using Conditional Generative Adversarial Networks (GANs) to generate future spatio-temporal trajectories of climatic indices, specifically the Soil Wetness Index (SWI), to assess drought severity in France. The approach aims to support the insurance sector in developing long-term strategies for natural catastrophe risk management amidst rising associated costs.