All organizations · GSoC 2026 · Science and medicine, Artificial Intelligence

MLLAM

Research software for AI weather forecasting

MLLAM is a collaborative community dedicated to advancing machine learning applications in weather forecasting, specifically for Limited Area Modeling (LAM). The organization hosts several open-source key repositories, including neural-lam, which focuses on neural weather prediction using graph-based models. Members are from various research institutions and national weather services committed to improve weather forecasting at regional, high-resolution scale.

python
numpy
pytorch
xarray
Zarr

machine learning
ai
deep learning
earth science
Weather Forecasting

Project ideas

4 ideas on its 2026 ideas page; of the 3 that state a difficulty: 3 medium. Sizes: 2 medium, 2 large. 4 mentors named.

Flexible graph construction large medium
Automatic generation of documentation from source code files medium medium
Generalizing to probabilistic forecasting models large
Global weather forecasting medium medium

Read the ideas page. Ideas are for scope reference; never copy one into a proposal.

History

In GSoC since 2026, 1 year. Projects per year: '26: 2.

On GitHub

4 repositories pushed to in the last year. Main languages: Python (3), JavaScript (1).

Links and channels

Website: https://github.com/mllam
Ideas page: https://github.com/mllam/neural-lam/wiki/GSoC-ideas
Contributor guide: https://github.com/mllam/neural-lam/wiki/GSoC-ideas
Source code: https://github.com/mllam/neural-lam
Chat: https://kutt.to/mllam

go deeper in your terminal

git-into-gsoc org "MLLAM" --shortlist
git-into-gsoc repos "MLLAM"
git-into-gsoc issues --org "MLLAM"

or ask your assistant:
"Which MLLAM repositories merge
newcomers' pull requests, and which beginner
issues are still free?"

Those commands read live data: which repositories merge outside pull requests, and which beginner issues nobody has claimed. Install in two minutes.