A lightweight framework for building Physics-Informed Neural Networks (PINNs) with symbolic PDE definitions using SymPy and automatic differentiation in PyTorch. It provides flexible neural archite…

This page reviews and organizes emerging hybrid Earth System Models (ESMs), which combine machine learning and physics-based components.

Spatial Representations for Artificial Intelligence - a Python library toolkit for geospatial machine learning focused on creating embeddings for downstream tasks

Tiger-HLM Runoff Routing module

Implementation of the Aurora model for Earth system forecasting

Benchmarking of weather forecasts based on station observations

Tiger HLM Runoff is component of the TigerHLM hydrologic model which generates runoff using GPU acceleration.

Demo for running ECMWF AIFS in the cloud

GeeFlow - generate and process large-scale geospatial datasets with Google Earth Engine.

Make river relative elevation models (REM) and REM visualizations from an input digital elevation model (DEM).

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

An open large-scale dataset for training high-resolution physics emulators in hybrid multi-scale climate simulators.

Example Notebooks for HyRiver software stack

A List of freely available datasets on climate change

Pytorch bindings for Fortran

A Python package for tackling diverse environmental prediction tasks with NPs.

Learning in infinite dimension with neural operators.

Using graph network to solve PDEs

Geometry-Aware Fourier Neural Operator (Geo-FNO)

Solve forward and inverse problems related to partial differential equations using finite basis physics-informed neural networks (FBPINNs)

Copilot like code suggestions using RAG and LLM

Deep learning models for global weather prediction on a cubed sphere

Course material for CSE 6740 -- Computational Data Analysis (Graduate-level introduction to machine learning)

Deep Learning Weather Prediction

A package for the sparse identification of nonlinear dynamical systems from data