Hi there! I'm Subhankar
I'm an Applied Scientist Intern at Amazon (Bellevue, WA), developing Generative AI and Multimodal Fusion methods for Geospatial Anomaly Detection.
I'm also a Computer Science Ph.D. candidate at the University of Minnesota, Twin Cities.
I am advised by Professor Shashi Shekhar and am a member of the Spatial Computing Research Group. I also work with Professor Aneesh Subramanian.
I am a Graduate Assistant at iHARP, where we aim to reduce uncertainty in sea level rise predictions from ice sheet melt.
Upcoming Events
- I am excited to be a Student Organizer for the Scientific Modeling out of distribution (Scientific-Mood) ML Challenge and workshop.
Past Work and Events
- I was a Research Intern at the Oak Ridge National Laboratory in Spring 2025. I worked with Vision Transformers and Diffusion models for Super-resolution tasks.
- I co-organized the 2025 NSF HDR Machine Learning Challenge on Anomaly Detection. Pre-print of the paper describing the Anomaly Detection Challenge is out now. Check out our AAAI Workshop on Anomaly Detection in Scientific Domains.
- Recently, I worked on spatial pattern mining, including regional and taxonomy-aware co-location patterns with statistical guarantees.
Ph.D. thesis Projects
- Spatial variability-aware downscaling of climate variables using Generative Models
- Adaptive Climate Model Fusion strategies
- Spatio-temporal Anomaly Detection in climate variables
- Causal discovery of factors influencing climate variables