[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-128829-105":59,"doc-detail-128829-en":134},{"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":127,"head_meta":129,"extra_data":131,"updated_unix":133},105,"en","machine-learning-vs-real-world-data-assessing-ann-performance-in-cod-removal-in-animal-feed-process-wastewater","Machine Learning vs. Real-World Data - Assessing ANN Performance in COD Removal in Animal Feed Process Wastewater","","This research builds a feedforward artificial neural network (ANN) with a 10-8 architecture to predict ozonation performance for chemical oxygen demand (COD) reduction in animal feed plant wastewater under 200–1000 mg/L COD and 100–180 min treatment time, then compares ANN predictions against experimental results to quantify accuracy. The model reaches 97.4% predicted COD removal at 180 min for 1000 mg/L (MSE 15.9, MAE 3.67, R² 0.34), while experiments show 97.83% at 160 min. The study captures non-linear degradation kinetics and supports optimization of advanced oxidation processes with practical error control (±2.1%).",{"@graph":69,"@context":126},[70,84,105],{"@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-vs-real-world-data-assessing-ann-performance-in-cod-removal-in-animal-feed-process-wastewater/128829/",{"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-vs-real-world-data-assessing-ann-performance-in-cod-removal-in-animal-feed-process-wastewater/128829.png","ImageObject",300,407,{"name":92,"@type":93},"Maeve","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-09-20","2026-08-06",true,{"@type":102,"interactionType":103,"userInteractionCount":44},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118,122],{"name":109,"@type":110,"acceptedAnswer":111},"What ANN model was used to predict ozonation performance for COD removal?","Question",{"text":112,"@type":113},"A feedforward artificial neural network (ANN) with a 10-8 neuron architecture was constructed to predict COD reduction efficiency based on operational parameters.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How did the ANN predictions compare with experimental results?",{"text":117,"@type":113},"The ANN predicted 97.4% COD removal at 180 min for 1000 mg/L, while experimental data showed 97.83% at 160 min for the same initial COD level, indicating a small discrepancy.",{"name":119,"@type":110,"acceptedAnswer":120},"Which factors were highlighted as key drivers of ozonation performance?",{"text":121,"@type":113},"Ozonation performance was described as being influenced by variables such as ozone dosage, contact duration, and initial pollutant concentration (initial COD).",{"name":123,"@type":110,"acceptedAnswer":124},"What improvement is suggested for future versions of the model?",{"text":125,"@type":113},"Future enhancements should integrate real-time oxidant concentration data to improve predictive performance, specifically aiming to increase R² beyond the current 0.34.","https://schema.org",{"og:url":83,"og:type":128,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":130,"canonical":83},"index,follow",{"doc_id":132,"site_id":62},128829,1786003749,{"code":4,"msg":5,"data":135},{"doc_id":132,"user_id":136,"nickname":92,"user_avatar":137,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":138,"file_id":139,"file_url":140,"file_type":141,"file_size":142,"view_count":44,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":39,"language":143,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":144,"faqs":145,"seo_title":146,"seo_description":67,"update_tm":133,"read_time":46},2336474466712,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","Machine Learning vs. Real-World Data: Assessing ANN Performance in COD Removal in Animal Feed Processing Wastewater  \nBeta Cahaya Pertiwia, Dean Tirkaamianab, Maudy Pratiwi Novia Matovannia, Ketut Sumadaa* aChemical Engineering Department, Engineering and Science Faculty, Universitas Pembangunan Nasional “Veteran” Jawa Timur,  \nIndonesia 60294  \nbIndustrial Engineering Department, Engineering and Science Faculty, Universitas Pembangunan Nasional “Veteran” Jawa Timur,  \nIndonesia 60294  \n*[Corresponding author:](Corresponding author: ksumada.tk@upnjatim.ac.id)[ ksumada.tk@upnjatim.ac.id](Corresponding author: ksumada.tk@upnjatim.ac.id)  \nDOI: [https://dx.doi.org/10.20961/equilibrium.v9i1.104192](https://dx.doi.org/10.20961/equilibrium.v9i1.104192)  \nArticle History  \nReceived: 15-06-2025, Accepted: 31-07-2025, Published: 02-08-2025  \nKeywords: ANN, COD, Ozonation Process, Wastewater  \nABSTRACT. This research establishes a feedforward artificial neural network (ANN) with 10-8 neuron architecture to predict ozonation performance for chemical oxygen demand (COD) reduction in animal feed plant wastewater (200–1000 mg/L COD, 100–180 min treatment), and systematically compare ANN predictions with experimental results to evaluate model accuracy. The ANN, achieved 97.4% predicted COD removal at 180 min for 1000 mg/L COD (MSE = 15.9, MAE = 3.67, R² = 0.34), while experimental data showed a marginally higher efficiency of 97.83% at 160 min for 1000 mg/L. This discrepancy reflects the ANN’s conservative optimization for industrial scalability over idealized lab conditions. The model successfully captured non-linear degradation kinetics of recalcitrant organics, demonstrating its capability to identify complex relationships between ozonation parameters (time, initial COD) and treatment efficiency. By bridging laboratory data with machine learning, this work provides a validated framework for optimizing advanced oxidation processes that balances predictive accuracy (±2.1% error vs. experiments) with operational practicality. Future enhancements should focus on integrating real-time oxidant concentration data to improve R² beyond the current 0.34.  \n1. INTRODUCTION  \nThe animal feed industry's rapid expansion has increased the production of high-strength effluent, which is distinguished by significantly elevated levels of organic pollutants, including Chemical Oxygen Demand (COD)[1,2] . Efficient wastewater treatment is essential for reducing environmental pollution and adhering to rigorous regulatory requirements. Conventional treatment approaches, such as biological and physicochemical processes, frequently encounter difficulties in attaining consistent chemical oxygen demand (COD) removal, especially when dealing with complex industrial effluents [3,4] .  \nAdvanced oxidation processes (AOPs), including ozonation, represent effective alternatives for the degradation of recalcitrant organic compounds [5–7] . The treatment of industrial wastewater, especially from animal feed production, presents considerable challenges owing to its elevated organic load and compositional variability. Conventional methods, such as activated sludge processes, demonstrate efficacy for moderate chemical oxygen demand (COD) levels but encounter several challenges[8] . Ozonation, a type of advanced oxidation process, has garnered interest for its capacity to oxidize complex organic molecules either directly or via the production of reactive oxygen species [6,9] . Research has shown its effectiveness in decreasing COD; however, the process is significantly influenced by variables including ozone dosage, contact duration, and initial pollutant concentration [10,11] .  \nOptimizing these processes for industrial applications necessitates precise control of operational parameters, atask often complicated by the non-linear relationships among variables. Recent advancements in computational modelling have facilitated enhanced predictions of wastewater treatment performa","cbCaipuh7HJww9ip","https://ap.wps.com/l/cbCaipuh7HJww9ip","pdf",530114,"English","# Introduction\n## Background: animal feed wastewater and COD removal challenges\n## Advanced oxidation processes and ozonation variables\n## Role of ANN in modeling non-linear wastewater treatment\n## Research gap and study contribution\n## Hybrid experimental-computational ANN approach","[{\"question\":\"What ANN model was used to predict ozonation performance for COD removal?\",\"answer\":\"A feedforward artificial neural network (ANN) with a 10-8 neuron architecture was constructed to predict COD reduction efficiency based on operational parameters.\"},{\"question\":\"How did the ANN predictions compare with experimental results?\",\"answer\":\"The ANN predicted 97.4% COD removal at 180 min for 1000 mg/L, while experimental data showed 97.83% at 160 min for the same initial COD level, indicating a small discrepancy.\"},{\"question\":\"Which factors were highlighted as key drivers of ozonation performance?\",\"answer\":\"Ozonation performance was described as being influenced by variables such as ozone dosage, contact duration, and initial pollutant concentration (initial COD).\"},{\"question\":\"What improvement is suggested for future versions of the model?\",\"answer\":\"Future enhancements should integrate real-time oxidant concentration data to improve predictive performance, specifically aiming to increase R² beyond the current 0.34.\"}]","Machine Learning vs. Real-World Data - Assessing ANN Performance in COD Removal in Animal Feed Process Wastewater | PDF"]