RINA - Démonstrateur d’utilisation de l’intelligence artificielle pour la gestion opérationnelle des risques naturels gravitaires géologiques | FEREC 2020

Abstract Rock falls cause numerous accidents around the world. A location where the risk is increased are roads where, due to modifications of topography, there are unstable bedrocks. One method of avoiding accidents is closing the road on days the risk is too high. In order to create the operational code statistical methods are utilized. This study will explore the capacities of artificial intelligence (AI) in order to better understand rock fall events and to compare the capacities of different statistical methods to predict the events. The first step was selecting which site to study. The RN1 from la Réunion was chosen due to its detailed data set with many events. The data needed to be acquired from different partners. When the data was transferred it could then be formatted and then analysed. It is important to do a simple analysis to have a good understanding of the situation and to spot any early tendencies and possible incorrect data. Subsequently predictive models can be created and finally analysed in order to draw conclusions. 3 different methods were used to create models, nearest neighbors, decision trees and NNs. For each method different models were tuned in order to produce an optimal performance for predictions over the test set. The results were summarized on confusion matrices and the models were compared between each other and with the operational system. This work permits us to observe that AI is capable of producing models with great performance, but further studies are needed in order to use it operationally. 2