{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/eagle-large-scale-learning-of-turbulent-fluid","title":"Eagle: Large-Scale Learning of Turbulent Fluid Dynamics with Mesh Transformers","arxiv_id":"2302.10803","date":"2023-02-16","proceeding":null,"authors":["Steeven Janny","Aurélien Béneteau","Madiha Nadri","Julie Digne","Nicolas Thome","Christian Wolf"],"abstract":"Estimating fluid dynamics is classically done through the simulation and integration of numerical models solving the Navier-Stokes equations, which is computationally complex and time-consuming even on high-end hardware. This is a notoriously hard problem to solve, which has recently been addressed with machine learning, in particular graph neural networks (GNN) and variants trained and evaluated on datasets of static objects in static scenes with fixed geometry. We attempt to go beyond existing work in complexity and introduce a new model, method and benchmark. We propose EAGLE, a large-scale dataset of 1.1 million 2D meshes resulting from simulations of unsteady fluid dynamics caused by a moving flow source interacting with nonlinear scene structure, comprised of 600 different scenes of three different types. To perform future forecasting of pressure and velocity on the challenging EAGLE dataset, we introduce a new mesh transformer. It leverages node clustering, graph pooling and global attention to learn long-range dependencies between spatially distant data points without needing a large number of iterations, as existing GNN methods do. We show that our transformer outperforms state-of-the-art performance on, both, existing synthetic and real datasets and on EAGLE. Finally, we highlight that our approach learns to attend to airflow, integrating complex information in a single iteration.","url_abs":"https://arxiv.org/abs/2302.10803v2","url_pdf":"https://arxiv.org/pdf/2302.10803v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"eagle-large-scale-learning-of-turbulent-fluid","repo_url":"https://github.com/eagle-dataset/eaglemeshtransformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"node-clustering","task_name":"Node Clustering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2302.10803","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.10803"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/eagle-dataset/eaglemeshtransformer","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"listed":{"samples":6,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"3bd285fef2ae851d","entry":"assignement","repo":"eagle-dataset/eaglemeshtransformer","repo_kind":"listed","path":"clusterize_eagle.py","file_url":"https://github.com/eagle-dataset/eaglemeshtransformer/blob/HEAD/clusterize_eagle.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3bd285fef2ae851d"}},{"code_sha256_prefix":"a6d46aca78175ca3","entry":"collate","repo":"eagle-dataset/eaglemeshtransformer","repo_kind":"listed","path":"Dataloader/eagle.py","file_url":"https://github.com/eagle-dataset/eaglemeshtransformer/blob/HEAD/Dataloader/eagle.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a6d46aca78175ca3"}},{"code_sha256_prefix":"8a184163875acd8d","entry":"get_loss","repo":"eagle-dataset/eaglemeshtransformer","repo_kind":"listed","path":"train_graphvit.py","file_url":"https://github.com/eagle-dataset/eaglemeshtransformer/blob/HEAD/train_graphvit.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8a184163875acd8d"}},{"code_sha256_prefix":"f6c4fbc5ce9e9f08","entry":"kmeans","repo":"eagle-dataset/eaglemeshtransformer","repo_kind":"listed","path":"clusterize_eagle.py","file_url":"https://github.com/eagle-dataset/eaglemeshtransformer/blob/HEAD/clusterize_eagle.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f6c4fbc5ce9e9f08"}},{"code_sha256_prefix":"5d1377a4b829f059","entry":"swap","repo":"eagle-dataset/eaglemeshtransformer","repo_kind":"listed","path":"clusterize_eagle.py","file_url":"https://github.com/eagle-dataset/eaglemeshtransformer/blob/HEAD/clusterize_eagle.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5d1377a4b829f059"}},{"code_sha256_prefix":"933c00a058a8bb12","entry":"validate","repo":"eagle-dataset/eaglemeshtransformer","repo_kind":"listed","path":"train_graphvit.py","file_url":"https://github.com/eagle-dataset/eaglemeshtransformer/blob/HEAD/train_graphvit.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"933c00a058a8bb12"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}