Enhancing semantic segmentation of Ecuadorian shrimp ponds through fine-tuned vision transformers and U-Net architectures utilizing open-source remote sensing data
文献类型：期刊论文
| 作者 | Jacome, Daniel2,3; Wang, Jianghao1,2,3; Ge, Yong1,2,3,4 |
| 刊名 | INTERNATIONAL JOURNAL OF DIGITAL EARTH
 |
| 出版日期 | 2025-12-31 |
| 卷号 | 18期号:1页码:2538214 |
| 关键词 | Pond segmentation remote sensing ViT U-Net fine-tuning |
| ISSN号 | 1753-8947 |
| DOI | 10.1080/17538947.2025.2538214 |
| 产权排序 | 1 |
| 文献子类 | Article |
| 英文摘要 | Aquaculture has emerged as an important pillar of global food production, and shrimp farming plays a critical role in fulfilling the growing demand for seafood. This is especially true in Ecuador, which is recognized as one of the world's largest exporters and producers of shrimp. However, conventional shrimp pond monitoring has limitations owing to the extensive scale and operational complexity. Traditional methods using low-resolution imagery and ground surveys are hampered by cloud cover, outdated maps, and insufficient temporal resolution, leading to inaccurate pond area estimations and hindering timely management. Our framework accurately segmented shrimp ponds from high-resolution satellite images. Using a fine-tuned Prithvi 100M model, we achieved a state-of-the-art mIoU of 0.970 and 0.993 accuracy, respectively. This significantly surpasses other models, such as ViT-base (mIoU = 0.878) and U-Net variants (mIoU = 0.949). The pre-training of the Prithvi 100M model allowed it to effectively capture intricate pond boundaries and subtle internal structures, resulting in highly accurate and detailed segmentation masks. Fine-tuning the encoder proved to be the most effective (mIoU = 0.991), whereas standard data augmentation negatively impacted the performance. This methodology offers a valuable tool for enhancing water resource management and promoting sustainable aquaculture practices in Ecuadorian coastal regions. |
| URL标识 | 查看原文 |
| WOS研究方向 | Physical Geography ; Remote Sensing |
| 语种 | 英语 |
| WOS记录号 | WOS:001537582000001 |
| 出版者 | TAYLOR & FRANCIS LTD |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/215599]  |
| 专题 | 资源与环境信息系统国家重点实验室_外文论文 |
| 通讯作者 | Wang, Jianghao; Ge, Yong |
| 作者单位 | 1.Jiangsu Ctr Collaborat Innovat Geog Informat Resou, Nanjing, Peoples R China; 2.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, 11A Datun Rd, Beijing 100101, Peoples R China; 3.Univ Chinese Acad Sci, Coll Resources & Environm, Beijing, Peoples R China; 4.Jiangxi Normal Univ, Sch Geog & Environm, Key Lab Poyang Lake Wetland & Watershed Res, Minist Educ, Nanchang, Peoples R China |
| 推荐引用方式 GB/T 7714 | Jacome, Daniel,Wang, Jianghao,Ge, Yong. Enhancing semantic segmentation of Ecuadorian shrimp ponds through fine-tuned vision transformers and U-Net architectures utilizing open-source remote sensing data[J]. INTERNATIONAL JOURNAL OF DIGITAL EARTH,2025,18(1):2538214. |
| APA | Jacome, Daniel,Wang, Jianghao,&Ge, Yong.(2025).Enhancing semantic segmentation of Ecuadorian shrimp ponds through fine-tuned vision transformers and U-Net architectures utilizing open-source remote sensing data.INTERNATIONAL JOURNAL OF DIGITAL EARTH,18(1),2538214. |
| MLA | Jacome, Daniel,et al."Enhancing semantic segmentation of Ecuadorian shrimp ponds through fine-tuned vision transformers and U-Net architectures utilizing open-source remote sensing data".INTERNATIONAL JOURNAL OF DIGITAL EARTH 18.1(2025):2538214. |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。