🕘 Meeting notes: Machine Learning WG
Jan 6, 2019
- Still working on Met disaggregation ML work
- Getting ready for AMS
- Working on continental scale streamflow prediction, finishing up data prep
- working on climate temperature emulator
- using xgboost
- NVIDIA Jlab extension for GPUs
Dec 2, 2019
- Noah: AGU next week, presentations on ML for climate modeling on Thursday
- Changes to data catalogs, turning off free egress (requester pays)
- Still working on ML environment in the cloud
- Tom: gcsfs now supports requester pays and fallback project auth.
- Sebastian: new data scientist at UW, a bit of ML background, going to work on GPUs on the cloud
- ML Cloud Environment
- Casper JupyterHub - https://jupyterhub.ucar.edu/dav-dev, GPUs on NCAR super computer in Jupyter
- ML for met disaggregation: Looking into best practices with packaging trained ML models in a python api.
- Tom pointed us to ONNX which looks promising.