Spatial evolution between snapshots
EvolutionHow can we infer the hidden transition process between two observed geographic distributions or spatial network states?
PhD candidate in Geography, Environment & Society at the University of Minnesota, Twin Cities.
Before I came to UMN, I obtained a B.S. in Geographic Information Science from China University of Geosciences, Beijing, and studied in the Spatial Data Science program at the Spatial Sciences Institute of the University of Southern California. My research interest lies in detecting, inferring, and interpreting spatial evolutionary processes, using current machine learning or deep learning methods.
“Πάντα ῥεῖ — Everything flows.” Heraclitus
How can we infer the hidden transition process between two observed geographic distributions or spatial network states?
How do collective movement patterns reveal mesoscopic structures and changing regional relationships?
How can machine learning and deep learning help detect, interpret, and explain spatio-temporal change?
Infer transition processes between observed spatial distributions using a network perspective.
Reveal mesoscopic structure between snapshots of spatial networks through collective flow patterns.
Use digital footprints and spatial data to depict activity spaces and urban movement behavior.
Apply spatial data science to mobility, inequality, health, and environmental dynamics.
International Journal of Geographical Information Science, 39(1), 86-117.
International Journal of Geographical Information Science, 40(4), 918-946.
arXiv:2603.19537 [physics.soc-ph].
In Proceedings of the 8th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery (pp. 45-48).
College of Liberal Arts, University of Minnesota
American Association of Geographers
American Association of Geographers
Here are some photos I have taken during travel, city walks, and everyday moments.
For research conversations, collaboration, or a current CV, email Zhongfu Ma through the University of Minnesota address below.