NeurIPS 2024 ML4CFD Competition: Results and Retrospective Analysis
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916787806797824 |
|---|---|
| author | Yagoubi, Mouadh Danan, David Leyli-Abadi, Milad Mazari, Ahmed Brunet, Jean-Patrick Kabalan, Abbas Casenave, Fabien Ma, Yuxin Catalani, Giovanni Fesquet, Jean Helwig, Jacob Zhang, Xuan Yu, Haiyang Bertrand, Xavier Tost, Frederic Baurheim, Michael Morlier, Joseph Ji, Shuiwang |
| author_facet | Yagoubi, Mouadh Danan, David Leyli-Abadi, Milad Mazari, Ahmed Brunet, Jean-Patrick Kabalan, Abbas Casenave, Fabien Ma, Yuxin Catalani, Giovanni Fesquet, Jean Helwig, Jacob Zhang, Xuan Yu, Haiyang Bertrand, Xavier Tost, Frederic Baurheim, Michael Morlier, Joseph Ji, Shuiwang |
| contents | The integration of machine learning (ML) into the physical sciences is reshaping computational paradigms, offering the potential to accelerate demanding simulations such as computational fluid dynamics (CFD). Yet, persistent challenges in accuracy, generalization, and physical consistency hinder the practical deployment of ML models in scientific domains. To address these limitations and systematically benchmark progress, we organized the ML4CFD competition, centered on surrogate modeling for aerodynamic simulations over two-dimensional airfoils. The competition attracted over 240 teams, who were provided with a curated dataset generated via OpenFOAM and evaluated through a multi-criteria framework encompassing predictive accuracy, physical fidelity, computational efficiency, and out-of-distribution generalization. This retrospective analysis reviews the competition outcomes, highlighting several approaches that outperformed baselines under our global evaluation score. Notably, the top entry exceeded the performance of the original OpenFOAM solver on aggregate metrics, illustrating the promise of ML-based surrogates to outperform traditional solvers under tailored criteria. Drawing from these results, we analyze the key design principles of top submissions, assess the robustness of our evaluation framework, and offer guidance for future scientific ML challenges. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_08516 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | NeurIPS 2024 ML4CFD Competition: Results and Retrospective Analysis Yagoubi, Mouadh Danan, David Leyli-Abadi, Milad Mazari, Ahmed Brunet, Jean-Patrick Kabalan, Abbas Casenave, Fabien Ma, Yuxin Catalani, Giovanni Fesquet, Jean Helwig, Jacob Zhang, Xuan Yu, Haiyang Bertrand, Xavier Tost, Frederic Baurheim, Michael Morlier, Joseph Ji, Shuiwang Machine Learning The integration of machine learning (ML) into the physical sciences is reshaping computational paradigms, offering the potential to accelerate demanding simulations such as computational fluid dynamics (CFD). Yet, persistent challenges in accuracy, generalization, and physical consistency hinder the practical deployment of ML models in scientific domains. To address these limitations and systematically benchmark progress, we organized the ML4CFD competition, centered on surrogate modeling for aerodynamic simulations over two-dimensional airfoils. The competition attracted over 240 teams, who were provided with a curated dataset generated via OpenFOAM and evaluated through a multi-criteria framework encompassing predictive accuracy, physical fidelity, computational efficiency, and out-of-distribution generalization. This retrospective analysis reviews the competition outcomes, highlighting several approaches that outperformed baselines under our global evaluation score. Notably, the top entry exceeded the performance of the original OpenFOAM solver on aggregate metrics, illustrating the promise of ML-based surrogates to outperform traditional solvers under tailored criteria. Drawing from these results, we analyze the key design principles of top submissions, assess the robustness of our evaluation framework, and offer guidance for future scientific ML challenges. |
| title | NeurIPS 2024 ML4CFD Competition: Results and Retrospective Analysis |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2506.08516 |