ECMWF is the leading centre for global, medium-range weather predictions and is the host of the largest archive of weather data in the world. ECMWF is both a research institute and a 24/7 operational service, producing and disseminatingnumerical weather predictions to its Member States.
ECMWF has also been entrusted to operate the Copernicus Atmosphere Monitoring Service (CAMS) and the Copernicus Climate Change Service (C3S) on behalf of the European Commission.
Every day, hundreds of millions of satellites and in situ observations are processed at ECMWF to provide the basis for up-to-date global analyses and climate reanalyses of the atmosphere, ocean and land surface, and to generate global weather predictions from hours up to a year ahead. To retain its world-leading position, ECMWF is performing cutting edge research in weather related sciences and high-performance computing. ECMWF’s weather forecasts are disseminated to the ECMWF Member States and thousands of users around the world.
Your role within ECMWF
ECMWF has embarked on an exciting new initiative to explore the use of artificial intelligence and Machine Learning (ML) in applications of numerical weather predictions and provide the developed tools and techniques to the public. As part of this effort, ECMWF is participating in the AI4Copernicus H2020 project which funds this position.
This position will be in the Computing Department which coordinates ECMWF’s participation to the project. The successful candidate will apply their skills, knowledge, and expertise to help achieving the goals, and complete the deliverables of the AI4Copernicus project. The main focus will be on the development of supervised ML techniques such as Convolutional Neural Networks, Generative Adversarial Networks, Recurrent Neural Networks and Long-Short Term Memory (LSTM) networks that will be developed for the AI4Copernicus platform for the analysis of single-date and time series of remote sensing images to serve the user cases of AI4Copernicus in the area of agriculture, energy, security and health.
The main responsibility of ECMWF’s contribution is in the development of customised ML models relating to health and wellbeing. This includes predictions of pollution based on a mixture of local observations and three-dimensional data of the atmosphere using three dimensional convolutional neural networks as well as the detection of Earth Observation (EO) related features such as warm spells related to diseases such as Malaria.
The successful applicant will also contribute to knowledge extraction from EO data using unsupervised learning and will support open calls from AI4Copernicus. The Scientist will work in close collaboration with other teams across the organisation and strong communication skills are essential.