Building-Level Population Estimation Method Using a Bayesian-Informed Hierarchical Learning Model
ISPRS International Journal of Geo-Information · 12.06.2026 · 15 (6) · 264
DOI: 10.3390/ijgi15060264 ↗Kurz gefasst
Fachartikel in der Zeitschrift ISPRS International Journal of Geo-Information, online erschienen am 12.06.2026. Verfasst von Jin Deng und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundamental Research Funds for the Central Universities, National Key Research and Development Programme of China.
Abstract (Originalsprache)
Although fine-grained spatial knowledge of the urban population distribution is fundamental for effective urban management, traditional census data lack sufficient resolution. Current disaggregation methods often struggle to probabilistically fuse heterogeneous data, such as noisy mobile signaling and building attributes, while ensuring hierarchical consistency between micro-level predictions and macro-level ground truth. To address these gaps, this study proposes a Bayesian-informed hierarchical learning (BIHL) model framework for building-level population estimation. The methodology integrates three distinct layers: (1) a data-driven prior model using a LightGBM ensemble to generate initial probabilistic estimates and uncertainty weights; (2) an enhanced neural network posterior estimator featuring a multi-branch architecture—incorporating Zone Bias Embedding and Zone Interaction networks—to capture non-linear urban dynamics and spatial heterogeneity; and (3) a constrained optimization layer utilizing a hierarchical loss function that enforces strict consistency between aggregated building estimates and official census data through dynamic curriculum learning. Through empirical validation in Haidian District, Beijing, it is demonstrated that the BIHL framework significantly outperforms baseline models (MLR, Random Forest, and LightGBM), achieving a Mean Absolute Percentage Error (MAPE) of 11.36%. This study confirms that incorporating building-level spatial locations and residential categories is vital for mitigating “spatial smoothing” and systematic under-prediction in high-density areas. This framework provides a robust, high-fidelity solution for generating residential population layers, which are essential for city planning.
Förderung
- Fundamental Research Funds for the Central Universities
- National Key Research and Development Programme of China
Zitieren
APA
Deng, J., Deng, Y., Liu, J., Zhu, Y., Yang, G., & Hu, Z. (2026). Building-Level Population Estimation Method Using a Bayesian-Informed Hierarchical Learning Model. ISPRS International Journal of Geo-Information, 15(6), 264. https://doi.org/10.3390/ijgi15060264
Vancouver
Deng J, Deng Y, Liu J, Zhu Y, Yang G, Hu Z. Building-Level Population Estimation Method Using a Bayesian-Informed Hierarchical Learning Model. ISPRS International Journal of Geo-Information. 2026;15(6):264. doi:10.3390/ijgi15060264
BibTeX
@article{Deng2026,
author = {Deng, Jin and Deng, Ying and Liu, Jianfeng and Zhu, Yadi and Yang, Guanhua and Hu, Zhou},
title = {Building-Level Population Estimation Method Using a Bayesian-Informed Hierarchical Learning Model},
journal = {ISPRS International Journal of Geo-Information},
year = {2026},
volume = {15},
number = {6},
pages = {264},
doi = {10.3390/ijgi15060264}
}
EUVIMED