A Neural Ordinary Differential Equations Approach for 2D Flow Properties Analysis of Hydraulic Structures

Sebastian Eilermann, Lisa Lüddecke, Michael Hohmann, Bernd Zimmering, Mario Oertel, Oliver Niggemann
Proceedings of the 1st ECAI Workshop on "Machine Learning Meets Differential Equations: From Theory to Applications", PMLR 255:1-17, 2024.

Abstract

In hydraulic engineering, the design and optimization of weir structures play a critical role in the management of river systems. Weirs must efficiently manage high flow rates while maintaining low overfall heights and predictable flow behavior. Determining upstream flow depths and discharge coefficients requires costly and time-consuming physical experiments or numerical simulations. Neural Ordinary Differential Equations (NODE) can be capable of predicting these flow features and reducing the effort of generating experimental and numerical data. We propose a simulation based 2D dataset of flow properties upstream of weir structures called FlowProp. In a second step we use a NODE-based approach to analyze flow behavior as well as discharge coefficients for various geometries. In the evaluation process, it is evident that the aforementioned approach is effective in describing the headwater, overfall height and tailwater.The approach is further capable of predicting the flow behavior of geometries beyond the training data. Project page and code: https://github.com/SEilermann/FlowProp

Cite this Paper

BibTeX
@InProceedings{pmlr-v255-eilermann24a, title = {A Neural Ordinary Differential Equations Approach for 2D Flow Properties Analysis of Hydraulic Structures}, author = {Eilermann, Sebastian and L\"{u}ddecke, Lisa and Hohmann, Michael and Zimmering, Bernd and Oertel, Mario and Niggemann, Oliver}, booktitle = {Proceedings of the 1st ECAI Workshop on "Machine Learning Meets Differential Equations: From Theory to Applications"}, pages = {1--17}, year = {2024}, editor = {Coelho, Cecı́lia and Zimmering, Bernd and Costa, M. Fernanda P. and Ferrás, Luı́s L. and Niggemann, Oliver}, volume = {255}, series = {Proceedings of Machine Learning Research}, month = {20 Oct}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v255/main/assets/eilermann24a/eilermann24a.pdf}, url = {https://proceedings.mlr.press/v255/eilermann24a.html}, abstract = {In hydraulic engineering, the design and optimization of weir structures play a critical role in the management of river systems. Weirs must efficiently manage high flow rates while maintaining low overfall heights and predictable flow behavior. Determining upstream flow depths and discharge coefficients requires costly and time-consuming physical experiments or numerical simulations. Neural Ordinary Differential Equations (NODE) can be capable of predicting these flow features and reducing the effort of generating experimental and numerical data. We propose a simulation based 2D dataset of flow properties upstream of weir structures called FlowProp. In a second step we use a NODE-based approach to analyze flow behavior as well as discharge coefficients for various geometries. In the evaluation process, it is evident that the aforementioned approach is effective in describing the headwater, overfall height and tailwater.The approach is further capable of predicting the flow behavior of geometries beyond the training data. Project page and code: https://github.com/SEilermann/FlowProp} }
Endnote
%0 Conference Paper %T A Neural Ordinary Differential Equations Approach for 2D Flow Properties Analysis of Hydraulic Structures %A Sebastian Eilermann %A Lisa Lüddecke %A Michael Hohmann %A Bernd Zimmering %A Mario Oertel %A Oliver Niggemann %B Proceedings of the 1st ECAI Workshop on "Machine Learning Meets Differential Equations: From Theory to Applications" %C Proceedings of Machine Learning Research %D 2024 %E Cecı́lia Coelho %E Bernd Zimmering %E M. Fernanda P. Costa %E Luı́s L. Ferrás %E Oliver Niggemann %F pmlr-v255-eilermann24a %I PMLR %P 1--17 %U https://proceedings.mlr.press/v255/eilermann24a.html %V 255 %X In hydraulic engineering, the design and optimization of weir structures play a critical role in the management of river systems. Weirs must efficiently manage high flow rates while maintaining low overfall heights and predictable flow behavior. Determining upstream flow depths and discharge coefficients requires costly and time-consuming physical experiments or numerical simulations. Neural Ordinary Differential Equations (NODE) can be capable of predicting these flow features and reducing the effort of generating experimental and numerical data. We propose a simulation based 2D dataset of flow properties upstream of weir structures called FlowProp. In a second step we use a NODE-based approach to analyze flow behavior as well as discharge coefficients for various geometries. In the evaluation process, it is evident that the aforementioned approach is effective in describing the headwater, overfall height and tailwater.The approach is further capable of predicting the flow behavior of geometries beyond the training data. Project page and code: https://github.com/SEilermann/FlowProp
APA
Eilermann, S., Lüddecke, L., Hohmann, M., Zimmering, B., Oertel, M. & Niggemann, O.. (2024). A Neural Ordinary Differential Equations Approach for 2D Flow Properties Analysis of Hydraulic Structures. Proceedings of the 1st ECAI Workshop on "Machine Learning Meets Differential Equations: From Theory to Applications", in Proceedings of Machine Learning Research 255:1-17 Available from https://proceedings.mlr.press/v255/eilermann24a.html.

Related Material