Hierarchical pyramid refined U-Net for creating the first 2 m resolution multi-class national-scale spatial distribution dataset of offshore observable marine aquaculture in China

Precise extraction and dynamic monitoring of observable offshore marine aquaculture (OOMA) areas in remote sensing imagery are essential for the rational layout of offshore aquaculture zones and assessing the marine ecological environment. At present, national-scale offshore marine aquaculture spati...

Full description

Saved in:
Bibliographic Details
Main Authors: Yanlin Chen, Guojin He, Ranyu Yin, Guizhou Wang, Xueli Peng
Format: Article
Language:English
Published: Taylor & Francis Group 2025-08-01
Series:International Journal of Digital Earth
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/17538947.2025.2520471
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849224296318107648
author Yanlin Chen
Guojin He
Ranyu Yin
Guizhou Wang
Xueli Peng
author_facet Yanlin Chen
Guojin He
Ranyu Yin
Guizhou Wang
Xueli Peng
author_sort Yanlin Chen
collection DOAJ
description Precise extraction and dynamic monitoring of observable offshore marine aquaculture (OOMA) areas in remote sensing imagery are essential for the rational layout of offshore aquaculture zones and assessing the marine ecological environment. At present, national-scale offshore marine aquaculture spatial distribution datasets derived from remote sensing imagery in China are of medium to low resolution, and there remains a lack of high-spatial-resolution (HSR) dataset. To address this gap, this study proposes a novel semantic segmentation framework, Hierarchical Pyramid Refined U-Net (HPR-UNet), based on multi-source 2 m resolution remote sensing imagery for the multi-scale extraction of OOMA. The first HSR OOMA spatial distribution dataset of China (RCdata_2022_2 m) has been generated. The study reveals the following: (1) The proposed method is effective in extracting multi-scale OOMA, especially small-scale ones. (2) The RCdata_2022_2 m achieved an overall accuracy of 97.27%. Compared to medium- and low-resolution datasets, RCdata_2022_2 m demonstrated higher accuracy and better extraction results. (3) From 2022 to 2023, the total area of OOMA in China was approximately 253,096.08 ha, with raft aquaculture occupying 232,523.69 ha, and cage aquaculture covering 20,572.39 ha.
format Article
id doaj-art-6a561b487de04339b2f4aff5bfb54ffd
institution Kabale University
issn 1753-8947
1753-8955
language English
publishDate 2025-08-01
publisher Taylor & Francis Group
record_format Article
series International Journal of Digital Earth
spelling doaj-art-6a561b487de04339b2f4aff5bfb54ffd2025-08-25T11:28:36ZengTaylor & Francis GroupInternational Journal of Digital Earth1753-89471753-89552025-08-0118110.1080/17538947.2025.2520471Hierarchical pyramid refined U-Net for creating the first 2 m resolution multi-class national-scale spatial distribution dataset of offshore observable marine aquaculture in ChinaYanlin Chen0Guojin He1Ranyu Yin2Guizhou Wang3Xueli Peng4Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, People’s Republic of ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing, People’s Republic of ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing, People’s Republic of ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing, People’s Republic of ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing, People’s Republic of ChinaPrecise extraction and dynamic monitoring of observable offshore marine aquaculture (OOMA) areas in remote sensing imagery are essential for the rational layout of offshore aquaculture zones and assessing the marine ecological environment. At present, national-scale offshore marine aquaculture spatial distribution datasets derived from remote sensing imagery in China are of medium to low resolution, and there remains a lack of high-spatial-resolution (HSR) dataset. To address this gap, this study proposes a novel semantic segmentation framework, Hierarchical Pyramid Refined U-Net (HPR-UNet), based on multi-source 2 m resolution remote sensing imagery for the multi-scale extraction of OOMA. The first HSR OOMA spatial distribution dataset of China (RCdata_2022_2 m) has been generated. The study reveals the following: (1) The proposed method is effective in extracting multi-scale OOMA, especially small-scale ones. (2) The RCdata_2022_2 m achieved an overall accuracy of 97.27%. Compared to medium- and low-resolution datasets, RCdata_2022_2 m demonstrated higher accuracy and better extraction results. (3) From 2022 to 2023, the total area of OOMA in China was approximately 253,096.08 ha, with raft aquaculture occupying 232,523.69 ha, and cage aquaculture covering 20,572.39 ha.https://www.tandfonline.com/doi/10.1080/17538947.2025.2520471Multi-source remote sensing imageryhigh spatial resolutionobservable offshore marine aquaculturesemantic segmentationU-Net
spellingShingle Yanlin Chen
Guojin He
Ranyu Yin
Guizhou Wang
Xueli Peng
Hierarchical pyramid refined U-Net for creating the first 2 m resolution multi-class national-scale spatial distribution dataset of offshore observable marine aquaculture in China
International Journal of Digital Earth
Multi-source remote sensing imagery
high spatial resolution
observable offshore marine aquaculture
semantic segmentation
U-Net
title Hierarchical pyramid refined U-Net for creating the first 2 m resolution multi-class national-scale spatial distribution dataset of offshore observable marine aquaculture in China
title_full Hierarchical pyramid refined U-Net for creating the first 2 m resolution multi-class national-scale spatial distribution dataset of offshore observable marine aquaculture in China
title_fullStr Hierarchical pyramid refined U-Net for creating the first 2 m resolution multi-class national-scale spatial distribution dataset of offshore observable marine aquaculture in China
title_full_unstemmed Hierarchical pyramid refined U-Net for creating the first 2 m resolution multi-class national-scale spatial distribution dataset of offshore observable marine aquaculture in China
title_short Hierarchical pyramid refined U-Net for creating the first 2 m resolution multi-class national-scale spatial distribution dataset of offshore observable marine aquaculture in China
title_sort hierarchical pyramid refined u net for creating the first 2 m resolution multi class national scale spatial distribution dataset of offshore observable marine aquaculture in china
topic Multi-source remote sensing imagery
high spatial resolution
observable offshore marine aquaculture
semantic segmentation
U-Net
url https://www.tandfonline.com/doi/10.1080/17538947.2025.2520471
work_keys_str_mv AT yanlinchen hierarchicalpyramidrefinedunetforcreatingthefirst2mresolutionmulticlassnationalscalespatialdistributiondatasetofoffshoreobservablemarineaquacultureinchina
AT guojinhe hierarchicalpyramidrefinedunetforcreatingthefirst2mresolutionmulticlassnationalscalespatialdistributiondatasetofoffshoreobservablemarineaquacultureinchina
AT ranyuyin hierarchicalpyramidrefinedunetforcreatingthefirst2mresolutionmulticlassnationalscalespatialdistributiondatasetofoffshoreobservablemarineaquacultureinchina
AT guizhouwang hierarchicalpyramidrefinedunetforcreatingthefirst2mresolutionmulticlassnationalscalespatialdistributiondatasetofoffshoreobservablemarineaquacultureinchina
AT xuelipeng hierarchicalpyramidrefinedunetforcreatingthefirst2mresolutionmulticlassnationalscalespatialdistributiondatasetofoffshoreobservablemarineaquacultureinchina