ABHNet
An Attention-Based Deep Learning Framework for Building Height Estimation Fusing Multimodal Data
Bibliographic Data
| ID | 22031280 |
|---|---|
| Authors | Zhanwu Zhuang (0009-0000-2579-6322, Chinese Academy of Sciences), Ning Li (0000-0003-4098-1838, Nanjing University of Posts and Telecommunications), Na Li (0000-0002-1103-6864, Nanjing University of Posts and Telecommunications), Weiye Xiao (0000-0003-1772-6572, Chinese Academy of Sciences, corresponding author), Jiawei Wu (0000-0002-3702-292X, Chinese Academy of Sciences), Lei Zhou (0000-0003-0741-5703, Nanjing University of Posts and Telecommunications) |
| Year | 2026 |
| Volume | 15 |
| Issue | 4 |
| Pages | 146 |
| Publication date | 2026-03-26 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | ISPRS International Journal of Geo-Information (JOURNAL) |
| Journal identifiers | ISSN: 2220-9964 • E-ISSN: 2220-9964 |
| Publisher | MDPI AG (PUBLISHER • IT) |
| DOI | 10.3390/ijgi15040146 |
| OpenAlex | W7141068775 |
| Language | EN |
| References cited | 36 |
Building height is a key indicator of vertical urbanization and urban morphological complexity, yet accurately mapping building height at fine spatial resolution and large spatial scales remains challenging. This study proposes an attention-based deep learning framework (ABHNet) for building height estimation at a 10 m spatial resolution by integrating multi-source remote sensing data and socioeconomic information. The model jointly exploits Sentinel-1 synthetic aperture radar data, Sentinel-2 multispectral imagery, and point of interest (POI) data. The proposed framework is evaluated in Shanghai, a megacity with dense and vertically complex urban structures, using Baidu Maps-derived building height data as reference information. The results demonstrate that the proposed method achieves accurate building height estimation, with a root mean squared error (RMSE) of 3.81 m and a mean absolute error (MAE) of 0.96 m for 2023, and an RMSE of 3.30 m and an MAE of 0.78 m for 2019, indicating robust performance across different time periods. Also, this model is applied in two other cities (Changzhou and Guiyang) and the results indicate good performance. In addition, the expandability of the framework is examined by incorporating higher-resolution ZY-3 imagery, for which the spatial resolution was increased to 2.5 m, highlighting the potential extension of the model to heterogeneous data sources. Overall, this study demonstrates the effectiveness of attention-based deep learning and multimodal data fusion for large-scale and fine-resolution building height estimation using open-source data
Convolutional neural network · Deep learning · Estimation · Image resolution · Mean squared error · Megacity · Multispectral image · Synthetic aperture radar · Remote Sensing and LiDAR Applications · Remote-Sensing Image Classification · Synthetic Aperture Radar (SAR) Applications and Techniques
The dimensions of global urban expansion
Investigating the effects of 3D urban morphology on the surface urban heat island effect in urban functional zones by using high-resolution remote sensing data
D-GloBFP
A first Chinese building height estimate at 10 m resolution (CNBH-10 m) using multi-source earth observations and machine learning
Hierarchical semantic cognition for urban functional zones with VHR satellite images and POI data
Google Earth Engine
Quantifying the influence of 2D and 3D urban morphology on the thermal environment across climatic zones
Generating megacity-scale building height maps without DGNSS surveyed GCPs
Measuring the Stringency of Land Use Regulation
Trends in urban land expansion, density, and land transitions from 1970 to 2010
| Highly cited | No |
|---|