通过深度学习和大坝检测增强更大区域的河流连通性评估

IF 3.2 3区 地球科学 Q1 Environmental Science
Xiao Zhang, Qi Liu, Dongwei Gui, Jianping Zhao, Yu Chen, Yunfei Liu, Jaime Martínez-Valderrama
{"title":"通过深度学习和大坝检测增强更大区域的河流连通性评估","authors":"Xiao Zhang,&nbsp;Qi Liu,&nbsp;Dongwei Gui,&nbsp;Jianping Zhao,&nbsp;Yu Chen,&nbsp;Yunfei Liu,&nbsp;Jaime Martínez-Valderrama","doi":"10.1002/hyp.70063","DOIUrl":null,"url":null,"abstract":"<div>\n \n <p>Monitoring river connectivity across large regions is essential for understanding hydrological processes and environmental management. However, comprehensive assessments of river connectivity are often hindered by inaccurate dam databases, which are biased towards larger dams while overlooking smaller or low-head dams. To enhance the accuracy of river connectivity assessments, we developed three advanced convolutional neural networks (CNNs; YOLOv5, Advance-You Only Look Once [YOLO], and Faster R-CNN) to accurately classify dams and evaluate river connectivity using high-resolution (1 m) remote sensing imagery. The evaluation results showed that Advance-YOLO performs best with an average mean average precision (mAP) of 86.6%, while Faster R-CNN performs mediocrely with an average mAP of 77.9%. Applying the well-trained model in the Tarim River Basin (China), one of the largest inland river basins around the globe, we found that there are currently 135 dams in total on the Tarim River and its sources. Conversely, the existing public dam database underestimates 85.9% of the dams. Notably, we found a 14.3% decline in river connectivity of the Tarim River over the past decade, and the current dam density of the Tarim River and its four source rivers is 1.12 per 10 000 km<sup>2</sup>. However, the existing public dam database overestimated river connectivity by 83.9%. The model developed here enhances river connectivity assessment across larger areas over a long period, thereby fostering more advanced research on hydrological processes and effective water resource management.</p>\n </div>","PeriodicalId":13189,"journal":{"name":"Hydrological Processes","volume":"39 1","pages":""},"PeriodicalIF":3.2000,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Enhanced River Connectivity Assessment Across Larger Areas Through Deep Learning With Dam Detection\",\"authors\":\"Xiao Zhang,&nbsp;Qi Liu,&nbsp;Dongwei Gui,&nbsp;Jianping Zhao,&nbsp;Yu Chen,&nbsp;Yunfei Liu,&nbsp;Jaime Martínez-Valderrama\",\"doi\":\"10.1002/hyp.70063\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div>\\n \\n <p>Monitoring river connectivity across large regions is essential for understanding hydrological processes and environmental management. However, comprehensive assessments of river connectivity are often hindered by inaccurate dam databases, which are biased towards larger dams while overlooking smaller or low-head dams. To enhance the accuracy of river connectivity assessments, we developed three advanced convolutional neural networks (CNNs; YOLOv5, Advance-You Only Look Once [YOLO], and Faster R-CNN) to accurately classify dams and evaluate river connectivity using high-resolution (1 m) remote sensing imagery. The evaluation results showed that Advance-YOLO performs best with an average mean average precision (mAP) of 86.6%, while Faster R-CNN performs mediocrely with an average mAP of 77.9%. Applying the well-trained model in the Tarim River Basin (China), one of the largest inland river basins around the globe, we found that there are currently 135 dams in total on the Tarim River and its sources. Conversely, the existing public dam database underestimates 85.9% of the dams. Notably, we found a 14.3% decline in river connectivity of the Tarim River over the past decade, and the current dam density of the Tarim River and its four source rivers is 1.12 per 10 000 km<sup>2</sup>. However, the existing public dam database overestimated river connectivity by 83.9%. The model developed here enhances river connectivity assessment across larger areas over a long period, thereby fostering more advanced research on hydrological processes and effective water resource management.</p>\\n </div>\",\"PeriodicalId\":13189,\"journal\":{\"name\":\"Hydrological Processes\",\"volume\":\"39 1\",\"pages\":\"\"},\"PeriodicalIF\":3.2000,\"publicationDate\":\"2025-01-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Hydrological Processes\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1002/hyp.70063\",\"RegionNum\":3,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"Environmental Science\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Hydrological Processes","FirstCategoryId":"89","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/hyp.70063","RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"Environmental Science","Score":null,"Total":0}
引用次数: 0

摘要

监测大区域的河流连通性对于了解水文过程和环境管理至关重要。然而,对河流连通性的全面评估往往受到水坝数据库不准确的阻碍,这些数据库偏向于大型水坝,而忽视了较小或低水头的水坝。为了提高河流连通性评估的准确性,我们开发了三种先进的卷积神经网络(cnn;YOLOv5, Advance-You Only Look Once [YOLO]和Faster R-CNN),利用高分辨率(1米)遥感图像准确分类水坝并评估河流连通性。评价结果表明,Advance-YOLO表现最好,平均平均精度(mAP)为86.6%,而Faster R-CNN表现一般,平均mAP为77.9%。将训练有素的模型应用于塔里木河流域(中国),这是全球最大的内陆河流域之一,我们发现塔里木河及其源头目前总共有135座水坝。相反,现有的公共水坝数据库低估了85.9%的水坝。值得注意的是,我们发现塔里木河的河流连通性在过去十年中下降了14.3%,目前塔里木河及其四源河的水坝密度为1.12 / 10000 km2。然而,现有的公共水坝数据库高估了83.9%的河流连通性。本研究开发的模型可以在更大范围内对河流连通性进行长期评估,从而促进对水文过程和有效水资源管理的更先进研究。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Enhanced River Connectivity Assessment Across Larger Areas Through Deep Learning With Dam Detection

Monitoring river connectivity across large regions is essential for understanding hydrological processes and environmental management. However, comprehensive assessments of river connectivity are often hindered by inaccurate dam databases, which are biased towards larger dams while overlooking smaller or low-head dams. To enhance the accuracy of river connectivity assessments, we developed three advanced convolutional neural networks (CNNs; YOLOv5, Advance-You Only Look Once [YOLO], and Faster R-CNN) to accurately classify dams and evaluate river connectivity using high-resolution (1 m) remote sensing imagery. The evaluation results showed that Advance-YOLO performs best with an average mean average precision (mAP) of 86.6%, while Faster R-CNN performs mediocrely with an average mAP of 77.9%. Applying the well-trained model in the Tarim River Basin (China), one of the largest inland river basins around the globe, we found that there are currently 135 dams in total on the Tarim River and its sources. Conversely, the existing public dam database underestimates 85.9% of the dams. Notably, we found a 14.3% decline in river connectivity of the Tarim River over the past decade, and the current dam density of the Tarim River and its four source rivers is 1.12 per 10 000 km2. However, the existing public dam database overestimated river connectivity by 83.9%. The model developed here enhances river connectivity assessment across larger areas over a long period, thereby fostering more advanced research on hydrological processes and effective water resource management.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Hydrological Processes
Hydrological Processes 环境科学-水资源
CiteScore
6.00
自引率
12.50%
发文量
313
审稿时长
2-4 weeks
期刊介绍: Hydrological Processes is an international journal that publishes original scientific papers advancing understanding of the mechanisms underlying the movement and storage of water in the environment, and the interaction of water with geological, biogeochemical, atmospheric and ecological systems. Not all papers related to water resources are appropriate for submission to this journal; rather we seek papers that clearly articulate the role(s) of hydrological processes.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信