Physics-Informed Neural networks for Advanced modeling

TensorFlow 2.0 implementation of Maziar Raissi's Physics Informed Neural Networks (PINNs).

Physics-constrained auto-regressive convolutional neural networks for dynamical PDEs

Dimensionless learning

Code for Rice et al. 2020 "Analyzing Koopman approaches to physics-informed machine learning for long-term sea-surface temperature forceasting"

SciML-Bench Benchmarks for Scientific Machine Learning (SciML), Physics-Informed Machine Learning (PIML), and Scientific AI Performance

TensorFlow 2.0 implementation of Yibo Yang, Paris Perdikaris’s adversarial Uncertainty Quantification in Physics Informed Neural Networks (UQPINNs).

Physics-informed information field theory - Solve inverse problems with built-in model form uncertainty estimation

Going through the tutorial on Physics-informed Neural Networks: https://github.com/madagra/basic-pinn

GIC Forecasting & Analysis — A data-driven framework for modeling Geomagnetically Induced Currents using solar wind data, SuperMAG observations, and advanced ML techniques. Integrates domain physics, feature engineering, and imputation strategies to tackle real-world space weather challenges.

Ununennium (Element 119, the next alkali metal) represents the cutting edge of satellite imagery machine learning. This library provides a unified, GPU-first framework for end-to-end Earth observation workflows, from cloud-native data access through model training to deployment.

Code for paper "Physics-based machine learning for modeling IP3 induced calcium oscillations" - DOI: 10.5281/zenodo.4839127

Spatiotemporal Gaussian process modeling for environmental data: non-stationary PDE prior, deep kernels, multi-fidelity fusion, and A-optimal sampling.非稳态 PDE + 核深度学习 + 多保真 Co-Kriging + 主动采样的物理约束克里金方法，用于复杂时空环境建模与预测

Physics-informed ensemble for 12-h city-region temperature forecasts. Advection–diffusion prior + ConvLSTM + RAFL + edRVFL-SC for extreme-event warnings.

Comprehensive JAX implementation of neural networks and scientific computing. Features distributed training, physics-informed networks, custom autodiff, and advanced optimization. Production-ready code with numerical stability, multi-device parallelism, and research-grade implementations.

UQ Group (Director: Hadi Meidani)

RVAV: a physics-informed PyTorch optimizer for energy-stable, high-LR training—with a simple closure API, tests, CI, and quickstart.

Physics informed graph neural network for snow water equivalent forecasting

Short review of Physics-Informed ML/DL

本项目复现了论文《Blind Unmixing Using Dispersion Model-Based Autoencoder to Address Spectral Variability》中的DMTS-Net模型，并在Jasper Ridge高光谱数据集上进行验证。