Spatial process-based transfer learning for prediction problems
Journal of Geographical Systems · 2025-01 · 27 (1) · 147-166
DOI: 10.1007/s10109-024-00455-y ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Geographical Systems, online erschienen am 31.01.2025. Verfasst von Daisuke Murakami und 2 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Japan Society for the Promotion of Science.
Abstract (Originalsprache)
Although spatial prediction is a versatile tool for urban and environmental monitoring, the predictive accuracy is often unsatisfactory when limited samples are available from the study area. The present study was conducted to improve the accuracy in such cases through transfer learning, which uses larger datasets from external areas. Specifically, we proposed the SpTrans method, which pre-trains map patterns for each area using spatial process models. These patterns are then used in transfer learning to distinguish between unique patterns in the study area and common patterns across areas. The performance of the proposed SpTrans method was examined using land price prediction, with empirical results suggesting that the model achieves higher prediction accuracy than conventional learning, which does not explicitly consider local spatial dependence.
Förderung
- Japan Society for the Promotion of Science
Zitieren
APA
Murakami, D., Kajita, M., & Kajita, S. (2025). Spatial process-based transfer learning for prediction problems. Journal of Geographical Systems, 27(1), 147-166. https://doi.org/10.1007/s10109-024-00455-y
Vancouver
Murakami D, Kajita M, Kajita S. Spatial process-based transfer learning for prediction problems. Journal of Geographical Systems. 2025;27(1):147-166. doi:10.1007/s10109-024-00455-y
BibTeX
@article{Murakami2025,
author = {Murakami, Daisuke and Kajita, Mami and Kajita, Seiji},
title = {Spatial process-based transfer learning for prediction problems},
journal = {Journal of Geographical Systems},
year = {2025},
volume = {27},
number = {1},
pages = {147--166},
doi = {10.1007/s10109-024-00455-y}
}
EUVIMED