Strategic Lead for Machine Learning
Forecast, Earth System Modelling, Innovation Platform
Summary:
Matthew Chantry is the Strategic Lead for Machine Learning at ECMWF and Head of the Innovation Platform. Matthew works across ECMWF to advise and coordinate on adoption of machine learning across ECMWF's mission. He champions the AIFS, which is delivering machine learning forecasting systems to operational forecasting. Work at ECMWF on these projects is distributed across an organisation, meaning Matthew must coordinate developments across departments, sections and teams. Matthew works closely with Member States in the co-development of Anemoi as a shared machine learning framework for data-driven forecasting systems. He also advises the ECMWF directorate on future directions for ML-based development.
Professional interests:
- Machine learning
- Atmospheric modelling
- Open-source software development
- Research to operations
Career background:
Professional experience
- Strategic Lead for Machine Learning 2025 - present
- Machine Learning Coordinator, 2023 - 2025
- Scientist, Earth System Modelling, Research Department, 2021 - 2023
- Postdoctoral researcher at the University of Oxford on reduced numerical precision and machine learning in weather and climate forecasting, 2016 - 2021
- Postdoctoral researcher at ESPCI, Paris on pattern formation in the transition to turbulence, 2014 - 2016
Education
- Ph.D. in Applied Mathematics (2014) from the University of Bristol, titled: "Localization in transitional shear flows"
- M.Math in Applied Mathematics (2010) from the University of St Andrews
- 2024
- (June 2024) Revisiting the Direct Assimilation of Scatterometer ‘Sigma0’ over the Ocean, Eumetsat Contract Report. DOI: 10.21957/2c3c85ad6b
- (October 2024) Data-driven ensemble forecasting with the AIFS, ECMWF Newsletter n. 181, pp. 32-37. DOI: 10.21957/ma3p95hxe2
- 2022
- Zied Ben Bouallègue, Fenwick Cooper, Matthew Chantry, Peter Dueben, Peter Bechtold, irina sandu (April 2022) Statistical modelling of 2m temperature and 10m wind speed forecast errors, ECMWF Technical Memoranda n. 896. DOI: 10.21957/vdcccja3f
- 2020
- Pavan V. Kashyap, Yohann Duguet, Matthew Chantry (October 2020) Far field of turbulent spots, Physical Review Fluids. DOI: 10.1103/physrevfluids.5.103902
- Laurette S. Tuckerman, Matthew Chantry, Dwight Barkley (January 2020) Patterns in Wall-Bounded Shear Flows, Annual Review of Fluid Mechanics. DOI: 10.1146/annurev-fluid-010719-060221
- 2019
- Matthew Chantry, Tobias Thornes, Tim Palmer, Peter Düben (January 2019) Scale-Selective Precision for Weather and Climate Forecasting, Monthly Weather Review. DOI: 10.1175/mwr-d-18-0308.1
- Sam Hatfield, Matthew Chantry, Peter Düben, Tim Palmer (June 2019) Accelerating High-Resolution Weather Models with Deep-Learning Hardware, Proceedings of the Platform for Advanced Scientific Computing Conference. DOI: 10.1145/3324989.3325711
- 2017
- Matthew Chantry, Laurette S. Tuckerman, Dwight Barkley (July 2017) Universal continuous transition to turbulence in a planar shear flow, Journal of Fluid Mechanics. DOI: 10.1017/jfm.2017.405
- 2016
- Matthew Chantry, Laurette S. Tuckerman, Dwight Barkley (February 2016) Turbulent–laminar patterns in shear flows without walls, Journal of Fluid Mechanics. DOI: 10.1017/jfm.2016.92
- 2014
- (March 2014) Genesis of Streamwise-Localized Solutions from Globally Periodic Traveling Waves in Pipe Flow, Phys. Rev. Lett..
- (March 2014) Studying edge geometry in transiently turbulent shear flows, Journal of Fluid Mechanics.
- (March 2014) Localization in a spanwise-extended model of plane Couette flow, Physical Review E.