A large scale Digital Elevation Model super-resolution Transformer
The Digital Elevation Model (DEM) super-resolution approach aims to improve the spatial resolution or detail of an existing DEM by applying techniques such as machine learning or spatial interpolation. Convolutional Neural Networks and Generative Adversarial Networks have exhibited remarkable capabi...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-11-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1569843223003205 |
| _version_ | 1827766968537579520 |
|---|---|
| author | Zhuoxiao Li Xiaohui Zhu Shanliang Yao Yong Yue Ángel F. García-Fernández Eng Gee Lim Andrew Levers |
| author_facet | Zhuoxiao Li Xiaohui Zhu Shanliang Yao Yong Yue Ángel F. García-Fernández Eng Gee Lim Andrew Levers |
| author_sort | Zhuoxiao Li |
| collection | DOAJ |
| description | The Digital Elevation Model (DEM) super-resolution approach aims to improve the spatial resolution or detail of an existing DEM by applying techniques such as machine learning or spatial interpolation. Convolutional Neural Networks and Generative Adversarial Networks have exhibited remarkable capabilities in generating high-resolution DEMs from corresponding low-resolution inputs, significantly outperforming conventional spatial interpolation methods. Nevertheless, these current methodologies encounter substantial challenges when tasked with processing exceedingly high-resolution DEMs (256×256,512×512, or higher), specifically pertaining to the accurate restore maximum and minimum elevation values, the terrain features, and the edges of DEMs. Aiming to solve the problems of current super-resolution techniques that struggle to effectively restore topographic details and produce high-resolution DEMs that preserve coordinate information, this paper proposes an improved DEM super-resolution Transformer(DSRT) network for large-scale DEM super-resolution and account for geographic information continuity. We design a window attention module that is used to engage more elevation points in low-resolution DEMs, which can learn more terrain features from the input high-resolution DEMs. A GeoTransform module is designed to generate coordinates and projections for the DSRT network. We conduct an evaluation of the network utilizing DEMs of various types of terrains and elevation differences at resolutions of 64×64,256×256 and 512 × 512. The network demonstrated leading performance across all assessments in terms of root mean square error (RMSE) for elevation, slope, aspect, and curvature, indicating that Transformer-based deep learning networks are superior to CNNs and GANs in learning DEM features. |
| first_indexed | 2024-03-11T11:51:37Z |
| format | Article |
| id | doaj.art-204b6a17600645268b009358ea3686b4 |
| institution | Directory Open Access Journal |
| issn | 1569-8432 |
| language | English |
| last_indexed | 2024-03-11T11:51:37Z |
| publishDate | 2023-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj.art-204b6a17600645268b009358ea3686b42023-11-09T04:11:32ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322023-11-01124103496A large scale Digital Elevation Model super-resolution TransformerZhuoxiao Li0Xiaohui Zhu1Shanliang Yao2Yong Yue3Ángel F. García-Fernández4Eng Gee Lim5Andrew Levers6School of Advanced Technology, Xi’an Jiaotong-Liverpool University, Suzhou, 215123, China; Department of Electrical Engineering and Electronics, University of Liverpool, Liverpool, L69 3GJ, UKSchool of Advanced Technology, Xi’an Jiaotong-Liverpool University, Suzhou, 215123, China; Corresponding author.School of Advanced Technology, Xi’an Jiaotong-Liverpool University, Suzhou, 215123, China; Department of Electrical Engineering and Electronics, University of Liverpool, Liverpool, L69 3GJ, UKSchool of Advanced Technology, Xi’an Jiaotong-Liverpool University, Suzhou, 215123, ChinaDepartment of Electrical Engineering and Electronics, University of Liverpool, Liverpool, L69 3GJ, UK; ARIES Research Centre, Universidad Antonio de Nebrija, Madrid, 263001, SpainSchool of Advanced Technology, Xi’an Jiaotong-Liverpool University, Suzhou, 215123, ChinaDigital Innovation Facility, University of Liverpool, Liverpool, 215123, UKThe Digital Elevation Model (DEM) super-resolution approach aims to improve the spatial resolution or detail of an existing DEM by applying techniques such as machine learning or spatial interpolation. Convolutional Neural Networks and Generative Adversarial Networks have exhibited remarkable capabilities in generating high-resolution DEMs from corresponding low-resolution inputs, significantly outperforming conventional spatial interpolation methods. Nevertheless, these current methodologies encounter substantial challenges when tasked with processing exceedingly high-resolution DEMs (256×256,512×512, or higher), specifically pertaining to the accurate restore maximum and minimum elevation values, the terrain features, and the edges of DEMs. Aiming to solve the problems of current super-resolution techniques that struggle to effectively restore topographic details and produce high-resolution DEMs that preserve coordinate information, this paper proposes an improved DEM super-resolution Transformer(DSRT) network for large-scale DEM super-resolution and account for geographic information continuity. We design a window attention module that is used to engage more elevation points in low-resolution DEMs, which can learn more terrain features from the input high-resolution DEMs. A GeoTransform module is designed to generate coordinates and projections for the DSRT network. We conduct an evaluation of the network utilizing DEMs of various types of terrains and elevation differences at resolutions of 64×64,256×256 and 512 × 512. The network demonstrated leading performance across all assessments in terms of root mean square error (RMSE) for elevation, slope, aspect, and curvature, indicating that Transformer-based deep learning networks are superior to CNNs and GANs in learning DEM features.http://www.sciencedirect.com/science/article/pii/S1569843223003205DEM super-resolutionSpatial interpolationShifted windowTransformerConvolutional neural networksGenerative adversarial networks |
| spellingShingle | Zhuoxiao Li Xiaohui Zhu Shanliang Yao Yong Yue Ángel F. García-Fernández Eng Gee Lim Andrew Levers A large scale Digital Elevation Model super-resolution Transformer International Journal of Applied Earth Observations and Geoinformation DEM super-resolution Spatial interpolation Shifted window Transformer Convolutional neural networks Generative adversarial networks |
| title | A large scale Digital Elevation Model super-resolution Transformer |
| title_full | A large scale Digital Elevation Model super-resolution Transformer |
| title_fullStr | A large scale Digital Elevation Model super-resolution Transformer |
| title_full_unstemmed | A large scale Digital Elevation Model super-resolution Transformer |
| title_short | A large scale Digital Elevation Model super-resolution Transformer |
| title_sort | large scale digital elevation model super resolution transformer |
| topic | DEM super-resolution Spatial interpolation Shifted window Transformer Convolutional neural networks Generative adversarial networks |
| url | http://www.sciencedirect.com/science/article/pii/S1569843223003205 |
| work_keys_str_mv | AT zhuoxiaoli alargescaledigitalelevationmodelsuperresolutiontransformer AT xiaohuizhu alargescaledigitalelevationmodelsuperresolutiontransformer AT shanliangyao alargescaledigitalelevationmodelsuperresolutiontransformer AT yongyue alargescaledigitalelevationmodelsuperresolutiontransformer AT angelfgarciafernandez alargescaledigitalelevationmodelsuperresolutiontransformer AT enggeelim alargescaledigitalelevationmodelsuperresolutiontransformer AT andrewlevers alargescaledigitalelevationmodelsuperresolutiontransformer AT zhuoxiaoli largescaledigitalelevationmodelsuperresolutiontransformer AT xiaohuizhu largescaledigitalelevationmodelsuperresolutiontransformer AT shanliangyao largescaledigitalelevationmodelsuperresolutiontransformer AT yongyue largescaledigitalelevationmodelsuperresolutiontransformer AT angelfgarciafernandez largescaledigitalelevationmodelsuperresolutiontransformer AT enggeelim largescaledigitalelevationmodelsuperresolutiontransformer AT andrewlevers largescaledigitalelevationmodelsuperresolutiontransformer |