Understanding and Modelling the Earth System with Machine Learning

ongoing

Earth system models are fundamental to understand climate change. Although they have improved significantly, considerable biases and uncertainties in their projections remain. Process parameterisations limit the models’ ability to simulate both global and regional Earth system responses, which are key for assessing climate change and its impacts on ecosystems and society. In recent years, the volume of data from high-resolution models and observations has substantially increased to petabyte scales. Concomitantly, the field of machine learning (ML) has quickly developed, promising breakthroughs in detecting and analysing non-linear relationships and patterns in large multivariate datasets. Yet, traditionally, physical modelling and ML have been often treated as two different worlds with opposite scientific paradigms (theory-driven versus data-driven). Thus, despite its great potential, ML has not yet been widely adopted for addressing the urgent need of improved understanding and modelling of the Earth system. USMILE will combine multi-disciplinary expertise in ML and process-based atmosphere and land modelling to completely rethink model development and evaluation. ML will further allow us to define novel observational constraints on Earth system feedbacks and climate projections. We will (1) develop ML algorithms to enhance Earth observation datasets accounting for spatio-temporal covariations, (2) deploy ML-based parameterisations and sub-models for clouds and land-surface processes that have hindered progress in climate modelling for decades, and (3) detect and understand modes of climate variability, multivariate extremes and uncover dynamical aspects of the Earth system with novel deep learning and causal inference techniques. USMILE will drive a paradigm shift in the current modelling of the Earth system towards a new data-driven physics-aware science and to an unprecedented reduction of uncertainties in projections.