Introduction of Deep Learning Development in Weather and Climate Studies

Name: Introduction of Deep Learning Development in Weather and Climate Studies
Start: 2024-08-28T13:00:41+1000
End: 2024-08-28T16:00:00+1000

Wed, 28 Aug 2024, 1pm - 4pm AEST

Online Event

National Computational Infrastructure

229 followers · Contact host

Event description

This is an online Zoom workshop on 28 Aug 2024. In this workshop we aim to help existing climate and weather researchers get hands-on experience of various SOTA (State-of-the-Art) deep-learning models in Weather and Climate Studies. This workshop aims to let you try some of our examples and then start training your own climate/weather deep-learning models for your own research.

To participate in the practice session in the second half of the workshop please check the prerequisites well in advance of the workshop.

Note: If you are not an existing NCI user, then you will need to create an account as per the instructions below.

Prerequisites

an NCI account ( create an account ) with a valid password
Membership in the following projects:

1. vp91 (join) [the training project which we will use for this workshop's compute and storage]
2. dk92 (join) [for environment modules and some examples]
3. wb00 (join) [for NCI-WeatherBench and ClimateNet datasets]
4. rt52 (join) [for ERA5 datasets]
5. ob53 (join) [for BARRA2 datasets]

Agenda

1:00-1:05	Dr. Ben Evans	Opening
1:05-1:20	Dr. Yue Sun	A gentle Introduction to the Interactive Workflow of Developing Deep Learning Models
1:20 - 2:05	Dr. Edison Guo Dr. Maruf Ahmed Dr. Rui Yang Dr. Yue Sun	Describing Deep Learning Models for Climate and Weather Studies Downscaling Models: CorrDiff on BARRA2 Prediction Models: CNN on NCI-WeatherBench, (ClimaX, Pangu-Weather, FourCastNet, GraphCast) on ERA5 Segmentation Models: CGNet on ClimateNet Physical Law Incorporation: SFNO on ERA5, ClimODE on NCI-WeatherBench
2:05 - 2:30	Dr. Rui Yang	Summary: Resources Available at NCI Datasets: ERA5, WeatherBench, BARRA2 and more Environments: Modules compatible with (ARE VDI/JupyterLab, PBS Jobs) x Examples Models and Training/Inference examples that are tested on Gadi and ready to use
2:20 - 2:30	Tea Break
2:30 - 3:30	Dr. Edison Guo Dr. Maruf Ahmed Dr. Rui Yang Dr. Yue Sun	Self-Directed Examples using ARE JupyterLab [All notebooks are available but recommended to focus on one of the first four during the training] CorrDiff: an Example of Generative Diffusion Model used for Downscaling task NCI WeatherBench Notebooks: a Benchmark Analysis of a CNN Model for Weather Prediction Evaluation of CGNet Model Using the ClimateNet Dataset: an Example of Weather Pattern Detection through Segmentation ClimODE: an Example of Neural Ordinary Differential Equation for Weather Prediction More Inference and Training Notebooks available at AI/ML for Climate & Weather
3:30 - 4:00		Discussions Feedback on the examples. Suggestions to further improvements. What more support do you need? What models/algorithms are you interested in / working on?