Theme:  A collaborative effort among three of the five NSF HDR institutes. Each HDR institute presented an ‘Anomaly Detection‘ problem to answer questions using complex datasets in polar science, astrophysics, ecology, and evolution. This challenge was geared towards bringing awareness to the broader community about the complexity of using deep learning for this problem since the availability of well-labeled datasets or training through systematic procedures, such as masking, is often insufficient.

 

Learn More About The Three Challenges:

 

---

Kick-off Hackathon Events

Approximately 10 local hackathon events to kick-off the 1st ML challenge were organized at several institutions such as University of Maryland, Baltimore County, University of Washington, and the University of California, San Diego.

AAAI 2025 Workshop and Challenge on Anomaly Detection in Scientific Domains

The workshop was co-located with The 39th Annual AAAI Conference on Artificial Intelligence. To learn more, visit https://www.nsfhdr.org/AAAI-workshop

Scholarship

• NSF HDR Machine Learning Challenge (A FAIR Perspective)

Dr. Philip Harris (Director, A3D3), Massachusetts Institute of Technology (HDR Ecosystem)

FAIR in ML, AI Readiness, & Reproducibility (FARR) Workshop, AGU Conference Center in Washington D.C. (October 9 – 10, 2024)

• Invited Talk at a ML Commons virtual event held in February 2025.

K-12 Connection

• Hack The Nest 2025 

iHARP’s Challenge: “Machine Learning to Predict Anomalous Flooding Events.”

iHARP Focused Outcomes: Proof-of-concept App; Virtual High School Hackathon Showcase

 

---

The ML challenge was led by faculty, post-doctoral, and student researchers within the HDR community from the several academic institutions:

 

 

 

---