[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-290986-105":59,"doc-detail-290986-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","machine-learning-in-environmental-monitoring-the-case-of-water-potability-prediction-research-findings-and-model-development","Machine learning in environmental monitoring: the case of water potability prediction - Research findings and model development","","Ensuring drinking water quality is a critical public health priority as industrial pollution and climate change intensify contamination risks. The study applies machine learning—specifically XGBoost—to predict water potability from physical and chemical parameters. A baseline XGBoost classifier showed moderate performance, with difficulty detecting potable water due to class underrepresentation. SMOTE balancing improved recall for the potable class. RandomizedSearchCV hyperparameter optimization and feature selection reduced model complexity while preserving comparable accuracy, enabling integration into automated monitoring for real-time deviation detection.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/machine-learning-in-environmental-monitoring-the-case-of-water-potability-prediction-research-findings-and-model-development/290986/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/machine-learning-in-environmental-monitoring-the-case-of-water-potability-prediction-research-findings-and-model-development/290986.png","ImageObject",300,407,{"name":92,"@type":93},"Evangeline","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-17","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",15,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What problem does the study address?","Question",{"text":113,"@type":114},"The study addresses predicting whether drinking water is potable using physical and chemical water parameters to support public health and environmental protection.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"Which machine learning approach is central to the research?",{"text":118,"@type":114},"XGBoost is the primary model, with performance improved through class balancing (SMOTE) and further tuned using RandomizedSearchCV.",{"name":120,"@type":111,"acceptedAnswer":121},"How does the study handle the imbalance in the dataset?",{"text":122,"@type":114},"It applies the SMOTE technique to balance the dataset, which improves recall for the potable water class.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},290986,1789643133,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":130,"read_time":145,"preview_page_count":4},13056703019662,"https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188","Machine learning in environmental monitoring: the case of water potability prediction  \nVasiliy Orlov1,2*, Anatoliy Kukartsev2,3, Ilya Panfilov2,3, Anastasia Kozlova2,3, and Andrey Boyko2,3  \n1 Institute of Business Process Management, Department of Digital Management Technologies, Siberian Federal University, Krasnoyarsk, Russia  \n2Bauman Moscow State Technical University, Artificial Intelligence Technology Scientific and Education Center, Moscow, Russia  \n3Reshetnev Siberian State of Science and Technology, Krasnoyarsk, Russia  \nAbstract. Ensuring the quality of drinking water is a critical public health issue, especially in the face of increasing industrial pollution and climate change. This study explores the application of machine learning techniques, specifically XGBoost, to predict water potability based on physical and chemical parameters. Initial experiments with a baseline XGBoost model demonstrated moderate success in classification, with particular difficulty inaccurately identifying potable water, which is often underrepresented in the dataset.To address this challenge, the SMOTE technique was applied to balance the dataset, resulting in improved recall for the potable water class.  \nAdditionally, hyperparameter optimization via RandomizedSearchCV further enhanced the model’s performance, albeit modestly. Reducing the model's complexity by selecting the most significant features led to a more efficient model with reduced computational overhead, while maintaining comparable accuracy.The findings of this study indicate that an optimized XGBoost model, supported by data preprocessing and feature selection, can be effectively integrated into automated water quality monitoring systems.  \nSuch a system would enable real-time detection of water quality deviations, facilitating prompt corrective actions to protect public health. This approach not only demonstrates the applicability of machine learning in environmental monitoring but also highlights the potential for broader  \napplication in resource management and public safety.  \n1 Introduction  \nWater is a vital resource for all living organisms, and its quality plays a crucial role in ensuring public health and well-being. With increasing population growth and industrial development, the quality of drinking water has become an increasingly pressing issue. Water contamination with chemical and biological substances can lead to serious health consequences, including acute and chronic diseases. Therefore, determining water potability is one of the key challenges in the fields of public health and environmental protection [1, 2] .  \n* [Corresponding author:](Corresponding author: vasi4244@gmail.com)[ vasi4244@gmail.com](Corresponding author: vasi4244@gmail.com)  \n© The Authors, published by EDP Sciences. This is an open access article distributed under the terms of the Creative Commons Attribution License 4.0 ([https://creativecommons.org/licenses/by/4.0/](https://creativecommons.org/licenses/by/4.0/)).  \nIn recent years, significant attention has been directed towards the development and application of various methods for water quality analysis, including traditional laboratory methods as well as modern approaches based on machine learning and data analysis. These methods allow for more efficient and accurate determination of the chemical composition of water and the prediction of its potability based on multiple parameters [3, 4] .  \nThe aim of this study is to develop and evaluate a machine learning model for predicting water potability based on chemical and physical parameters, such as pH, hardness, solids content, and others. The study explores various machine learning algorithms, including Random Forest and XGBoost, as well as data processing techniques such as class balancing using SMOTE and the selection of the most significant features [5, 6] .  \nThis work is aimed at improving existing methods for predicting water quality and can make a significant contribution t","cbCairWHsiAsPp4G","https://ap.wps.com/l/cbCairWHsiAsPp4G","pdf",2309609,14,"English","# Abstract\n# 1 Introduction\n# 2 Materials and methods\n## 2.1 Data Sources\n## 2.2 Data Description","[{\"question\":\"What problem does the study address?\",\"answer\":\"The study addresses predicting whether drinking water is potable using physical and chemical water parameters to support public health and environmental protection.\"},{\"question\":\"Which machine learning approach is central to the research?\",\"answer\":\"XGBoost is the primary model, with performance improved through class balancing (SMOTE) and further tuned using RandomizedSearchCV.\"},{\"question\":\"How does the study handle the imbalance in the dataset?\",\"answer\":\"It applies the SMOTE technique to balance the dataset, which improves recall for the potable water class.\"}]","Machine learning in environmental monitoring: the case of water potability prediction - Research findings and model development | PDF",35]