EGU23-3276, updated on 22 Feb 2023
EGU General Assembly 2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.

A large-scale flood modeling using geometry-adaptive physics-informed neural solver and Earth observation data

Qingsong Xu1, Yilei Shi2, Jonathan Bamber1,3, Chaojun Ouyang4, and Xiao Xiang Zhu1
Qingsong Xu et al.
  • 1Data Science in Earth Observation, Technical University of Munich (TUM), Munich, Germany
  • 2Chair of Remote Sensing Technology (LMF), Technical University of Munich (TUM), Munich, Germany
  • 3School of Geographical Sciences, University of Bristol, UK
  • 4Institute of Mountain Hazards and Environment, Chinese Academy of Sciences, China

Large-scale hydrodynamic models generally rely on fixed-resolution spatial grids and model parameters as well as incurring a high computational cost. This limits their ability to accurately forecast flood crests and issue time-critical hazard warnings. In this work, we build a fast, stable, accurate, resolution-invariant, and geometry-adaptative flood modeling and forecasting framework that can perform at scales from continental to global. We achieve this by combining continuous flow modeling of a geometry-adaptive physics-informed neural solver (GeoPINS) with the authenticity of Earth observation data. Specifically, the GeoPINS is proposed based on the advantages of no training data in physics-informed neural networks (PINNs), as well as possessing a fast, accurate, and resolution-invariant architecture through the implementation of Fourier neural operators (FNO). In particular, to adapt to complex and irregular geometries that exist in rivers, we reformulate PINNs in a geometry-adaptive space by taking full advantage of coordinate transformations and the efficiency of numerical methods in solving the spatial gradient. We validate our GeoPINS on popular partial differential equations on both regular and irregular domains, demonstrating fast, stable, and accurate performance, as well as resolution-invariant, geometry-adaptive properties. Next, due to a lack of large-scale ground truth data, time-series flood records are generated using freely available Sentinel-1 data and a SAR-based flood mapping algorithm. These flood records are used as boundary conditions and flood inundation extent verification of the proposed hydrodynamic model. Finally, we compare our GeoPINS results with a 30 m resolution, SAR-based flood record, and measured discharge from gauging stations, obtaining good agreement among the three. The experimental results for the Pakistan flood in 2022 indicate that the proposed method can maintain high-precision large-scale flood dynamics solutions at different resolutions and flood hazards can be forecast in real-time with the aid of reliable precipitation data.

How to cite: Xu, Q., Shi, Y., Bamber, J., Ouyang, C., and Zhu, X. X.: A large-scale flood modeling using geometry-adaptive physics-informed neural solver and Earth observation data, EGU General Assembly 2023, Vienna, Austria, 24–28 Apr 2023, EGU23-3276,, 2023.

Supplementary materials

Supplementary material file

Comments on the supplementary material

to access the discussion