About Me Career Publications Return To Top

About Me

I am a Data Scientist and Software Engineer who stumbled into the field of Meteorology – and what a field it is.

I am passionate about empowering scientists to do science, which is ever more important in this rapidly changing landscape of Machine Learning and Artificial Intelligence.

I have experience developing large software packages and tools for working with environmental data at 100+ PB scales.

I am particularly interested in the application of ML and AI to enhance weather forecasts. I firmly believe a rigorous scientific approach is needed to understand the impact these new technologies will have.

Career

European Centre for Medium-Range Weather Forecasts (ECMWF)

Research Software Engineer

Working within the Data Processing Services Team of the Development Section, and partially embedded within the Innovation Platform.

Working to explore Machine Learning applications for weather forecasting, with an interest in the exploration of coupled models.

Additionally working to provide on demand production generation from ML models.

2026
Bureau of Meteorology, Australia

Data Scientist
2 years 5 months

Within this role I was the technical lead and founder of the development of PyEarthTools. A framework to enable Machine Learning (ML) Research for Weather Modelling.

I was additionally embedded in the Bureau’s Coupled Modelling team, exploring the applications of ML for a multiweek to subseasonal prediction system.

  • Technical Lead of PyEarthTools
  • Contributed to scores
  • Contributed to ML Earth System Model Verification
    • GraphCast, SFNO, Pangu, etc..
  • Coordinated discussion forums with Universities
2024
Queensland University of Technology

4 years

Bachelor of IT and Science. Computer Science and Physics.

Graduated with Honours.

2022

Publications

Working with some fantastic people has meant I have had the opportunity to contribute to a collection of papers. ORCID

Papers & Preprints

Guo, Edison et al.. FourCastNeXt: Optimizing FourCastNet training for limited compute. ,.doi: 10.48550/arXiv.2401.05584.

Leeuwenburg, Tennessee et al. (2024 6). Scores: A python package for verifying and evaluating models and predictions with xarray and pandas. ,.http://arxiv.org/abs/2406.07817.

Cook, Harrison et al. (2025 6 28). PyEarthTools: Machine learning for Earth system science. doi: 10.5281/zenodo.15760769.

Moldovan, Gabriel et al. (2025 10). AIFS 1.1.0: An update to ECMWF's machine-learned weather forecast model AIFS. ,.doi: 10.5194/egusphere-2025-4716.

de Burgh-Day, Catherine et al. (2026 6). Evaluation of medium range machine learning models for sub-seasonal prediction. ,.doi: 10.48550/arXiv.2606.25417.

Hahner, Sara et al. (2026 4). Representing the Surface Ocean in ECMWF's data-driven forecasting system AIFS. ,.doi: 10.48550/arXiv.2604.25559.

Ingstad, Magnus Sikora et al. (2026 7). HourGlass: A probabilistic data-driven temporal downscaler for global and regional weather forecasting. ,.doi: 10.48550/arXiv.2607.11457.

Conference Presentations

Carton de Wiart, Corentin et al. (2026 3). Forecast-in-a-Box: AI weather forecasting, easy to run and simple to deploy. In: EGU General Assembly 2026, .https://meetingorganizer.copernicus.org/EGU26/EGU26-20013.html.

Zampieri, Lorenzo et al. (2025 4). Coupling approaches for data-driven Earth system models. In: EGU General Assembly 2025, .https://ui.adsabs.harvard.edu/abs/2025EGUGA..27.4499Z/abstract.