[Webinar Series] Contrails in the climate system – enhancing NWP through cloud observation and AI

The CONTRAILS project aims to provide tools to monitor the impact of contrails on climate. As a joint work of the German Weather Service DWD (DE), Thalès Research & Technology (FR), Reuniwatt SAS (FR) and Laboratoire atmosphères, milieux, observations spatiales (FR), the goal of the subproject at DWD was to develop assimilation and prediction methods for contrail and cirrus observations within the Numerical Weather Prediction (NWP) systems, using the ICON model and its ensemble-variational data assimilation.

This webinar will present contrails observation using all-sky imagers by Reuniwatt, as well as AI tools that have been developed to detect contrails in camera and satellite images, enabling the identification of contrail clusters. These clusters can be used to evaluate the representation of ice-supersaturated regions in the NWP model. Our speakers are happy to present the remarkable progress the team has achieved in the identification, representation, and data assimilation of contrails and high cirrus clouds.

In our webinar, you will learn more about the methos for AI-based parameterizations for subgrid-scale cloud properties in the NWP model developed by DWD in collaboration with the other CONTRAILS project parterns. These AI parameterizations have been trained using satellite observations, allowing for a more realistic representation of cloud distributions compared to traditional purely physical parameterizations.

Based on these parameterizations, an all-sky data assimilation method has been implemented and successfully tested for incorporating visible satellite images into global numerical weather prediction. This enables a more realistic representation of current humidity and cloud distributions in the atmosphere, leading to improved forecasts for these parameters.

Prof. Roland Potthast is the Head of Numerical Weather Prediction (NWP) forecasts provided to millions of users every day. He will introduce the project’s objectives, scientific advances and implications for prediction systems and applications.

Dr. Stefanie Hollborn will provide her expertise on how artificial intelligence methods results are automatically fed into the observation pool for the analyses of the numerical weather forecast, where they provide a significantly improved formation probability of contrails and climate-relevant clouds.

Sarah Vadillo-Quesada will present the different technologies leveraged within the project to observe contrails, and support the data assimilation and prediction of contrails.

The webinar will be chaired by Dr. Teodora Petrisor, who will lead the audience through the webinar, and forward your questions on the observation, modelling and prediction of contrails to the panelists.

After this webinar, you will have a better understanding of:

  • Ground-based all-sky camera observations in combination with new satellite-based cloud observations

  • Trustworthy AI methods and physical models to improve the monitoring and characterisation of contrails

  • Get a better understanding of the entire physical process underlying the formation of contrails

  • Learn about the results of CONTRAILS and augmenting NWP models accordingly

About the speakers:

Dr. Teodora Petrisor is a senior research engineer in AI at CortAIx Labs, Thales, leading the AI algorithm validation roadmap. She holds a PhD in Signal and Image Processing from Telecom Paris. For the past couple of years she has been focusing on trustworthy AI algorithms with applications to green operations in avionics and more specifically to contrail detection and prediction. She is currently leading the French consortium in the BPI/DLR CONTRAILS project.

Prof. Roland Potthast, is Director for Meteorological Modeling and Analysis at the German Weather Service (Deutscher Wetterdienst, DWD), EUMETNET AI Programme Coordinator, and Professor for Applied Mathematics at the University of Reading, UK.

Dr. Stefanie Hollborn is a scientist at DWD, and leads the Department of Observation Modeling and Verification. She holds a PhD in Numerical Mathematics with a specialization in Inverse Problems from the University of Mainz. Her research focuses on developing and implementing data assimilation methods to enhance Numerical Weather Prediction. Recently, her work has increasingly concentrated on the application of artificial intelligence in weather forecasting and weather and climate services.

Sarah Vadillo-Quesada graduated with a dual degree in energy engineering and business administration, before developing an extensive background in public affairs by integrating the French Ministry of Ecological Transition and the Ministry of Foreign Affairs, where she contributed to developing research partnerships between French and American Universities. She joined Reuniwatt’s Paris office in 2021 to develop collaborations with universities and projects in the PV sector.

Teodora Petrisor

Moderator
Senior Research Engineer AI @Thales

 

 

Prof. Roland Potthast

Speaker
Head of NWP (Numerical Weather Prediction) @DWD

 

 

Stefanie Hollborn, PhD

Speaker
Head of Observation Modelling and Verification NWP @DWD

 

Sarah Vadillo-Quesada

Speaker
Business Developer @Reuniwatt

 

This webinar will take place on March 20, 2025 starting 3pm CET.

About Thales (www.thalesgroup.com)

Thales is a global technology leader with more than 81,000 employees on five continents. The Group is investing in digital and deep tech innovations – Big Data, Artificial Intelligence, connectivity, cybersecurity and quantum technology – to build a future we can all trust. In the markets of defence, aerospace and space, cyber and digital, Thales provides solutions, services and products to help its customers carry out their critical missions. Within Thales, the cortAIx entity, gathers over 600 AI experts and more than 100 PhD each year and brings together Thales’s Artificial Intelligence capabilities in the fields of research, sensors and systems. Its goal is to build AI solutions which are trustworthy, transparent, explicable and ethical, whilst taking into account specific constraints such as cybersecurity, embeddability and frugality that are related to critical environments.

About DWD (dwd.de)

Germany’s National Meteorological Service, the Deutscher Wetterdienst (DWD), is responsible for meeting meteorological requirements arising from all areas of economy and society in Germany. It is a public institution with partial legal capacity under the Federal Ministry of Transport and Digital Infrastructure. DWD is a leader in R&D of Numerical Weather Prediction Models and meteorological algorithms and applications.

About Reuniwatt (reuniwatt.com/)

Reuniwatt is a major player of the solar radiation and cloud cover assessment and solar and wind power forecasting. Based on solid Research and Development works, the company offers reliable products and services intended for professionals of various fields, making the best out of two key facets of the meteorology: atmospheric physics and data sciences. A particular focus has been placed on solar energy forecasting, while developing cutting edge solutions to improve the short-term prediction of the solar resource.
The company has won many grants, including H2020’s SME Phase 1 programme, which makes Reuniwatt a European Champion with regard to innovation. Reuniwatt has also been selected among the national fast-growing companies to join the prestigious French Tech 120 programme in 2020 and 2021, and the French Space Tour 2021.

This project is supported by the Digital Technologies for Business funding program: Artificial Intelligence Technologies for Risk Prevention, Crisis Management and Resilience, as well as BPI France.