High-Resolution Geochemical Data Mapping With Swin Transformer-Convolution-Based Multisource Geoscience Data Fusion
Geochemical data are crucial for reflecting geological features and is extensively applied in mineral exploration, environmental impact assessment, and geological research. However, the high economic cost of geochemical data analysis hinders large-scale studies, leading to low spatial resolution, es...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10824821/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592967277215744 |
|---|---|
| author | Ye Yuan Shuguang Zhou Jianhua Bian Jinlin Wang Wei Han Jining Yan |
| author_facet | Ye Yuan Shuguang Zhou Jianhua Bian Jinlin Wang Wei Han Jining Yan |
| author_sort | Ye Yuan |
| collection | DOAJ |
| description | Geochemical data are crucial for reflecting geological features and is extensively applied in mineral exploration, environmental impact assessment, and geological research. However, the high economic cost of geochemical data analysis hinders large-scale studies, leading to low spatial resolution, especially in remote areas. Although remote sensing data provides rich surface spectral information and shows a strong correlation with geological features, its accuracy in large-scale geochemical data inversion is insufficient. Therefore, we improve the accuracy and reliability by fusing multisource geoscience data. Vegetation information, digital elevation models, and aeromagnetic data, among other geoscience data, offer new perspectives for geochemical data analysis. This article proposes a novel multimodal spatial–spectral fusion model with swin transformer and convolutional networks for regression (MSSF-SCR). This model extracts spatial features from multisource geoscience data using a multibranch swin transformer and dynamically adjusts feature weights with the multimodal multihead convolutional attention module. The swin transformer unifies spatial features, addressing semantic disparities among diverse data sources. Spectral features from remote sensing data are then fused with spatial features through 2-D convolutional regression, producing 15 m resolution geochemical maps. Experiments conducted in the Dananhu–Tousuquan Island Arc region of East Tianshan demonstrate that MSSF-SCR achieves superior performance in terms of R-squared (<inline-formula><tex-math notation="LaTeX">$R^{2}$</tex-math></inline-formula>) score, Pearson correlation coefficient (<italic>R</italic>), mean absolute error, and root-mean-squared error indices for five elements (Al<sub>2</sub>O<sub>3</sub>, Fe<sub>2</sub>O<sub>3</sub>, K<sub>2</sub>O, MgO, and SiO<sub>2</sub>). |
| format | Article |
| id | doaj-art-e495b23240194a8ab2dc8af47a393308 |
| institution | Kabale University |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-e495b23240194a8ab2dc8af47a3933082025-01-21T00:00:23ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01183530354310.1109/JSTARS.2025.352567510824821High-Resolution Geochemical Data Mapping With Swin Transformer-Convolution-Based Multisource Geoscience Data FusionYe Yuan0https://orcid.org/0009-0008-0504-210XShuguang Zhou1https://orcid.org/0000-0002-5133-5228Jianhua Bian2Jinlin Wang3Wei Han4https://orcid.org/0000-0003-3882-1616Jining Yan5https://orcid.org/0000-0003-0680-5427School of Computer Science, China University of Geosciences, Wuhan, ChinaXinjiang Research Centre for Mineral Resources, Xinjiang Institute of Ecology and Geography, Chinese Academy of Sciences, Urumqi, ChinaSchool of Arts and Communication, China University of Geosciences, Wuhan, ChinaTechnology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing, ChinaSchool of Computer Science, China University of Geosciences, Wuhan, ChinaSchool of Computer Science, China University of Geosciences, Wuhan, ChinaGeochemical data are crucial for reflecting geological features and is extensively applied in mineral exploration, environmental impact assessment, and geological research. However, the high economic cost of geochemical data analysis hinders large-scale studies, leading to low spatial resolution, especially in remote areas. Although remote sensing data provides rich surface spectral information and shows a strong correlation with geological features, its accuracy in large-scale geochemical data inversion is insufficient. Therefore, we improve the accuracy and reliability by fusing multisource geoscience data. Vegetation information, digital elevation models, and aeromagnetic data, among other geoscience data, offer new perspectives for geochemical data analysis. This article proposes a novel multimodal spatial–spectral fusion model with swin transformer and convolutional networks for regression (MSSF-SCR). This model extracts spatial features from multisource geoscience data using a multibranch swin transformer and dynamically adjusts feature weights with the multimodal multihead convolutional attention module. The swin transformer unifies spatial features, addressing semantic disparities among diverse data sources. Spectral features from remote sensing data are then fused with spatial features through 2-D convolutional regression, producing 15 m resolution geochemical maps. Experiments conducted in the Dananhu–Tousuquan Island Arc region of East Tianshan demonstrate that MSSF-SCR achieves superior performance in terms of R-squared (<inline-formula><tex-math notation="LaTeX">$R^{2}$</tex-math></inline-formula>) score, Pearson correlation coefficient (<italic>R</italic>), mean absolute error, and root-mean-squared error indices for five elements (Al<sub>2</sub>O<sub>3</sub>, Fe<sub>2</sub>O<sub>3</sub>, K<sub>2</sub>O, MgO, and SiO<sub>2</sub>).https://ieeexplore.ieee.org/document/10824821/Data fusiondeep learninggeochemical datamultisource geoscience dataremote sensing |
| spellingShingle | Ye Yuan Shuguang Zhou Jianhua Bian Jinlin Wang Wei Han Jining Yan High-Resolution Geochemical Data Mapping With Swin Transformer-Convolution-Based Multisource Geoscience Data Fusion IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Data fusion deep learning geochemical data multisource geoscience data remote sensing |
| title | High-Resolution Geochemical Data Mapping With Swin Transformer-Convolution-Based Multisource Geoscience Data Fusion |
| title_full | High-Resolution Geochemical Data Mapping With Swin Transformer-Convolution-Based Multisource Geoscience Data Fusion |
| title_fullStr | High-Resolution Geochemical Data Mapping With Swin Transformer-Convolution-Based Multisource Geoscience Data Fusion |
| title_full_unstemmed | High-Resolution Geochemical Data Mapping With Swin Transformer-Convolution-Based Multisource Geoscience Data Fusion |
| title_short | High-Resolution Geochemical Data Mapping With Swin Transformer-Convolution-Based Multisource Geoscience Data Fusion |
| title_sort | high resolution geochemical data mapping with swin transformer convolution based multisource geoscience data fusion |
| topic | Data fusion deep learning geochemical data multisource geoscience data remote sensing |
| url | https://ieeexplore.ieee.org/document/10824821/ |
| work_keys_str_mv | AT yeyuan highresolutiongeochemicaldatamappingwithswintransformerconvolutionbasedmultisourcegeosciencedatafusion AT shuguangzhou highresolutiongeochemicaldatamappingwithswintransformerconvolutionbasedmultisourcegeosciencedatafusion AT jianhuabian highresolutiongeochemicaldatamappingwithswintransformerconvolutionbasedmultisourcegeosciencedatafusion AT jinlinwang highresolutiongeochemicaldatamappingwithswintransformerconvolutionbasedmultisourcegeosciencedatafusion AT weihan highresolutiongeochemicaldatamappingwithswintransformerconvolutionbasedmultisourcegeosciencedatafusion AT jiningyan highresolutiongeochemicaldatamappingwithswintransformerconvolutionbasedmultisourcegeosciencedatafusion |