Deep-learning sliding window attention with circular boundary conditions. No tokenization, no patchify-ing.

ClimaAtmos.jl is a library for building atmospheric circulation models that is designed from the outset to leverage data assimilation and machine learning tools. We welcome contributions!

CliMA model dycore

ClimaCoupler: bringing atmosphere, land, and ocean together

Repository that containts climate relevant ML datasets from the Climate Modeling Alliance.

A framework to define and output observables and statistics from CliMA simulations

Clima's Land Model

Clima's Land Model

🌎 Tools for realistic regional-to-global ocean simulations, and coupled ocean + sea-ice simulations based on Oceananigans and ClimaSeaIce. Basis for the ocean and sea-ice component of CliMA's Earth system model.

🧊 Coupled and stand-alone simulations of sea ice for Earth system modeling

A CPU- and GPU-friendly package for solving ordinary differential equations

Simulate quantum systems consisting of many spins interacting via dipole-dipole interaction

Predictive Uncertainty Quantification through Conformal Prediction for Machine Learning models trained in MLJ.

Various correlation functions for 1,2, and 3 dimensional arrays

Type for fast updating of correlation functions

Implementation of DDA and CEMD method in julia

Julia library for deep reinforcement learning

Fast `StatsBase.countmap` for small types on the GPU via CUDA.jl

CUDA programming in Julia.

Convenience wrappers to incomplete factorizations from CUSPARSE to be used for iterative solvers of sparse linear systems on the GPU

-

Explicit SIMD types for CUDA

-

GPU-accelerated algorithms for flux sampling in CUDA.jl

A Julia wrapper for cusolverRF

The fastest Tropical number matrix multiplication on GPU

CUDA extension for Yao.jl

GPU integrations for Dagger.jl

Unfolded convolutional learning for motif discovery

Julia wrapper for Devito functionality. Part of the COFII framework.

Extension functionality which uses Stan.jl, DynamicHMC.jl, and Turing.jl to estimate the parameters to differential equations and perform Bayesian probabilistic scientific machine learning

Tutorials for doing scientific machine learning (SciML) and high-performance differential equation solving with open source software.

Model coupled diffusion of major elements in garnet using natural data.

DINCAE (Data-Interpolating Convolutional Auto-Encoder) is a neural network to reconstruct missing data in satellite observations.

Discriminative Circuits from the Juice library

Abstraction layer for spanning factor graphs over various technologies

-

Implementation of robust dynamic Hamiltonian Monte Carlo methods (NUTS) in Julia.

Examples for Bayesian inference using DynamicHMC.jl and related packages.

DynamicHMC versions of StatisticalRethinking models