[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118024-en":3,"doc-seo-118024-105":30,"detail-sidebar-cat-0-en-105":95},{"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},118024,4398048949847,"Eliana","https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267",8,"Research & Report","Forecasting and Optimizing Dual Media Filter Performance via Machine Learning","Four machine learning models—Decision Tree, Random Forest, Multivariable Linear Regression, Support Vector Regression, and Gaussian Process Regression—are used to forecast the performance of a multi-media filter based on raw water quality and plant operating variables. Training data cover seven years of measurements including true colour, turbidity, plant flow, and dosing of chlorine, KMnO4, FeCl3, and PolyDADMAC. Results show the best predictions at a 1-day time lag, with Random Forest using grid search achieving the highest reliability (RMSE 31.58, R2 0.98) and strong ROC-AUC performance (>0.8) during extreme wet weather, enabling real-time warning of potential turbidity breakthrough for operators.","Forecasting and Optimizing Dual Media Filter Performance via Machine Learning  \nAuthor:  \nMoradi , Sina; Omar, Amr; Zhou , Zhuoyu; Agostino , Anthony; Gandomkar, Ziba; Bustamante , Heriberto; Power, Kaye; Henderson , Rita; Leslie , Greg  \nPublication details:  \nWater Research  \nv. 235  \nMedium: Print-Electronic 0043-1354 (ISSN); 1879-2448 (ISSN)  \nPublication Date:  \n2023-03  \nPublisher DOI:  \n[https://doi.org/10.1016/j.watres.2023.119874](https://doi.org/10.1016/j.watres.2023.119874)  \nLicense:  \n[https://creativecommons.org/licenses/by/4.0/](https://creativecommons.org/licenses/by/4.0/)  \nLink to license to see what you are allowed to do with this resource.  \nDownloaded from [http://hdl.handle. net/1959.4/unsworks_83084](http://hdl.handle. net/1959.4/unsworks_83084) in [https://](https://)[ ](https://)[unsworks. unsw.edu.au](unsworks. unsw.edu.au) on 2024-05-18  \nForecasting and Optimizing Dual Media Filter Performance via Machine  \nLearning  \nSina Moradi1,2 , Amr Omar3 , Zhuoyu Zhou4 , Anthony Agostino1 , Ziba Gandomkar5 , Heriberto Bustamante6 , Kaye Power6 , Rita Henderson1 ,3 , Greg Leslie 1 ,2,3*  \n1 1 Algae & Organic Matter Laboratory, School of Chemical Engineering, University of New South  \n2 Wales, Sydney 2052, Australia  \n3 2 UNESCO Centre for Membrane Science & Technology, School of Chemical Engineering, 4 University of New South Wales, Sydney 2052, Australia  \n5 3 School of Chemical Engineering, University of New South Wales, Sydney 2052, Australia  \n6 4 School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, 518172, 7 China  \n8 5 Discipline of Medical Imaging Sciences, Faculty of Medicine and Health, University of Sydney, 9 Sydney 2006, Australia  \n10 6 Sydney WaterCorporation, Sydney, Australia 11  \n12 Abstract  \n13 Four different machine learning algorithms, including Decision Tree (DT), Random Forest (RF), 14 Multivariable Linear Regression (MLR), Support Vector Regressions (SVR), and Gaussian Process  \n15 Regressions (GPR), were applied to predict the performance of a multi-media filter operating as a  \n16 function of raw water quality and plant operating variables. The models were trained using data  \n17 collected over a seven year period covering water quality and operating variables, including true  \n18 colour, turbidity, plant flow, and chemical dose for chlorine, KMnO4, FeCl3, and Cationic Polymer  \n19 (PolyDADMAC) . The machine learning algorithms have shown that the best prediction is at a 1-day  \n20 time lag between input variables and unit filter run volume (UFRV) . Furthermore, the RF algorithm  \n21 with grid search using the input metrics mentioned above with a 1-day time lag has provided the  \n22 highest reliability in predicting UFRV with a RMSE and R2 of 31.58 and 0.98, respectively. Similarly, RF  \n23 with grid search has shown the shortest training time, prediction accuracy, and forecasting events  \n24 using a ROC-AUC curve analysis (AUC over 0.8) in extreme wet weather events. Therefore, Random  \n25 Forest with grid search and a 1-day time lag is an effective and robust machine learning algorithm that  \n26 can predict the filter performance to aid water treatment operators in their decision makings by  \n27 providing real-time warning of the potential turbidity breakthrough from the filters.  \n28 Keywords: Filtration Performance, Machine Learning Approach, Hyper-parameter Optimisation, Unit  \n29 Filter Run Volume  \n* Corresponding author: Greg Leslie, E-mail address: [g.leslie@unsw.edu.au](g.leslie@unsw.edu.au)  \n30 Graphical Abstract  \n31  \n32 Nomenclature  \n\n| Symbols\u003Cbr>􀜥􀜥􀝋􀝁􀝂0\u003Cbr>􀜥􀝌\u003Cbr>􀜨􀜰\u003Cbr>􀜨􀜲\u003Cbr>􀜨􀜲􀜴\u003Cbr>􀜫􀜳􀜴􀜭(􀯫 􀳔,􀯫 􀳕) mtry\u003Cbr>p | Cost of Constraints Violation Constant Parameter in the Sigmoid or Polynomial Kernel Function Complexity Parameter\u003Cbr>False-Negative\u003Cbr>False-Positive\u003Cbr>False-Positive Rate Interquartile Range Kernel Function\u003Cbr>Number of candidate variables considered at each split\u003Cbr>Number of variables in the input matrix | MLR\u003Cbr>MSE\u003Cbr>NOM\u003Cbr>NTU\u003Cbr","cbCairlXEYxaqtMy","https://ap.wps.com/l/cbCairlXEYxaqtMy","pdf",2046000,1,27,"English","en",105,"# Abstract\n# Keywords\n# Introduction\n## Motivation: extreme weather impacts\n## Need for reliable forecasting","[{\"question\":\"哪些机器学习算法被用于预测双介质过滤器性能？\",\"answer\":\"文中使用了决策树（DT）、随机森林（RF）、多变量线性回归（MLR）、支持向量回归（SVR）以及高斯过程回归（GPR）来预测多介质过滤器的性能。\"},{\"question\":\"最佳预测效果对应的时间滞后是多少？\",\"answer\":\"模型显示，输入变量与单位滤池运行体积（UFRV）之间采用1天时间滞后时，预测效果最佳。\"},{\"question\":\"随机森林（RF）在性能预测上的主要结果是什么？\",\"answer\":\"在1天时间滞后条件下，采用网格搜索的随机森林模型对UFRV预测的可靠性最高，RMSE为31.58、R2为0.98；并在极端潮湿天气事件中通过ROC-AUC分析表现出较高准确性（AUC\\u003e0.8）。\"},{\"question\":\"该方法如何帮助水处理运行决策？\",\"answer\":\"通过实时预警可能的浊度突破风险，该算法可为水处理厂运行人员提供辅助决策，从而提升控制效果与运行效率。\"}]","Forecasting and Optimizing Dual Media Filter Performance via Machine Learning | PDF",1785680797,68,{"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":90,"head_meta":92,"extra_data":94,"updated_unix":28},"forecasting-and-optimizing-dual-media-filter-performance-via-machine-learning","",{"@graph":36,"@context":89},[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/forecasting-and-optimizing-dual-media-filter-performance-via-machine-learning/118024/",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",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"哪些机器学习算法被用于预测双介质过滤器性能？","Question",{"text":75,"@type":76},"文中使用了决策树（DT）、随机森林（RF）、多变量线性回归（MLR）、支持向量回归（SVR）以及高斯过程回归（GPR）来预测多介质过滤器的性能。","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"最佳预测效果对应的时间滞后是多少？",{"text":80,"@type":76},"模型显示，输入变量与单位滤池运行体积（UFRV）之间采用1天时间滞后时，预测效果最佳。",{"name":82,"@type":73,"acceptedAnswer":83},"随机森林（RF）在性能预测上的主要结果是什么？",{"text":84,"@type":76},"在1天时间滞后条件下，采用网格搜索的随机森林模型对UFRV预测的可靠性最高，RMSE为31.58、R2为0.98；并在极端潮湿天气事件中通过ROC-AUC分析表现出较高准确性（AUC>0.8）。",{"name":86,"@type":73,"acceptedAnswer":87},"该方法如何帮助水处理运行决策？",{"text":88,"@type":76},"通过实时预警可能的浊度突破风险，该算法可为水处理厂运行人员提供辅助决策，从而提升控制效果与运行效率。","https://schema.org",{"og:url":52,"og:type":91,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":93,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,119,124,127,132,135,139],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},6,"Technology",50,"technology",{"id":120,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":122,"slug":123},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":125,"slug":126},30,"research-report",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":130,"slug":131},9,"Religion & Spirituality",20,"religion-spirituality",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":130,"slug":134},"World Cup","world-cup",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":136,"slug":138},10,"Lifestyle","lifestyle",{"id":140,"doc_module":4,"doc_module_name":46,"category_name":141,"show_sort_weight":110,"slug":142},19,"General","general"]