The climate crisis is one of the most pressing challenges facing our societies. While mitigating further climate change remains crucial — e.g. through the conservation of natural carbon stocks and biodiversity hot spots — the adaptation to new climate conditions with increased risks of flooding, heat waves, and wildfires is becoming inevitable. Machine learning (ML) promises advanced analytical tools to better understand climate processes and to monitor biodiversity and vegetation health.
The focus of the AICC workshop will be on identifying open problems in the domain of Climate and Conservation, but also on hearing success stories, where artificial intelligence (AI) made a positive impact on our planet. Hence, this workshop aims to bring domain experts alongside ML experts to discuss open challenges in their work and to inspire the ML audience to contribute to these urgent challenges.
The following questions will guide the program of the AICC workshop:
What are the open problems in climate and conservation? (for modellers, practitioners)
What is actually needed from AI researchers?
How can AI researchers contribute and help practitioners make better decisions?
How can AI help to make better decisions?
About the EurIPS conference: EurIPS is a European conference officially endorsed by NeurIPS, the most prestigious AI conferences globally; EurIPS showcases cutting-edge research papers that shape the future of artificial intelligence; EurIPS workshops are independent of NeurIPS workshops; the ELLIS UnConference is the kick-off event of EurIPS and welcomes all participants to join.
More information on the EurIPS website: eurips.cc
Philippe Ciais
LCSE
Sagar Vaze
Mistral AI
Verena Griess
ETH Zürich
Natalie Ahlstrand
University of Copenhagen
Drew Purves
Google DeepMind
Workshop format
The AICC workshop collocated with EurIPS invites researchers to present and discuss their recent work at the intersection of climate and conservation science and machine learning. We encourage the submission of novel unpublished work and recently published work. All accepted papers will be presented as a poster. Authors can express their interest in presenting their work as an oral talk, which will be evaluated by the Program Committee.
Submission guidelines
Novel unpublished work should be formatted using the single column NeurIPS template with max. 4 pages (excluding references). The submission will be single-blind and non-archival, which means that we will not formally publish the submissions.
Published papers can be submitted by providing a URL to the online PDF (no reformatting needed).
Submission portal: [COMING SOON]
Timeline
Submission deadline: October 10, 2025
Notification of acceptance: October 31
Camera ready poster submission: November 28
Scope
The scope of topics relevant for this workshop is broad. We are interested in discussing both methodological advances and applied ML projects. Relevant topics to the workshop include but are not limited to:
Applications of AI:
Carbon flux modeling
species distribution modeling
biodiversity monitoring
land cover and vegetation traits mapping
weather forecasting
Physical process understanding:
Hybrid modeling
ML-based emulators
Climate predictions
Multi-modal learning:
Data fusion
Acoustic sensors
Remote sensing
Climate data
Recognition:
Fine-grained recognition
Open world recognition
Representation learning:
Supervised learning
Weakly supervised learning
Self-supervised learning
Joakim B. Haurum
University of Southern Denmark
Nico Lang
University of Copenhagen
Oisin Mac Aodha
University of Edinburgh
Lynn H. Kaack
Hertie School
Ankit Kariryaa
University of Copenhagen
Isabelle Tingzon
The World Bank
Lucia Gordon
Harvard University
Aleksis Pirinen
RISE Research Institutes of Sweden