Enhancing coastal bathymetric mapping with physics-informed recurrent neural networks synergizing Gaofen satellite imagery and ICESat-2 lidar data: A case in the South China Sea
Satellite-derived bathymetry (SDB) has emerged as a critical technique in response to the growing demand for large-scale coastal bathymetric mapping. However, high-resolution multispectral imagery from Gaofen satellites presents significant challenges owing to low signal-to-noise ratios (SNRs). This...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-07-01
|
| Series: | Ecological Informatics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S157495412500130X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850197360152412160 |
|---|---|
| author | Congshuang Xie Siqi Zhang Zhenhua Zhang Peng Chen Delu Pan |
| author_facet | Congshuang Xie Siqi Zhang Zhenhua Zhang Peng Chen Delu Pan |
| author_sort | Congshuang Xie |
| collection | DOAJ |
| description | Satellite-derived bathymetry (SDB) has emerged as a critical technique in response to the growing demand for large-scale coastal bathymetric mapping. However, high-resolution multispectral imagery from Gaofen satellites presents significant challenges owing to low signal-to-noise ratios (SNRs). This study aimed to enhance coastal bathymetric mapping by integrating high-resolution Gaofen satellite imagery with ICESat-2 lidar-derived bathymetry. The specific goals are to develop a novel physics-informed recurrent neural network (PI-RNN) for SDB that does not rely on prior information and assess its performance in terms of accuracy and robustness. We propose a physics-based RNN model that combines spectral and radiative transfer information from Gaofen satellite imagery with reference bathymetric data from ICESat-2. This methodology includes an adaptive ellipse density-based spatial clustering of applications with noise (AE-DBSCAN) algorithm for ICESat-2 data extraction, which surpasses standard DBSCAN in terms of accuracy. The RNN model was trained using various band combinations of Gaofen satellite data, and its performance was evaluated against in-situ measurements from Ganquan Island in the South China Sea. The physics-based RNN model achieved good bathymetric accuracy, with a coefficient of determination (R2) value >0.93 and a root mean square error (RMSE) < 0.83 m when compared to in-situ measurements on Ganquan Island, indicating the model demonstrates high robustness even under low-SNR satellite imagery conditions. In addition, the inclusion of radiative transfer information in the band combination significantly improved the training accuracy of the model, with the average RMSE being 0.2 m lower and the average R2 improving by 3 % compared to results without physical information. On Huaguang Reef, the model performance further improved with R2 values ranging from 0.93 to 0.97 and RMSE between 0.55 and 0.66 m after applying atmospheric correction when compared to the ICESat-2 reference bathymetric data. Without atmospheric correction, the R2 of the estimated depth was in the range of 0.85 to 0.94 and RMSE in the range of 0.62 to 0.71 m, indicating that although the model mitigated some atmospheric interference effects, atmospheric correction was still necessary to achieve higher accuracy under strong atmospheric conditions. This study demonstrates that a PI-RNN can significantly enhance SDB accuracy, even under challenging conditions. The integration of active and passive remote-sensing data provides a reliable and efficient tool for large-scale coastal bathymetric mapping. The unique contribution of this study lies in the development of a novel RNN model that leverages both spectral and physical information, offering a more accurate and generalised approach to SDB. Plain language summary: Traditional methods for creating these maps are limited because of their high cost, time consumption, and reliance on favourable weather and sea conditions. To overcome these challenges, we integrated high-resolution images from China's Gaofen satellite with precise laser measurements obtained from NASA's ICESat-2 satellite. Using a physics-based recurrent neural network (RNN), we processed these data and generated detailed bathymetric maps without the need for onsite measurements. The key steps in our process included developing a new algorithm to extract accurate seafloor data from ICESat-2 laser measurements, and a neural network that incorporated both spectral information from satellite images and the physical principles of light interaction in water bodies. We tested our method in the South China Sea, where it produced highly accurate results with a coefficient of variation (R2) value >0.93 and a root mean square error (RMSE) < 0.83 m when compared to actual measurements from an island in the area. This study demonstrates that our method not only achieves remarkable bathymetric accuracy but also simplifies the mapping process by eliminating the need for complex atmospheric corrections. This advancement is a significant step forwards in the field of coastal mapping and offers a more efficient and effective tool for managing and understanding coastal resources and the environment. |
| format | Article |
| id | doaj-art-c71219d07bcc4bbda4161d3fbc37e59f |
| institution | OA Journals |
| issn | 1574-9541 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecological Informatics |
| spelling | doaj-art-c71219d07bcc4bbda4161d3fbc37e59f2025-08-20T02:13:11ZengElsevierEcological Informatics1574-95412025-07-018710312110.1016/j.ecoinf.2025.103121Enhancing coastal bathymetric mapping with physics-informed recurrent neural networks synergizing Gaofen satellite imagery and ICESat-2 lidar data: A case in the South China SeaCongshuang Xie0Siqi Zhang1Zhenhua Zhang2Peng Chen3Delu Pan4State Key Laboratory of Satellite Ocean Environment Dynamics, Second Institute of Oceanography, Ministry of Natural Resources, Hangzhou 310012, ChinaState Key Laboratory of Satellite Ocean Environment Dynamics, Second Institute of Oceanography, Ministry of Natural Resources, Hangzhou 310012, China; Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou), No. 1119, Haibin Rd., Nansha District, Guangzhou, ChinaState Key Laboratory of Satellite Ocean Environment Dynamics, Second Institute of Oceanography, Ministry of Natural Resources, Hangzhou 310012, China; Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou), No. 1119, Haibin Rd., Nansha District, Guangzhou, ChinaState Key Laboratory of Satellite Ocean Environment Dynamics, Second Institute of Oceanography, Ministry of Natural Resources, Hangzhou 310012, China; Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou), No. 1119, Haibin Rd., Nansha District, Guangzhou, China; Donghai Laboratory, No. 1, Zhejiang Da Rd., Dinghai District, Zhoushan 310030, China; Institute of Oceanographic Instrumentation, Qilu University of Technology (Shandong Academy of Sciences), Qingdao 266061, China; Corresponding author at: State Key Laboratory of Satellite Ocean Environment Dynamics, Second Institute of Oceanography, Ministry of Natural Resources, Hangzhou 310012, China.State Key Laboratory of Satellite Ocean Environment Dynamics, Second Institute of Oceanography, Ministry of Natural Resources, Hangzhou 310012, China; Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou), No. 1119, Haibin Rd., Nansha District, Guangzhou, China; Institute of Oceanographic Instrumentation, Qilu University of Technology (Shandong Academy of Sciences), Qingdao 266061, ChinaSatellite-derived bathymetry (SDB) has emerged as a critical technique in response to the growing demand for large-scale coastal bathymetric mapping. However, high-resolution multispectral imagery from Gaofen satellites presents significant challenges owing to low signal-to-noise ratios (SNRs). This study aimed to enhance coastal bathymetric mapping by integrating high-resolution Gaofen satellite imagery with ICESat-2 lidar-derived bathymetry. The specific goals are to develop a novel physics-informed recurrent neural network (PI-RNN) for SDB that does not rely on prior information and assess its performance in terms of accuracy and robustness. We propose a physics-based RNN model that combines spectral and radiative transfer information from Gaofen satellite imagery with reference bathymetric data from ICESat-2. This methodology includes an adaptive ellipse density-based spatial clustering of applications with noise (AE-DBSCAN) algorithm for ICESat-2 data extraction, which surpasses standard DBSCAN in terms of accuracy. The RNN model was trained using various band combinations of Gaofen satellite data, and its performance was evaluated against in-situ measurements from Ganquan Island in the South China Sea. The physics-based RNN model achieved good bathymetric accuracy, with a coefficient of determination (R2) value >0.93 and a root mean square error (RMSE) < 0.83 m when compared to in-situ measurements on Ganquan Island, indicating the model demonstrates high robustness even under low-SNR satellite imagery conditions. In addition, the inclusion of radiative transfer information in the band combination significantly improved the training accuracy of the model, with the average RMSE being 0.2 m lower and the average R2 improving by 3 % compared to results without physical information. On Huaguang Reef, the model performance further improved with R2 values ranging from 0.93 to 0.97 and RMSE between 0.55 and 0.66 m after applying atmospheric correction when compared to the ICESat-2 reference bathymetric data. Without atmospheric correction, the R2 of the estimated depth was in the range of 0.85 to 0.94 and RMSE in the range of 0.62 to 0.71 m, indicating that although the model mitigated some atmospheric interference effects, atmospheric correction was still necessary to achieve higher accuracy under strong atmospheric conditions. This study demonstrates that a PI-RNN can significantly enhance SDB accuracy, even under challenging conditions. The integration of active and passive remote-sensing data provides a reliable and efficient tool for large-scale coastal bathymetric mapping. The unique contribution of this study lies in the development of a novel RNN model that leverages both spectral and physical information, offering a more accurate and generalised approach to SDB. Plain language summary: Traditional methods for creating these maps are limited because of their high cost, time consumption, and reliance on favourable weather and sea conditions. To overcome these challenges, we integrated high-resolution images from China's Gaofen satellite with precise laser measurements obtained from NASA's ICESat-2 satellite. Using a physics-based recurrent neural network (RNN), we processed these data and generated detailed bathymetric maps without the need for onsite measurements. The key steps in our process included developing a new algorithm to extract accurate seafloor data from ICESat-2 laser measurements, and a neural network that incorporated both spectral information from satellite images and the physical principles of light interaction in water bodies. We tested our method in the South China Sea, where it produced highly accurate results with a coefficient of variation (R2) value >0.93 and a root mean square error (RMSE) < 0.83 m when compared to actual measurements from an island in the area. This study demonstrates that our method not only achieves remarkable bathymetric accuracy but also simplifies the mapping process by eliminating the need for complex atmospheric corrections. This advancement is a significant step forwards in the field of coastal mapping and offers a more efficient and effective tool for managing and understanding coastal resources and the environment.http://www.sciencedirect.com/science/article/pii/S157495412500130XCoastal bathymetrySatellite-derived bathymetry (SDB)Physics-informed recurrent neural network (PI-RNN)Gaofen satellite imageryICESat-2/ATLAS LidarAdaptive ellipse DBSCAN (AE-DBSCAN) |
| spellingShingle | Congshuang Xie Siqi Zhang Zhenhua Zhang Peng Chen Delu Pan Enhancing coastal bathymetric mapping with physics-informed recurrent neural networks synergizing Gaofen satellite imagery and ICESat-2 lidar data: A case in the South China Sea Ecological Informatics Coastal bathymetry Satellite-derived bathymetry (SDB) Physics-informed recurrent neural network (PI-RNN) Gaofen satellite imagery ICESat-2/ATLAS Lidar Adaptive ellipse DBSCAN (AE-DBSCAN) |
| title | Enhancing coastal bathymetric mapping with physics-informed recurrent neural networks synergizing Gaofen satellite imagery and ICESat-2 lidar data: A case in the South China Sea |
| title_full | Enhancing coastal bathymetric mapping with physics-informed recurrent neural networks synergizing Gaofen satellite imagery and ICESat-2 lidar data: A case in the South China Sea |
| title_fullStr | Enhancing coastal bathymetric mapping with physics-informed recurrent neural networks synergizing Gaofen satellite imagery and ICESat-2 lidar data: A case in the South China Sea |
| title_full_unstemmed | Enhancing coastal bathymetric mapping with physics-informed recurrent neural networks synergizing Gaofen satellite imagery and ICESat-2 lidar data: A case in the South China Sea |
| title_short | Enhancing coastal bathymetric mapping with physics-informed recurrent neural networks synergizing Gaofen satellite imagery and ICESat-2 lidar data: A case in the South China Sea |
| title_sort | enhancing coastal bathymetric mapping with physics informed recurrent neural networks synergizing gaofen satellite imagery and icesat 2 lidar data a case in the south china sea |
| topic | Coastal bathymetry Satellite-derived bathymetry (SDB) Physics-informed recurrent neural network (PI-RNN) Gaofen satellite imagery ICESat-2/ATLAS Lidar Adaptive ellipse DBSCAN (AE-DBSCAN) |
| url | http://www.sciencedirect.com/science/article/pii/S157495412500130X |
| work_keys_str_mv | AT congshuangxie enhancingcoastalbathymetricmappingwithphysicsinformedrecurrentneuralnetworkssynergizinggaofensatelliteimageryandicesat2lidardataacaseinthesouthchinasea AT siqizhang enhancingcoastalbathymetricmappingwithphysicsinformedrecurrentneuralnetworkssynergizinggaofensatelliteimageryandicesat2lidardataacaseinthesouthchinasea AT zhenhuazhang enhancingcoastalbathymetricmappingwithphysicsinformedrecurrentneuralnetworkssynergizinggaofensatelliteimageryandicesat2lidardataacaseinthesouthchinasea AT pengchen enhancingcoastalbathymetricmappingwithphysicsinformedrecurrentneuralnetworkssynergizinggaofensatelliteimageryandicesat2lidardataacaseinthesouthchinasea AT delupan enhancingcoastalbathymetricmappingwithphysicsinformedrecurrentneuralnetworkssynergizinggaofensatelliteimageryandicesat2lidardataacaseinthesouthchinasea |