Deep learning-based super-resolution for harmful algal bloom monitoring of inland water
Inland water frequently occurs during harmful algal blooms (HABs), rendering it challenging to comprehend the spatiotemporal features of algal dynamics. Recently, remote sensing has been applied to effectively detect the algal spatiotemporal behaviors in expensive water bodies. However, image sensor...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2023-12-01
|
| Series: | GIScience & Remote Sensing |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/15481603.2023.2249753 |
| _version_ | 1827811624411463680 |
|---|---|
| author | Do Hyuck Kwon Seok Min Hong Ather Abbas Sanghyun Park Gibeom Nam Jae-Hyun Yoo Kyunghyun Kim Hong Tae Kim JongCheol Pyo Kyung Hwa Cho |
| author_facet | Do Hyuck Kwon Seok Min Hong Ather Abbas Sanghyun Park Gibeom Nam Jae-Hyun Yoo Kyunghyun Kim Hong Tae Kim JongCheol Pyo Kyung Hwa Cho |
| author_sort | Do Hyuck Kwon |
| collection | DOAJ |
| description | Inland water frequently occurs during harmful algal blooms (HABs), rendering it challenging to comprehend the spatiotemporal features of algal dynamics. Recently, remote sensing has been applied to effectively detect the algal spatiotemporal behaviors in expensive water bodies. However, image sensor resolution limitation can render the understanding of spatiotemporal features of relatively small water bodies challenging. In addition, few studies have improved the resolution of remote sensing images to investigate inland water quality, owing to the image sensor resolution limitations. Therefore, this study applied deep learning-based Super-resolution for transforming satellite imagery of 20 m to airborne imagery of 5 m. After performing atmospheric correction for the acquired images, we adopted super-resolution (SR) methodologies using a super-resolution convolutional neural network (SRCNN) and super-resolution generative adversarial networks (SRGAN) to estimate the Chlorophyll-a (Chl-a) concentration in the Geum River of South Korea. Both methods generated SR images with water reflectance at 665, 705, and 740 nm. Then, two band-ratio algorithms at 665 and 740 nm wavelengths were applied to the reflectance images to estimate the Chl-a concentration maps. The SRCNN model outperformed SRGAN and bicubic interpolation with peak signal-to-noise ratios (PSNR), mean square errors (MSE), and structural similarity index measures (SSIM) for the validation dataset of 24.47 (dB), 0.0074, and 0.74, respectively. SR maps from the SRCNN provided more detailed spatial information on Chl-a in the Geum River compared to the information obtained from satellite images. Therefore, these findings showed the potential of deep learning-based SR algorithms by providing further information according to the algal dynamics for inland water management with remote sensing images. |
| first_indexed | 2024-03-11T23:08:16Z |
| format | Article |
| id | doaj.art-3f12053e68594d26bfbef3c5634fd85b |
| institution | Directory Open Access Journal |
| issn | 1548-1603 1943-7226 |
| language | English |
| last_indexed | 2024-03-11T23:08:16Z |
| publishDate | 2023-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | GIScience & Remote Sensing |
| spelling | doaj.art-3f12053e68594d26bfbef3c5634fd85b2023-09-21T12:43:10ZengTaylor & Francis GroupGIScience & Remote Sensing1548-16031943-72262023-12-0160110.1080/15481603.2023.22497532249753Deep learning-based super-resolution for harmful algal bloom monitoring of inland waterDo Hyuck Kwon0Seok Min Hong1Ather Abbas2Sanghyun Park3Gibeom Nam4Jae-Hyun Yoo5Kyunghyun Kim6Hong Tae Kim7JongCheol Pyo8Kyung Hwa Cho9Ulsan National Institute of Science and TechnologyUlsan National Institute of Science and TechnologyUlsan National Institute of Science and TechnologyNational Institute of Environmental ResearchK-Water Institute, K-WaterR&D Center, UWATECH,incNational Institute of Environmental ResearchNational Institute of Environmental ResearchPusan National UniversitySchool of Civil, Environmental and Architectural EngineeringInland water frequently occurs during harmful algal blooms (HABs), rendering it challenging to comprehend the spatiotemporal features of algal dynamics. Recently, remote sensing has been applied to effectively detect the algal spatiotemporal behaviors in expensive water bodies. However, image sensor resolution limitation can render the understanding of spatiotemporal features of relatively small water bodies challenging. In addition, few studies have improved the resolution of remote sensing images to investigate inland water quality, owing to the image sensor resolution limitations. Therefore, this study applied deep learning-based Super-resolution for transforming satellite imagery of 20 m to airborne imagery of 5 m. After performing atmospheric correction for the acquired images, we adopted super-resolution (SR) methodologies using a super-resolution convolutional neural network (SRCNN) and super-resolution generative adversarial networks (SRGAN) to estimate the Chlorophyll-a (Chl-a) concentration in the Geum River of South Korea. Both methods generated SR images with water reflectance at 665, 705, and 740 nm. Then, two band-ratio algorithms at 665 and 740 nm wavelengths were applied to the reflectance images to estimate the Chl-a concentration maps. The SRCNN model outperformed SRGAN and bicubic interpolation with peak signal-to-noise ratios (PSNR), mean square errors (MSE), and structural similarity index measures (SSIM) for the validation dataset of 24.47 (dB), 0.0074, and 0.74, respectively. SR maps from the SRCNN provided more detailed spatial information on Chl-a in the Geum River compared to the information obtained from satellite images. Therefore, these findings showed the potential of deep learning-based SR algorithms by providing further information according to the algal dynamics for inland water management with remote sensing images.http://dx.doi.org/10.1080/15481603.2023.2249753super-resolutionconvolutional neural network (cnn)generative adversarial network (gan)remote sensingchlorophyll-a |
| spellingShingle | Do Hyuck Kwon Seok Min Hong Ather Abbas Sanghyun Park Gibeom Nam Jae-Hyun Yoo Kyunghyun Kim Hong Tae Kim JongCheol Pyo Kyung Hwa Cho Deep learning-based super-resolution for harmful algal bloom monitoring of inland water GIScience & Remote Sensing super-resolution convolutional neural network (cnn) generative adversarial network (gan) remote sensing chlorophyll-a |
| title | Deep learning-based super-resolution for harmful algal bloom monitoring of inland water |
| title_full | Deep learning-based super-resolution for harmful algal bloom monitoring of inland water |
| title_fullStr | Deep learning-based super-resolution for harmful algal bloom monitoring of inland water |
| title_full_unstemmed | Deep learning-based super-resolution for harmful algal bloom monitoring of inland water |
| title_short | Deep learning-based super-resolution for harmful algal bloom monitoring of inland water |
| title_sort | deep learning based super resolution for harmful algal bloom monitoring of inland water |
| topic | super-resolution convolutional neural network (cnn) generative adversarial network (gan) remote sensing chlorophyll-a |
| url | http://dx.doi.org/10.1080/15481603.2023.2249753 |
| work_keys_str_mv | AT dohyuckkwon deeplearningbasedsuperresolutionforharmfulalgalbloommonitoringofinlandwater AT seokminhong deeplearningbasedsuperresolutionforharmfulalgalbloommonitoringofinlandwater AT atherabbas deeplearningbasedsuperresolutionforharmfulalgalbloommonitoringofinlandwater AT sanghyunpark deeplearningbasedsuperresolutionforharmfulalgalbloommonitoringofinlandwater AT gibeomnam deeplearningbasedsuperresolutionforharmfulalgalbloommonitoringofinlandwater AT jaehyunyoo deeplearningbasedsuperresolutionforharmfulalgalbloommonitoringofinlandwater AT kyunghyunkim deeplearningbasedsuperresolutionforharmfulalgalbloommonitoringofinlandwater AT hongtaekim deeplearningbasedsuperresolutionforharmfulalgalbloommonitoringofinlandwater AT jongcheolpyo deeplearningbasedsuperresolutionforharmfulalgalbloommonitoringofinlandwater AT kyunghwacho deeplearningbasedsuperresolutionforharmfulalgalbloommonitoringofinlandwater |