Skip to main content
UMD College of Behavorial & Social Sciences UMD College of Behavorial & Social Sciences
MENU

Topbar Menu

  • About Us
  • People
  • Alumni and Giving
  • Diversity
  • Undergraduate
    • Prospective Students
    • Courses & Facilities
    • Advising
    • Special Programs
    • Graduation
    • Geography Club
  • Graduate
    • Prospective Ph.D. Students
    • Graduate Courses
    • Graduate Student Publications
    • Graduate Student Awards
    • Graduate Students
    • Master of Science and Graduate Certificate Programs
    • Combined BS/MS Program
  • Research
    • Research Areas
      • Geospatial-Information Science and Remote Sensing
      • Human Dimensions of Global Change
      • Land Cover and Land Use Change
      • Carbon, Vegetation Dynamics and Landscape-Scale Processes
    • Centers
      • Center for Geospatial Information Science
      • International Center for Innovation in Geospatial Analytics & Earth Observation
  • High School Hub
    • Program Overview
    • High School Awards
    • High School Internship Program
    • GIS Day
  • Resources
    • Graduate Student Organization
    • Student Life
    • Graduate School
    • Responsible Conduct of Research
    • Emergency Preparedness
    • Job Opportunities
    • Graduation
Search

Main navigation

  • Undergraduate
    • Prospective Students
    • Courses & Facilities
    • Advising
    • Special Programs
    • Graduation
    • Geography Club
  • Graduate
    • Prospective Ph.D. Students
    • Graduate Courses
    • Graduate Student Publications
    • Graduate Student Awards
    • Graduate Students
    • Master of Science and Graduate Certificate Programs
    • Combined BS/MS Program
  • Research
    • Research Areas
      • Geospatial-Information Science and Remote Sensing
      • Human Dimensions of Global Change
      • Land Cover and Land Use Change
      • Carbon, Vegetation Dynamics and Landscape-Scale Processes
    • Centers
      • Center for Geospatial Information Science
      • International Center for Innovation in Geospatial Analytics & Earth Observation
  • High School Hub
    • Program Overview
    • High School Awards
    • High School Internship Program
    • GIS Day
  • Resources
    • Graduate Student Organization
    • Student Life
    • Graduate School
    • Responsible Conduct of Research
    • Emergency Preparedness
    • Job Opportunities
    • Graduation

Search our site:

SDM'23 Best Application Paper Award: Method Improves Prediction of Stream Baseflow using Physics-Guided Meta-Learning

Breadcrumb

  • Home
  • Featured Content
  • SDM'23 Best Application Paper Award: Method Improves Prediction of Stream Baseflow Using Physics-Guided Meta-Learning
Yiqun Xie headshot

Assistant Professor Yiqun Xie and coauthors received the Best Application Paper Award at the SIAM International Conference on Data Mining (SDM) on April 27 to 29, 2023, for their paper titled “Physics-Guided Meta-Learning Method in Baseflow Prediction over Large Regions” (Authors: Shengyu Chen, Yiqun Xie, Xiang Li, Xu Liang, and Xiaowei Jia).*

Deep learning has achieved promising success in computer vision and natural language processing tasks. Recent large language models such as ChatGPT also gained a tremendous amount of attention with their versatility and efficiency in performing human tasks. However, the success is still very limited in scientific domains where data are scarce and hard to collect.

This paper tackles the problem of baseflow prediction. Baseflow is the portion of the stream flow that is sustained between rainfall events and during dry periods, which is essential for ecosystem functioning. Due to the difficulty in collecting real observations, various physics-based models have been developed for baseflow estimation under different assumptions. In practice, however, it is often challenging to know which assumption – or if any existing assumption – aligns with the real complex environmental condition.

This work develops a physics-guided meta-learning framework to incorporate diverse knowledge from multiple physics-based models to enhance the training of the deep learning model, using limited observations. In particular, the approach learns to select a mixture of physics-based models to guide the training for different environment conditions. Experiment results in 60 river basins showed superior performance of the new approach compared to the other methods.

The paper shows the exciting potential of meta-learning-based integration between data-driven and physical models. The team will continue to explore new techniques along this direction through their collaborative projects from NSF and NASA.

*By both selectivity and impact, premier computing conferences are often preferred to premier journals (Statement by CRA, National Academies Press).

Photo: Yiqun Xie. Courtesy of Xie.

Published on Mon, 05/15/2023 - 09:20

College of Behavorial & Social Sciences
  • Facebook
  • Twitter
  • Instagram
  • YouTube
  • LinkedIn
  • Zenfolio

Department of Geographical Sciences

2181 Samuel J. LeFrak Hall, 7251 Preinkert Drive,
University of Maryland, College Park, MD 20742
Phone: 301-405-4050

Join Our Newsletter

Contact Us

Links
  • UMD Land Acknowledgement
  • UMD Staff Directory
  • Give to GEOG
  • UMD Web Accessibility
  • Alumni
© 2025 College of Behavorial & Social Sciences. All Rights Reserved.
Login