Machine Learning for Climate and Weather Working Group Announce

Machine Learning for Climate and Weather Working Group
, , ,
1

This topic will be used for announcements to the Machine Learning for Climate and Weather Working Group by the leadership team.

For example, we will announce meetings, workshops and events through this topic. There will not be an email list.

You need to watch this topic to receive new announcements via email notifications

To avoid individuals accidentally spamming the whole group, this topic is closed and only the leadership team will be able to post replies. If you have questions, check if it has already been asked in the Machine Learning for Climate and Weather Category, and if not either open a topic on the forum or reply to the Working Group description topic.

Useful links/information:

  • Monthly Meetings:
    Held first Friday of the month at 2pm.

    Zoom details: Launch Meeting - Zoom
    Zoom Meeting ID: 83187307759 (password: 123456)

    Meeting schedule: ML for Weather and Climate Meeting Talks - Google Sheets , NOTE: As the link to this document is publicly available, access has been restricted to “comment only”. If you wish to edit it please add a comment and it will be periodically edited, or contact one of the co-chairs.

1 Like
3

Hi Micael,
will you post a link for the ML monthly meetings? Will there be one on the 4th October?
Best,
Terry

4

Hi Terry,

Yes, there will be a meeting on the 4th and we will soon share a link. Stay tuned!

Micael

1 Like
5

Hi everyone,

The first monthly meeting of the new Machine Learning for Climate and Weather Working Group will take place next Friday, 4th October. Time and zoom details can be found at the top, in the first post.

Here is the agenda:

See you next week!

3 Likes
6

Hi everyone,

The next monthly meeting of the Machine Learning for Climate and Weather Working Group will take place Friday, 1 November. Time and zoom details can be found at the top, in the first post.

Here is the agenda:

Facilitator: Sanaa Hobeichi
Co-chairs: Vassili, Tennessee, Micael, Sanaa

  • Acknowledgement of country
  • Updates from ACCESS-NRI and a tour of ACCESS-Hive forum
  • New member introductions
  • Updates from the Chairs:
    o Join the ML WG if you haven’t already
    o AMOS abstracts submission: Session 8.6 Advancing Weather and Climate Research with Machine Learning. Who do we want to invite as a keynote speaker for the session?
    Abstract submission portal, Deadline: 30 Nov 2024
  • Updates from the Community
  • ML talk by community member David Fuchs (Senior Scientist at the NSW Department of Planning and Environment)
    • Title: TorchClim v1.0: A deep-learning plugin for climate model physics: Initial results and future developments
    • Q&A
  • Share the minutes from the previous community meeting. Add new items, and discuss priorities, and actions.
  • Tennessee will present the Edit tool briefly

See you next week!

1 Like
7

Hi everyone,

The next monthly meeting of the Machine Learning for Climate and Weather Working Group will take place Friday, 6 December. Time and zoom details can be found at the top, in the first post.

Here is the agenda:

Facilitator: Ryan Holmes
Co-chairs: Ryan, Tennessee, Micael, Sanaa

  • Acknowledgement of country
  • Updates from ACCESS-NRI
  • New member introductions
  • Updates from the Chairs:
    • AMOS Session 8.6 Advancing Weather and Climate Research with Machine Learning - Keynote speaker: Terry O’Kane (CSIRO)
  • Updates from the Community
    • From a community member: Can allocations of GPU through the WG be extended beyond the current 48-hours limit?
  • ML talks:
    • Nicholas Loveday from the Bureau of Meteorology will give a presentation on verification of AI models:
      Understanding the performance of the latest data-driven (pure AI) models is a pressing scientific question. While much of the evaluation in the past has focused on point-based verification, spatial verification techniques have received less attention. Additionally, there has been a lack of evaluation using threshold-weighted scoring rules to assess how well these models predict extremes. In this talk, we demonstrate how combining threshold-weighted scoring rules with spatial verification techniques allows us to compare how well the HRRR and GraphCast models in predict extreme events. This verification approach has several advantages; a) it does not suffer from the double penalty issue within a specified radius, b) it can emphasize the performance of predicting extremes, c) it discourages hedging and does not reward biased forecasts, d) it can account for climatological differences when calculating the mean score across the domain, and e) it can be used to compare models with different grid resolutions. The verification approach demonstrated has the potential to be a useful tool in the future to complement other evaluation methods in a testing and evaluation framework.
    • Tennessee will present 'PyEarthTools" (was ‘Edit’), a tool developed by the BoM to facilitate ML/AI programming. This will be followed by community feedback on interest in making the tool available, with the potential for ACCESS-NRI to host it.
  • Share the minutes from the previous community meeting. Add new items, and discuss priorities, and actions.
  • Papers of the month.

See you in a couple of weeks!

2 Likes
8

Hi everyone,

Just a reminder that we have our monthly meeting on this afternoon from 2-3pm. We will be hearing from Nicholas Loveday on verification of AI NWP models, as well as a few other agenda items. See above for the agenda and zoom details.

See you all this afternoon.

Ryan

10

Hi everyone,

The next monthly meeting of the Machine Learning for Climate and Weather Working Group will take place Friday, 7 February. Time and zoom details can be found at the top, in the first post.

Here is the agenda:

Facilitator: Vassili Kitsios
Co-chairs: Ryan Holmes, Tennessee Leeuwenburg, Micael Oliveira, Sanaa Hobeichi

  • Acknowledgement of country
  • Updates from ACCESS-NRI
    • Introduction of Edward Yang, new ACCESS-NRI member
    • NCRIS proposal
    • Future of analysis3 conda environments
    • Status of PyEarthTools: an end-to-end toolkit for ML in earth system science (introduced and presented by Tennessee in Nov and Dec 2024)
  • Updates from the Chairs:
    • 2025 ACCESS Community Workshop will be held in Melbourne in the week of 8-12 September, what would you like to see?
  • Updates from the community & new community member introductions
  • ML talk by Michael Groom (CSIRO):
    This paper builds on previous work in applying the entropy-optimal Sparse Probabilistic Approximation (eSPA) machine learning algorithm to the task of classifying the phase of ENSO, as determined by the Niño3.4 index (Groom et al., Artif. Intell. Earth Syst., 2024). In this study, only observations and reanalyses from the satellite era are employed when training and validating the entropic learning models, and a full set of hindcasts are performed over the period from 2012 to 2022 (with a maximum lead time of 24 months) in order to determine out-of-sample skill. The features used for prediction are the leading principal components from a delay-embedded EOF analysis of global sea surface temperature, the vertical derivative of temperature at the equator and the zonal and meridional wind stresses in the tropical Pacific. Despite the limited number of data instances available for training (ranging from 350 monthly averages for the earliest hindcast to 520 as of December 2024), eSPA is shown to avoid overfitting in this small data regime and produces categorical forecasts with comparable skill to the combined (model-based) probabilistic forecasts produced from the International Research Institute for Climate and Society (IRI) ENSO prediction plume. At lead times longer than those available from the IRI plume, eSPA maintains skill out to 15 months in terms of the ranked probability skill score and 24 months in terms of the area under the Reciever Operating Characteristic curve, all at a small fraction of the computational cost of running a dynamical ensemble prediction system. Furthermore, eSPA is shown to successfully forecast the 2015/16 and 2018/19 El Niño events at 24 months lead time, the 2016/17, 2018/19 and 2020/21 La Niña events at 24 months lead time and the 2021/22 and 2022/23 La Niña events at 14 and 12 months lead time.
  • Discussion :
    • Plans for using project nm47 on NCI
    • How this WG can use allocated NCI/NRI resources?
      • Development of an “ML cookbook”, filled with example Jupyter notebooks for sets of ML based problems, based on PyEarthTools. What initial examples would you like to see?
      • Compute resources: Should benefit the entire community. However, this is a bit challenging for this group as it’s not clear whether there are key applications interesting to a wide range of the community (e.g. like COSIMA reference datasets).
      • Appropriate for ECRS/new students to get started if they have trouble getting resources through other means.
      • Requirement that the project result in a contribution to the “ML cookbook”.
  • Events:
    • EXCLAIM Symposium “Is AI the Future of Weather and Climate Modeling?”, ETH Zurich, Switzerland, June 2-4, 2025. The sessions will be live-streamed.

See you in next week!

1 Like
11

Hi everyone,

The next monthly meeting of the Machine Learning for Climate and Weather Working Group will take place Friday, 7 March. Time and zoom details can be found at the top, in the first post.

Here is the agenda:

Facilitator: Tennessee Leeuwenburg
Co-chairs: Vassili Kitsios, Sanaa Hobeichi, Ryan Holmes, Micael Oliveira,

  • Acknowledgement of country
  • Updates from ACCESS-NRI
    • Status of PyEarthTools: an end-to-end toolkit for ML in earth system science (introduced and presented by Tennessee in Nov and Dec 2024)
  • Updates from the Chairs:
    • 2025 ACCESS Community Workshop will be held in Melbourne in the week of 8-12 September, what would you like to see?
  • Updates from the community & new community member introductions
  • Talk by Clare Richards (ACCESS-NRI) about ACCESS-NRI support for reference datasets:
    Improving access to data that is fit-for-purpose, trustworthy and (re)usable is a priority. ACCESS-NRI is funded by the Australian Government’s National Collaborative Research Infrastructure Strategy (NCRIS) to provide storage resources at the National Computational Infrastructure (NCI). These resources are distributed to the ACCESS community through a merit-based process, which includes support for reference datasets. Reference datasets are those that are for sharing and reuse among the community and require active data management to ensure trust and reliability in the data.
    This presentation will explain the types of datasets that are supported by ACCESS-NRI, how to make a request and the approach that we will take to ensure collections remain of value to the community.
  • Discussion :
    • Development of an “ML cookbook”, filled with example Jupyter notebooks for sets of ML based problems, based on PyEarthTools. What initial examples would you like to see?
    • Compute resources:
      • Should benefit the entire community. However, this is a bit challenging for this group as it’s not clear whether there are key applications interesting to a wide range of the community (e.g. like COSIMA reference datasets).
      • Appropriate for ECRS/new students to get started if they have trouble getting resources through other means.
      • Requirement that the project result in a contribution to the “ML cookbook”.

See you in next week!

12

ACCESS-NRI Training Day 2025
ACCESS-NRI Training Day 20251920×576 64.5 KB

Hi everyone!

To gather suggestions and ideas for potential training topics for the 2025 ACCESS-NRI Community Workshop (in Melbourne from 8-12 Sept.), the ACCESS-NRI training team has created a poll :triangular_flag_on_post: on the ACCESS-Hive Forum.

:woman_raising_hand: We would love to hear feedback from all community members about the training sessions they’d like to see this year!

There are 3 main ways to add or vote on the suggestions (similar to StackOverflow):
1. :check_box_with_check: Choose up to 10 options from the existing options on the poll.
2. :writing_hand: Add a new suggestion by hitting the Screenshot 2025-03-05 at 10.37.58 button.
3. ↑ You can also upvote any suggestion found in the replies.

We are looking forward to meeting you at the working group meetings as well :waving_hand: .

Please note that the poll will close on 2025-03-30T13:00:00Z.

Thanks heaps!
Jasmeen Kaur
ACCESS-NRI User Training Team

13

Hi everyone,

The next monthly meeting of the Machine Learning for Climate and Weather Working Group will take place Friday, 4 April. Time and zoom details can be found at the top, in the first post.

Here is the agenda:

Facilitator: Sanaa Hobeichi
Co-chairs: Vassili Kitsios, Ryan Holmes, Tennessee Leeuwenburg, Micael Oliveira, Yue Sun

  • Acknowledgement of country
  • Updates from ACCESS-NRI
    • Yue Sun is now the NCI liaison of this WG
  • Updates from the Chairs
    • PyEarthTools: an end-to-end toolkit for ML in earth system science (many tutorials are now live: Tutorial Gallery — PyEarthTools 0.1.0 documentation )
    • 2025 ACCESS Community Workshop: will be held in Melbourne in the week of 8-12 September. There’ll be training on using PyEarthTools and Machine Learning pipeline. What else would you like to see?
  • Updates from the community & new community member introductions
  • Presentation by Neelesh Rampal (Details provided below).
  • Discussion :
    • Plans for using project nm47 on NCI
    • How can this WG best use allocated NCI/NRI resources?
      • Development of an “ML cookbook”, filled with example Jupyter notebooks for sets of ML based problems, based on PyEarthTools. What initial examples would you like to see?
      • Compute resources:
        • Should benefit the entire community. However, this is a bit challenging for this group as it’s not clear whether there are key applications interesting to a wide range of the community (e.g. like COSIMA reference datasets).
        • Appropriate for ECRs/new students to get started if they have trouble getting resources through other means.
        • Requirement that the project result in a contribution to the “ML cookbook”.
  • Machine Learning events:
    • ‘Machine Learning for Ocean Modelling’, taking place on 24-25 June, 2025 at the University of Reading, UK (In-person + Virtually) https://mloceanmodel.github.io/
    • ECMWF Code For Earth 2025 programme: call for participation to team up with Earth Science and ML experts to work on challenges. https://codeforearth.ecmwf.int/

See you on Friday!

Details of this month’s presentation:

Presenter: Neelesh Rampal (NIWA, 21st Century Weather & UNSW Sydney)
Title: Quantifying Internal Variability Uncertainty in Regional Climate Projections using Artificial Intelligence
Abstract: The large computational cost of Regional Climate Models (RCMs) means that only one ensemble member per climate model is typically downscaled; subsequently, internal variability uncertainty is generally not accounted for in coordinated regional climate downscaling efforts (e.g., CORDEX). Surrogate Artificial Intelligence (AI) based emulators are several orders of magnitude faster than RCMs and have been well-tested in their ability to generate reliable regional climate projections. This study uses Generative AI to downscale daily precipitation for 20 Global Climate Models (GCMs) to adequately capture model structural uncertainty, and two single-model initial condition large ensembles (CanESM5, n=20; ACCESS-ESM1-5, n=40) to sample internal variability uncertainty at a 12km resolution over New Zealand. First, we show that the emulator reliably captures the present-day climatology, and the climate change signals compared to dynamical downscaling. We then assess internal variability uncertainty. Consistent with past studies using low-resolution models, our results show robust future changes in winter precipitation but significant uncertainty in summer. The large ensemble of downscaled climate projections better samples extremely rare localized extreme events, which are not adequately sampled using a single ensemble member. Using this ensemble, we can calculate the relative contributions of internal variability and model structural uncertainty in climate projections of local-scale extreme events. Overall, our study highlights the significant potential of AI to complete dynamical downscaling and allow quantification of internal variability uncertainty at regional scales.

1 Like
14

Hi everyone,

This month’s meeting of the Machine Learning for Climate and Weather Working Group will take place Friday, 2 May. Time and zoom details can be found at the top, in the first post.

Here is the agenda:

Facilitator: Vassili Kitsios
Co-chairs: Sanaa Hobeichi, Ryan Holmes, Tennessee Leeuwenburg, Micael Oliveira (ACCESS-NRI liaison), Yue Sun (NCI liaison)

  • Acknowledgement of country
  • Updates from ACCESS-NRI and NCI
  • Updates from the Chairs
    • PyEarthTools: an end-to-end toolkit for ML in earth system science (many tutorials are now live: Tutorial Gallery — PyEarthTools 0.1.0 documentation )
    • 2025 ACCESS Community Workshop: will be held in Melbourne in the week of 8-12 September. There’ll be training on using PyEarthTools and Machine Learning pipeline. What else would you like to see?
  • Updates from the community & new community member introductions
  • Presentation by Taimoor Sohail (Details provided below).
  • Discussion (ongoing) :
    • Plans for using project nm47 on NCI
    • How can this WG best use allocated NCI/NRI resources?
      • Development of an “ML cookbook”, filled with example Jupyter notebooks for sets of ML based problems, based on PyEarthTools. What initial examples would you like to see?
      • Compute resources:
        • Should benefit the entire community. However, this is a bit challenging for this group as it’s not clear whether there are key applications interesting to a wide range of the community (e.g. like COSIMA reference datasets).
        • Appropriate for ECRs/new students to get started if they have trouble getting resources through other means.
        • Requirement that the project result in a contribution to the “ML cookbook”.
  • Machine Learning events:
    • ‘Machine Learning for Ocean Modelling’, taking place on 24-25 June, 2025 at the University of Reading, UK (In-person + Virtually) https://mloceanmodel.github.io/
  • ML Book:

See you on Friday!

Details of this month’s presentation:

Presenter: Taimor Sohail (Research Fellow, University of Melbourne)
Title: Quantifying Internal Variability Uncertainty in Regional Climate Projections using Artificial Intelligence
Abstract: The ocean around Antarctica is crucially important to the climate, with changes there impacting ice melting, global sea level, and ocean circulation patterns. However, the sensors used to measure ocean properties can experience long-term drift and biases, owing in part to the remote and harsh conditions of Antarctica. To ensure the highest quality data is available to study the Antarctic margins, it is essential to develop and apply novel quality assurance methods to available observations. In this talk, I introduce a new, machine learning based approach to assess the quality of ocean salinity measurements around Antarctica. I train a neural network on high-quality ocean measurements taken from research vessels, and use this trained model to assess the quality of salinity measurements in drifting floats (called Argo) and sensors mounted on seals. I find that Argo salinity observations are relatively high quality, and lie within the uncertainty bounds. However, data from seal-mounted sensors has a consistent salty bias, which worsens until around 5 months after deployment. These results highlight a new method to assess ocean observations using neural networks.
Biography: Taimoor Sohail is a physical oceanographer and climate scientist currently working as a Research Fellow at the School of Geography, Earth and Atmospheric Science at the University of Melbourne. He previously completed his PhD at the Australian National University, followed by postdoctoral appointments at UNSW Sydney. Taimoor’s research interests lie in combining machine learning and data science methods to study ocean heat and freshwater changes and large-scale ocean circulation. He is interested in studying the dynamical response of the ocean to anthropogenic climate change by uniting a variety of tools, including high-resolution direct numerical simulations (DNS), novel water mass transformation frameworks, climate models and ocean observations, using data science-based methodologies.

15

Hi everyone,

This month’s meeting of the Machine Learning for Climate and Weather Working Group will take place Friday, 6 June, at 2pm.

:warning: NOTE: This month we will be using different Zoom details! :warning:

Here is the agenda:

Facilitator: Tennessee Leeuwenburg
Co-chairs: Vassili Kitsios, Sanaa Hobeichi, Ryan Holmes, Micael Oliveira (ACCESS-NRI liaison), Yue Sun (NCI liaison)

  • Acknowledgement of country
  • Updates from ACCESS-NRI and NCI
  • Updates from the Chairs
    • Compute resources for this quarter will be allocated to two projects:
      1. Rui Yang (NCI) will develop an interface that allows users to make inferences with AIFS, ECMWF’s new AI-powered weather forecasting model
    • 2025 ACCESS Community Workshop: will be held in Melbourne in the week of 8-12 September. Abstract submissions are now open, until 15 June. There’ll be training on using PyEarthTools and Machine Learning pipeline. What else would you like to see? Are there potential invited speakers for plenary sessions that this Working Group could nominate?
    • PyEarthTools: an end-to-end toolkit for ML in earth system science - FourCastNeXt bundling on the way for a training demonstration; radar data accessor added; CMIP access tested; various documentation enhancements
  • Updates from the community & new community member introductions
  • Presentation by Maxime Marrin (Details provided below).
  • Discussion (ongoing) :
    • Plans for using project nm47 on NCI
    • How can this WG best use allocated NCI/NRI resources?
      • Development of an “ML cookbook”, filled with example Jupyter notebooks for sets of ML based problems, based on PyEarthTools. What initial examples would you like to see?
      • Compute resources:
        • Should benefit the entire community. However, this is a bit challenging for this group as it’s not clear whether there are key applications interesting to a wide range of the community (e.g. like COSIMA reference datasets).
        • Appropriate for ECRs/new students to get started if they have trouble getting resources through other means.
        • Requirement that the project result in a contribution to the “ML cookbook”.

See you on Friday!

Details of this month’s presentation:

Presenter: Maxime Marin | Senior Risk Scientist, Risk Frontiers
Title: Applying Machine Learning to Model Natural Peril Risk Across Australia
Description: Maxime will explore how machine learning techniques are applied to model financial risk from natural perils across Australia. Drawing on Risk Frontiers’ work, the talk will cover the use of various methods in the development and refinement of models for hazards such as tropical cyclones, hail, and bushfires. Maxime will discuss how these approaches improve spatial accuracy, event representation, and loss estimation, while also addressing current challenges. The presentation will highlight the role of ML in creating more robust and actionable catastrophe risk models for use in insurance, reinsurance, and resilience planning.
Biography: Maxime Marin is a Senior Risk Scientist at Risk Frontiers, where he leads the development of the organisation’s Tropical Cyclone risk model and contributes to the advancement of other models and tools within Risk Frontiers’ suite of natural hazard solutions. He holds a PhD in Quantitative Marine Science from the University of Tasmania, where his research focused on the drivers and impacts of marine heatwaves. Maxime now leverages his strong background in climate and data science to enhance the precision, transparency, and practical relevance of catastrophe loss models, supporting applications in insurance, emergency management, and infrastructure risk assessment.

16

2025 ACCESS Workshop - Scholarships for students and ECRs

Are you a student or Early Career Researcher interested in climate and weather science and modelling? Join us at the 2025 ACCESS Community Workshop! Connect with other researchers using the same models and tools as you and discover new software tools that could transform your research!**

The ACCESS Community Workshop will take place 8-12 September 2025 in Melbourne and we are welcoming students and Early Career Researchers (ECRs) to contribute and attend. The Workshop takes place over 4 days: 2 days of presentations, 1 training day, and 1 day devoted to specific domain working groups (Land Surface, Machine learning for Climate and Weather, Atmosphere, Ocean and Sea ice, Cryosphere and Earth System modeling).

Scholarships are available to support ECR/student travel and attendance via the abstract submission. Applications close 22 June 2025. See here for more information

19

Hi everyone,

There will be no meeting of the ACCESS-NRI Machine Learning Working Group in July.

The meeting was originally scheduled for Friday, 4 July at 2pm, but with several members away this month, we’ve decided to skip July’s meeting.
We’ll be back as usual in August, and look forward to seeing you then!

In the meantime, feel free to share updates or discussion points here on the forum.

20

Call for Expressions of Interest – ACCESS-NRI Visualisation Project

Antarctica visualisation
Antarctica visualisation720×720 174 KB

ACCESS-NRI is inviting expressions of interest from domain experts and researchers who would like to collaborate on a 3-month visualisation project. We’re offering technical support and expert guidance to help you bring your science to life.

We encourage bold, creative ideas that explore new ways to visualise ACCESS model outputs. It could be a compelling snapshot of climate change impacts, a journey through the ocean’s depths, or a flyover of modelled land surface processes. Be ambitious!

This is your chance to create high-impact visuals (animations, videos, or 3D still images) that showcase your research and amplify its visibility across media, conferences, and the broader community. Successful projects will be supported by:

  • Owen Kaluza, visualisation expert at ACCESS-NRI:
    Owen is developing high-impact visualisations to better communicate the work done with ACCESS models and data. His work spans 3D graphics (OpenGL), GPU programming, Python, and notebook-based tools.
    Explore recent work on our Vimeo Channel.
  • The ACCESS-NRI Engagement and Communications team, offering guidance on science communication and media promotion.

:backhand_index_pointing_right: Submit your Expression of Interest (EoI)

How will EOIs be evaluated?

  • Priority will be given to projects using models supported by ACCESS-NRI
    (List of models)
  • Data availability on NCI Gadi at project start
    (new model runs must be arranged separately)
  • Feasibility within a 3-month timeframe
  • Impact and relevance to the ACCESS community and broader audiences

Why get involved?

  • Give your science an extra “wow” factor
  • Enhance conference presentations
  • Stand out on social media
  • Reach a broader audience outside traditional publishing channels

Key dates

  • Call open until: Wednesday 30 July 2025
  • Selected projects announced at: ACCESS-NRI Annual Workshop in Melbourne (early September)
  • Project start: Any time during FY25–26
    (must be scoped for delivery in 3 months)

If you have any questions or want to discuss a concept before submitting, feel free to reach out to romain.beucher@anu.edu.au

21

Hi everyone,

This month’s meeting of the Machine Learning for Climate and Weather Working Group is on this Friday, 1st August, at 2pm. Zoom details and agenda attached below.

See you all on Friday!

—-----------------------------------------------
Zoom details: Launch Meeting - Zoom , Zoom Meeting ID: 831 873 07759 (password: 123456)
—-----------------------------------------------
Agenda:
Facilitator: Ryan Holmes
Co-chairs: Tennessee Leeuwenburg, Sanaa Hobeichi, Vassili Kitsios, Micael Oliveira (ACCESS-NRI liaison), and Yue Sun (NCI liaison)

  • Acknowledgement of country
  • Updates from ACCESS-NRI and NCI
  • Updates from the Chairs
    • Compute resources for this quarter will be allocated to Terry O’Kane - 200kSU.
    • 2025 ACCESS Community Workshop (Melbourne, 8-12 September). For the ML group, there will be a training on using PyEarthTools and the Machine Learning pipeline on Tuesday 9 September, and a ML workshop day on Friday 19 September. Who’s planning to attend?
  • Updates from the Community & new community member introductions
  • Short presentation by Edison and Yue - ML downscaling.
  • Presentation by Sanaa Hobeichi (abstract below).
  • Discussion (ongoing): Plans for using project nm47 (100TB gdata storage, 875kSU/quarter) on NCI. How can this WG best use allocated NCI/NRI resources?
    • Development of an “ML cookbook”, filled with example Jupyter notebooks for sets of ML based problems, based on PyEarthTools. What initial examples would you like to see?
    • Compute resources:
      • Should benefit the entire community. However, this is a bit challenging for this group as it’s not clear whether there are key applications interesting to a wide range of the community (e.g. like COSIMA reference datasets).
      • Appropriate for ECRs/new students to get started if they have trouble getting resources through other means.
      • Requirement that the project result in a contribution to the “ML cookbook”.

—------------------------------------------

Speaker details:

Presenter: Sanaa Hobeichi | Senior Research Fellow, Centre of Excellence for the 21st Century Weather @UNSW Sydney

Title: Comparison of Machine Learning Models with Dynamical Downscaling for Australian Precipitation Using a Standardised Benchmark Framework

Abstract: Downscaling techniques are essential for refining coarse-resolution climate projections to scales relevant for local and regional impact assessments, with Artificial Intelligence (AI) emerging as a promising approach for this task. However, a standardised benchmarking framework for evaluating these AI-based downscaling methods has been lacking.

This study presents the first evaluation of AI-based downscaling methods using established performance expectations within a standardised benchmarking framework. Three Machine Learning (ML) models, including a Generative Diffusion Model, a Vision Transformer, and a Recurrent Neural Network, are assessed against observational data and compared with 24 simulations by Regional Climate Models (RCMs). The evaluation employs minimum standard metrics focused on four fundamental rainfall characteristics across Australia: total precipitation, spatial distribution, seasonal cycle, and temporal trends. Results show that all three ML models and ten RCMs meet the minimum performance benchmarks, with rankings varying depending on the rainfall characteristic and region assessed. ML models demonstrate comparable performance to RCMs while offering substantial computational advantages.

This highlights the potential of ML models to supplement traditional downscaled simulations, thereby enhancing climate projection ensembles and improving uncertainty quantification. Such an approach aligns with recommendations advocating for diverse modelling methodologies in national assessments.

Biography: Sanaa Hobeichi is a Senior Research Associate at the ARC Centre of Excellence for the 21st Century Weather, based at UNSW Sydney. Her research develops Artificial Intelligence and Machine Learning methods for various climate and weather applications focussing on climate downscaling and drought analysis.