Super-resolution for terrain modeling using deep learning in high mountain Asia
High Mountain Asia (HMA) is characterized by some of the most complex and rugged terrain conditions in the world. However, high resolution terrain data are not easy to quickly acquire from the area due to difficulties in accessing the region. In this study, we trained a modified super-resolution res...
Ausführliche Beschreibung
Autor*in: |
Jiang, Yinghui [verfasserIn] Xiong, Liyang [verfasserIn] Huang, Xiaohui [verfasserIn] Li, Sijin [verfasserIn] Shen, Wang [verfasserIn] |
---|
Format: |
E-Artikel |
---|---|
Sprache: |
Englisch |
Erschienen: |
2023 |
---|
Schlagwörter: |
---|
Übergeordnetes Werk: |
Enthalten in: International journal of applied earth observation and geoinformation - Amsterdam [u.a.] : Elsevier Science, 1999, 118 |
---|---|
Übergeordnetes Werk: |
volume:118 |
DOI / URN: |
10.1016/j.jag.2023.103296 |
---|
Katalog-ID: |
ELV009767037 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | ELV009767037 | ||
003 | DE-627 | ||
005 | 20240114093228.0 | ||
007 | cr uuu---uuuuu | ||
008 | 230530s2023 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1016/j.jag.2023.103296 |2 doi | |
035 | |a (DE-627)ELV009767037 | ||
035 | |a (ELSEVIER)S1569-8432(23)00118-8 | ||
040 | |a DE-627 |b ger |c DE-627 |e rda | ||
041 | |a eng | ||
082 | 0 | 4 | |a 550 |q VZ |
084 | |a KARTEN |q DE-1a |2 fid | ||
084 | |a 38.03 |2 bkl | ||
084 | |a 74.48 |2 bkl | ||
084 | |a 74.41 |2 bkl | ||
100 | 1 | |a Jiang, Yinghui |e verfasserin |4 aut | |
245 | 1 | 0 | |a Super-resolution for terrain modeling using deep learning in high mountain Asia |
264 | 1 | |c 2023 | |
336 | |a nicht spezifiziert |b zzz |2 rdacontent | ||
337 | |a Computermedien |b c |2 rdamedia | ||
338 | |a Online-Ressource |b cr |2 rdacarrier | ||
520 | |a High Mountain Asia (HMA) is characterized by some of the most complex and rugged terrain conditions in the world. However, high resolution terrain data are not easy to quickly acquire from the area due to difficulties in accessing the region. In this study, we trained a modified super-resolution residual network (MSRResNet) to develop super-resolution (SR) digital elevation models (DEMs) in the HMA areas by using freely available DEM data from the HMA region and limited high resolution (HR) DEMs from other areas to train the model. In this network, a new loss function was constructed that considered the terrain parameters of slope and curvature to constrain the network learning and convergence. The proposed method was applied to and validated by data from the Hengduan Mountains in the southeastern part of HMA, which is a world-famous longitudinal belt of mountains and canyons. A comparative analysis between the current and existing methods (i.e., SRGAN and Bicubic interpolation) was conducted to assess the effectiveness of the proposed approach. The experimental results were also investigated and evaluated by visual inspection and analysis of the terrain parameters. The results demonstrate that the proposed MSRResNet super-resolution process can achieve highly accurate terrain data by downscaling DEMs in HMA. This SR process also outperforms the other comparable methods. Compared to the Bicubic interpolation method, the RMSE and MAE accuracy are improved by 32.17% and 33.97%, and compared to the SRGAN method, the RMSE and MAE accuracy are improved by 39.15% and 32.47%. The HR DEM generated by the new method is more conducive to improving the accuracy of extracted terrain features, such as stream networks. It is promising to apply this model on other areas on Earth or even other planets with terrain similar to that of HMA. | ||
650 | 4 | |a Terrain modeling | |
650 | 4 | |a DEM super-resolution | |
650 | 4 | |a Deep learning | |
650 | 4 | |a High Mountain Asia | |
700 | 1 | |a Xiong, Liyang |e verfasserin |4 aut | |
700 | 1 | |a Huang, Xiaohui |e verfasserin |4 aut | |
700 | 1 | |a Li, Sijin |e verfasserin |4 aut | |
700 | 1 | |a Shen, Wang |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t International journal of applied earth observation and geoinformation |d Amsterdam [u.a.] : Elsevier Science, 1999 |g 118 |h Online-Ressource |w (DE-627)359784119 |w (DE-600)2097960-5 |w (DE-576)25927254X |x 1872-826X |7 nnns |
773 | 1 | 8 | |g volume:118 |
912 | |a GBV_USEFLAG_U | ||
912 | |a GBV_ELV | ||
912 | |a SYSFLAG_U | ||
912 | |a FID-KARTEN | ||
912 | |a SSG-OPC-GGO | ||
912 | |a SSG-OPC-AST | ||
912 | |a SSG-OPC-GEO | ||
912 | |a GBV_ILN_11 | ||
912 | |a GBV_ILN_20 | ||
912 | |a GBV_ILN_22 | ||
912 | |a GBV_ILN_23 | ||
912 | |a GBV_ILN_24 | ||
912 | |a GBV_ILN_31 | ||
912 | |a GBV_ILN_39 | ||
912 | |a GBV_ILN_40 | ||
912 | |a GBV_ILN_60 | ||
912 | |a GBV_ILN_62 | ||
912 | |a GBV_ILN_63 | ||
912 | |a GBV_ILN_65 | ||
912 | |a GBV_ILN_69 | ||
912 | |a GBV_ILN_70 | ||
912 | |a GBV_ILN_73 | ||
912 | |a GBV_ILN_95 | ||
912 | |a GBV_ILN_105 | ||
912 | |a GBV_ILN_110 | ||
912 | |a GBV_ILN_151 | ||
912 | |a GBV_ILN_161 | ||
912 | |a GBV_ILN_170 | ||
912 | |a GBV_ILN_213 | ||
912 | |a GBV_ILN_224 | ||
912 | |a GBV_ILN_230 | ||
912 | |a GBV_ILN_285 | ||
912 | |a GBV_ILN_293 | ||
912 | |a GBV_ILN_370 | ||
912 | |a GBV_ILN_602 | ||
912 | |a GBV_ILN_2004 | ||
912 | |a GBV_ILN_2005 | ||
912 | |a GBV_ILN_2008 | ||
912 | |a GBV_ILN_2014 | ||
912 | |a GBV_ILN_2034 | ||
912 | |a GBV_ILN_2044 | ||
912 | |a GBV_ILN_2048 | ||
912 | |a GBV_ILN_2064 | ||
912 | |a GBV_ILN_2088 | ||
912 | |a GBV_ILN_2106 | ||
912 | |a GBV_ILN_2112 | ||
912 | |a GBV_ILN_2122 | ||
912 | |a GBV_ILN_2143 | ||
912 | |a GBV_ILN_2152 | ||
912 | |a GBV_ILN_2153 | ||
912 | |a GBV_ILN_2232 | ||
912 | |a GBV_ILN_2336 | ||
912 | |a GBV_ILN_4012 | ||
912 | |a GBV_ILN_4037 | ||
912 | |a GBV_ILN_4112 | ||
912 | |a GBV_ILN_4125 | ||
912 | |a GBV_ILN_4126 | ||
912 | |a GBV_ILN_4249 | ||
912 | |a GBV_ILN_4305 | ||
912 | |a GBV_ILN_4306 | ||
912 | |a GBV_ILN_4307 | ||
912 | |a GBV_ILN_4313 | ||
912 | |a GBV_ILN_4322 | ||
912 | |a GBV_ILN_4323 | ||
912 | |a GBV_ILN_4324 | ||
912 | |a GBV_ILN_4325 | ||
912 | |a GBV_ILN_4335 | ||
912 | |a GBV_ILN_4338 | ||
912 | |a GBV_ILN_4367 | ||
912 | |a GBV_ILN_4700 | ||
936 | b | k | |a 38.03 |j Methoden und Techniken der Geowissenschaften |q VZ |
936 | b | k | |a 74.48 |j Geoinformationssysteme |q VZ |
936 | b | k | |a 74.41 |j Luftaufnahmen |j Photogrammetrie |q VZ |
951 | |a AR | ||
952 | |d 118 |
author_variant |
y j yj l x lx x h xh s l sl w s ws |
---|---|
matchkey_str |
article:1872826X:2023----::uersltofrerimdlnuigeperig |
hierarchy_sort_str |
2023 |
bklnumber |
38.03 74.48 74.41 |
publishDate |
2023 |
allfields |
10.1016/j.jag.2023.103296 doi (DE-627)ELV009767037 (ELSEVIER)S1569-8432(23)00118-8 DE-627 ger DE-627 rda eng 550 VZ KARTEN DE-1a fid 38.03 bkl 74.48 bkl 74.41 bkl Jiang, Yinghui verfasserin aut Super-resolution for terrain modeling using deep learning in high mountain Asia 2023 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier High Mountain Asia (HMA) is characterized by some of the most complex and rugged terrain conditions in the world. However, high resolution terrain data are not easy to quickly acquire from the area due to difficulties in accessing the region. In this study, we trained a modified super-resolution residual network (MSRResNet) to develop super-resolution (SR) digital elevation models (DEMs) in the HMA areas by using freely available DEM data from the HMA region and limited high resolution (HR) DEMs from other areas to train the model. In this network, a new loss function was constructed that considered the terrain parameters of slope and curvature to constrain the network learning and convergence. The proposed method was applied to and validated by data from the Hengduan Mountains in the southeastern part of HMA, which is a world-famous longitudinal belt of mountains and canyons. A comparative analysis between the current and existing methods (i.e., SRGAN and Bicubic interpolation) was conducted to assess the effectiveness of the proposed approach. The experimental results were also investigated and evaluated by visual inspection and analysis of the terrain parameters. The results demonstrate that the proposed MSRResNet super-resolution process can achieve highly accurate terrain data by downscaling DEMs in HMA. This SR process also outperforms the other comparable methods. Compared to the Bicubic interpolation method, the RMSE and MAE accuracy are improved by 32.17% and 33.97%, and compared to the SRGAN method, the RMSE and MAE accuracy are improved by 39.15% and 32.47%. The HR DEM generated by the new method is more conducive to improving the accuracy of extracted terrain features, such as stream networks. It is promising to apply this model on other areas on Earth or even other planets with terrain similar to that of HMA. Terrain modeling DEM super-resolution Deep learning High Mountain Asia Xiong, Liyang verfasserin aut Huang, Xiaohui verfasserin aut Li, Sijin verfasserin aut Shen, Wang verfasserin aut Enthalten in International journal of applied earth observation and geoinformation Amsterdam [u.a.] : Elsevier Science, 1999 118 Online-Ressource (DE-627)359784119 (DE-600)2097960-5 (DE-576)25927254X 1872-826X nnns volume:118 GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-KARTEN SSG-OPC-GGO SSG-OPC-AST SSG-OPC-GEO GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2008 GBV_ILN_2014 GBV_ILN_2034 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2064 GBV_ILN_2088 GBV_ILN_2106 GBV_ILN_2112 GBV_ILN_2122 GBV_ILN_2143 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 38.03 Methoden und Techniken der Geowissenschaften VZ 74.48 Geoinformationssysteme VZ 74.41 Luftaufnahmen Photogrammetrie VZ AR 118 |
spelling |
10.1016/j.jag.2023.103296 doi (DE-627)ELV009767037 (ELSEVIER)S1569-8432(23)00118-8 DE-627 ger DE-627 rda eng 550 VZ KARTEN DE-1a fid 38.03 bkl 74.48 bkl 74.41 bkl Jiang, Yinghui verfasserin aut Super-resolution for terrain modeling using deep learning in high mountain Asia 2023 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier High Mountain Asia (HMA) is characterized by some of the most complex and rugged terrain conditions in the world. However, high resolution terrain data are not easy to quickly acquire from the area due to difficulties in accessing the region. In this study, we trained a modified super-resolution residual network (MSRResNet) to develop super-resolution (SR) digital elevation models (DEMs) in the HMA areas by using freely available DEM data from the HMA region and limited high resolution (HR) DEMs from other areas to train the model. In this network, a new loss function was constructed that considered the terrain parameters of slope and curvature to constrain the network learning and convergence. The proposed method was applied to and validated by data from the Hengduan Mountains in the southeastern part of HMA, which is a world-famous longitudinal belt of mountains and canyons. A comparative analysis between the current and existing methods (i.e., SRGAN and Bicubic interpolation) was conducted to assess the effectiveness of the proposed approach. The experimental results were also investigated and evaluated by visual inspection and analysis of the terrain parameters. The results demonstrate that the proposed MSRResNet super-resolution process can achieve highly accurate terrain data by downscaling DEMs in HMA. This SR process also outperforms the other comparable methods. Compared to the Bicubic interpolation method, the RMSE and MAE accuracy are improved by 32.17% and 33.97%, and compared to the SRGAN method, the RMSE and MAE accuracy are improved by 39.15% and 32.47%. The HR DEM generated by the new method is more conducive to improving the accuracy of extracted terrain features, such as stream networks. It is promising to apply this model on other areas on Earth or even other planets with terrain similar to that of HMA. Terrain modeling DEM super-resolution Deep learning High Mountain Asia Xiong, Liyang verfasserin aut Huang, Xiaohui verfasserin aut Li, Sijin verfasserin aut Shen, Wang verfasserin aut Enthalten in International journal of applied earth observation and geoinformation Amsterdam [u.a.] : Elsevier Science, 1999 118 Online-Ressource (DE-627)359784119 (DE-600)2097960-5 (DE-576)25927254X 1872-826X nnns volume:118 GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-KARTEN SSG-OPC-GGO SSG-OPC-AST SSG-OPC-GEO GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2008 GBV_ILN_2014 GBV_ILN_2034 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2064 GBV_ILN_2088 GBV_ILN_2106 GBV_ILN_2112 GBV_ILN_2122 GBV_ILN_2143 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 38.03 Methoden und Techniken der Geowissenschaften VZ 74.48 Geoinformationssysteme VZ 74.41 Luftaufnahmen Photogrammetrie VZ AR 118 |
allfields_unstemmed |
10.1016/j.jag.2023.103296 doi (DE-627)ELV009767037 (ELSEVIER)S1569-8432(23)00118-8 DE-627 ger DE-627 rda eng 550 VZ KARTEN DE-1a fid 38.03 bkl 74.48 bkl 74.41 bkl Jiang, Yinghui verfasserin aut Super-resolution for terrain modeling using deep learning in high mountain Asia 2023 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier High Mountain Asia (HMA) is characterized by some of the most complex and rugged terrain conditions in the world. However, high resolution terrain data are not easy to quickly acquire from the area due to difficulties in accessing the region. In this study, we trained a modified super-resolution residual network (MSRResNet) to develop super-resolution (SR) digital elevation models (DEMs) in the HMA areas by using freely available DEM data from the HMA region and limited high resolution (HR) DEMs from other areas to train the model. In this network, a new loss function was constructed that considered the terrain parameters of slope and curvature to constrain the network learning and convergence. The proposed method was applied to and validated by data from the Hengduan Mountains in the southeastern part of HMA, which is a world-famous longitudinal belt of mountains and canyons. A comparative analysis between the current and existing methods (i.e., SRGAN and Bicubic interpolation) was conducted to assess the effectiveness of the proposed approach. The experimental results were also investigated and evaluated by visual inspection and analysis of the terrain parameters. The results demonstrate that the proposed MSRResNet super-resolution process can achieve highly accurate terrain data by downscaling DEMs in HMA. This SR process also outperforms the other comparable methods. Compared to the Bicubic interpolation method, the RMSE and MAE accuracy are improved by 32.17% and 33.97%, and compared to the SRGAN method, the RMSE and MAE accuracy are improved by 39.15% and 32.47%. The HR DEM generated by the new method is more conducive to improving the accuracy of extracted terrain features, such as stream networks. It is promising to apply this model on other areas on Earth or even other planets with terrain similar to that of HMA. Terrain modeling DEM super-resolution Deep learning High Mountain Asia Xiong, Liyang verfasserin aut Huang, Xiaohui verfasserin aut Li, Sijin verfasserin aut Shen, Wang verfasserin aut Enthalten in International journal of applied earth observation and geoinformation Amsterdam [u.a.] : Elsevier Science, 1999 118 Online-Ressource (DE-627)359784119 (DE-600)2097960-5 (DE-576)25927254X 1872-826X nnns volume:118 GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-KARTEN SSG-OPC-GGO SSG-OPC-AST SSG-OPC-GEO GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2008 GBV_ILN_2014 GBV_ILN_2034 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2064 GBV_ILN_2088 GBV_ILN_2106 GBV_ILN_2112 GBV_ILN_2122 GBV_ILN_2143 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 38.03 Methoden und Techniken der Geowissenschaften VZ 74.48 Geoinformationssysteme VZ 74.41 Luftaufnahmen Photogrammetrie VZ AR 118 |
allfieldsGer |
10.1016/j.jag.2023.103296 doi (DE-627)ELV009767037 (ELSEVIER)S1569-8432(23)00118-8 DE-627 ger DE-627 rda eng 550 VZ KARTEN DE-1a fid 38.03 bkl 74.48 bkl 74.41 bkl Jiang, Yinghui verfasserin aut Super-resolution for terrain modeling using deep learning in high mountain Asia 2023 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier High Mountain Asia (HMA) is characterized by some of the most complex and rugged terrain conditions in the world. However, high resolution terrain data are not easy to quickly acquire from the area due to difficulties in accessing the region. In this study, we trained a modified super-resolution residual network (MSRResNet) to develop super-resolution (SR) digital elevation models (DEMs) in the HMA areas by using freely available DEM data from the HMA region and limited high resolution (HR) DEMs from other areas to train the model. In this network, a new loss function was constructed that considered the terrain parameters of slope and curvature to constrain the network learning and convergence. The proposed method was applied to and validated by data from the Hengduan Mountains in the southeastern part of HMA, which is a world-famous longitudinal belt of mountains and canyons. A comparative analysis between the current and existing methods (i.e., SRGAN and Bicubic interpolation) was conducted to assess the effectiveness of the proposed approach. The experimental results were also investigated and evaluated by visual inspection and analysis of the terrain parameters. The results demonstrate that the proposed MSRResNet super-resolution process can achieve highly accurate terrain data by downscaling DEMs in HMA. This SR process also outperforms the other comparable methods. Compared to the Bicubic interpolation method, the RMSE and MAE accuracy are improved by 32.17% and 33.97%, and compared to the SRGAN method, the RMSE and MAE accuracy are improved by 39.15% and 32.47%. The HR DEM generated by the new method is more conducive to improving the accuracy of extracted terrain features, such as stream networks. It is promising to apply this model on other areas on Earth or even other planets with terrain similar to that of HMA. Terrain modeling DEM super-resolution Deep learning High Mountain Asia Xiong, Liyang verfasserin aut Huang, Xiaohui verfasserin aut Li, Sijin verfasserin aut Shen, Wang verfasserin aut Enthalten in International journal of applied earth observation and geoinformation Amsterdam [u.a.] : Elsevier Science, 1999 118 Online-Ressource (DE-627)359784119 (DE-600)2097960-5 (DE-576)25927254X 1872-826X nnns volume:118 GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-KARTEN SSG-OPC-GGO SSG-OPC-AST SSG-OPC-GEO GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2008 GBV_ILN_2014 GBV_ILN_2034 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2064 GBV_ILN_2088 GBV_ILN_2106 GBV_ILN_2112 GBV_ILN_2122 GBV_ILN_2143 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 38.03 Methoden und Techniken der Geowissenschaften VZ 74.48 Geoinformationssysteme VZ 74.41 Luftaufnahmen Photogrammetrie VZ AR 118 |
allfieldsSound |
10.1016/j.jag.2023.103296 doi (DE-627)ELV009767037 (ELSEVIER)S1569-8432(23)00118-8 DE-627 ger DE-627 rda eng 550 VZ KARTEN DE-1a fid 38.03 bkl 74.48 bkl 74.41 bkl Jiang, Yinghui verfasserin aut Super-resolution for terrain modeling using deep learning in high mountain Asia 2023 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier High Mountain Asia (HMA) is characterized by some of the most complex and rugged terrain conditions in the world. However, high resolution terrain data are not easy to quickly acquire from the area due to difficulties in accessing the region. In this study, we trained a modified super-resolution residual network (MSRResNet) to develop super-resolution (SR) digital elevation models (DEMs) in the HMA areas by using freely available DEM data from the HMA region and limited high resolution (HR) DEMs from other areas to train the model. In this network, a new loss function was constructed that considered the terrain parameters of slope and curvature to constrain the network learning and convergence. The proposed method was applied to and validated by data from the Hengduan Mountains in the southeastern part of HMA, which is a world-famous longitudinal belt of mountains and canyons. A comparative analysis between the current and existing methods (i.e., SRGAN and Bicubic interpolation) was conducted to assess the effectiveness of the proposed approach. The experimental results were also investigated and evaluated by visual inspection and analysis of the terrain parameters. The results demonstrate that the proposed MSRResNet super-resolution process can achieve highly accurate terrain data by downscaling DEMs in HMA. This SR process also outperforms the other comparable methods. Compared to the Bicubic interpolation method, the RMSE and MAE accuracy are improved by 32.17% and 33.97%, and compared to the SRGAN method, the RMSE and MAE accuracy are improved by 39.15% and 32.47%. The HR DEM generated by the new method is more conducive to improving the accuracy of extracted terrain features, such as stream networks. It is promising to apply this model on other areas on Earth or even other planets with terrain similar to that of HMA. Terrain modeling DEM super-resolution Deep learning High Mountain Asia Xiong, Liyang verfasserin aut Huang, Xiaohui verfasserin aut Li, Sijin verfasserin aut Shen, Wang verfasserin aut Enthalten in International journal of applied earth observation and geoinformation Amsterdam [u.a.] : Elsevier Science, 1999 118 Online-Ressource (DE-627)359784119 (DE-600)2097960-5 (DE-576)25927254X 1872-826X nnns volume:118 GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-KARTEN SSG-OPC-GGO SSG-OPC-AST SSG-OPC-GEO GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2008 GBV_ILN_2014 GBV_ILN_2034 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2064 GBV_ILN_2088 GBV_ILN_2106 GBV_ILN_2112 GBV_ILN_2122 GBV_ILN_2143 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 38.03 Methoden und Techniken der Geowissenschaften VZ 74.48 Geoinformationssysteme VZ 74.41 Luftaufnahmen Photogrammetrie VZ AR 118 |
language |
English |
source |
Enthalten in International journal of applied earth observation and geoinformation 118 volume:118 |
sourceStr |
Enthalten in International journal of applied earth observation and geoinformation 118 volume:118 |
format_phy_str_mv |
Article |
bklname |
Methoden und Techniken der Geowissenschaften Geoinformationssysteme Luftaufnahmen Photogrammetrie |
institution |
findex.gbv.de |
topic_facet |
Terrain modeling DEM super-resolution Deep learning High Mountain Asia |
dewey-raw |
550 |
isfreeaccess_bool |
false |
container_title |
International journal of applied earth observation and geoinformation |
authorswithroles_txt_mv |
Jiang, Yinghui @@aut@@ Xiong, Liyang @@aut@@ Huang, Xiaohui @@aut@@ Li, Sijin @@aut@@ Shen, Wang @@aut@@ |
publishDateDaySort_date |
2023-01-01T00:00:00Z |
hierarchy_top_id |
359784119 |
dewey-sort |
3550 |
id |
ELV009767037 |
language_de |
englisch |
fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV009767037</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240114093228.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230530s2023 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.jag.2023.103296</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV009767037</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S1569-8432(23)00118-8</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">550</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">KARTEN</subfield><subfield code="q">DE-1a</subfield><subfield code="2">fid</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">38.03</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">74.48</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">74.41</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Jiang, Yinghui</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Super-resolution for terrain modeling using deep learning in high mountain Asia</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">High Mountain Asia (HMA) is characterized by some of the most complex and rugged terrain conditions in the world. However, high resolution terrain data are not easy to quickly acquire from the area due to difficulties in accessing the region. In this study, we trained a modified super-resolution residual network (MSRResNet) to develop super-resolution (SR) digital elevation models (DEMs) in the HMA areas by using freely available DEM data from the HMA region and limited high resolution (HR) DEMs from other areas to train the model. In this network, a new loss function was constructed that considered the terrain parameters of slope and curvature to constrain the network learning and convergence. The proposed method was applied to and validated by data from the Hengduan Mountains in the southeastern part of HMA, which is a world-famous longitudinal belt of mountains and canyons. A comparative analysis between the current and existing methods (i.e., SRGAN and Bicubic interpolation) was conducted to assess the effectiveness of the proposed approach. The experimental results were also investigated and evaluated by visual inspection and analysis of the terrain parameters. The results demonstrate that the proposed MSRResNet super-resolution process can achieve highly accurate terrain data by downscaling DEMs in HMA. This SR process also outperforms the other comparable methods. Compared to the Bicubic interpolation method, the RMSE and MAE accuracy are improved by 32.17% and 33.97%, and compared to the SRGAN method, the RMSE and MAE accuracy are improved by 39.15% and 32.47%. The HR DEM generated by the new method is more conducive to improving the accuracy of extracted terrain features, such as stream networks. It is promising to apply this model on other areas on Earth or even other planets with terrain similar to that of HMA.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Terrain modeling</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">DEM super-resolution</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Deep learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">High Mountain Asia</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Xiong, Liyang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Huang, Xiaohui</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Li, Sijin</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Shen, Wang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">International journal of applied earth observation and geoinformation</subfield><subfield code="d">Amsterdam [u.a.] : Elsevier Science, 1999</subfield><subfield code="g">118</subfield><subfield code="h">Online-Ressource</subfield><subfield code="w">(DE-627)359784119</subfield><subfield code="w">(DE-600)2097960-5</subfield><subfield code="w">(DE-576)25927254X</subfield><subfield code="x">1872-826X</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:118</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">FID-KARTEN</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OPC-GGO</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OPC-AST</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OPC-GEO</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_224</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2004</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2005</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2008</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2034</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2044</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2048</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2064</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2088</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2106</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2122</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2143</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2152</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2153</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2232</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2336</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">38.03</subfield><subfield code="j">Methoden und Techniken der Geowissenschaften</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">74.48</subfield><subfield code="j">Geoinformationssysteme</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">74.41</subfield><subfield code="j">Luftaufnahmen</subfield><subfield code="j">Photogrammetrie</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">118</subfield></datafield></record></collection>
|
author |
Jiang, Yinghui |
spellingShingle |
Jiang, Yinghui ddc 550 fid KARTEN bkl 38.03 bkl 74.48 bkl 74.41 misc Terrain modeling misc DEM super-resolution misc Deep learning misc High Mountain Asia Super-resolution for terrain modeling using deep learning in high mountain Asia |
authorStr |
Jiang, Yinghui |
ppnlink_with_tag_str_mv |
@@773@@(DE-627)359784119 |
format |
electronic Article |
dewey-ones |
550 - Earth sciences |
delete_txt_mv |
keep |
author_role |
aut aut aut aut aut |
collection |
elsevier |
remote_str |
true |
illustrated |
Not Illustrated |
issn |
1872-826X |
topic_title |
550 VZ KARTEN DE-1a fid 38.03 bkl 74.48 bkl 74.41 bkl Super-resolution for terrain modeling using deep learning in high mountain Asia Terrain modeling DEM super-resolution Deep learning High Mountain Asia |
topic |
ddc 550 fid KARTEN bkl 38.03 bkl 74.48 bkl 74.41 misc Terrain modeling misc DEM super-resolution misc Deep learning misc High Mountain Asia |
topic_unstemmed |
ddc 550 fid KARTEN bkl 38.03 bkl 74.48 bkl 74.41 misc Terrain modeling misc DEM super-resolution misc Deep learning misc High Mountain Asia |
topic_browse |
ddc 550 fid KARTEN bkl 38.03 bkl 74.48 bkl 74.41 misc Terrain modeling misc DEM super-resolution misc Deep learning misc High Mountain Asia |
format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
format_main_str_mv |
Text Zeitschrift/Artikel |
carriertype_str_mv |
cr |
hierarchy_parent_title |
International journal of applied earth observation and geoinformation |
hierarchy_parent_id |
359784119 |
dewey-tens |
550 - Earth sciences & geology |
hierarchy_top_title |
International journal of applied earth observation and geoinformation |
isfreeaccess_txt |
false |
familylinks_str_mv |
(DE-627)359784119 (DE-600)2097960-5 (DE-576)25927254X |
title |
Super-resolution for terrain modeling using deep learning in high mountain Asia |
ctrlnum |
(DE-627)ELV009767037 (ELSEVIER)S1569-8432(23)00118-8 |
title_full |
Super-resolution for terrain modeling using deep learning in high mountain Asia |
author_sort |
Jiang, Yinghui |
journal |
International journal of applied earth observation and geoinformation |
journalStr |
International journal of applied earth observation and geoinformation |
lang_code |
eng |
isOA_bool |
false |
dewey-hundreds |
500 - Science |
recordtype |
marc |
publishDateSort |
2023 |
contenttype_str_mv |
zzz |
author_browse |
Jiang, Yinghui Xiong, Liyang Huang, Xiaohui Li, Sijin Shen, Wang |
container_volume |
118 |
class |
550 VZ KARTEN DE-1a fid 38.03 bkl 74.48 bkl 74.41 bkl |
format_se |
Elektronische Aufsätze |
author-letter |
Jiang, Yinghui |
doi_str_mv |
10.1016/j.jag.2023.103296 |
dewey-full |
550 |
author2-role |
verfasserin |
title_sort |
super-resolution for terrain modeling using deep learning in high mountain asia |
title_auth |
Super-resolution for terrain modeling using deep learning in high mountain Asia |
abstract |
High Mountain Asia (HMA) is characterized by some of the most complex and rugged terrain conditions in the world. However, high resolution terrain data are not easy to quickly acquire from the area due to difficulties in accessing the region. In this study, we trained a modified super-resolution residual network (MSRResNet) to develop super-resolution (SR) digital elevation models (DEMs) in the HMA areas by using freely available DEM data from the HMA region and limited high resolution (HR) DEMs from other areas to train the model. In this network, a new loss function was constructed that considered the terrain parameters of slope and curvature to constrain the network learning and convergence. The proposed method was applied to and validated by data from the Hengduan Mountains in the southeastern part of HMA, which is a world-famous longitudinal belt of mountains and canyons. A comparative analysis between the current and existing methods (i.e., SRGAN and Bicubic interpolation) was conducted to assess the effectiveness of the proposed approach. The experimental results were also investigated and evaluated by visual inspection and analysis of the terrain parameters. The results demonstrate that the proposed MSRResNet super-resolution process can achieve highly accurate terrain data by downscaling DEMs in HMA. This SR process also outperforms the other comparable methods. Compared to the Bicubic interpolation method, the RMSE and MAE accuracy are improved by 32.17% and 33.97%, and compared to the SRGAN method, the RMSE and MAE accuracy are improved by 39.15% and 32.47%. The HR DEM generated by the new method is more conducive to improving the accuracy of extracted terrain features, such as stream networks. It is promising to apply this model on other areas on Earth or even other planets with terrain similar to that of HMA. |
abstractGer |
High Mountain Asia (HMA) is characterized by some of the most complex and rugged terrain conditions in the world. However, high resolution terrain data are not easy to quickly acquire from the area due to difficulties in accessing the region. In this study, we trained a modified super-resolution residual network (MSRResNet) to develop super-resolution (SR) digital elevation models (DEMs) in the HMA areas by using freely available DEM data from the HMA region and limited high resolution (HR) DEMs from other areas to train the model. In this network, a new loss function was constructed that considered the terrain parameters of slope and curvature to constrain the network learning and convergence. The proposed method was applied to and validated by data from the Hengduan Mountains in the southeastern part of HMA, which is a world-famous longitudinal belt of mountains and canyons. A comparative analysis between the current and existing methods (i.e., SRGAN and Bicubic interpolation) was conducted to assess the effectiveness of the proposed approach. The experimental results were also investigated and evaluated by visual inspection and analysis of the terrain parameters. The results demonstrate that the proposed MSRResNet super-resolution process can achieve highly accurate terrain data by downscaling DEMs in HMA. This SR process also outperforms the other comparable methods. Compared to the Bicubic interpolation method, the RMSE and MAE accuracy are improved by 32.17% and 33.97%, and compared to the SRGAN method, the RMSE and MAE accuracy are improved by 39.15% and 32.47%. The HR DEM generated by the new method is more conducive to improving the accuracy of extracted terrain features, such as stream networks. It is promising to apply this model on other areas on Earth or even other planets with terrain similar to that of HMA. |
abstract_unstemmed |
High Mountain Asia (HMA) is characterized by some of the most complex and rugged terrain conditions in the world. However, high resolution terrain data are not easy to quickly acquire from the area due to difficulties in accessing the region. In this study, we trained a modified super-resolution residual network (MSRResNet) to develop super-resolution (SR) digital elevation models (DEMs) in the HMA areas by using freely available DEM data from the HMA region and limited high resolution (HR) DEMs from other areas to train the model. In this network, a new loss function was constructed that considered the terrain parameters of slope and curvature to constrain the network learning and convergence. The proposed method was applied to and validated by data from the Hengduan Mountains in the southeastern part of HMA, which is a world-famous longitudinal belt of mountains and canyons. A comparative analysis between the current and existing methods (i.e., SRGAN and Bicubic interpolation) was conducted to assess the effectiveness of the proposed approach. The experimental results were also investigated and evaluated by visual inspection and analysis of the terrain parameters. The results demonstrate that the proposed MSRResNet super-resolution process can achieve highly accurate terrain data by downscaling DEMs in HMA. This SR process also outperforms the other comparable methods. Compared to the Bicubic interpolation method, the RMSE and MAE accuracy are improved by 32.17% and 33.97%, and compared to the SRGAN method, the RMSE and MAE accuracy are improved by 39.15% and 32.47%. The HR DEM generated by the new method is more conducive to improving the accuracy of extracted terrain features, such as stream networks. It is promising to apply this model on other areas on Earth or even other planets with terrain similar to that of HMA. |
collection_details |
GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-KARTEN SSG-OPC-GGO SSG-OPC-AST SSG-OPC-GEO GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2008 GBV_ILN_2014 GBV_ILN_2034 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2064 GBV_ILN_2088 GBV_ILN_2106 GBV_ILN_2112 GBV_ILN_2122 GBV_ILN_2143 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 |
title_short |
Super-resolution for terrain modeling using deep learning in high mountain Asia |
remote_bool |
true |
author2 |
Xiong, Liyang Huang, Xiaohui Li, Sijin Shen, Wang |
author2Str |
Xiong, Liyang Huang, Xiaohui Li, Sijin Shen, Wang |
ppnlink |
359784119 |
mediatype_str_mv |
c |
isOA_txt |
false |
hochschulschrift_bool |
false |
doi_str |
10.1016/j.jag.2023.103296 |
up_date |
2024-07-07T00:16:58.282Z |
_version_ |
1803877265737515008 |
fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV009767037</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240114093228.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230530s2023 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.jag.2023.103296</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV009767037</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S1569-8432(23)00118-8</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">550</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">KARTEN</subfield><subfield code="q">DE-1a</subfield><subfield code="2">fid</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">38.03</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">74.48</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">74.41</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Jiang, Yinghui</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Super-resolution for terrain modeling using deep learning in high mountain Asia</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">High Mountain Asia (HMA) is characterized by some of the most complex and rugged terrain conditions in the world. However, high resolution terrain data are not easy to quickly acquire from the area due to difficulties in accessing the region. In this study, we trained a modified super-resolution residual network (MSRResNet) to develop super-resolution (SR) digital elevation models (DEMs) in the HMA areas by using freely available DEM data from the HMA region and limited high resolution (HR) DEMs from other areas to train the model. In this network, a new loss function was constructed that considered the terrain parameters of slope and curvature to constrain the network learning and convergence. The proposed method was applied to and validated by data from the Hengduan Mountains in the southeastern part of HMA, which is a world-famous longitudinal belt of mountains and canyons. A comparative analysis between the current and existing methods (i.e., SRGAN and Bicubic interpolation) was conducted to assess the effectiveness of the proposed approach. The experimental results were also investigated and evaluated by visual inspection and analysis of the terrain parameters. The results demonstrate that the proposed MSRResNet super-resolution process can achieve highly accurate terrain data by downscaling DEMs in HMA. This SR process also outperforms the other comparable methods. Compared to the Bicubic interpolation method, the RMSE and MAE accuracy are improved by 32.17% and 33.97%, and compared to the SRGAN method, the RMSE and MAE accuracy are improved by 39.15% and 32.47%. The HR DEM generated by the new method is more conducive to improving the accuracy of extracted terrain features, such as stream networks. It is promising to apply this model on other areas on Earth or even other planets with terrain similar to that of HMA.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Terrain modeling</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">DEM super-resolution</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Deep learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">High Mountain Asia</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Xiong, Liyang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Huang, Xiaohui</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Li, Sijin</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Shen, Wang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">International journal of applied earth observation and geoinformation</subfield><subfield code="d">Amsterdam [u.a.] : Elsevier Science, 1999</subfield><subfield code="g">118</subfield><subfield code="h">Online-Ressource</subfield><subfield code="w">(DE-627)359784119</subfield><subfield code="w">(DE-600)2097960-5</subfield><subfield code="w">(DE-576)25927254X</subfield><subfield code="x">1872-826X</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:118</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">FID-KARTEN</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OPC-GGO</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OPC-AST</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OPC-GEO</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_224</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2004</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2005</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2008</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2034</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2044</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2048</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2064</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2088</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2106</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2122</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2143</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2152</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2153</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2232</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2336</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">38.03</subfield><subfield code="j">Methoden und Techniken der Geowissenschaften</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">74.48</subfield><subfield code="j">Geoinformationssysteme</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">74.41</subfield><subfield code="j">Luftaufnahmen</subfield><subfield code="j">Photogrammetrie</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">118</subfield></datafield></record></collection>
|
score |
7.3967133 |