密集监测点的溪流硝酸盐动态主要受排放和流域物理及土壤特性的驱动:深度学习的启示

IF 4.6 1区 地球科学 Q2 ENVIRONMENTAL SCIENCES Water Resources Research Pub Date : 2024-09-26 DOI:10.1029/2023wr036591
G. Gorski, L. Larsen, J. Wingenroth, L. Zhang, D. Bellugi, A. P. Appling
{"title":"密集监测点的溪流硝酸盐动态主要受排放和流域物理及土壤特性的驱动:深度学习的启示","authors":"G. Gorski, L. Larsen, J. Wingenroth, L. Zhang, D. Bellugi, A. P. Appling","doi":"10.1029/2023wr036591","DOIUrl":null,"url":null,"abstract":"We developed a suite of models using deep learning to make hindcast predictions of the 7-day average backward-looking nitrate concentration at 46 predominantly agricultural sites across the midwestern and eastern United States. The models used daily observations of discharge and meteorological variables and watershed attributes describing anthropogenic modification to hydrology, nitrogen application, climate, groundwater, land use, watershed physiographic attributes, and soils. Across all sites, discharge and watershed soil and physiographic attributes showed a strong influence on model performance. Analysis of drivers across sites revealed considerable regional differences related to controlling processes such as groundwater contributions. We tested several ways to pool data across sites to develop accurate models and make the most effective use of available data. Single-site models, in which models are trained and tested at a single location, showed generally strong predictive performance (median Kling-Gupta Efficiency = 0.66), and accuracy at poorly performing sites could be improved by grouping sites with similar characteristics. Developing a single model for all sites reduced performance at several locations with distinct characteristics, suggesting that there is a threshold of dissimilarity beyond which more data does not improve the model. While many deep learning studies have shown that national or even global models can outperform local models, it is not clear that this is true for water quality constituents. This study demonstrates how data can be combined effectively, using deep learning to develop accurate and interpretable models of instream nitrate at sites where varying processes are responsible for changes in nitrate concentration.","PeriodicalId":23799,"journal":{"name":"Water Resources Research","volume":"38 1","pages":""},"PeriodicalIF":4.6000,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Stream Nitrate Dynamics Driven Primarily by Discharge and Watershed Physical and Soil Characteristics at Intensively Monitored Sites: Insights From Deep Learning\",\"authors\":\"G. Gorski, L. Larsen, J. Wingenroth, L. Zhang, D. Bellugi, A. P. Appling\",\"doi\":\"10.1029/2023wr036591\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We developed a suite of models using deep learning to make hindcast predictions of the 7-day average backward-looking nitrate concentration at 46 predominantly agricultural sites across the midwestern and eastern United States. The models used daily observations of discharge and meteorological variables and watershed attributes describing anthropogenic modification to hydrology, nitrogen application, climate, groundwater, land use, watershed physiographic attributes, and soils. Across all sites, discharge and watershed soil and physiographic attributes showed a strong influence on model performance. Analysis of drivers across sites revealed considerable regional differences related to controlling processes such as groundwater contributions. We tested several ways to pool data across sites to develop accurate models and make the most effective use of available data. Single-site models, in which models are trained and tested at a single location, showed generally strong predictive performance (median Kling-Gupta Efficiency = 0.66), and accuracy at poorly performing sites could be improved by grouping sites with similar characteristics. Developing a single model for all sites reduced performance at several locations with distinct characteristics, suggesting that there is a threshold of dissimilarity beyond which more data does not improve the model. While many deep learning studies have shown that national or even global models can outperform local models, it is not clear that this is true for water quality constituents. This study demonstrates how data can be combined effectively, using deep learning to develop accurate and interpretable models of instream nitrate at sites where varying processes are responsible for changes in nitrate concentration.\",\"PeriodicalId\":23799,\"journal\":{\"name\":\"Water Resources Research\",\"volume\":\"38 1\",\"pages\":\"\"},\"PeriodicalIF\":4.6000,\"publicationDate\":\"2024-09-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Water Resources Research\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://doi.org/10.1029/2023wr036591\",\"RegionNum\":1,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENVIRONMENTAL SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Water Resources Research","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.1029/2023wr036591","RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
引用次数: 0

摘要

我们利用深度学习技术开发了一套模型,对美国中西部和东部 46 个以农业为主的地点的 7 天平均硝酸盐后向浓度进行后报预测。这些模型使用了排水和气象变量的每日观测数据,以及描述人为改变水文、施氮、气候、地下水、土地利用、流域地貌属性和土壤的流域属性。在所有观测点中,排水量、流域土壤和地貌属性对模型性能的影响都很大。对各站点驱动因素的分析表明,与地下水贡献等控制过程有关的区域差异相当大。我们测试了几种跨站点汇集数据的方法,以开发精确的模型并最有效地利用可用数据。单站点模型,即在单个地点对模型进行训练和测试,总体上显示出较强的预测性能(Kling-Gupta 效率中值 = 0.66),通过对具有相似特征的站点进行分组,可以提高性能较差站点的准确性。为所有地点开发一个单一模型会降低几个具有不同特征地点的性能,这表明存在一个差异阈值,超过这个阈值,更多的数据并不能改善模型。虽然许多深度学习研究表明,全国甚至全球模型都能优于本地模型,但对于水质成分来说,这一点并不明显。本研究展示了如何有效地结合数据,利用深度学习在不同过程导致硝酸盐浓度变化的地点建立准确且可解释的硝酸盐内流模型。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Stream Nitrate Dynamics Driven Primarily by Discharge and Watershed Physical and Soil Characteristics at Intensively Monitored Sites: Insights From Deep Learning
We developed a suite of models using deep learning to make hindcast predictions of the 7-day average backward-looking nitrate concentration at 46 predominantly agricultural sites across the midwestern and eastern United States. The models used daily observations of discharge and meteorological variables and watershed attributes describing anthropogenic modification to hydrology, nitrogen application, climate, groundwater, land use, watershed physiographic attributes, and soils. Across all sites, discharge and watershed soil and physiographic attributes showed a strong influence on model performance. Analysis of drivers across sites revealed considerable regional differences related to controlling processes such as groundwater contributions. We tested several ways to pool data across sites to develop accurate models and make the most effective use of available data. Single-site models, in which models are trained and tested at a single location, showed generally strong predictive performance (median Kling-Gupta Efficiency = 0.66), and accuracy at poorly performing sites could be improved by grouping sites with similar characteristics. Developing a single model for all sites reduced performance at several locations with distinct characteristics, suggesting that there is a threshold of dissimilarity beyond which more data does not improve the model. While many deep learning studies have shown that national or even global models can outperform local models, it is not clear that this is true for water quality constituents. This study demonstrates how data can be combined effectively, using deep learning to develop accurate and interpretable models of instream nitrate at sites where varying processes are responsible for changes in nitrate concentration.
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
Water Resources Research
Water Resources Research 环境科学-湖沼学
CiteScore
8.80
自引率
13.00%
发文量
599
审稿时长
3.5 months
期刊介绍: Water Resources Research (WRR) is an interdisciplinary journal that focuses on hydrology and water resources. It publishes original research in the natural and social sciences of water. It emphasizes the role of water in the Earth system, including physical, chemical, biological, and ecological processes in water resources research and management, including social, policy, and public health implications. It encompasses observational, experimental, theoretical, analytical, numerical, and data-driven approaches that advance the science of water and its management. Submissions are evaluated for their novelty, accuracy, significance, and broader implications of the findings.
期刊最新文献
A Three-Stage Partitioning Framework for Modeling Mean Annual Groundwater Evapotranspiration Causal Discovery Analysis Reveals Global Sources of Predictability for Regional Flash Droughts Bridging the Gap Between Top-Down and Bottom-Up Climate Vulnerability Assessments: Process Informed Exploratory Scenarios Identify System-Based Water Resource Vulnerabilities Combining a Multi-Lake Model Ensemble and a Multi-Domain CORDEX Climate Data Ensemble for Assessing Climate Change Impacts on Lake Sevan Impact of Forest Dieback on Hydrology and Nitrogen Export Using a New Dynamic Water Quality Model
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1