[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-116970-en":3,"doc-seo-116970-105":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},116970,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","Combining Synthetic and Observed Data to Enhance Machine Learning Model Performance for Streamflow Prediction","Machine learning models support streamflow prediction and early warning systems, yet they often show low precision for high streamflow values and struggle with extrapolation—exactly the conditions tied to floods. A common limitation is evaluating models as if all records were equally informative, despite streamflow datasets being imbalanced with few but critical high values. This study improves a regression-enhanced random forest by augmenting the observed training set with physically generated synthetic data using Iber, then compares it with an observed-only baseline.","water   \nArticle  \nCombining Synthetic and Observed Data to Enhance Machine Learning Model Performance for Streamflow Prediction  \nSergio Ricardo Lâpez-Chacân 1,2, *, Fernando Salazar 1,3 and Ernest Blad² 3  \nCitation: López-Chacón, S.R.; Salazar, F.; Bladé, E. Combining Synthetic and Observed Data to Enhance Machine Learning Model Performance for Streamflow Prediction. Water 2023, 15, 2020. [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)w15112020  \nAcademic Editor: Huijuan Cui  \nReceived: 26 April 2023  \nRevised: 17 May 2023  \nAccepted: 21 May 2023  \nPublished: 26 May 2023  \nCopyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) .  \n1 International Centre for Numerical Methods in Engineering (CIMNE), 08034 Barcelona, Spain; [fsalazar@cimne.upc.edu](fsalazar@cimne.upc.edu)  \n2 Universitat Polit±cnica de Catalunya (UPC BarcelonaTech), 08034 Barcelona, Spain  \n3 Flumen Institute, Universitat Polit±cnica de Catalunya (UPC BarcelonaTech)—International Centre for Numerical Methods in Engineering (CIMNE), 08034 Barcelona, Spain; [ernest.blade@upc.edu](ernest.blade@upc.edu)  \n* Correspondence: [slopez@cimne.upc.edu](slopez@cimne.upc.edu)  \nAbstract: Machine learning (ML) models have been shown to be valuable tools employed for streamflow prediction, reporting considerable accuracy and demonstrating their potential to be part of early warning systems to mitigate flood impacts. However, one of the main drawbacks of these models is the low precision of high streamflow values and extrapolation, which are precisely the ones related to floods. Moreover, the great majority of these models are evaluated considering all the data to be equally relevant, regardless of the imbalanced nature of the streamflow records, where the proportion of high values is small but the most important. Consequently, this study tackles these issues by adding synthetic data to the observed training set of a regression-enhanced random forest model to increase the number of high streamflow values and introduce extrapolated cases. The synthetic data are generated with the physically based model Iber for synthetic precipitations of different return periods. To contrast the results, this model is compared to a model only fed with observed data. The performance evaluation is primarily focused on high streamflow values using scalar errors, graphically based errors and errors by event, taking into account precision, over-and underestimation, and cost-sensitivity analysis. The results show a considerable improvement in the performance of the model trained with the combination of observed and synthetic data with respect to the observed-data model regarding high streamflow values, where the root mean squared error and percentage bias decrease by 23.1% and 38.7%, respectively, for streamflow values larger than three years of return period. The utility of the model increases by 10.5% . The results suggest that the addition of synthetic precipitation events to existing records might lead to further improvements in the models.  \nKeywords: machine learning; physically based; Iber; streamflow; high values; synthetic; floods; regression-enhanced random forest  \n1. Introduction  \nFloods are natural hazards that have the highest impact on the population worldwide [1–3] . Among these, flash floods have the potential to be extremely costly in terms of material damage and fatalities [4] . They usually occur suddenly as a product of intense rainfall in a small catchment with considerable slopes [5,6] . The frequency of flash floods has increased in recent years as a result of more common high-intensity rainfall and larger urban areas [7,8] . One of the main tools to prevent an","cbCairIT5UB8S1a2","https://ap.wps.com/l/cbCairIT5UB8S1a2","pdf",6021063,1,25,"English","en",105,"# Introduction\n## Flood early warning systems and streamflow prediction\n## Physically based vs. machine learning approaches\n# Methodology and data augmentation\n## Regression-enhanced random forest\n## Synthetic precipitation generation with Iber\n# Performance evaluation\n## Focus on high streamflow values\n## Error metrics and event-based/cost-sensitive analysis\n# Results and implications\n## Improvement over observed-data model\n## Utility and practical guidance","[{\"question\":\"What problem does the study address in machine learning streamflow prediction?\",\"answer\":\"It targets low precision for high streamflow values and poor extrapolation, which are crucial for flood-related risk.\"},{\"question\":\"How does the proposed method improve model performance?\",\"answer\":\"It adds synthetic precipitation events, generated with the physically based Iber model, to the observed training set for a regression-enhanced random forest.\"},{\"question\":\"How is performance evaluated, especially for high flows?\",\"answer\":\"Evaluation emphasizes high streamflow values using scalar and graphical errors, event-based assessment, and precision/over- and underestimation with cost-sensitivity analysis.\"}]","Combining Synthetic and Observed Data to Enhance Machine Learning Model Performance for Streamflow Prediction | PDF",1785672907,63,{"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},"combining-synthetic-and-observed-data-to-enhance-machine-learning-model-performance-for-streamflow-prediction","",{"@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/combining-synthetic-and-observed-data-to-enhance-machine-learning-model-performance-for-streamflow-prediction/116970/",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},"What problem does the study address in machine learning streamflow prediction?","Question",{"text":75,"@type":76},"It targets low precision for high streamflow values and poor extrapolation, which are crucial for flood-related risk.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed method improve model performance?",{"text":80,"@type":76},"It adds synthetic precipitation events, generated with the physically based Iber model, to the observed training set for a regression-enhanced random forest.",{"name":82,"@type":73,"acceptedAnswer":83},"How is performance evaluated, especially for high flows?",{"text":84,"@type":76},"Evaluation emphasizes high streamflow values using scalar and graphical errors, event-based assessment, and precision/over- and underestimation with cost-sensitivity analysis.","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"]