Project description
Algorithms for improved rainfall predictions
The Mediterranean region (MED) is a hot-spot of anthropogenic climate change. To assure effective near-term planning, decisionmakers in weather-dependent sectors depend on skilful forecasts of precipitation on sub-seasonal to seasonal (S2S) timescales. However, some fundamental challenges prevent reliable predictions beyond approximately 10 days. The EU-funded CausalBoost project will apply an innovative method to improve S2S forecasts of MED rainfall. The approach relies on a combination of innovative causal discovery algorithms from machine learning with operational forecast models. The project will identify central S2S drivers of MED rainfall, systematically assess them with prediction models and produce process-based bias corrections.
Objective
The Mediterranean region (MED) is a hotspot of anthropogenic climate change and impacts are probably already felt today; recent heatwaves and persistent droughts have led to crop failures, wild fires and water shortages, causing large economic losses. Climate models robustly project further warming and drying of the region, putting it at risk of desertification. The particular vulnerability of this water-limited region to climatic changes has created an urgent need for reliable forecasts of rainfall on subseasonal to seasonal (S2S) timescales, i.e. 2 weeks up to a season ahead. This S2S time-range is particularly crucial, as the prediction lead time is long enough to implement adaptation measures, and short enough to be of immediate relevance for decision makers. However, predictions on lead-times beyond approximately 10 days fall into the so-called “weather-climate prediction gap”, with operational forecast models only providing marginal skill. The reasons for this are a range of fundamental challenges, including a limited causal understanding of the underlying sources of predictability.
The proposed research effort aims to improve S2S forecasts of MED rainfall by taking an innovative, interdisciplinary approach that combines novel causal discovery algorithms from complex system science with operational forecast models. This will overcome current limitations of conventional statistical methods to identify relevant sources of predictability and to evaluate modelled teleconnection processes. The outcomes of this project will (i) identify key S2S drivers of MED rainfall, (ii) systematically evaluate them in forecast models, (iii) derive process-based bias corrections to (iv) boost forecast skill. My strong background in both causal inference techniques and atmospheric dynamics puts me in a unique position to lead this innovative effort and to achieve real progress in reducing the “weather-climate prediction gap” for the MED region.
Fields of science
Programme(s)
Funding Scheme
MSCA-IF-EF-ST - Standard EFCoordinator
RG6 6AH Reading
United Kingdom