/Physics-Based-Deep-Learning

Physics Based Deep Learning

Surveys

EN

  1. Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems, arXiv 2019, paper
  2. Three Ways to Solve Partial Differential Equations with Neural Networks -- A Review, GAMM‐Mitteilungen 2021, paper
  3. Physics-informed machine learning, Nature Reviews Physics 2021, paper
  4. DeepXDE: A deep learning library for solving differential equations, SIAM Review 2021, paper, code
  5. Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's next, arXiv 2022, paper
  6. State-of-the-Art Review of Design of Experiments for Physics-Informed Deep Learning, arXiv 2022, paper
  7. Physics-Informed Graph Learning: A Survey, arXiv 2022, paper
  8. When Physics Meets Machine Learning: A Survey of Physics-Informed Machine Learning, arXiv 2022, paper

ZH

  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
  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

Tutorials

  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, 视频

  2. [MIT Course] Parallel Computing and Scientific Machine Learning (SciML): Methods and Applications. Homepage

Applied Papers

Traffic Related

  1. Enhancing Urban Flow Maps via Neural ODEs, IJCAI 2020, paper
  2. Urban flow prediction with spatial–temporal neural ODEs, Transportation Research Part C: Emerging Technologies 2021, paper
  3. Spatial-temporal graph ode networks for traffic flow forecasting, KDD 2021, paper
  4. Physics-informed Learning for Identification and State Reconstruction of Traffic Density, arXiv 2021, paper
  5. STR-GODEs: Spatial-Temporal-Ridership Graph ODEs for Metro Ridership Prediction, arXiv 2021, paper
  6. A Physics-Informed Deep Learning Paradigm for Car-following Models, Transportation Research Part C: Emerging Technologies 2021, paper
  7. Physics-informed deep learning for traffic state estimation: A hybrid paradigm informed by second-order traffic models, AAAI 2021, paper
  8. A Physics-Informed Deep Learning Paradigm for Traffic State and Fundamental Diagram Estimation, IEEE Transactions on Intelligent Transportation Systems 2021, paper
  9. Boundary Control for Multi-Directional Traffic on Urban Networks, IEEE Conference on Decision and Control 2021, paper
  10. Incorporating Kinematic Wave Theory Into a Deep Learning Method for High-Resolution Traffic Speed Estimation, IEEE Transactions on Intelligent Transportation Systems 2022, paper
  11. STDEN: Towards Physics-guided Neural Networks for Traffic Flow Prediction, AAAI 2022, paper
  12. Multi-directional continuous traffic model for large-scale urban networks, Transportation Research Part B: Methodological 2022, paper
  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

Time Series Related

  1. Latent Ordinary Differential Equations for Irregularly-Sampled Time Series, NIPS 2019, paper, code
  2. Neural Controlled Differential Equations for Irregular Time Series, NIPS 2020, paper, code
  3. Attentive Neural Controlled Differential Equations for Time-series Classification and Forecasting, IEEE International Conference on Data Mining 2021, paper
  4. Spatiotemporal Representation Learning on Time Series with Dynamic Graph ODEs, OpenReview 2021, paper
  5. Explainable Tensorized Neural Ordinary Differential Equations for Arbitrary-step Time Series Prediction, IEEE Transactions on Knowledge and Data Engineering 2022, paper

Graph Related

  1. Physics-aware Difference Graph Networks for Sparsely-Observed Dynamics, ICLR 2020, paper, code
  2. Learning continuous-time PDEs from sparse data with graph neural networks, ICLR 2021, paper, code
  3. GRAND: Graph Neural Diffusion, ICML 2021, paper
  4. Continuous-Depth Neural Models for Dynamic Graph Prediction, arXiv 2021, paper
  5. physics-informed graph neural Galerkin networks: A unified framework for solving PDE-governed forward and inverse problems, arXiv 2021, paper
  6. Learning time-dependent PDE solver using Message Passing Graph Neural Networks, arXiv 2022, paper
  7. Scalable algorithms for physics-informed neural and graph networks, arXiv 2022, paper

Books & Thesis

  1. Physics-based Deep Learning, 2021. single-PDF version, online readable version
  2. Patrick Kidger, On Neural Differential Equations, 2022. thesis
  3. Peter J. Olver, Introduction to Partial Differential Equations, 2014. book