Published: November 21, 2024; Aithor: Julia Sonrisa
Address: 2276 12th Avenue, Room 206, New York, NY 10027, United States
Speaker: Tim Hermans (Utrecht)
Time: 12:00 pm
Format: Hybrid
Virtual: Zoom link provided upon registration
In-person: Columbia Innovation Hub
*Please note that in-person space is limited.*
Abstract: Projections of atmospherically driven changes in extreme storm surges are often based on small ensembles of climate model simulations because they are computed with computationally expensive hydrodynamic models. Consequently, these projections are sensitive to internal climate variability and inter-model differences. Data-driven storm surge models are emerging as a promising, computationally cheaper alternative to translating simulated changes in atmospheric variables to changes in storm surges. However, the ability of data-driven models to predict extreme storm surges in Europe is unclear because previous studies did not address the underrepresentation of extremes in the training data. Therefore, we investigated how well neural networks can reconstruct extreme storm surges when addressing the imbalance in the training data using the cost-sensitive learning approach in which samples with a lower density contribute to the training loss more.
We find that density-based weighting improves both the RMSE and F1 score of predictions v.s. observed extremes, although the optimal weights depend on the location. Our neural networks typically outperform an existing multi-linear regression model but perform less well than a state-of-the-art hydrodynamic model (GTSM). Using a ConvLSTM instead of an LSTM layer reduces both the underestimation of the highest extremes and the number of false positive predictions, improving the error metrics of the neural networks at almost all selected locations. In light of the potential application of neural networks to global climate model simulations to project changes in extreme storm surges, I will also discuss preliminary results of the application of our neural networks to atmospheric forcing from a global climate model participating in HighResMIP.
Bio: Tim Hermans is a postdoctoral researcher at Utrecht University, currently working on projecting sea-level extremes and compound flooding using climate model simulations and data-driven modeling. He is also interested in the interface between sea-level science and adaptation. As a chapter scientist for Chapter 9 of the IPCC AR6 (WG1), Tim was responsible for developing part of the global, regional, and extreme sea-level projections of the report (2020-2022). He also co-developed the modular framework for assessing changes to sea level (FACTS). Tim obtained a PhD at the NIOZ (Dutch Institute for Sea Research) & Delft University of Technology on regional and global mean sea-level change using global climate model simulations and dynamical downscaling (2018-2022).
Time: 12:00 pm EST
Free!
Detailed information and discussion of the event.