Bathymetry Inversion Using Attention-Based Band Optimization Model for Hyperspectral or Multispectral Satellite Imagery
Satellite-derived bathymetry enables the non-contact derivation of large-scale shallow water depths. Hyperspectral satellite images provide more information than multispectral satellite images, making them theoretically more effective and accurate for bathymetry inversion. This paper focuses on the...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Water |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4441/15/18/3205 |
| _version_ | 1797576304234594304 |
|---|---|
| author | Yingxi Wang Ming Chen Xiaotao Xi Hua Yang |
| author_facet | Yingxi Wang Ming Chen Xiaotao Xi Hua Yang |
| author_sort | Yingxi Wang |
| collection | DOAJ |
| description | Satellite-derived bathymetry enables the non-contact derivation of large-scale shallow water depths. Hyperspectral satellite images provide more information than multispectral satellite images, making them theoretically more effective and accurate for bathymetry inversion. This paper focuses on the use of hyperspectral satellite images (PRISMA) for bathymetry inversion and compares the retrieval capabilities of multispectral satellite images (Sentinel-2 and Landsat 9) in the southeastern waters of Molokai Island in the Hawaiian Archipelago and Yinyu Island in the Paracel Archipelago. This paper proposes an attention-based band optimization one-dimensional convolutional neural network model (ABO-CNN) to better utilize the increased spectral information from multispectral and hyperspectral images for bathymetry inversion, and this model is compared with a traditional empirical model (Stumpf model) and two deep learning models (feedforward neural network and one-dimensional convolutional neural network). The results indicate that the ABO-CNN model outperforms the above three models, and the root mean square errors of retrieved bathymetry using the PRISMA images are 1.43 m and 0.73 m in the above two study areas, respectively. In summary, this paper demonstrates that PRISMA hyperspectral imagery has superior bathymetry inversion capabilities compared to multispectral images (Sentinel-2 and Landsat 9), and the proposed deep learning model ABO-CNN is a promising candidate model for satellite-derived bathymetry using hyperspectral imagery. With the increasing availability of ICESat-2 bathymetric data, the use of a combination of the proposed ABO-CNN model and the ICEsat-2 data as the training data provides a practical approach for bathymetric retrieval applications. |
| first_indexed | 2024-03-10T21:51:17Z |
| format | Article |
| id | doaj.art-310ffab42a0b4a958edc553f17196590 |
| institution | Directory Open Access Journal |
| issn | 2073-4441 |
| language | English |
| last_indexed | 2024-03-10T21:51:17Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Water |
| spelling | doaj.art-310ffab42a0b4a958edc553f171965902023-11-19T13:25:18ZengMDPI AGWater2073-44412023-09-011518320510.3390/w15183205Bathymetry Inversion Using Attention-Based Band Optimization Model for Hyperspectral or Multispectral Satellite ImageryYingxi Wang0Ming Chen1Xiaotao Xi2Hua Yang3College of Information, Shanghai Ocean University, No. 999 Huchenghuan Road, Shanghai 201306, ChinaCollege of Information, Shanghai Ocean University, No. 999 Huchenghuan Road, Shanghai 201306, ChinaCollege of Information, Shanghai Ocean University, No. 999 Huchenghuan Road, Shanghai 201306, ChinaCollege of Information, Shanghai Ocean University, No. 999 Huchenghuan Road, Shanghai 201306, ChinaSatellite-derived bathymetry enables the non-contact derivation of large-scale shallow water depths. Hyperspectral satellite images provide more information than multispectral satellite images, making them theoretically more effective and accurate for bathymetry inversion. This paper focuses on the use of hyperspectral satellite images (PRISMA) for bathymetry inversion and compares the retrieval capabilities of multispectral satellite images (Sentinel-2 and Landsat 9) in the southeastern waters of Molokai Island in the Hawaiian Archipelago and Yinyu Island in the Paracel Archipelago. This paper proposes an attention-based band optimization one-dimensional convolutional neural network model (ABO-CNN) to better utilize the increased spectral information from multispectral and hyperspectral images for bathymetry inversion, and this model is compared with a traditional empirical model (Stumpf model) and two deep learning models (feedforward neural network and one-dimensional convolutional neural network). The results indicate that the ABO-CNN model outperforms the above three models, and the root mean square errors of retrieved bathymetry using the PRISMA images are 1.43 m and 0.73 m in the above two study areas, respectively. In summary, this paper demonstrates that PRISMA hyperspectral imagery has superior bathymetry inversion capabilities compared to multispectral images (Sentinel-2 and Landsat 9), and the proposed deep learning model ABO-CNN is a promising candidate model for satellite-derived bathymetry using hyperspectral imagery. With the increasing availability of ICESat-2 bathymetric data, the use of a combination of the proposed ABO-CNN model and the ICEsat-2 data as the training data provides a practical approach for bathymetric retrieval applications.https://www.mdpi.com/2073-4441/15/18/3205bathymetrysatellite-derived bathymetryhyperspectralsatellite imageryconvolutional neural networkICESat-2 |
| spellingShingle | Yingxi Wang Ming Chen Xiaotao Xi Hua Yang Bathymetry Inversion Using Attention-Based Band Optimization Model for Hyperspectral or Multispectral Satellite Imagery Water bathymetry satellite-derived bathymetry hyperspectral satellite imagery convolutional neural network ICESat-2 |
| title | Bathymetry Inversion Using Attention-Based Band Optimization Model for Hyperspectral or Multispectral Satellite Imagery |
| title_full | Bathymetry Inversion Using Attention-Based Band Optimization Model for Hyperspectral or Multispectral Satellite Imagery |
| title_fullStr | Bathymetry Inversion Using Attention-Based Band Optimization Model for Hyperspectral or Multispectral Satellite Imagery |
| title_full_unstemmed | Bathymetry Inversion Using Attention-Based Band Optimization Model for Hyperspectral or Multispectral Satellite Imagery |
| title_short | Bathymetry Inversion Using Attention-Based Band Optimization Model for Hyperspectral or Multispectral Satellite Imagery |
| title_sort | bathymetry inversion using attention based band optimization model for hyperspectral or multispectral satellite imagery |
| topic | bathymetry satellite-derived bathymetry hyperspectral satellite imagery convolutional neural network ICESat-2 |
| url | https://www.mdpi.com/2073-4441/15/18/3205 |
| work_keys_str_mv | AT yingxiwang bathymetryinversionusingattentionbasedbandoptimizationmodelforhyperspectralormultispectralsatelliteimagery AT mingchen bathymetryinversionusingattentionbasedbandoptimizationmodelforhyperspectralormultispectralsatelliteimagery AT xiaotaoxi bathymetryinversionusingattentionbasedbandoptimizationmodelforhyperspectralormultispectralsatelliteimagery AT huayang bathymetryinversionusingattentionbasedbandoptimizationmodelforhyperspectralormultispectralsatelliteimagery |