[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118286-en":3,"doc-seo-118286-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},118286,7971461740886,"Theodore","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",8,"Research & Report","Time Series Predictions in Unmonitored Sites - A Survey of Machine Learning Techniques in Water Resources","Prediction of dynamic environmental variables in unmonitored sites remains a central challenge in water resources science, driven by inadequate monitoring for freshwater management. The review synthesizes state-of-the-art machine learning approaches that increasingly outperform traditional process-based and empirical models for hydrologic time series tasks. It focuses on streamflow, water quality, and related prediction problems, and evaluates how emerging methods can integrate watershed characteristics and process knowledge into classical ML, deep learning, and transfer learning. The paper also highlights gaps in current comparisons across ML categories and outlines open research questions on dynamic inputs, site context, mechanistic understanding, spatial relationships, and explainable AI.","arXiv :2308 .09766v3 [ cs .LG] 14 Aug 2024  \nEnvironmental Data Science (Accepted for Publication on May 8th, 2024) (2024), xx:xx 1–39  \nSurvey Paper  \nTime Series Predictions in Unmonitored Sites: A Survey of Machine Learning Techniques in Water Resources  \nJared D. Willard 1,4 , Charuleka Varadharajan2 , Xiaowei Jia3 and Vipin Kumar4  \n1 Computing Sciences Area, Lawrence Berkeley National Laboratory, Berkeley, 94720, CA, USA, E-mail: [jwillard@lbl.gov](jwillard@lbl.gov).  \n2Earth and Environmental Sciences Area, Lawrence Berkeley National Laboratory, Berkeley, 94720, CA, USA, E-mail: [jwillard@lbl.gov](jwillard@lbl.gov), [cvaradharajan@lbl.gov](cvaradharajan@lbl.gov).  \n3 Department of Computer Science, University of Pittsburgh, Pittsburgh, 15260, PA, USA, E-mail: [xiaowei@pitt.edu](xiaowei@pitt.edu).  \n4Department of Computer Science and Engineering, University of Minnesota Twin Cities, Minneapolis, 55455, MN, USA, [E-mail: kumar001@umn.edu](E-mail: kumar001@umn.edu).  \nKeywords: prediction in unmonitored basins, machine learning, transfer learning, deep learning  \nMSC Codes: Primary – 68-02; Secondary – 68T07, 92F05,86A05  \nAbstract  \nPrediction of dynamic environmental variables in unmonitored sites remains a long-standing challenge for water resources science. The majority of the world’s freshwater resources have inadequate monitoring of critical environmental variables needed for management. Yet, the need to have widespread predictions of hydrological variables such as river flow and water quality has become increasingly urgent due to climate and land use change over the past decades, and their associated impacts on water resources. Modern machine learning methods increasingly outperform their process-based and empirical model counterparts for hydrologic time series prediction with their ability to extract information from large, diverse data sets. We review relevant state-of-the art applications of machine learning for streamflow, water quality, and other water resources prediction and discuss opportunities to improve the use of machine learning with emerging methods for incorporating watershed characteristics and process knowledge into classical, deep learning, and transfer learning methodologies . The analysis here suggests most prior efforts have been focused on deep learning frameworks built on many sites for predictions at daily time scales in the United States, but that comparisons between different classes of machine learning methods are few and inadequate. We identify several open questions for time series predictions in unmonitored sites that include incorporating dynamic inputs and site characteristics, mechanistic understanding and spatial context, and explainable AI techniques in modern machine learning frameworks.  \nImpact Statement  \nThis review addresses a gap that different types of ML methods for hydrological time series prediction in unmonitored sites are often not compared in detail and best practices are unclear. We consolidate and synthesize state-of-the-art ML techniques for researchers and water resources management, where the strengths and limitations of different ML techniques are described allowing for a more informed selection of existing ML frameworks and development of new ones. Open questions that require further investigation are highlighted to encourage researchers to address specific issues like training data and input selection, model explainability, and the incorporation of process-based knowledge.  \n1. Introduction  \nEnvironmental data for water resources often does not exist at the appropriate spatiotemporal resolution or coverage for scientific studies or management decisions. Although advanced sensor networks and  \n2 Willard et al.  \nremote sensing are generating more environmental data (Hubbard et al., 2020; Reichstein et al., 2019 ; Topp et al., 2020), the amount of observations available will continue to be inadequate for the foreseeable future, notably for variables that are o","cbCaioMwxHi4Ng49","https://ap.wps.com/l/cbCaioMwxHi4Ng49","pdf",1091037,1,39,"English","en",105,"# Introduction\n## Data gaps and monitoring limitations\n## Prediction across unmonitored basins\n# Machine learning for hydrologic time series\n## Streamflow and water quality applications\n## Classical ML, deep learning, and transfer learning\n# Open questions and future directions\n## Dynamic inputs and site characteristics\n## Mechanistic understanding, spatial context, and explainability","[{\"question\":\"Why are predictions needed for unmonitored sites in water resources science?\",\"answer\":\"Widespread monitoring of critical environmental variables is insufficient for management, and growing climate and land-use changes increase the urgency for hydrological predictions such as river flow and water quality.\"},{\"question\":\"What does the survey cover regarding machine learning approaches?\",\"answer\":\"It reviews state-of-the-art ML applications for streamflow, water quality, and other water-resources prediction tasks, and discusses opportunities to incorporate watershed characteristics and process knowledge across classical ML, deep learning, and transfer learning.\"},{\"question\":\"What limitation in existing research does the paper emphasize?\",\"answer\":\"Prior efforts concentrate on deep learning frameworks for daily-scale predictions in the United States, while detailed and adequate comparisons across different ML method classes are limited.\"}]","Time Series Predictions in Unmonitored Sites - A Survey of Machine Learning Techniques in Water Resources | PDF",1785682809,98,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"time-series-predictions-in-unmonitored-sites-a-survey-of-machine-learning-techniques-in-water-resources","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/time-series-predictions-in-unmonitored-sites-a-survey-of-machine-learning-techniques-in-water-resources/118286/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why are predictions needed for unmonitored sites in water resources science?","Question",{"text":75,"@type":76},"Widespread monitoring of critical environmental variables is insufficient for management, and growing climate and land-use changes increase the urgency for hydrological predictions such as river flow and water quality.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What does the survey cover regarding machine learning approaches?",{"text":80,"@type":76},"It reviews state-of-the-art ML applications for streamflow, water quality, and other water-resources prediction tasks, and discusses opportunities to incorporate watershed characteristics and process knowledge across classical ML, deep learning, and transfer learning.",{"name":82,"@type":73,"acceptedAnswer":83},"What limitation in existing research does the paper emphasize?",{"text":84,"@type":76},"Prior efforts concentrate on deep learning frameworks for daily-scale predictions in the United States, while detailed and adequate comparisons across different ML method classes are limited.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]