Extracting Water Surfaces of the Dike-Pond System from High Spatial Resolution Images Using Deep Learning Methods DOI Creative Commons

Jinhao Zhou,

K. S. Fu, Shen Liang

et al.

Remote Sensing, Journal Year: 2024, Volume and Issue: 17(1), P. 111 - 111

Published: Dec. 31, 2024

A type of aquaculture pond called a dike-pond system is distributed in the low-lying river delta China’s eastern coast. Along with swift growth coastal economy, water surfaces (WDPS) play major role attributed to yielding more profits than dike agriculture. This study aims explore performance deep learning methods for extracting WDPS from high spatial resolution remote sensing images. We developed three fully convolutional network (FCN) models: SegNet, UNet, and UNet++, which are compared two traditional same testing regions Guangdong–Hong Kong–Macao Greater Bay Area. The extraction results five evaluated parts. first part general comparison that shows biggest advantage FCN models over P-score, an average lead 13%, but R-score not ideal. Our analysis reveals low problem due omission outer ring rather quantity WDPS. also analyzed reasons behind it provided potential solutions. second error, demonstrates have few connected, jagged, or perforated WDPS, beneficial assessing fishery production, pattern changes, ecological value, other applications extracted by visually close ground truth, one most significant improvements methods. third special scenarios, including various shape types, intricate configurations, multiple conditions. irregular shapes juxtaposed land types increases difficulty extraction, still achieve P-scores above 0.95 while conditions causes sharp drop indicators all methods, requires further improvement solve it. integrated performances provide recommendations their use. offers valuable insights enhancing leveraging practical applications.

Language: Английский

Spatial extraction of sea-cucumber aquaculture ponds using remote sensing spectral and temporal features DOI Creative Commons
Du R, He Li, Chong Huang

et al.

Frontiers in Marine Science, Journal Year: 2025, Volume and Issue: 12

Published: March 24, 2025

The spatial distribution of aquaculture ponds plays a critical role in the layout, management, and evaluation industry. While extensive research has been conducted on pond extraction monitoring, studies focusing differentiation by species remain limited. similar shapes spectral features water bodies associated with different pose challenge for extraction. A method extracting sea-cucumber is proposed based temporal using Sentinel-2 satellite imagery this study. involves selecting optimal sensitive bands or combinations to construct two remote sensing indices land-based ponds. Using time-series dataset these indices, three key features—the mean slopes—are extracted. corresponding time windows thresholds are identified develop decision-tree algorithm This was applied coastal zones Liaoning Province, China, identify 2016 2023. results showed that: (1) achieved high accuracy, an overall accuracy 79.24%; (2) Total area Province 931.08 km 2 , primarily located along Huludao Xingcheng-Jinzhou Linghai Yingkou Xishi-Dalian Zhuanghe zones; (3) Over past seven years, increased 624.57 expansion concentrated northwest coast Liaodong Bay both eastern western sides Peninsula. These findings provide scientific support sustainable development aquaculture.

Language: Английский

Citations

0
Temporal dynamics of soil salinization due to vertical and lateral saltwater intrusion at an onshore aquaculture farm DOI Creative Commons
Xuan Yu, Beiyuan Xu, Rongjiang Yao

et al.

Agricultural Water Management, Journal Year: 2024, Volume and Issue: 306, P. 109179 - 109179

Published: Nov. 16, 2024

Language: Английский

Citations

2
Extracting Water Surfaces of the Dike-Pond System from High Spatial Resolution Images Using Deep Learning Methods DOI Creative Commons

Jinhao Zhou,

K. S. Fu, Shen Liang

et al.

Remote Sensing, Journal Year: 2024, Volume and Issue: 17(1), P. 111 - 111

Published: Dec. 31, 2024

A type of aquaculture pond called a dike-pond system is distributed in the low-lying river delta China’s eastern coast. Along with swift growth coastal economy, water surfaces (WDPS) play major role attributed to yielding more profits than dike agriculture. This study aims explore performance deep learning methods for extracting WDPS from high spatial resolution remote sensing images. We developed three fully convolutional network (FCN) models: SegNet, UNet, and UNet++, which are compared two traditional same testing regions Guangdong–Hong Kong–Macao Greater Bay Area. The extraction results five evaluated parts. first part general comparison that shows biggest advantage FCN models over P-score, an average lead 13%, but R-score not ideal. Our analysis reveals low problem due omission outer ring rather quantity WDPS. also analyzed reasons behind it provided potential solutions. second error, demonstrates have few connected, jagged, or perforated WDPS, beneficial assessing fishery production, pattern changes, ecological value, other applications extracted by visually close ground truth, one most significant improvements methods. third special scenarios, including various shape types, intricate configurations, multiple conditions. irregular shapes juxtaposed land types increases difficulty extraction, still achieve P-scores above 0.95 while conditions causes sharp drop indicators all methods, requires further improvement solve it. integrated performances provide recommendations their use. offers valuable insights enhancing leveraging practical applications.

Language: Английский

Citations

0