{"id":29829217,"url":"https://github.com/mariamabidi/pinn-based-flow-prediction","last_synced_at":"2025-08-05T09:29:37.630Z","repository":{"id":284992353,"uuid":"956731270","full_name":"mariamabidi/PINN-Based-Flow-Prediction","owner":"mariamabidi","description":"This repository contains code and experiments for predicting 3D aerodynamic flow around car geometries using Physics-Informed Neural Networks (PINNs) and for analyzing flow features via autoencoder-based clustering.","archived":false,"fork":false,"pushed_at":"2025-07-02T18:08:34.000Z","size":44,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-07-29T08:50:56.593Z","etag":null,"topics":["computer-vision","machine-learning","neural-network","numpy","pytorch","pyvista","scikit-learn"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/mariamabidi.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-03-28T19:00:49.000Z","updated_at":"2025-07-03T01:57:16.000Z","dependencies_parsed_at":"2025-07-02T19:19:57.531Z","dependency_job_id":"08b5cd31-9a20-4f34-a2c0-7eab1883643a","html_url":"https://github.com/mariamabidi/PINN-Based-Flow-Prediction","commit_stats":null,"previous_names":["mariamabidi/airflow-anomaly-by-pinns","mariamabidi/pinn-based-flow-prediction"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/mariamabidi/PINN-Based-Flow-Prediction","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mariamabidi%2FPINN-Based-Flow-Prediction","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mariamabidi%2FPINN-Based-Flow-Prediction/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mariamabidi%2FPINN-Based-Flow-Prediction/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mariamabidi%2FPINN-Based-Flow-Prediction/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mariamabidi","download_url":"https://codeload.github.com/mariamabidi/PINN-Based-Flow-Prediction/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mariamabidi%2FPINN-Based-Flow-Prediction/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":268871612,"owners_count":24321327,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-08-05T02:00:12.334Z","response_time":2576,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["computer-vision","machine-learning","neural-network","numpy","pytorch","pyvista","scikit-learn"],"created_at":"2025-07-29T08:32:16.340Z","updated_at":"2025-08-05T09:29:37.604Z","avatar_url":"https://github.com/mariamabidi.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# PINN-Based Aerodynamic Flow Prediction and Clustering 🚗\n\nThis repository contains code and experiments for predicting 3D aerodynamic flow around car geometries using Physics-Informed Neural Networks (PINNs) and for analyzing flow features via autoencoder-based clustering.\n\n## Features\n\n- ✅ **Physics-Informed Neural Networks (PINNs)**  \n  Predict 3D velocity fields around car shapes without full CFD simulations.\n\n- ✅ **Streamline Visualization**  \n  Visualize predicted flow fields and identify regions of interest.\n\n- ✅ **Autoencoder for Feature Compression**  \n  Reduce high-dimensional CFD data to meaningful latent representations.\n\n- ✅ **KMeans Clustering in Latent Space**  \n  Detect and classify distinct aerodynamic zones like wakes, stagnation points, and freestream regions.\n\n- ✅ **3D Visualization of Clusters**  \n  Overlay cluster labels on mesh geometry for intuitive interpretation.\n\n## Use Cases\n\n- Aerodynamic analysis and design exploration  \n- Data-driven identification of critical flow regions  \n- Reducing reliance on computationally expensive CFD runs\n\n## Technologies\n\n- PyTorch  \n- PyVista  \n- scikit-learn  \n- NumPy\n\n## Authors\n\n- Mariam Abidi — PINN \u0026 Autoencoder \u0026 clustering implementation \n- Suhas Vittal — PINN implementation, streamline visualizations \n- Nishith Hingoo — Dataset sourcing, preprocessing pipelines\n\n---\n\n\u003e This project demonstrates the feasibility of physics-guided machine learning for aerodynamic analysis and provides a framework for faster, simulation-free flow predictions and feature detection.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmariamabidi%2Fpinn-based-flow-prediction","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmariamabidi%2Fpinn-based-flow-prediction","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmariamabidi%2Fpinn-based-flow-prediction/lists"}