Harnessing Artificial Intelligence to Strengthen Climate Prediction and Early Warning Systems Across Sub- Saharan Africa
Sub-Saharan Africa faces rising climate risks, and Artificial Intelligence (AI) is emerging as a powerful tool to improve weather and climate prediction across the region. This webinar will highlight practical AI and machine learning applications being used by National Meteorological and Hydrological Services (NMHSs), Regional Climate Centres (RCCs), researchers, and innovators to enhance forecasting at different timescales, from short-range weather prediction to long-range climate outlooks.
Objectives:
- Showcase AI innovations supporting climate and weather prediction across Africa.
- Highlight leading AI initiatives by NMHSs and RCCs.
- Identify pathways for operationalising AI tools within national and regional climate centres.
Expected Outputs:
- A showcase of AI/Machine Learning (ML) innovations from across the continent.
- A technical summary document on strengths, gaps, and integration pathways for AI in forecasting.
Expected Impact:
- Increased visibility of Africa’s AI/ML innovations in climate prediction on the global stage.
Panelists
Tim Palmer
University of Oxforddiscussant
Tim Palmer is a Royal Society Research Professor Emeritus at Oxford University. He is a Fellow of the Royal Society and an International Member of the US National Academy of Sciences. He has won the Charney and Rossby medais of the American Meteorological Society and the IMO medal of WMO. For many years he worked at ECMWF, leading the team that introduced the ensemble prediction system into operations.
Sinclair Chinyoka
Weather and Climate Modelerdiscussant
Sinclair Chinyoka is a NORCAP expert and PhD candidate at Wageningen University in the Netherlands, specialising in numerical weather prediction (NWP) modeling and machine learning. His research focuses on advancing forecasting systems in Africa by integrating cutting-edge machine learning methods with traditional numerical models to improve the accuracy, reliability, and applicability of weather forecasts.
Nishadh Kalladath
Data Science and Machine Learning Expert ICPACdiscussant
Nishadh is a NORCAP expert in Data Science and Machine Learning at the IGAD Climate Prediction and Applications Centre (ICPAC) in Nairobi, Kenya. He is actively involved in the research and development of impact-based forecasting (IBF) systems for the East African region. Nishadh holds a PhD in Environmental Sciences from Bharathiar University in Tamil Nadu, India. Currently, Nishadh is working on a CRAF-funded project within the Disaster Risk Management Programme at ICPAC, aiming to operationalise impact-based forecasting through Ensemble Prediction Systems, hazard and impact modelling using the storylines approach and leveraging Bayesian networks.
Håvard Alsaker Futsæter
Team Leader MET Norwaydiscussant
Team leader for a product team at MET Norway. We work closely with the researchers at MET Norway to develop open data web services, used by yr.no and others. Most recently, we are collaborating with ECMWF to make our AI-WP model, Bris, available for use in domains outside the Nordic region, and are currently testing our setup in Malawi together with DCCMS.
Hannah Wangari
Kenya Meteorological Departmentdiscussant
Hannah is a climate scientist with extensive experience in weather and climate forecasting. She holds both a bachelor’s and a master’s degree in Meteorology from the University of Nairobi. Her work focuses on producing high-impact forecasts across multiple timescales and co-producing advisories for climate-sensitive sectors at the national level.
She contributed to the development of the regional Standard Operating Procedures for Lake Victoria forecasts, supporting vulnerable communities in the region. She also co-designed and co-developed the Nairobi County forecasts targeting informal settlements.
Hannah currently leads a World Food Programme–supported project on strengthening Early Warning Systems for Anticipatory Action, where she oversees efforts to assess the skill and sustainability of a cloud-based machine learning post-processing system for improved high-impact weather forecasting.
