Mingke Erin Li

My research develops agentic GeoAI, in which large language model (LLM) agents plan, reason, and act over geospatial data grounded in Discrete Global Grid Systems (DGGS). A DGGS gives spatial operations a consistent frame across resolutions, which supports an operational Digital Earth.

I build geospatial intelligence frameworks that integrate multi-source spatial data with machine learning and AI agents, and I apply them to environmental and climate modelling, including methane emissions monitoring, flood risk assessment, and environmental resilience.

My research interests also include geospatial data science, spatial data infrastructure, and geospatial decision-support systems.

• Ph.D. in Geomatics Engineering, University of Calgary (2023)
• M.Sc. in Forestry, University of New Brunswick (2019)
• B.Sc. in Geographic Information Science, Nanjing Forestry University (2017)

I am looking for motivated MSc students to join my research group in the Department of Geography, Environment and Geomatics at the University of Guelph, starting in Fall 2027. Potential PhD opportunities may also be available depending on funding and research fit.

My research focuses on developing the next generation of Digital Earth and agentic GeoAI systems that can integrate heterogeneous geospatial data, reason reliably about space, and support environmental monitoring and decision-making.

Current and emerging research directions include:

🌍 Intelligent Digital Earth and Agentic GeoAI
🧠 Geospatial Reasoning with Large Language Models
🗺️ Discrete Global Grid Systems (DGGS) and Scalable Geospatial Data Infrastructure
🛰️ GeoAI for Earth Observation and Environmental Monitoring
⏱️ Spatio-Temporal Analysis, Change Detection, and Anomaly Monitoring

Applications span areas such as climate change, greenhouse gas emissions, flooding, wildfire, and other environmental challenges. Students will have opportunities to work across GeoAI, GIScience, Earth observation, spatial data engineering, and artificial intelligence, while contributing to open-source software, geospatial standards, and research with real-world environmental applications.

We will also explore AI-native research and development workflows. Students will have opportunities to work with frontier AI coding and research agents, such as Claude Code, OpenAI Codex, and emerging tools, to support software development, geospatial analysis, experiment automation, and reproducible research.

I welcome students with backgrounds in areas such as:

• Geography, Geomatics, or GIScience
• Computer Science, AI, or Machine Learning
• Remote Sensing and Earth Observation
• Environmental Science
• Statistics, Data Science, or related quantitative disciplines

Depending on the project, relevant experience may include programming, GIS and spatial analysis, machine learning, remote sensing, environmental modeling, cloud computing, or large language models. I especially welcome applicants who are enthusiastic about conducting research, keeping pace with rapidly changing technologies, exploring new ideas, and learning new skills.

Interested applicants are encouraged to email me (mingkeli@uoguelph.ca) with:

• Curriculum Vitae
• Academic transcripts
• A brief description of research interests and how they connect with the topics above
• Relevant publications, research projects, GitHub profile, or other examples of previous work, if available

Li, M.E., Wang, J., & Liang, S.H.L. (2026). GridMind: A DGGS-Grounded Multi-Agent System for Spatial Reasoning. In Proceedings of the 34th ACM International Conference on Advances in Geographic Information Systems (SIGSPATIAL '26). https://doi.org/10.1145/3841645.3843111
Wang, J., Li, M.E., & Liang, S.H.L. (2026). GeoScout: A Conversational Agentic GeoAI Framework for Spatial Decision Support in Methane Leak Detection and Repair. In Proceedings of the 9th ACM SIGSPATIAL International Workshop on GeoSpatial Simulation (GeoSim 2026). https://doi.org/10.1145/3849737.3849835
Li, M.E., Gao, M., & Liang, S.H.L. (2026). Harmonized Global-to-Regional Gridded Methane Inventories in a Discrete Global Grid Framework. ISPRS International Journal of Geo-Information, 15(10), 466. https://doi.org/10.3390/ijgi15100466
Li, M.E., & Liang, S.H.L. (2026). Natural Language to DGGS-Aware Methane Insights with a Multi-LLM-Agent Framework. In Proceedings of Spatial Knowledge and Information Canada 2026. https://doi.org/10.5281/zenodo.20598496
Li, M.E., & Liang, S.H.L. (2026). Enabling a Digital Earth for Methane Emissions Management with Equal-Area Discrete Global Grids. International Journal of Digital Earth, 19(1), 2607210. https://doi.org/10.1080/17538947.2025.2607210
Liao, C., Engwirda, D., Cooper, M., Li, M., & Fang, Y. (2025). Discrete Global Grid System-based flow routing datasets in the Amazon and Yukon basins. Earth System Science Data, 17(5), 2035–2062. https://doi.org/10.5194/essd-17-2035-2025
Li, M., Tousignant, C., Chaudhuri, C., & Chabbouh, A. (2024). Utilizing serverless framework for dynamic visualization and operations in geospatial applications. International Journal of Digital Earth, 17(1), 2392835. https://doi.org/10.1080/17538947.2024.2392835
Liu, J., Li, J., Qiao, L., Li, M., Stefanakis, E., Zhao, X., Huang, Q., Wang, H., & Zhang, C. (2024). QuadGridSIM: A quadrilateral grid-based method for high-performance and robust trajectory similarity analysis. Transactions in GIS, 28(1), 83–107. https://doi.org/10.1111/tgis.13126
Li, M., McGrath, H., & Stefanakis, E. (2022). Multi-scale Flood Mapping under Climate Change Scenarios in Hexagonal Discrete Global Grids. ISPRS International Journal of Geo-Information, 11(12), 627. https://doi.org/10.3390/ijgi11120627
Li, M., McGrath, H., & Stefanakis, E. (2022). Multi-resolution topographic analysis in hexagonal Discrete Global Grid Systems. International Journal of Applied Earth Observation and Geoinformation, 113, 102985. https://doi.org/10.1016/j.jag.2022.102985
Li, M., McGrath, H., & Stefanakis, E. (2022). Geovisualization of Hydrological Flow in Hexagonal Grid Systems. Geographies, 2(2), 227–244. https://doi.org/10.3390/geographies2020016
Li, M., McGrath, H., & Stefanakis, E. (2021). Integration of Heterogeneous Terrain Data into Discrete Global Grid Systems. Cartography and Geographic Information Science, 48(6), 546–564. https://doi.org/10.1080/15230406.2021.1966648
Li, M., Stefanakis, E., & McGrath, H. (2020). National Terrain Data Management on Discrete Global Grids in Canada. In AutoCarto 2020.
Li, M., & Stefanakis, E. (2020). Geo-feature Modeling Uncertainties in Discrete Global Grids: A Case in Canada. Geomatica, 74, 175–195. https://doi.org/10.1139/geomat-2020-0011
Li, M., & Stefanakis, E. (2020). Geospatial Operations of Discrete Global Grid Systems – A Comparison with Traditional GIS. Journal of Geovisualization and Spatial Analysis, 4(2), 26. https://doi.org/10.1007/s41651-020-00066-3