Profile

My research: The focus of my project is the combination of Machine Learning (ML) algorithms with numerical simulation models, what we call hybrid modelling, to predict and understand geophysical processes.

Current work: I have two ongoing case study is the desertification of semiarid hillslope ecosystems, in which I have applied different ML algorithms to simulate the aggregate behaviour of vegetation and soil, using data from spatially detailed simulation models. The results outperform previously used expert-based models, enabling an evidence-based analysis of the desertification mechanisms. The other one is focused on improving snow water equivalent simulations by either augmenting the observations fed into the ML model with simulated data, or using ML to correct the output from the simulation model.

Future plans: The continuation of my work will involve applying hybrid algorithms to other case studies, e.g. wind speed mapping.