-
University of California San Diego
- San Diego
- duncanwp.github.io
- @dwatsonparris
Highlights
- Pro
Stars
GCM Physics written in JAX
Slide decks, coding exercises, and quick references for learning the JAX AI Stack
🌪 Limited area LES-to-mesoscale atmosphere simulations based on Oceananigans
Benchmarking tools for applying AI/ML to data assimilation
Jatmos is a scalable simulator for atmospheric dynamics, written in JAX.
Open-source implementation of AlphaEvolve
Automatic calibration of vertical ocean physics in JAX
A generative foundation model for the kilometer-scale atmosphere
This repo contains material for the paper "FaIRGP: A Bayesian Energy Balance Model for Surface Temperatures Emulation"
Jupyter notebooks used on Cal-Adapt: Analytics Engine JupyterHub.
Hybrid ML + physics model of the Earth's atmosphere
Research Software for Neural Weather Prediction for Limited Area Modeling
A single column model of atmospheric boundary layer turbulence and clouds
A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery (EMNLP'24)
Re-implementation of GP-GOMEA that attempts to be simpler to understand and use than the original.
Earth-2 Model Intercomparison Project (MIP) is a python framework that enables climate researchers and scientists to inter-compare AI models for weather and climate.
Examples of CMIP6 cloud data analysis with Pangeo





