ML Challenges

HDR Machine Learning Challenges invite participants to tackle real-world scientific problems using machine learning. Each challenge focuses on cutting-edge areas, encouraging models to go beyond their training data and address critical, unsolved questions. Whether you’re an experienced researcher or an aspiring ML practitioner, these challenges offer the opportunity to innovate, contribute to science, and showcase your skills.

Scientific-Mood FAIR Challenge - ML Challenge 2025 (Year 2)

Open

Submissions Open September 18, 2025

                Submissions Close
                January 31, 2026
            

Winners Announced Spring 2026

FARR Workshop April 8-9, 2026

Submissions Open
Submissions Close
Winners Announced
FARR Workshop

The HDR ML Challenge program is hosting its second FAIR challenge, this year presenting three scientific benchmarks for modeling out of distribution in three critical areas: Neural Forecasting, Climate Prediction using Ecological Data, and Coastal Flooding Prediction over time. In this challenge, we ask models to extend beyond their training by performing out of domain extrapolation to practical critical scientific process that have not yet been well studied.

Learn more

Anomaly Detection Challenge - ML Challenge 2024 (Year 1)

Archived

September 9, 2024 – January 31, 2025

The machine learning anomaly detection challenge invited participants to uncover unexpected patterns using machine learning in three different scientific setups: discovering hybrid butterfly species, anomaly detection in gravitational-wave astronomy, and identifying water level irregularities. Winners were recognized at the Anomaly Detection in Scientific Domains AAAI Workshop.

View archive