Application of Artificial Intelligence for understanding and prediction of human and volcanic activity

Nowadays, a key challenge in Earth observation and human behavior analysis, is data management and processing. Data acquisition of natural and human environment produces every day a large set of information from which more and more knowledge must be extracted and classified. Thus classical approaches to manage and process these data can no longer be used. Big data and IA approaches seem more appropriate. However, to investigate their potential and to make significant improvements in specific domains, it is necessary to build multidisciplinary teams. This project proposed by University Savoie Mont Blanc gathers researchers from two laboratories working respectively in geophysics (ISTerre) and computer sciences (LISTIC). These two laboratories are used to work together in different projects where they bring their complementary expertise to develop advanced methods for the processing of large data sets. Both laboratories intend to develop and apply IA techniques to improve the understanding and modeling of complex situations observed by different sensors. Two specific contexts will be investigated: • The context of volcanology, with two PhD theses proposed on the analysis of volcanic activity by machine learning approaches, and on the integration of dynamic physical models into data driven methods to improve predictions; • The context of human activity with one PhD thesis proposed on the development of “wise objects” which can progressively learn on them-selves and detect changes in human behavior in different cases: at home in home automation and home care for elderly persons, or through energy consumption when using computers. The 3 PhD theses are proposed by ISTerre, by LISTIC and by a joint ISTerre-LISTIC supervision. All researchers involved in the project are working on Bourget-du-Lac and/or Annecy Campuses of research and teaching activities. The project will organize regular meetings in both laboratories with the 3 recruited PhD students, in order to share the developed tools and the experience acquired on investigated IA methods.