[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121540-en":3,"doc-seo-121540-105":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},121540,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","Machine Learning for Short-Term Water Demand Predictions - Thesis for Doctor of Philosophy (Engineering)","Urban water supply faces mounting pressure from urbanisation, water scarcity, and climate change. Effective urban water management depends on accurate short-term demand and consumption forecasting to support capacity expansion, financing, and efficient operation of water distribution systems. This thesis explores data-centric forecasting approaches that improve the efficiency of data and computation, instead of solely enhancing model-centric performance. Experiments compare intrinsically different models, assess interpretability, and evaluate transfer learning using multiple UK and Chinese demand datasets.","Machine Learning for ShortTerm Water Demand Predictions  \nSubmitted by Guoxuan Liu  \nto the University of Exeter as a thesis for the degree of Doctor of Philosophy in Engineering  \nMay 2023  \nThis thesis is available for Library use on the understanding that it is copyright material and that no quotation from the thesis may be published without proper acknowledgement.  \nI certify that all material in this thesis which is not my own work has been identified and that any material that has previously been submitted and approved for the award of a degree by this or any other University has been acknowledged.  \nAbstract  \nUrban water supply is coming under increased pressure due to urbanisation, water scarcity and climate change. Efficient urban water management can help alleviate this pressure by improving service quality and reducing water loss. Accurate demand and consumption forecasting enables expansion planning, financing, and operation of water distribution systems. Current research often focuses on model-centric approaches where the model is improved to drive forecast accuracy; however, more efficient data usage could be realised as an alternative to model-centric approaches, without incurring additional computation costs. This work investigates the potential of data-centric forecasting approaches, focusing on ways to improve the efficiency of data and computation resource usage for short-term water demand forecasting.  \nTo initiate the investigation, several intrinsically different forecasting models are analysed. A total of four different forecasting models, i.e. , Prophet, Autoregressive Integrated Moving Average, Neural Network (NN) and Random Forest (RF) are applied to four demand datasets, i.e. , one Chinese hourly demand dataset and three UK 15-minute demand datasets. Various aspects of data and model requirements for optimal performance are investigated. Results obtained from the case studies show that prolonging training data may not be necessary, and that accurate sub-daily water demand forecasting is possible with 10 days of past data for model training. In terms of accuracy, neural network and random forest tend to be better suited towards short-term water demand forecasting over statistical models.  \nThe second part of the work aims to unbox the four black-box machine learning methods – NN, Long Short-Term Memory (LSTM), RF, Extreme Gradient Boosting (XGB) and explain their inner workings using SHapley Additive exPlanations and Local Interpretable Model-Agnostic Explanations, Prophet and ARIMA are excluded due to inferior forecasting accuracy. Results have found that feature requirement depends on data resolution, the forecasting model used and the forecast time of day. Network-based models (NN and LSTM) are more temporally dependent and feature intensive, indicating that they require more feature inputs to produce equal accuracy compared to tree-based models (RFand XGB) . High-resolution forecasts can maintain a high level of accuracy with only one feature at the previous point.  \nThe final part of the work analyses the possibility of incorporating Transfer Learning (TL) into the context of water demand forecasting. To evaluate the potential of TL, 18 UK DMAs water demand datasets are used. Experiments are designed to predict water demands in one DMA that has limited or unavailable data, with an aim to anaysing the forecasting ability of models built with alternative DMA data. Results have found that four and eight external DMA datasets are respectively suitable for 15-minute and hourly demand and that limited accuracy gains are achieved from samples size larger than 20,000 . Finally, TLincorporated methods can improve machine learning forecasting accuracy when there is limited data availability.  \nThe results obtained in this study prove the usefulness of data-centric approaches’ ability to improve forecasting accuracy. The data-centric approaches explored in this thesis can be used to guide the development o","cbCaieDKavCB6vjY","https://ap.wps.com/l/cbCaieDKavCB6vjY","pdf",10440366,1,146,"English","en",105,"# Acknowledgements\n# List of Figures\n# List of Tables\n# List of Abbreviations\n# Chapter 1 - Introduction\n## Motivation\n## Research Questions and Aims\n## Thesis Overview\n## Contributions\n## Published papers\n# Chapter 2 - Literature Review","[{\"question\":\"What problem does the thesis address?\",\"answer\":\"The thesis addresses the need for more accurate short-term urban water demand forecasting under growing pressure from urbanisation, water scarcity, and climate change.\"},{\"question\":\"Which forecasting models are evaluated in the study?\",\"answer\":\"The study applies four forecasting models—Prophet, ARIMA, Neural Network (NN), and Random Forest (RF)—and later examines black-box methods including NN, LSTM, RF, and XGBoost while excluding Prophet and ARIMA due to inferior accuracy.\"},{\"question\":\"How does the thesis approach explainability and feature requirements?\",\"answer\":\"Explainability uses SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) to interpret black-box behavior. Feature requirements vary with data resolution, forecasting model, and time of day, with network-based models generally more feature intensive than tree-based models.\"},{\"question\":\"How is transfer learning used for water demand forecasting?\",\"answer\":\"Transfer learning is tested using 18 UK DMA datasets to predict demand in a DMA with limited or unavailable data. Results indicate that four and eight external DMA datasets are suitable for 15-minute and hourly forecasts, and accuracy gains are more limited when sample size exceeds 20,000, while TL can help under data scarcity.\"}]","Machine Learning for Short-Term Water Demand Predictions - Thesis for Doctor of Philosophy (Engineering) | PDF",1785736161,368,{"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},"machine-learning-for-short-term-water-demand-predictions-thesis-for-doctor-of-philosophy-engineering","",{"@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/machine-learning-for-short-term-water-demand-predictions-thesis-for-doctor-of-philosophy-engineering/121540/",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","2026-08-03",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},"What problem does the thesis address?","Question",{"text":75,"@type":76},"The thesis addresses the need for more accurate short-term urban water demand forecasting under growing pressure from urbanisation, water scarcity, and climate change.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which forecasting models are evaluated in the study?",{"text":80,"@type":76},"The study applies four forecasting models—Prophet, ARIMA, Neural Network (NN), and Random Forest (RF)—and later examines black-box methods including NN, LSTM, RF, and XGBoost while excluding Prophet and ARIMA due to inferior accuracy.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the thesis approach explainability and feature requirements?",{"text":84,"@type":76},"Explainability uses SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) to interpret black-box behavior. Feature requirements vary with data resolution, forecasting model, and time of day, with network-based models generally more feature intensive than tree-based models.",{"name":86,"@type":73,"acceptedAnswer":87},"How is transfer learning used for water demand forecasting?",{"text":88,"@type":76},"Transfer learning is tested using 18 UK DMA datasets to predict demand in a DMA with limited or unavailable data. Results indicate that four and eight external DMA datasets are suitable for 15-minute and hourly forecasts, and accuracy gains are more limited when sample size exceeds 20,000, while TL can help under data scarcity.","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"]