New tender for the development of an LLM AI chatbot opens
Are you ready to take the challenge of building a chatbot that can interact with the users of Destination Earth’s digital twins? Do you have strong expertise in large language models and want to be part of a unique initiative to build a new information system within the ambitious Destination Earth initiative of the European Commission?
The European Centre for Medium-range Weather Forecasts (ECMWF) is seeking proposals to build a climate and weather chatbot that will ease information access for users of DestinE digital twins and the wider community. The invitation to tender is open until 17 July 2024.
Destination Earth (DestinE) is ramping up the integration of machine learning and artificial intelligence techniques. After the successful completion of Phase I, the ambitious initiative of the European Commission to build a digital replica of the Earth system will boost machine learning and artificial intelligence activities in its second Phase (June 2024 – June 2026).
While the digital twins on Weather-induced Extremes and on Climate Change Adaptation, and the Digital Twin Engine built by ECMWF for Destination Earth included already ML/AI elements, for example, for uncertainty quantification, ECMWF has recently recruited and issued calls for tenders specifically to cover the enhancement of ML/AI during Phase II.
The weather and climate web-based chatbot to be developed through this tender funded by the European Commission in DestinE will ease access to Digital Twin information by guiding users through their queries and providing help and support. The chatbot will generate answers by using data, graphical products, news, documents, and scientific publications and guide the user through the support materials.
See the full invitation to tender on ECMWF website
The chatbot will be key to widening the community of users of DestinE, ensuring they can easily obtain the information they need amidst the huge volumes of data generated by the digital twins and other sources available on the DestinE core platform and in the DestinE Data Lake.
The successful tenderer will need to liaise closely with ECMWF and its partner institutions developing the Climate DT and the Extremes DT to ensure synergies between the different applications and interfaces being developed.
ECMWF has also issued a tender for the Development of Ethical Machine Learning Strategies for Destination Earth that will set recommendations about the ethical and legal aspects and must be taken into consideration for the implementation of the chatbot.
The tenderers are free to propose their solutions based on open-source version Large Language Model (LLM), with a preference for an LLM based in the European domain.
See the full invitation to tender on ECMWF website
Destination Earth is a European Union-funded initiative launched in 2022, with the aim to build a digital replica of the Earth system by 2030. The initiative is being jointly implemented under the leadership of DG CNECT by three entrusted entities: the European Centre for Medium-Range Weather Forecasts (ECMWF), responsible for the creation of the first two ‘digital twins’ and the ‘Digital Twin Engine’, the European Space Agency (ESA) responsible for building the ‘Core Service Platform’, and the European Organisation for the Exploitation of Meteorological Satellites (EUMETSAT), responsible for the creation of the ‘Data Lake’.
We acknowledge the EuroHPC Joint Undertaking for awarding this project strategic access to the EuroHPC supercomputers LUMI, hosted by CSC (Finland), and the LUMI consortium, Marenostrum5, hosted by BSC (Spain) Leonardo, hosted by Cineca (Italy) and MeluXina, hosted by LuxProvide (Luxembourg) through a EuroHPC Special Access call.
More information about Destination Earth is on the Destination Earth website and the EU Commission website.
For more information about ECMWF’s role visit ecmwf.int/DestinE
For any questions related to the role of ECMWF in Destination Earth, please use the following email links:
Press and Communications enquiries
Main picture: © primopiano – stock-adobe.com