AfriClimate AI Monthly Webinar Series

Upcomming Events

RainOverAfrica.AI: Nowcasting Precipitation with Uncertainty from Geostationary Imagery

Speaker: Adrià Amell

Date: 19 March, 2025

Time: 16:00 GMT

Adrià Amell

Adrià Amell is a PhD student at Chalmers University of Technology in Sweden. He started working with satellite data before his PhD in 2017 and quickly became fascinated by space-borne measurements' possibilities. At the same time, he began delving into machine learning. With a strong educational background in engineering physics and mathematics and a keen interest in artificial intelligence, he is also driven by cutting-edge technology for handling large data volumes, as they often enable new findings at the intersection of satellite data and machine learning. Adrià is primarily focused on working with geostationary imagery and neural networks, particularly on studying cloud ice masses and precipitation. His work involves leveraging advanced machine learning techniques to use complex satellite data, contributing to a deeper understanding of atmospheric phenomena and climate.

Talk Abstract:

Geostationary satellites offer unrivalled spatiotemporal coverage, but their measurements have often been considered only complementary to the complex problem of estimating precipitation from space. In this seminar, we will walk through Rain over Africa (RoA), a method based on a neural network and geostationary imagery that can provide not only continuous precipitation estimates over the entire African continent but also case-specific uncertainties, facilitating the detection of extreme events. We will also see how anyone can produce RoA estimates with low latency after the dissemination of satellite data, enabling resilience planning through near real-time monitoring. This nowcasting aspect of RoA is not at the expense of accuracy, since it results superior to established higher latency products.

Registration Link here

Past Events

Assessing the Impact of Carbon Tax Policy on Renewable Energy Investment: The Potential Use of AI with a Special Focus on Developing Countries

Speaker: Narindra RALEFOMANANA

Date: 26th February, 2025

Time: 16:00 GMT

Narindra RALEFOMANANA

Narindra RALEFOMANANA is a Malagasy Economist Researcher and Climate Activist with over 10 years of experience in research, education, and climate advocacy. She holds a Master’s degree in Public Economy and Environment from the University of Antananarivo and is currently pursuing a PhD at Ecole Doctorale en Gestion des Ressources Naturelles et Développement (University of Antananarivo). Her research focuses on accelerating the energy transition through carbon tax for a just and equitable policy. She is skilled in data collection, analysis, and applying research to support sustainable development and informed decision-making.

Current Affiliations:

University of Antananarivo – PhD Student, Ecole Doctorale en Gestion des Ressources Naturelles et Développement
Ministry of Technical Education and Vocational Training, Madagascar – Research and Project Officer, Civic and Environmental Engagement Unit

Talk Abstract:

Carbon taxation is widely recognized as a key policy tool for reducing greenhouse gas emissions and promoting renewable energy investment. However, in developing countries, its implementation raises concerns about economic feasibility, social equity, and policy effectiveness. This presentation explores how Artificial Intelligence (AI) can enhance the assessment of carbon tax policies by improving data analysis, scenario modeling, and predictive insights. By integrating AI-driven techniques with economic modeling approaches, the discussion highlights innovative methods to evaluate the economic, environmental, and social implications of carbon taxation in resource-constrained settings. The session aims to provide insights into how AI can support evidence-based policy-making for a more sustainable energy transition, especially in developing economies.

Registration Link here

AfriClimate AI Community Town Hall (29/05/2024)

Date: 29 May 2024

Time: 16:00 - 17:00 GMT

AfriClimate AI is hosting its first Community Town Hall on Wednesday, 29 May 2024 🎉.

The Town Hall agenda includes:

A discussion on the next steps from our position paper titled "Leveraging AI for Climate Resilience in Africa: Challenges, Opportunities, and the Need for Collaboration"
Lightning talks from community members.

We invite all community members to join this session. If you would like to share your work and ideas with the community through a lightning talk, please complete the form linked below.

Registration Link: https://forms.gle/XHpThnvYpUsHYoYR6

Lightning talk submission form: https://tinyurl.com/2etyf6h9

Zoom Details:

Link: https://us06web.zoom.us/j/83709728315pwd=SKpbFPDvXum5NcszMaUBww4qIkndaB.1

Meeting ID: 837 0972 8315

Passcode: 416397

Open Benchmarking to Drive S2S Weather Intelligence in East Africa

Speaker: Dr. Genevieve Flaspohler

Date: 29th January, 2025

Time: 16:00 GMT

Genevieve Flaspohler

Dr. Genevieve Flaspohler is co-founder and Executive Director of Rhiza Research, a nonprofit organization developing open technology to serve people and the planet. She currently leads the Gates Foundation-funded SheerWater Project, which works to address global inequity in weather forecasting with a focus on providing actionable insights for smallholder farmers in East Africa. Previously, as Chief Data Officer at nLine, she led large-scale deployments of open power monitoring sensors across Africa, helping to collect and release the largest public dataset on grid performance on the continent (1,500+ sensors deployed over 6 years in Accra, Ghana), and using data to guide energy investments in Senegal, Kenya, the DRC, and Sierra Leone. She received her Ph.D. in Electrical Engineering and Computer Science from MIT CSAIL and Woods Hole Oceanographic Institute Joint Program, focusing on scientific machine learning and Bayesian inference.

Talk Abstract:

Smallholder farmers in Africa would substantially benefit from better rainfall forecasts weeks to months in advance. This is particularly urgent in the face of changing climates and rainfall patterns, as evidenced by the recent extreme droughts and flooding across East Africa. Can AI-based forecasting and data assimilation techniques overcome predictability challenges in long-term rainfall forecasting and the sparsity of meteorological data on the African continent to enable this and other critical agricultural advisories? This talk will introduce the SheerWater Project, an initiative to develop open, use-driven, and localized benchmarks of weather and climate models, and to democratize the tools upon which the next generation of weather intelligence services for agriculture in Africa can be built.

Registration Link here

AfriClimate AI Community Town Hall (29/05/2024)

Date: 29 May 2024

Time: 16:00 - 17:00 GMT

AfriClimate AI is hosting its first Community Town Hall on Wednesday, 29 May 2024 🎉.

The Town Hall agenda includes:

A discussion on the next steps from our position paper titled "Leveraging AI for Climate Resilience in Africa: Challenges, Opportunities, and the Need for Collaboration"
Lightning talks from community members.

We invite all community members to join this session. If you would like to share your work and ideas with the community through a lightning talk, please complete the form linked below.

Registration Link: https://forms.gle/XHpThnvYpUsHYoYR6

Lightning talk submission form: https://tinyurl.com/2etyf6h9

Zoom Details:

Link: https://us06web.zoom.us/j/83709728315pwd=SKpbFPDvXum5NcszMaUBww4qIkndaB.1

Meeting ID: 837 0972 8315

Passcode: 416397

Global Prediction of Extreme Floods in Ungauged Watersheds (24/04/2024)

Speaker: Dr Grey Nearing

Date: 24th April, 2024

Time: 16:30 GMT

Grey Nearing

Grey Nearing is a Research Scientist at Google. He holds a PhD in Hydrology from the University of Arizona and has worked on global hydrological modelling at NASA, the National Center for Atmospheric Research, and NOAA. Before joining Google, he was a professor at the University of Alabama and the University of California Davis. Dr. Nearing and colleagues developed early implementations of machine learning flood forecasting models that are now used at Google and in the NOAA Next-Generation National Water Model.

Talk Abstract:

Floods pose a significant threat to communities across Africa, often leading to devastating consequences. The challenge of predicting floods is amplified by the lack of weather stations and hydrological data in many regions. Google has developed an AI-based river and inundation forecasting system and is partnering with governments and water agencies around the world to provide real-time flood alerts directly to individuals, communities, and NGOs through existing Google information channels like Maps, Search, and Android Alerts. This talk will cover the background, development, and impact of this effort.

Recording : youtu.be/xskF3ggRxog?si=WDjzAn-BsvJkq8k-