I am a PhD candidate in the Department of Geography at the University of Colorado Boulder, advised by Dr. Guofeng Cao at Spatiotemporal Pattern Analysis & Research Laboratory (STARlab).

My research focuses on developing spatially-explicit deep learning (GeoAI) methods to support uncertainty-aware knowledge discovery and decision-making in geospatial applications. I am also interested in the applications of large language models (LLMs), pre-trained foundation models, and physics-informed machine learning in geospatial data analysis and modeling.

I have a strong background in geospatial data analysis, machine learning, and remote sensing. I am passionate about advancing the field of GeoAI and contributing to the development of innovative solutions for geospatial challenges.

📖 Educations

• 2025 - now, PhD candidate, Department of Geography, University of Colorado Boulder
• 2021 - 2025, PhD student, Department of Geography, University of Colorado Boulder
• 2020 - 2021, PhD student, Department of Geosciences, Texas Tech University
• 2016 - 2020, Bachelor of Science in Geographic Information Science, Department of Resources and Environmental Sciences, Hubei University

🎖 Honors and Awards

• 2025 Jennifer Dinaburg Memorial Research Awards, Department of Geography, University of Colorado Boulder
• 2020 Distinguished Graduate Student Fellowship, Texas Tech University
• 2020 Top 10 Students, Hubei University
• 2019 & 2018 Scientific Research Scholarship, Hubei University

Travel Grants:

• 2025 Geography Graduate Student Travel & Research Funds, Department of Geography, University of Colorado Boulder
• 2024 ACM SIGSPATIAL 2024 Travel Grant, National Science Foundation
• 2023 Graduate School Student Travel Grant, University of Colorado Boulder

👨‍🏫 Teaching and Research Experiences

Research Assistant

Department of Geography, University of Colorado Boulder

• Fall 2021 - Fall 2023, Summer 2024, Summer 2025 (Advisor: Dr. Guofeng Cao)

Department of Geosciences, Texas Tech University

• Fall 2020 - Spring 2021 (Advisor: Dr. Guofeng Cao)

Teaching Assistant

Department of Geography, University of Colorado Boulder

• GEOG 4203: Geographic Information Science: Spatial Modeling (Fall 2025)
• GEOG 4023/5023: Advanced Quantitative Methods (Spring 2024 and Spring 2025)
• GEOG 3023: Statistics and Geographic Data (Fall 2024 and Spring 2026)

📝 Publications

(* indicates corresponding author)

Peer-Reviewed Journal Articles

• Li, G.*, Yu, Z., and Cao, G., 2026. The Perception-Precision Trade-Off in GeoAI. (Manuscript in Preparation)
• Li, G. and Cao, G.*, 2026. Neural Kriging: a scalable deep probabilistic framework for uncertainty-aware spatial interpolation under data sparsity. (Under Review)
• Wu, D.*, Srygley, R., Li, G., and Cao, G., 2026. Modeling the spatiotemporal dynamics of Mormon crickets across western United States using Bayesian species distribution models. (Under Review) [Code] | [Website]
• Li, G.* and Cao, G., 2026. Bayesian Geospatial Downscaling with Deep Generative Models. (In Revision)
• Li, G. and Cao, G.*, 2025. Generative adversarial models for extreme geospatial downscaling. International Journal of Applied Earth Observation and Geoinformation, 139, p.104541. [JAG] | [ArXiv] | [Code]
• Huang, L.*, Willis, M.J., Li, G., Lantz, T.C., Schaefer, K., Wig, E., Cao, G. and Tiampo, K.F., 2023. Identifying active retrogressive thaw slumps from ArcticDEM. ISPRS Journal of Photogrammetry and Remote Sensing, 205, pp.301-316. [ISPRS] | [Code]

Conference Proceedings with Full Paper Review

• Li, G. and Cao, G.*, 2024, October. Neural process for uncertainty-aware geospatial modeling. In Proceedings of the 7th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery (pp. 106-109). [Paper] | [Code]
• Li, G. and Cao, G.*, 2024, October. Statistical downscaling of climate datasets with deep generative model and Bayesian inference. In Proceedings of the I-GUIDE Forum 2024: Convergence Science and Geospatial AI for Environmental Sustainability. [Paper]
• Li, G.* and Cao, G., 2023, September. Bayesian Super-Resolution of Geospatial Datasets with Deep Generative Models. Paper presented at the Geospatial Knowledge Graphs and GeoAI Workshop, GIScience 2023, Leeds, UK. [Paper]

💬 Conference and Symposium Presentations

(Presenter is in the first position.)

• Li, G., Yu, Z., and Cao, G.: The Perception-Precision Trade-Off in GeoAI. AAG 2026. San Francisco, CA. March 2026
• Li, G. and Cao, G.: GeoAI for small geospatial data. AAG 2026. San Francisco, CA. March 2026
• Wu, D., Cao, G., Srygley, R. and Li, G.: High resolution mapping of Mormon cricket with a Bayesian spatiotemporal species distribution model. AGU 2025. New Orleans, LA. December 2025
• Cao, G. and Li, G.: GeoAI for small geospatial data. AAG 2025. Detroit, MI. March 2025
• Cao, G., Srygley, R., Li, G., Wu, D. and Branson, D.: GeoAI for Grasshopper Outbreak Risk Mapping in the Western United States. AGU 2024. Washington, D.C. December 2024
• Li, G. and Cao, G.: Neural process for uncertainty-aware geospatial modeling. ACM SIGSPATIAL 2024. Altanta, GA. October 2024
• Cao, G. and Li, G.: Statistical Downscaling of Climate Datasets with Deep Generative Model and Bayesian inference. I-GUIDE Forum 2024. Jackson, Wyoming. October 2024
• Cao, G. and Li, G.: Generative Adversarial Models for Extreme Downscaling of Geospatial Datasets. The 7th International Conference on Econometrics and Statistics (EcoSta 2024). Beijing Normal University, Beijing, China. July 2024
• Cao, G. and Li, G.: Generative Adversarial Models for Extreme Super-Resolution of Climate Datasets. Evaluating the Science of Geospatial AI. Harvard University, Cambridge, MA. May 2024
• Li, G. and Cao, G.: Bayesian Super-Resolution of Climate Datasets with Deep Generative Models. AAG 2024. Honolulu, HI. April 2024
• Cao, G. and Li, G.: Uncertainty Modeling in GeoAI. AAG 2024. Honolulu, HI. April 2024
• Li, G. and Cao, G.: Bayesian Super-Resolution of Geospatial Datasets with Deep Generative Models. Geospatial Knowledge Graphs and GeoAI Workshop, GIScience 2023. Leeds, UK. September 2023
• Li, G. and Cao, G.: Generative Adversarial Models for Extreme Super-Resolution of Climate Datasets. AAG 2023. Denver, CO. March 2023
• Cao, G. and Li, G.: A deep learning-based geostatistical framework for geospatial uncertainty modeling. AAG 2023. Denver, CO. March 2023

🏆 Professional Services and Memberships

Journal Reviewer for:

• Geographical Analysis
• Journal of Geophysical Research: Machine Learning and Computation
• International journal of applied earth observation and geoinformation

Professional Memberships:

• Association of American Geographers (AAG)
• Chinese Professional in Geographic Information Systems (CPGIS)
• ACM Special Interest Group on Spatial Information (SIGSPATIAL)