I am a spatial data scientist interested in advancing statistical and machine learning models to understand human behavior across different spatial contexts. I am the developer of GeoShapley, one of the primary developers of Multi-scale Geographically Weighted Regression (MGWR) and a core developer of Python Spatial Analysis Library (PySAL). My current work centers on developing spatially explicit machine learning models and improving their interpretability and explainability.
Members
SDSC Faculty
Biography
Selected Publications
5- DOIAnnals of the American Association of Geographers114(7), 1365-1385.
GeoShapley: A game theory approach to measuring spatial effects in machine learning models.
Li, Z. (2024)
- DOITravel Behaviour and Society31, 284-294.
Leveraging explainable artificial intelligence and big trip data to understand factors influencing willingness to ridesharing.
Li, Z. (2023)
- DOICRC Press.194
Multiscale geographically weighted regression: Theory and practice.
Fotheringham, A. S., Oshan, T. M., & Li, Z. (2023).
- DOIAnnals of the American Association of Geographers113(10), 2269-2286
Measuring the unmeasurable: Models of geographical context
Fotheringham, A. S., & Li, Z. (2023)
- DOIComputers, Environment and Urban Systems96, 101845.
Extracting spatial effects from machine learning model using local interpretation method: An example of SHAP and XGBoost.
Li, Z. (2022)