An Interpretable Implicit-Based Approach for Modeling Local Spatial Effects: A Case Study of Global Gross Primary Productivity Estimation
In Earth sciences, unobserved factors exhibit non-stationary spatial distributions, causing the relationships between features and targets to display spatial heterogeneity. In geographic machine learning tasks, conventional statistical learning methods often struggle to capture spatial heterogeneity...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2025-07-01
|
| Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/395/2025/isprs-archives-XLVIII-G-2025-395-2025.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850078841319456768 |
|---|---|
| author | S. Du H. Huang K. Shen Z. Liu S. Tang |
| author_facet | S. Du H. Huang K. Shen Z. Liu S. Tang |
| author_sort | S. Du |
| collection | DOAJ |
| description | In Earth sciences, unobserved factors exhibit non-stationary spatial distributions, causing the relationships between features and targets to display spatial heterogeneity. In geographic machine learning tasks, conventional statistical learning methods often struggle to capture spatial heterogeneity, leading to unsatisfactory prediction accuracy and unreliable interpretability. While approaches like Geographically Weighted Regression (GWR) capture local variations, they fall short of uncovering global patterns and tracking the continuous evolution of spatial heterogeneity. Motivated by this limitation, we propose a novel perspective—that is, simultaneously modeling common features across different locations alongside spatial differences using deep neural networks. The proposed method is a dual-branch neural network with an encoder-decoder structure. In the encoding stage, the method aggregates node information in a spatiotemporal conditional graph using GCN and LSTM, encoding location-specific spatiotemporal heterogeneity as an implicit conditional vector. Additionally, a self-attention-based encoder is used to extract location-invariant common features from the data. In the decoding stage, the approach employs a conditional generation strategy that predicts response variables and interpretative weights based on data features under spatiotemporal conditions. The approach is validated by predicting vegetation gross primary productivity (GPP) using global climate and land cover data from 2001 to 2020. Trained on 50 million samples and tested on 2.8 million, the proposed model achieves an RMSE of 0.836, outperforming LightGBM (1.063) and TabNet (0.944). Visualization analyses indicate that our method can reveal the distribution differences of the dominant factors of GPP across various times and locations. |
| format | Article |
| id | doaj-art-4bbd7b58485248d7bb85a27ebbd5ccff |
| institution | DOAJ |
| issn | 1682-1750 2194-9034 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj-art-4bbd7b58485248d7bb85a27ebbd5ccff2025-08-20T02:45:27ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342025-07-01XLVIII-G-202539540210.5194/isprs-archives-XLVIII-G-2025-395-2025An Interpretable Implicit-Based Approach for Modeling Local Spatial Effects: A Case Study of Global Gross Primary Productivity EstimationS. Du0H. Huang1K. Shen2Z. Liu3S. Tang4College of Urban and Environmental Sciences, Peking University, Beijing, P.R. ChinaDepartment of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University, Hong Kong, P.R. ChinaSchool of Safety Science, Tsinghua University, Beijing, P.R. ChinaCollege of Surveying and Geo-Informatics, Tongji University, Shanghai, P.R. ChinaResearch Institute for Smart Cities, School of Architecture and Urban Planning, Shenzhen University, Shenzhen, P.R. ChinaIn Earth sciences, unobserved factors exhibit non-stationary spatial distributions, causing the relationships between features and targets to display spatial heterogeneity. In geographic machine learning tasks, conventional statistical learning methods often struggle to capture spatial heterogeneity, leading to unsatisfactory prediction accuracy and unreliable interpretability. While approaches like Geographically Weighted Regression (GWR) capture local variations, they fall short of uncovering global patterns and tracking the continuous evolution of spatial heterogeneity. Motivated by this limitation, we propose a novel perspective—that is, simultaneously modeling common features across different locations alongside spatial differences using deep neural networks. The proposed method is a dual-branch neural network with an encoder-decoder structure. In the encoding stage, the method aggregates node information in a spatiotemporal conditional graph using GCN and LSTM, encoding location-specific spatiotemporal heterogeneity as an implicit conditional vector. Additionally, a self-attention-based encoder is used to extract location-invariant common features from the data. In the decoding stage, the approach employs a conditional generation strategy that predicts response variables and interpretative weights based on data features under spatiotemporal conditions. The approach is validated by predicting vegetation gross primary productivity (GPP) using global climate and land cover data from 2001 to 2020. Trained on 50 million samples and tested on 2.8 million, the proposed model achieves an RMSE of 0.836, outperforming LightGBM (1.063) and TabNet (0.944). Visualization analyses indicate that our method can reveal the distribution differences of the dominant factors of GPP across various times and locations.https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/395/2025/isprs-archives-XLVIII-G-2025-395-2025.pdf |
| spellingShingle | S. Du H. Huang K. Shen Z. Liu S. Tang An Interpretable Implicit-Based Approach for Modeling Local Spatial Effects: A Case Study of Global Gross Primary Productivity Estimation The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | An Interpretable Implicit-Based Approach for Modeling Local Spatial Effects: A Case Study of Global Gross Primary Productivity Estimation |
| title_full | An Interpretable Implicit-Based Approach for Modeling Local Spatial Effects: A Case Study of Global Gross Primary Productivity Estimation |
| title_fullStr | An Interpretable Implicit-Based Approach for Modeling Local Spatial Effects: A Case Study of Global Gross Primary Productivity Estimation |
| title_full_unstemmed | An Interpretable Implicit-Based Approach for Modeling Local Spatial Effects: A Case Study of Global Gross Primary Productivity Estimation |
| title_short | An Interpretable Implicit-Based Approach for Modeling Local Spatial Effects: A Case Study of Global Gross Primary Productivity Estimation |
| title_sort | interpretable implicit based approach for modeling local spatial effects a case study of global gross primary productivity estimation |
| url | https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/395/2025/isprs-archives-XLVIII-G-2025-395-2025.pdf |
| work_keys_str_mv | AT sdu aninterpretableimplicitbasedapproachformodelinglocalspatialeffectsacasestudyofglobalgrossprimaryproductivityestimation AT hhuang aninterpretableimplicitbasedapproachformodelinglocalspatialeffectsacasestudyofglobalgrossprimaryproductivityestimation AT kshen aninterpretableimplicitbasedapproachformodelinglocalspatialeffectsacasestudyofglobalgrossprimaryproductivityestimation AT zliu aninterpretableimplicitbasedapproachformodelinglocalspatialeffectsacasestudyofglobalgrossprimaryproductivityestimation AT stang aninterpretableimplicitbasedapproachformodelinglocalspatialeffectsacasestudyofglobalgrossprimaryproductivityestimation AT sdu interpretableimplicitbasedapproachformodelinglocalspatialeffectsacasestudyofglobalgrossprimaryproductivityestimation AT hhuang interpretableimplicitbasedapproachformodelinglocalspatialeffectsacasestudyofglobalgrossprimaryproductivityestimation AT kshen interpretableimplicitbasedapproachformodelinglocalspatialeffectsacasestudyofglobalgrossprimaryproductivityestimation AT zliu interpretableimplicitbasedapproachformodelinglocalspatialeffectsacasestudyofglobalgrossprimaryproductivityestimation AT stang interpretableimplicitbasedapproachformodelinglocalspatialeffectsacasestudyofglobalgrossprimaryproductivityestimation |