Harnessing AI Challenges for Earth Science Problems
From Space to Physics by Dr. Yiqun Xie
Tuesday, October 10, 2023 · 4 - 5 PM
Guest Speaker: Dr. Yiqun Xie, Assistant Professor in Geospatial Information Science at the University of Maryland
Presentation Title
Harnessing AI Challenges for Earth Science Problems: From Space to Physics
Abstract
Advances in deep learning have continued to set new expectations for
general tasks (e.g., computer vision, natural language processing) and
bring new potential to harness geospatial big data for Earth Science
problems. However, direct applications of deep learning often fall short
due to challenges posed by geospatial data, including spatial
heterogeneity/variability, sparse labels, etc. This talk will start with
two general frameworks that explicitly tackle the challenges with: (1) A
heterogeneity-aware framework that automatically recognize and handle
spatial variability during model training; and (2) A physics-informed
meta-learning framework that learns to select ensembles of physical
models to assist training and reduce the need of labeled data. Then, the
talk will show several examples of use-inspired AI for Earth Science,
with applications in ICESat-2 height interpolation, global ecosystem
model approximation, and label-free cloud masking. Finally, I will
discuss our recent work on a coincidental data discovery platform to
facilitate Arctic research.
Bio
Dr. Yiqun Xie is an Assistant Professor in Geospatial
Information Science at the University of Maryland. He received his PhD
in Computer Science at the University of Minnesota. One-size AI does not
fit all. His research addresses challenges facing AI for spatial data,
including heterogeneity, sparse training data, and locational bias. The
spatial-aware AI techniques developed by his group have received
multiple best paper awards from flagship conferences, including IEEE
International Conference on Data Mining, SIAM International Conference
on Data Mining, ACM SIGSPATIAL, and SSTD. His work was also highlighted
by the Great Innovative Ideas at the Computing Community Consortium,
Computing Research Association. His work is currently supported by the
NSF, NASA, Google, etc.
More about iHARP
To learn about iHARP and upcoming events, visit our site iharp.umbc.edu.