The role

We are looking for a highly motivated Scientist to work on hybrid modelling that combines physics-based and machine learned approaches to Earth system modelling. The successful candidate will work with ECMWF teams in implementing a new approach that nudges the large scales of ECMWF’s physical weather forecasting model – the Integrated Forecasting System (IFS) – towards the machine learned forecasting model – the Artificial Intelligence Forecast System (AIFS) – to develop a forecast system that combines the best of both worlds achieving the (better) large-scale skill of the AIFS and the physical consistency and detailed representation of small-scale features of the IFS. The work will combine cutting edge, km-scale modelling and machined learned weather forecasts. The hybrid model configurations will be prepared for application in numerical weather predictions both in the context of operational products at ECMWF and for use in the weather induced-extremes Digital Twin implemented by ECMWF in the Destination Earth (DestinE) initiative of the European Commission.

This position will work in close collaboration with AIFS developers and is based in the Numerical Methods Team that is mainly responsible for the development and maintenance of the dynamical core of the IFS. The team is part of the Earth System Modelling Section of the Research Department.

At ECMWF, you will find a passionate community, collectively aiming to build world-leading global Earth system models for numerical weather prediction. This effort supports ECMWF’s strategy of producing cutting‐edge science and world-leading weather predictions and monitoring of the Earth system.

About ECMWF

The European Centre for Medium-Range Weather Forecasts (ECMWF) is a world-leader in weather and environmental forecasting. As an international organisation we serve our members and the wider community with global weather predictions and data that is critical for understanding and solving the climate crisis. We function as a 24/7 research and operational centre with a focus on medium and long-range predictions, holding one of the largest meteorological data archives in the world. The success of our activities builds on the talent of our scientists and experts, strong partnerships with 35 Member and Co-operating States and the international community, some of the most powerful supercomputers in the world, and the use of innovative technologies and machine learning across our operations. ECMWF is a multi-site organisation, with a main office in Reading, UK, a data centre/supercomputer in Bologna, Italy, and a large presence in Bonn, Germany.

ECMWF has developed a strong partnership with the European Union and has been entrusted with the implementation and operation of the Destination Earth Initiative and the Climate Change and Atmosphere Monitoring Services of the Copernicus Programme. Other areas of work include High Performance Computing and the development of digital tools that enable ECMWF to extend provision of data and products covering weather, climate, air quality, fire and flood prediction and monitoring.

See www.ecmwf.int for more info about what we do.

About Destination Earth (DestinE)

ECMWF is one of the three entities entrusted to implement the DestinE initiative of the European Commission, alongside with ESA and EUMETSAT as partners. DestinE aims to deploy several highly accurate thematic digital replicas of the Earth, called Digital Twins. The Digital Twins will help monitor and predict environmental change and human impact, in order to develop and test scenarios that would support sustainable development and corresponding European policies for the Green Deal. ECMWF is responsible for the delivery of these digital twins and of the Digital Twin engine, the software infrastructure needed to power them of some of Europe’s largest supercomputers, those of the European HPC Joint Undertaking (EuroHPC).

The second phase of DestinE covers the period June 2024 – May 2026, and future phases are foreseen (subject to funding). Phase 2 will focus on early operations with consolidation, maintenance, and continuous evolution of the DestinE system components developed in the first phase. There will also be an enhanced focus on ML activities, including the deployment of workflows of components of a ML model for the Earth system, optimisation of the Digital Twin Engine to enable efficient model training and simulations, and other activities.

For more information on DestinE, see https://ec.europa.eu/digital-single-market/en/destination-earth-destine and https://www.ecmwf.int/en/about/what-we-do/environmental-services/destination-earth

Your responsibilities

• Develop new hybrid model configurations that couple IFS and AIFS in the optimal way to improve numerical weather predictions
• Train variants of the AIFS for both deterministic and ensemble predictions in close collaboration with other machine learning experts at ECMWF that can be used for nudging experiments and represent the full vertical resolution of the IFS
• Evaluate model simulations with the hybrid model configuration and compare the quality of predictions against simulations with both the IFS and AIFS regarding forecast scores and for specific weather events, across a range of resolutions from tenths of km to km-scale
• Prepare and test the configurations that will be implemented for use in the extremes Digital Twin of DestinE and for operational weather prediction.

What we are looking for

• Excellent analytical and problem-solving skills with a proactive approach to improve models and tools
• Excellent interpersonal and communication skills
• Self-motivated and able to work with minimal supervision as well as collectively as part of a team
• Dedication, passion and enthusiasm to succeed both individually and collaboratively
• Ability to maintain effective communication and documentation of scientific results
• Highly organised with the capacity to work on a diverse range of tasks to tight deadlines.

Education/experience/knowledge and skills (including language)

• Advanced university degree (EQ7 level or above) in a physical, mathematical, computer or environmental science, or equivalent professional experience
• Experience in Earth system modelling
• Very good programming and scripting skills
• Experience in machine learning for applications in Earth sciences would be desirable
• Knowledge of atmospheric dynamics and the evaluation of the quality of weather forecast models is desirable
• Experience working with operational numerical weather prediction models is desirable
• Candidates must be able to work effectively in English.