Journal article
Explainable Mapping of the Irregular Land Use Parcel With a Data Fusion Deep-Learning Model
IEEE transactions on geoscience and remote sensing, Vol.63, pp.1-15
01/01/2025
DOI: 10.1109/TGRS.2025.3542628
Abstract
Real land parcels exhibit high variability in size and complexity. Existing deep learning-based models often rely on grids or simple resampling to ensure consistent input sizes, which makes it hard to accurately represent real land distribution while preserving information. Current research also lacks the interpretability of model recognition and data fusion. In order to address these limitations, this article introduces the irregular parcel classification model (IPCM), a novel multisource fusion approach. IPCM uses Poisson disk sampling to regularize samples while retaining essential information. IPCM's interpretability is analyzed by exploring its classification process and data fusion using gradient-weighted class activation mapping++ (Grad-CAM++) and Explainable Boosting. The results highlight the model's attention to different functional categories in multimodal data and reveal the phenomenon of poorer fusion results for certain categories due to information mismatch during the fusion process; furthermore, the model optimizes data fusion weight to enhance the correct information to mitigate the negative impact when multisource data information has excessive mismatch. Optimized IPCM achieves 0.892 test accuracy and 0.862 Kappa on irregular parcels. This research can serve as an important reference for high-precision land use mapping and understanding the data fusion process.
Details
- Title: Subtitle
- Explainable Mapping of the Irregular Land Use Parcel With a Data Fusion Deep-Learning Model
- Creators
- Yao Yao - China University of GeosciencesRonghui Gao - China University of GeosciencesHao Wu - China University of GeosciencesAnning Dong - China University of GeosciencesZhihui Hu - China University of GeosciencesYueheng Ma - China University of GeosciencesQingfeng Guan - China University of GeosciencesPeng Luo - Massachusetts Institute of Technology
- Resource Type
- Journal article
- Publication Details
- IEEE transactions on geoscience and remote sensing, Vol.63, pp.1-15
- DOI
- 10.1109/TGRS.2025.3542628
- ISSN
- 0196-2892
- eISSN
- 1558-0644
- Publisher
- IEEE
- Number of pages
- 15
- Grant note
- 20228670 / Alibaba Group through Alibaba Innovation Research Program 2020B1212030009 / Guangdong-Hong Kong-Macau Joint Laboratory Program 24H00012 / Japan Society for the Promotion of Science (JSPS) KAKENHI; Ministry of Education, Culture, Sports, Science and Technology, Japan (MEXT); Japan Society for the Promotion of Science; Grants-in-Aid for Scientific Research (KAKENHI) KF-2023-08-04 / Open Fund of Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Natural Resources 42471491; 42171466 / National Natural Science Foundation of China; National Natural Science Foundation of China (NSFC) 2022034 / The "CUG Scholar"Scientific Research Funds at China University of Geosciences (Wuhan)
- Language
- English
- Date published
- 01/01/2025
- Academic Unit
- School of Earth, Environment, and Sustainability; Center for Social Science Innovation
- Record Identifier
- 9985219862302771
Metrics
5 Record Views