Marine aquaculture mapping using GF-1 WFV satellite images and full resolution cascade convolutional neural network
Growing demand for seafood and reduced fishery harvests have raised intensive farming of marine aquaculture in coastal regions, which may cause severe coastal water problems without adequate environmental management. Effective mapping of mariculture areas is essential for the protection of coastal e...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2022-12-01
|
| Series: | International Journal of Digital Earth |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/17538947.2022.2133184 |
| _version_ | 1797678476174557184 |
|---|---|
| author | Yongyong Fu Shucheng You Shujuan Zhang Kun Cao Jianhua Zhang Ping Wang Xu Bi Feng Gao Fangzhou Li |
| author_facet | Yongyong Fu Shucheng You Shujuan Zhang Kun Cao Jianhua Zhang Ping Wang Xu Bi Feng Gao Fangzhou Li |
| author_sort | Yongyong Fu |
| collection | DOAJ |
| description | Growing demand for seafood and reduced fishery harvests have raised intensive farming of marine aquaculture in coastal regions, which may cause severe coastal water problems without adequate environmental management. Effective mapping of mariculture areas is essential for the protection of coastal environments. However, due to the limited spatial coverage and complex structures, it is still challenging for traditional methods to accurately extract mariculture areas from medium spatial resolution (MSR) images. To solve this problem, we propose to use the full resolution cascade convolutional neural network (FRCNet), which maintains effective features over the whole training process, to identify mariculture areas from MSR images. Specifically, the FRCNet uses a sequential full resolution neural network as the first-level subnetwork, and gradually aggregates higher-level subnetworks in a cascade way. Meanwhile, we perform a repeated fusion strategy so that features can receive information from different subnetworks simultaneously, leading to rich and representative features. As a result, FRCNet can effectively recognize different kinds of mariculture areas from MSR images. Results show that FRCNet obtained better performance than other classical and recently proposed methods. Our developed methods can provide valuable datasets for large-scale and intelligent modeling of the marine aquaculture management and coastal zone planning. |
| first_indexed | 2024-03-11T23:00:19Z |
| format | Article |
| id | doaj.art-3326cdaba74149f9878677742855eec9 |
| institution | Directory Open Access Journal |
| issn | 1753-8947 1753-8955 |
| language | English |
| last_indexed | 2024-03-11T23:00:19Z |
| publishDate | 2022-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | International Journal of Digital Earth |
| spelling | doaj.art-3326cdaba74149f9878677742855eec92023-09-21T14:57:11ZengTaylor & Francis GroupInternational Journal of Digital Earth1753-89471753-89552022-12-011512047206010.1080/17538947.2022.21331842133184Marine aquaculture mapping using GF-1 WFV satellite images and full resolution cascade convolutional neural networkYongyong Fu0Shucheng You1Shujuan Zhang2Kun Cao3Jianhua Zhang4Ping Wang5Xu Bi6Feng Gao7Fangzhou Li8Shanxi University of Finance and EconomicsLand Satellite Remote Sensing Application CenterShandong Agricultural Ecology and Resource Protection StationChinese Academy of Fishery SciencesZhejiang UniversityShanxi University of Finance and EconomicsShanxi University of Finance and EconomicsShanxi University of Finance and EconomicsMinistry of Natural ResourcesGrowing demand for seafood and reduced fishery harvests have raised intensive farming of marine aquaculture in coastal regions, which may cause severe coastal water problems without adequate environmental management. Effective mapping of mariculture areas is essential for the protection of coastal environments. However, due to the limited spatial coverage and complex structures, it is still challenging for traditional methods to accurately extract mariculture areas from medium spatial resolution (MSR) images. To solve this problem, we propose to use the full resolution cascade convolutional neural network (FRCNet), which maintains effective features over the whole training process, to identify mariculture areas from MSR images. Specifically, the FRCNet uses a sequential full resolution neural network as the first-level subnetwork, and gradually aggregates higher-level subnetworks in a cascade way. Meanwhile, we perform a repeated fusion strategy so that features can receive information from different subnetworks simultaneously, leading to rich and representative features. As a result, FRCNet can effectively recognize different kinds of mariculture areas from MSR images. Results show that FRCNet obtained better performance than other classical and recently proposed methods. Our developed methods can provide valuable datasets for large-scale and intelligent modeling of the marine aquaculture management and coastal zone planning.http://dx.doi.org/10.1080/17538947.2022.2133184mariculture areasgaofen-1 wide-field-of-view imagesfully convolutional neural networksdeep learning |
| spellingShingle | Yongyong Fu Shucheng You Shujuan Zhang Kun Cao Jianhua Zhang Ping Wang Xu Bi Feng Gao Fangzhou Li Marine aquaculture mapping using GF-1 WFV satellite images and full resolution cascade convolutional neural network International Journal of Digital Earth mariculture areas gaofen-1 wide-field-of-view images fully convolutional neural networks deep learning |
| title | Marine aquaculture mapping using GF-1 WFV satellite images and full resolution cascade convolutional neural network |
| title_full | Marine aquaculture mapping using GF-1 WFV satellite images and full resolution cascade convolutional neural network |
| title_fullStr | Marine aquaculture mapping using GF-1 WFV satellite images and full resolution cascade convolutional neural network |
| title_full_unstemmed | Marine aquaculture mapping using GF-1 WFV satellite images and full resolution cascade convolutional neural network |
| title_short | Marine aquaculture mapping using GF-1 WFV satellite images and full resolution cascade convolutional neural network |
| title_sort | marine aquaculture mapping using gf 1 wfv satellite images and full resolution cascade convolutional neural network |
| topic | mariculture areas gaofen-1 wide-field-of-view images fully convolutional neural networks deep learning |
| url | http://dx.doi.org/10.1080/17538947.2022.2133184 |
| work_keys_str_mv | AT yongyongfu marineaquaculturemappingusinggf1wfvsatelliteimagesandfullresolutioncascadeconvolutionalneuralnetwork AT shuchengyou marineaquaculturemappingusinggf1wfvsatelliteimagesandfullresolutioncascadeconvolutionalneuralnetwork AT shujuanzhang marineaquaculturemappingusinggf1wfvsatelliteimagesandfullresolutioncascadeconvolutionalneuralnetwork AT kuncao marineaquaculturemappingusinggf1wfvsatelliteimagesandfullresolutioncascadeconvolutionalneuralnetwork AT jianhuazhang marineaquaculturemappingusinggf1wfvsatelliteimagesandfullresolutioncascadeconvolutionalneuralnetwork AT pingwang marineaquaculturemappingusinggf1wfvsatelliteimagesandfullresolutioncascadeconvolutionalneuralnetwork AT xubi marineaquaculturemappingusinggf1wfvsatelliteimagesandfullresolutioncascadeconvolutionalneuralnetwork AT fenggao marineaquaculturemappingusinggf1wfvsatelliteimagesandfullresolutioncascadeconvolutionalneuralnetwork AT fangzhouli marineaquaculturemappingusinggf1wfvsatelliteimagesandfullresolutioncascadeconvolutionalneuralnetwork |