└── README.md /README.md: -------------------------------------------------------------------------------- 1 | ## Physics Based Deep Learning 2 | 3 | ### Surveys 4 | #### EN 5 | 1. Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems, *arXiv 2019*, [paper](https://arxiv.org/abs/1903.12394) 6 | 2. Three Ways to Solve Partial Differential Equations with Neural Networks -- A Review, *GAMM‐Mitteilungen 2021*, [paper](https://arxiv.org/pdf/2102.11802.pdf) 7 | 3. Physics-informed machine learning, *Nature Reviews Physics 2021*, [paper](https://www.nature.com/articles/s42254-021-00314-5) 8 | 4. DeepXDE: A deep learning library for solving differential equations, *SIAM Review 2021*, [paper](https://epubs.siam.org/doi/abs/10.1137/19M1274067), [code](https://github.com/lululxvi/deepxde) 9 | 5. Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's next, *arXiv 2022*, [paper](https://arxiv.org/abs/2201.05624) 10 | 6. State-of-the-Art Review of Design of Experiments for Physics-Informed Deep Learning, *arXiv 2022*, [paper](https://arxiv.org/abs/2202.06416) 11 | 7. Physics-Informed Graph Learning: A Survey, *arXiv 2022*, [paper](https://arxiv.org/abs/2202.10679) 12 | 8. When Physics Meets Machine Learning: A Survey of Physics-Informed Machine Learning, *arXiv 2022*, [paper](https://arxiv.org/abs/2203.16797) 13 | #### ZH 14 | 1. 基于物理信息的神经网络：最新进展与展望, *计算机科学 2022*, [论文](https://www.jsjkx.com/CN/Y2022/V49/I4/254) 15 | 2. 基于神经网络的偏微分方程求解方法研究综述, *力学学报* 2022, [论文](https://pubs.cstam.org.cn/article/doi/10.6052/0459-1879-21-617) 16 | 17 | 18 | ### Tutorials 19 | 20 | 1. [国家天元数学东南中心 短期课程] **《深度学习与科学计算的结合：基础与提高》** [课程介绍](http://tianyuan.xmu.edu.cn/cn/MiniCourses/637.html), [视频](https://www.bilibili.com/video/BV1B3411j7of/) 21 | 22 | 2. [MIT Course] **Parallel Computing and Scientific Machine Learning (SciML): Methods and Applications**. [Homepage](https://book.sciml.ai/) 23 | 24 | ### Applied Papers 25 | 26 | #### Traffic Related 27 | 28 | 1. Enhancing Urban Flow Maps via Neural ODEs, *IJCAI 2020*, [paper](https://par.nsf.gov/biblio/10211118) 29 | 2. Urban flow prediction with spatial–temporal neural ODEs, *Transportation Research Part C: Emerging Technologies 2021*, [paper](https://www.sciencedirect.com/science/article/pii/S0968090X2030810X?casa_token=HLbQCcOzBfIAAAAA:LkxJZcIiEQtVEc0NFrer-FOQk_LZJgldp_j6RxJAaAX9hkcjH1APvRDvfshtRY40j2JkswMBoQ) 30 | 3. Spatial-temporal graph ode networks for traffic flow forecasting, *KDD 2021*, [paper](https://dl.acm.org/doi/abs/10.1145/3447548.3467430?casa_token=Iwkpbx-jan4AAAAA:WA_NcQSiHp7Pz5WbSduQvqRLfmeXoE-BhvSo_nrjWS5AbYyNZNFTYYs0bwFD68Uyd_MnwOTwq2zQOQ) 31 | 4. Physics-informed Learning for Identification and State Reconstruction of Traffic Density, *arXiv 2021*, [paper](https://arxiv.org/abs/2103.13852) 32 | 5. STR-GODEs: Spatial-Temporal-Ridership Graph ODEs for Metro Ridership Prediction, *arXiv 2021*, [paper](https://arxiv.org/abs/2107.04980) 33 | 6. A Physics-Informed Deep Learning Paradigm for Car-following Models, *Transportation Research Part C: Emerging Technologies 2021*, [paper](https://www.sciencedirect.com/science/article/pii/S0968090X21002539?casa_token=HOt_zIw9cksAAAAA:NlezNM9_93WEhfR7dDIa-U23wM0er4OimCf_jrc-wkJ5GX8nf8MKHHMYoMW8u6tlmHRvgGz-ZA) 34 | 7. Physics-informed deep learning for traffic state estimation: A hybrid paradigm informed by second-order traffic models, *AAAI 2021*, [paper](https://www.aaai.org/AAAI21Papers/AAAI-3617.ShiR.pdf) 35 | 8. A Physics-Informed Deep Learning Paradigm for Traffic State and Fundamental Diagram Estimation, *IEEE Transactions on Intelligent Transportation Systems 2021*, [paper](https://ieeexplore.ieee.org/abstract/document/9531557) 36 | 9. Boundary Control for Multi-Directional Traffic on Urban Networks, IEEE Conference on Decision and Control 2021, [paper](https://hal.archives-ouvertes.fr/hal-03182546/) 37 | 10. Incorporating Kinematic Wave Theory Into a Deep Learning Method for High-Resolution Traffic Speed Estimation, *IEEE Transactions on Intelligent Transportation Systems 2022*, [paper](https://ieeexplore.ieee.org/abstract/document/9740401) 38 | 11. STDEN: Towards Physics-guided Neural Networks for Traffic Flow Prediction, *AAAI 2022*, [paper](https://www.aaai.org/AAAI22Papers/AAAI-211.JiJ.pdf) 39 | 12. Multi-directional continuous traffic model for large-scale urban networks, *Transportation Research Part B: Methodological 2022*, [paper](https://www.sciencedirect.com/science/article/pii/S0191261522000303?casa_token=oqpofNHOmjsAAAAA:qpQ1A15Y2axDrxV9zMraZ1wS_8_NMYs6GjooQCWyFl-8Z7siWJ92OMiQ0N6xMXh5VKsSXdBfsw) 40 | 13. Fitting Spatial-Temporal Data via a Physics Regularized Multi-Output Grid Gaussian Process: Case Studies of a Bike-Sharing System, *IEEE Transactions on Intelligent Transportation Systems 2022*, [paper](https://ieeexplore.ieee.org/abstract/document/9774971) 41 | 42 | #### Time Series Related 43 | 44 | 1. Latent Ordinary Differential Equations for Irregularly-Sampled Time Series, *NIPS 2019*, [paper](https://proceedings.neurips.cc/paper/2019/hash/42a6845a557bef704ad8ac9cb4461d43-Abstract.html), [code](https://github.com/YuliaRubanova/latent_ode) 45 | 2. Neural Controlled Differential Equations for Irregular Time Series, *NIPS 2020*, [paper](https://arxiv.org/abs/2005.08926), [code](https://github.com/patrick-kidger/NeuralCDE) 46 | 3. Attentive Neural Controlled Differential Equations for Time-series Classification and Forecasting, *IEEE International Conference on Data Mining 2021*, [paper](https://ieeexplore.ieee.org/abstract/document/9679144) 47 | 4. Spatiotemporal Representation Learning on Time Series with Dynamic Graph ODEs, *OpenReview 2021*, [paper](https://openreview.net/forum?id=Jh9VxCkrEZn) 48 | 5. Explainable Tensorized Neural Ordinary Differential Equations for Arbitrary-step Time Series Prediction, *IEEE Transactions on Knowledge and Data Engineering 2022*, [paper](https://ieeexplore.ieee.org/abstract/document/9757812) 49 | 50 | #### Graph Related 51 | 52 | 1. Physics-aware Difference Graph Networks for Sparsely-Observed Dynamics, ICLR 2020, [paper](https://openreview.net/forum?id=r1gelyrtwH), [code](https://github.com/USC-Melady/ICLR2020-PADGN?utm_source=catalyzex.com) 53 | 2. Learning continuous-time PDEs from sparse data with graph neural networks, *ICLR 2021*, [paper](https://arxiv.org/abs/2006.08956), [code](https://github.com/yakovlev31/graphpdes_experiments) 54 | 3. GRAND: Graph Neural Diffusion, *ICML 2021*, [paper](https://arxiv.org/abs/2106.10934) 55 | 4. Continuous-Depth Neural Models for Dynamic Graph Prediction, arXiv 2021, [paper](https://arxiv.org/abs/2106.11581) 56 | 5. physics-informed graph neural Galerkin networks: A unified framework for solving PDE-governed forward and inverse problems, *arXiv 2021*, [paper](https://arxiv.org/abs/2107.12146) 57 | 6. Learning time-dependent PDE solver using Message Passing Graph Neural Networks, *arXiv 2022*, [paper](https://arxiv.org/abs/2204.07651) 58 | 7. Scalable algorithms for physics-informed neural and graph networks, *arXiv 2022*, [paper](https://arxiv.org/abs/2205.08332) 59 | 60 | ### Books & Thesis 61 | 62 | 1. Physics-based Deep Learning, 2021. [single-PDF version](https://arxiv.org/abs/2109.05237), [online readable version](https://physicsbaseddeeplearning.org/intro.html) 63 | 2. Patrick Kidger, On Neural Differential Equations, 2022. [thesis](https://arxiv.org/pdf/2202.02435.pdf) 64 | 3. Peter J. Olver, Introduction to Partial Differential Equations, 2014. [book](https://www.usb.ac.ir/FileStaff/3223_2019-10-28-13-12-55.pdf) 65 | --------------------------------------------------------------------------------