Climate Informatics: Machine Learning for the Study of Climate Change
De Claire Monteleoni
A Space Test of the Equivalence Principle with MICROSCOPE
De Manuel Rodrigues
Apparaît dans la collection : Nonlinear and stochastic methods in climate and geophysical fluid dynamics
Many key problems in climate dynamics require a huge computational effort. For instance, the study of extreme or rare events, the study of precursors, or the probabilistic prediction at the predictability margin, are three examples for which the computation of the relevant statistical quantities is impossible with reasonable computation resources, in comprehensive climate models. I will present several examples of new approaches we have developed, for instance using rare event algorithms and machine learning, for which we have solved these computational bottlenecks using concepts from statistical mechanics and dynamical systems. I will discuss applications to the study of extreme heat waves or for the prediction of El Nino.