Graph-Based Unsupervised Learning for Spatial Data
Spatial formulations for defining spatially-contiguous regions in geospatial data
References
2023
- Probabilistic Regionalization via Evidence Accumulation with Random Spanning Trees as Weak Spatial RepresentationsGeographical Analysis, 2023
2021
- A quantitative comparison of regionalization methodsInternational Journal of Geographical Information Science, 2021
2018
- SKATER-CON: Unsupervised regionalization via stochastic tree partitioning within a consensus framework using random spanning treesIn Proceedings of the 2nd ACM SIGSPATIAL international workshop on AI for geographic knowledge discovery, 2018