ResGAT-F: a novel graph neural network-based approach for evaluating landing suitability in the lunar southern polar region
Landing suitability evaluation in the Lunar Southern Polar region is critical for future exploration, it requires integrating various environmental factors to balance safety and scientific value. This study proposes a Residual Connection Graph Attention Forest (ResGAT-F) model, which systematically...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2025-08-01
|
| Series: | International Journal of Digital Earth |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/17538947.2025.2547291 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849224282395115520 |
|---|---|
| author | Shibo Wen Yongzhi Wang Xingyu Chen Qizhou Gong Jianzhong Liu Xiaoxi Kang Hengxi Liu Kai Zhu Sheng Zhang |
| author_facet | Shibo Wen Yongzhi Wang Xingyu Chen Qizhou Gong Jianzhong Liu Xiaoxi Kang Hengxi Liu Kai Zhu Sheng Zhang |
| author_sort | Shibo Wen |
| collection | DOAJ |
| description | Landing suitability evaluation in the Lunar Southern Polar region is critical for future exploration, it requires integrating various environmental factors to balance safety and scientific value. This study proposes a Residual Connection Graph Attention Forest (ResGAT-F) model, which systematically integrates multi-source spatial data to extract regional features and environmental relationships, enabling a quantitative assessment of landing suitability that addressing safety and multi-disciplinary scientific exploration scenarios. Results show all ResGAT sub-models achieve over 96% accuracy based on pixel-wise labels generated by the adapted Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) from multiple small-sample regions. Ensemble ResGAT-F attains AUC above 0.92, outperforming the baseline model Attn-CNN (accuracy: 93%, AUC: 0.86). A 256 m resolution suitability map between 80°S to 90°S was generated and been scored (scoring ≥8 means highly suitable), which can evaluate site suitability across the region. Only 7.81% of the area meets safety requirements and potential of multi-target scientific exploration. Suitability evaluations for Artemis III candidate landing zones, such as Malapert Massif, indicates 28% of this area meets the requirements. The ResGAT-F in handling complex, multi-dimensional lunar data shows potential for supporting future landing missions and improving lunar exploration planning. |
| format | Article |
| id | doaj-art-3f6363b41d2e4a3ba00b56e2ae91d8a9 |
| institution | Kabale University |
| issn | 1753-8947 1753-8955 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | International Journal of Digital Earth |
| spelling | doaj-art-3f6363b41d2e4a3ba00b56e2ae91d8a92025-08-25T11:31:45ZengTaylor & Francis GroupInternational Journal of Digital Earth1753-89471753-89552025-08-0118110.1080/17538947.2025.2547291ResGAT-F: a novel graph neural network-based approach for evaluating landing suitability in the lunar southern polar regionShibo Wen0Yongzhi Wang1Xingyu Chen2Qizhou Gong3Jianzhong Liu4Xiaoxi Kang5Hengxi Liu6Kai Zhu7Sheng Zhang8College of Geoexploration Science and Technology, Jilin University, Changchun, People’s Republic of ChinaCollege of Geoexploration Science and Technology, Jilin University, Changchun, People’s Republic of ChinaCollege of Geoexploration Science and Technology, Jilin University, Changchun, People’s Republic of ChinaCollege of Instrumentation and Electrical Engineering, Jilin University, Changchun, People’s Republic of ChinaCenter for Lunar and Planetary Science, Institute of Geochemistry, Chinese Academy of Sciences, Guiyang, People’s Republic of ChinaDeep Space Exploration Laboratory, Beijing, People’s Republic of ChinaCollege of Geoexploration Science and Technology, Jilin University, Changchun, People’s Republic of ChinaCenter for Lunar and Planetary Science, Institute of Geochemistry, Chinese Academy of Sciences, Guiyang, People’s Republic of ChinaCenter for Lunar and Planetary Science, Institute of Geochemistry, Chinese Academy of Sciences, Guiyang, People’s Republic of ChinaLanding suitability evaluation in the Lunar Southern Polar region is critical for future exploration, it requires integrating various environmental factors to balance safety and scientific value. This study proposes a Residual Connection Graph Attention Forest (ResGAT-F) model, which systematically integrates multi-source spatial data to extract regional features and environmental relationships, enabling a quantitative assessment of landing suitability that addressing safety and multi-disciplinary scientific exploration scenarios. Results show all ResGAT sub-models achieve over 96% accuracy based on pixel-wise labels generated by the adapted Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) from multiple small-sample regions. Ensemble ResGAT-F attains AUC above 0.92, outperforming the baseline model Attn-CNN (accuracy: 93%, AUC: 0.86). A 256 m resolution suitability map between 80°S to 90°S was generated and been scored (scoring ≥8 means highly suitable), which can evaluate site suitability across the region. Only 7.81% of the area meets safety requirements and potential of multi-target scientific exploration. Suitability evaluations for Artemis III candidate landing zones, such as Malapert Massif, indicates 28% of this area meets the requirements. The ResGAT-F in handling complex, multi-dimensional lunar data shows potential for supporting future landing missions and improving lunar exploration planning.https://www.tandfonline.com/doi/10.1080/17538947.2025.2547291Lunar south polelanding suitabilitygraph neural networksensemble learningwater ice detection |
| spellingShingle | Shibo Wen Yongzhi Wang Xingyu Chen Qizhou Gong Jianzhong Liu Xiaoxi Kang Hengxi Liu Kai Zhu Sheng Zhang ResGAT-F: a novel graph neural network-based approach for evaluating landing suitability in the lunar southern polar region International Journal of Digital Earth Lunar south pole landing suitability graph neural networks ensemble learning water ice detection |
| title | ResGAT-F: a novel graph neural network-based approach for evaluating landing suitability in the lunar southern polar region |
| title_full | ResGAT-F: a novel graph neural network-based approach for evaluating landing suitability in the lunar southern polar region |
| title_fullStr | ResGAT-F: a novel graph neural network-based approach for evaluating landing suitability in the lunar southern polar region |
| title_full_unstemmed | ResGAT-F: a novel graph neural network-based approach for evaluating landing suitability in the lunar southern polar region |
| title_short | ResGAT-F: a novel graph neural network-based approach for evaluating landing suitability in the lunar southern polar region |
| title_sort | resgat f a novel graph neural network based approach for evaluating landing suitability in the lunar southern polar region |
| topic | Lunar south pole landing suitability graph neural networks ensemble learning water ice detection |
| url | https://www.tandfonline.com/doi/10.1080/17538947.2025.2547291 |
| work_keys_str_mv | AT shibowen resgatfanovelgraphneuralnetworkbasedapproachforevaluatinglandingsuitabilityinthelunarsouthernpolarregion AT yongzhiwang resgatfanovelgraphneuralnetworkbasedapproachforevaluatinglandingsuitabilityinthelunarsouthernpolarregion AT xingyuchen resgatfanovelgraphneuralnetworkbasedapproachforevaluatinglandingsuitabilityinthelunarsouthernpolarregion AT qizhougong resgatfanovelgraphneuralnetworkbasedapproachforevaluatinglandingsuitabilityinthelunarsouthernpolarregion AT jianzhongliu resgatfanovelgraphneuralnetworkbasedapproachforevaluatinglandingsuitabilityinthelunarsouthernpolarregion AT xiaoxikang resgatfanovelgraphneuralnetworkbasedapproachforevaluatinglandingsuitabilityinthelunarsouthernpolarregion AT hengxiliu resgatfanovelgraphneuralnetworkbasedapproachforevaluatinglandingsuitabilityinthelunarsouthernpolarregion AT kaizhu resgatfanovelgraphneuralnetworkbasedapproachforevaluatinglandingsuitabilityinthelunarsouthernpolarregion AT shengzhang resgatfanovelgraphneuralnetworkbasedapproachforevaluatinglandingsuitabilityinthelunarsouthernpolarregion |