The growing interconnectedness between socio-economic and natural systems, coupled with the escalating challenges presented by climate changes, has led to increased complexity in the human-environmental risk dynamics. Simultaneously, the wealth of data stemming from these systems is ever increasing thanks to advances in digitization and remote sensing. In this context, machine learning and artificial intelligence are powerful tools which offer great potential to discover emerging relationships which can help the understanding and the prediction of environmental risks.
In this session, we invite contributions on machine learning applications (such as Deep Learning, but also Bayesian Networks, Random Forest, etc.) for assessing multi-risk dynamics and identifying underlying risk drivers at different spatio-temporal scales and common points of failure. The aim of the papers should be achieving enhanced multi-risk modellingmodeling and proposing solutions to support the design of climate change adaptation and disaster risk management plans in view of current and future risk scenarios. This way, our session aims to foster the exchange and collaboration on recent applications of cutting-edge methods to the field of multi-risk analytics.