Towards AI for approximating hydrodynamic simulations as a 2D segmentation task

Lydia Bryan-Smith, Nina Dethlefs
Proceedings of the 5th Northern Lights Deep Learning Conference ({NLDL}), PMLR 233:27-35, 2024.

Abstract

Traditional predictive simulations and remote sensing techniques for forecasting floods are based on fixed and spatially restricted physics-based models. These models are computationally expensive and can take many hours to run, resulting in predictions made based on outdated data. They are also spatially fixed, and unable to scale to unknown areas. By modelling the task as an image segmentation problem, an alternative approach using artificial intelligence to approximate the parameters of a physics-based model in 2D is demonstrated, enabling rapid predictions to be made in real-time.

Cite this Paper

BibTeX
@InProceedings{pmlr-v233-bryan-smith24a, title = {Towards {AI} for approximating hydrodynamic simulations as a 2D segmentation task}, author = {Bryan-Smith, Lydia and Dethlefs, Nina}, booktitle = {Proceedings of the 5th Northern Lights Deep Learning Conference ({NLDL})}, pages = {27--35}, year = {2024}, editor = {Lutchyn, Tetiana and Ramírez Rivera, Adín and Ricaud, Benjamin}, volume = {233}, series = {Proceedings of Machine Learning Research}, month = {09--11 Jan}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v233/bryan-smith24a/bryan-smith24a.pdf}, url = {https://proceedings.mlr.press/v233/bryan-smith24a.html}, abstract = {Traditional predictive simulations and remote sensing techniques for forecasting floods are based on fixed and spatially restricted physics-based models. These models are computationally expensive and can take many hours to run, resulting in predictions made based on outdated data. They are also spatially fixed, and unable to scale to unknown areas. By modelling the task as an image segmentation problem, an alternative approach using artificial intelligence to approximate the parameters of a physics-based model in 2D is demonstrated, enabling rapid predictions to be made in real-time.} }
Endnote
%0 Conference Paper %T Towards AI for approximating hydrodynamic simulations as a 2D segmentation task %A Lydia Bryan-Smith %A Nina Dethlefs %B Proceedings of the 5th Northern Lights Deep Learning Conference ({NLDL}) %C Proceedings of Machine Learning Research %D 2024 %E Tetiana Lutchyn %E Adín Ramírez Rivera %E Benjamin Ricaud %F pmlr-v233-bryan-smith24a %I PMLR %P 27--35 %U https://proceedings.mlr.press/v233/bryan-smith24a.html %V 233 %X Traditional predictive simulations and remote sensing techniques for forecasting floods are based on fixed and spatially restricted physics-based models. These models are computationally expensive and can take many hours to run, resulting in predictions made based on outdated data. They are also spatially fixed, and unable to scale to unknown areas. By modelling the task as an image segmentation problem, an alternative approach using artificial intelligence to approximate the parameters of a physics-based model in 2D is demonstrated, enabling rapid predictions to be made in real-time.
APA
Bryan-Smith, L. & Dethlefs, N.. (2024). Towards AI for approximating hydrodynamic simulations as a 2D segmentation task. Proceedings of the 5th Northern Lights Deep Learning Conference ({NLDL}), in Proceedings of Machine Learning Research 233:27-35 Available from https://proceedings.mlr.press/v233/bryan-smith24a.html.

Related Material