Extreme Event Monitoring, Everywhere, All at Once: Challenges and Strategies

The automatic anticipation and detection of extreme events such as droughts and heatwaves constitute a major challenge in the current context of climate change. However, their elusive and subjective definition, due to the complex physical, chemical and biological processes of the Earth system they involve, makes their management an arduous challenge to researchers, as well as decision-makers and policymakers. This talk presents our most recent advances in machine learning models in three complementary lines of research about droughts: detection, forecasting and understanding. While detection is about gaining the time series of drought maps and discovering underlying patterns and correlations, forecasting or prediction is to anticipate future droughts. Last but not least, understanding or explaining models through expert-comprehensible representations is equally important as accurately addressing these tasks, especially for their deployment in real scenarios. Thanks to the emergence and success of deep learning, all of these tasks can be tackled by the design of spatio-temporal data-driven approaches based on climate variables (soil moisture, precipitation, temperature, vegetation health, etc.) and/or satellite imagery. The possibilities are endless, from the design of convolutional architectures and attention mechanisms to the use of generative models such as Normalizing Flows (NFs) or Generative Adversarial Networks (GANs), trained both in a supervised and unsupervised manner, among others. Different application examples in Europe from 2003 onwards are provided, to reflect on the possibilities of the strategies proposed, and also to foresee alternatives and future lines of development.