A Graph Attention Network Method Coupled With Geographical Laws for Land Mass Valuation Under Limited Samples: A Case Study of Shenzhen
Transactions in GIS · 2026-11 · 30 (7)
DOI: 10.1111/tgis.70462 ↗Kurz gefasst
Fachartikel in der Zeitschrift Transactions in GIS, online erschienen am 09.11.2026. Verfasst von Guang Li und 7 weiteren Autor:innen. Die Arbeit nennt 99 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Guangzhou Office of Philosophy and Social Science, Guangdong Provincial Department of Science and Technology.
Abstract (Originalsprache)
Constructing continuous urban land value surfaces is critical but consistently challenged by “limited samples.” Existing spatial interpolation and machine learning methodologies often fail due to over‐smoothing or insufficient theoretical integration. To address this, we propose Geo‐PHS‐GAT, a novel Graph Attention Network that systematically integrates the Laws of Geographical Proximity, Heterogeneity, and Similarity. The framework features three key innovations: a composite similarity metric for graph edge definition, a node feature vector fusing parcel attributes with neighborhood contexts, and a Transductive Learning strategy for information propagation from sparse labels. Applied to Shenzhen's residential land market, Geo‐PHS‐GAT outperformed nine baseline models, achieving the lowest RMSE in both Independent Out‐of‐Sample Validation (2943.07 RMB/m 2 ) and Leave‐One‐Out Cross‐Validation (7759.94 RMB/m 2 ). Mechanism ablation studies demonstrate that the synergistic coupling of all three geographical laws is essential for preventing value distortion, providing a robust tool for reliable land valuation in data‐scarce scenarios.
Förderung
- National Natural Science Foundation of China
- Guangzhou Office of Philosophy and Social Science
- Guangdong Provincial Department of Science and Technology
Zitieren
APA
Li, G., Yang, Y., Liu, Y., Yu, H., Lin, C., Weng, Q., Wang, Y., & Liu, Y. (2026). A Graph Attention Network Method Coupled With Geographical Laws for Land Mass Valuation Under Limited Samples: A Case Study of Shenzhen. Transactions in GIS, 30(7). https://doi.org/10.1111/tgis.70462
Vancouver
Li G, Yang Y, Liu Y, Yu H, Lin C, Weng Q, et al. A Graph Attention Network Method Coupled With Geographical Laws for Land Mass Valuation Under Limited Samples: A Case Study of Shenzhen. Transactions in GIS. 2026;30(7). doi:10.1111/tgis.70462
BibTeX
@article{Li2026,
author = {Li, Guang and Yang, Yuzhu and Liu, Ying and Yu, Haicong and Lin, Chuan and Weng, Qiulan and Wang, Yuan and Liu, Yilun},
title = {A Graph Attention Network Method Coupled With Geographical Laws for Land Mass Valuation Under Limited Samples: A Case Study of Shenzhen},
journal = {Transactions in GIS},
year = {2026},
volume = {30},
number = {7},
doi = {10.1111/tgis.70462}
}
EUVIMED