Identifying TSM dynamics in arid inland lakes combining satellite imagery and wind speed

IF 5.9 1区 地球科学 Q1 ENGINEERING, CIVIL
Ashkan Noori , Yusef Kheyruri , Ahmad Sharafati , Seyed Hossein Mohajeri , Mojtaba Mehraein , Amir Samadi
{"title":"Identifying TSM dynamics in arid inland lakes combining satellite imagery and wind speed","authors":"Ashkan Noori ,&nbsp;Yusef Kheyruri ,&nbsp;Ahmad Sharafati ,&nbsp;Seyed Hossein Mohajeri ,&nbsp;Mojtaba Mehraein ,&nbsp;Amir Samadi","doi":"10.1016/j.jhydrol.2024.132423","DOIUrl":null,"url":null,"abstract":"<div><div>The Chah Nimeh Reservoirs (CNRs), located in Iran’s Sistan region, are critical arid inland lakes that support agriculture and supply drinking water to the region. A major concern regarding water quality in these reservoirs is the concentration of Total Suspended Matter (TSM), which has significant implications for both the local communities and the aquatic ecosystem. This study demonstrates the complicated connection between wind speed and TSM values, indicating that wind speed is an essential variable influencing TSM concentrations. By combining in-situ wind measurements with satellite imagery, we mapped TSM distributions using empirically derived models. Our investigation identified the Long Short-Term Memory (LSTM) and Attention-Mechanism-Based Dynamic Inner Partial Least Squares Long Short-Term Memory (ADiPLS-LSTM) models as effective predictors of TSM levels. Specifically, two distinct machine learning models were utilized: R<sub>rs</sub>2TSM, which relies solely on Remote Sensing Reflectance (R<sub>rs</sub>(λ)), and the more advanced R<sub>rs</sub>&amp;Wind2TSM, which incorporates both R<sub>rs</sub>(λ) and wind data. The ADiPLS-LSTM model generated results with minimal variance, showing exceptional consistency. The Root Mean Square Error (RMSE) remains low at 0.617, while the R<sup>2</sup> value maintained continually elevated at 0.997. It’s interesting to note that modest variations in TSM concentrations occurred when wind speed data was incorporated into the algorithm, especially during times of greater wind speeds. This study emphasizes the significant impact of wind speed on TSM dynamics in arid inland lakes, showcasing the value of satellite imagery in conducting such analyses. The findings provide essential insights for developing strategies that promote sustainable water resource management.</div></div>","PeriodicalId":362,"journal":{"name":"Journal of Hydrology","volume":"648 ","pages":"Article 132423"},"PeriodicalIF":5.9000,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Hydrology","FirstCategoryId":"89","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0022169424018195","RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, CIVIL","Score":null,"Total":0}
引用次数: 0

Abstract

The Chah Nimeh Reservoirs (CNRs), located in Iran’s Sistan region, are critical arid inland lakes that support agriculture and supply drinking water to the region. A major concern regarding water quality in these reservoirs is the concentration of Total Suspended Matter (TSM), which has significant implications for both the local communities and the aquatic ecosystem. This study demonstrates the complicated connection between wind speed and TSM values, indicating that wind speed is an essential variable influencing TSM concentrations. By combining in-situ wind measurements with satellite imagery, we mapped TSM distributions using empirically derived models. Our investigation identified the Long Short-Term Memory (LSTM) and Attention-Mechanism-Based Dynamic Inner Partial Least Squares Long Short-Term Memory (ADiPLS-LSTM) models as effective predictors of TSM levels. Specifically, two distinct machine learning models were utilized: Rrs2TSM, which relies solely on Remote Sensing Reflectance (Rrs(λ)), and the more advanced Rrs&Wind2TSM, which incorporates both Rrs(λ) and wind data. The ADiPLS-LSTM model generated results with minimal variance, showing exceptional consistency. The Root Mean Square Error (RMSE) remains low at 0.617, while the R2 value maintained continually elevated at 0.997. It’s interesting to note that modest variations in TSM concentrations occurred when wind speed data was incorporated into the algorithm, especially during times of greater wind speeds. This study emphasizes the significant impact of wind speed on TSM dynamics in arid inland lakes, showcasing the value of satellite imagery in conducting such analyses. The findings provide essential insights for developing strategies that promote sustainable water resource management.

Abstract Image

结合卫星影像和风速识别干旱内陆湖的TSM动态
Chah Nimeh水库(CNRs)位于伊朗的锡斯坦地区,是重要的干旱内陆湖泊,为该地区提供农业支持和饮用水。这些水库中水质的一个主要问题是总悬浮物(TSM)的浓度,这对当地社区和水生生态系统都有重大影响。研究表明,风速与TSM值之间存在复杂的联系,表明风速是影响TSM浓度的重要变量。通过将现场风测量与卫星图像相结合,我们利用经验推导的模型绘制了TSM分布。本研究发现长短期记忆(LSTM)和基于注意机制的动态内偏最小二乘长短期记忆(ADiPLS-LSTM)模型是TSM水平的有效预测因子。具体来说,使用了两种不同的机器学习模型:Rrs2TSM,它只依赖于遥感反射率(Rrs(λ)),以及更先进的Rrs&;Wind2TSM,它结合了Rrs(λ)和风数据。ADiPLS-LSTM模型生成的结果方差最小,具有优异的一致性。均方根误差(RMSE)保持在0.617的低位,而R2值保持在0.997的高位。有趣的是,当风速数据被纳入算法时,TSM浓度会发生适度的变化,尤其是在风速较大的时候。本研究强调了风速对干旱内陆湖泊TSM动态的显著影响,展示了卫星图像在进行此类分析中的价值。研究结果为制定促进可持续水资源管理的战略提供了重要见解。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Journal of Hydrology
Journal of Hydrology 地学-地球科学综合
CiteScore
11.00
自引率
12.50%
发文量
1309
审稿时长
7.5 months
期刊介绍: The Journal of Hydrology publishes original research papers and comprehensive reviews in all the subfields of the hydrological sciences including water based management and policy issues that impact on economics and society. These comprise, but are not limited to the physical, chemical, biogeochemical, stochastic and systems aspects of surface and groundwater hydrology, hydrometeorology and hydrogeology. Relevant topics incorporating the insights and methodologies of disciplines such as climatology, water resource systems, hydraulics, agrohydrology, geomorphology, soil science, instrumentation and remote sensing, civil and environmental engineering are included. Social science perspectives on hydrological problems such as resource and ecological economics, environmental sociology, psychology and behavioural science, management and policy analysis are also invited. Multi-and interdisciplinary analyses of hydrological problems are within scope. The science published in the Journal of Hydrology is relevant to catchment scales rather than exclusively to a local scale or site.
×
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