25/04/2025

Climate and Artificial Intelligence: for the first time in the Global South, Climate Informatics arrives in Brazil organized by FGV EMAp

The conference will take place from April 28 to 30 at the FGV Cultural Center in Rio de Janeiro, bringing together international researchers who are developing data-driven solutions to predict and mitigate the effects of climate change.

Image1

As the nation home to the world’s largest tropical rainforest and one of the richest biodiversities on the planet, Brazil plays a strategic role not only in environmental preservation but also in the production of scientific knowledge about the climate. It is in this context that the country hosts, for the first time, the International Conference on Climate Informatics (CI2025) taking place from April 28 to 30 in Rio de Janeiro. Organized by the School of Applied Mathematics at Fundação Getulio Vargas (FGV EMAp), in collaboration with the Climate Informatics committee and with support from IBM Research Brazil, the event brings together leading experts in climate and artificial intelligence (AI) to discuss methods with direct applications in food security, disaster prediction, public policy, and environmental sustainability. For the scientific community, it is a unique opportunity for exchange, and for society, it represents progress in data-driven solutions to real-world problems.

“It is significant for FGV EMAp to co-organize the first edition of Climate Informatics outside the traditional circuit. This highlights the leading role of our School and of Brazilian science at the intersection of AI and climate change—urgent topics for our region,” says Dário Oliveira, conference coordinator and researcher at FGV EMAp.

The proposal to host the conference in Brazil stems from a strong collaboration between FGV EMAp and IBM Research, which has produced joint papers, patents, and solutions on extreme climate events, risk modeling, and AI applied to climate science.

According to researcher Ricardo Barros Lourenço, a member of the event’s organizing committee, Climate Informatics has become an essential conference by bringing together, in a common space, computer scientists and experts from physical sciences such as meteorology, climatology, hydrology, and remote sensing.

“CI fosters a more focused interdisciplinary dialogue, which is especially important since there is still a lack of integration between computer science and geosciences,” emphasizes Ricardo, who also serves as Communications Editor for Environmental Data Science, an academic journal from Cambridge University Press.

For researchers, the event has served as a true catalyst for innovation, especially on topics such as predictive modeling, learning from sparse data, AI-based simulations, and multisensor data integration.

A notable example was the 2024 edition in the UK, when researchers from DeepMind first presented the GenCast model, which went on to outperform the then most accurate operational weather model, ENS, from the European Centre for Medium-Range Weather Forecasts (ECMWF). The final paper was only published in 2025, in the journal Nature.

“Having access to this kind of result before publication allows research groups to critically discuss advancements, identify limitations, and adjust their approaches in real time. This accelerates scientific progress without compromising reliability,” says Ricardo.

A CI 2025 ocorre no Centro Cultural da FGV, no Rio de Janeiro, contando com uma programação que inclui sessões sobre oceanografia, hidrologia, sensoriamento remoto, tempo e clima, impactos sociais e estudos regionais | Imagem: FGV

CI 2025 will take place at the FGV Cultural Center in Rio de Janeiro, with a program that includes sessions on oceanography, hydrology, remote sensing, weather and climate, social impacts, and regional studies | Image: FGV

Program Highlights

This year’s program was designed to reflect the challenges and opportunities of applied climate science. One of the most anticipated panels is on weather modeling and practical applications, which traditionally features the most significant advances in the field and will be held on Tuesday, April 29.

On the morning of Wednesday, April 30, the “Societal Impacts” panel will feature the presentation “A Multimodal AI Model for Understanding the Climate-Driven Insurance Crisis across the U.S.,” which introduces a model to predict climate risk in insurance premiums and non-renewal rates. The initiative aims to both diversify the insurance market and support public managers in mitigating climate-induced financial risks.

In addition to technical sessions, CI will include tutorials and workshops aimed at training young researchers and spreading cutting-edge tools for use in various climate contexts.

As in previous editions, CI2025 will be held in a hybrid format, with both in-person and online participation, expanding its reach and promoting values such as open science, interdisciplinarity, and collaborations that transcend institutional and geographic boundaries.

Climate Informatics is centered on advancing climate science through state-of-the-art methods in Data Science and Scientific Computing | Image: National Oceanic and Atmospheric Administration

Climate Informatics is centered on advancing climate science through state-of-the-art methods in Data Science and Scientific Computing | Image: National Oceanic and Atmospheric Administration

Registration

Undergraduate students interested in participating in the International Conference on Climate Informatics (CI2025) can choose the online option, priced at R$750.00, or attend in person for R$950.00. For professionals, registration fees are R$1,950.00 for online participation and R$2,250.00 for in-person attendance. Payments should be made through the FGV Eventos platform using Visa or Mastercard credit cards.

Climate Informatics 2025

When: April 28 to 30, 2025

Where: FGV Cultural Center – Praia de Botafogo, 190 – Rio de Janeiro, RJ

Important links: [Registration] | [Program] | [Official Event Website]

Questions? Contact: ci2025@climateinformatics.com.br

A A A
High contrast

Nosso website coleta informações do seu dispositivo e da sua navegação e utiliza tecnologias como cookies para armazená-las e permitir funcionalidades como: melhorar o funcionamento técnico das páginas, mensurar a audiência do website e oferecer produtos e serviços relevantes por meio de anúncios personalizados. Para mais informações, acesse o nosso Aviso de Cookies e o nosso Aviso de Privacidade.