Extreme Event
Extreme events, encompassing high-impact phenomena like floods, heatwaves, and storms, are a major focus of scientific inquiry due to their increasing frequency and severity. Current research emphasizes improving the accuracy and reliability of extreme event prediction using advanced machine learning models, such as deep learning architectures (e.g., LSTMs, convolutional neural networks) and ensemble methods, often incorporating high-resolution datasets and explainable AI techniques. This work is crucial for enhancing disaster preparedness, risk assessment, and resource allocation, ultimately contributing to improved societal resilience and mitigation strategies.
Papers
Model-assisted deep learning of rare extreme events from partial observations
Anna Asch, Ethan Brady, Hugo Gallardo, John Hood, Bryan Chu, Mohammad Farazmand
Unsupervised Change Detection of Extreme Events Using ML On-Board
Vít Růžička, Anna Vaughan, Daniele De Martini, James Fulton, Valentina Salvatelli, Chris Bridges, Gonzalo Mateo-Garcia, Valentina Zantedeschi