{"id":{"repo_id":"york","oai_identifier":"oai:yorkspace.library.yorku.ca:10315/38799"},"canonical_url":"https://search.dev.ndltd.org/etd/york/oai:yorkspace.library.yorku.ca:10315/38799","repository":{"repo_id":"york","name":"York University","base_url":"https://yorkspace.library.yorku.ca/oai/request"},"display":{"title":"Forecasting Chlorine Residual for Water Safety Using Artificial Neural Networks Ensembles in Humanitarian Water Systems","abstract":"Waterborne illnesses are a leading health concern in refugee and internally displaced person (IDP) settlements where waterborne pathogens often spread through household recontamination of stored water. Ensuring sufficient chlorine residual is important for protecting drinking water against recontamination and ensuring water remains safe up to the point-of-consumption. This thesis investigated the use of ensembles of artificial neural networks (ANNs) to probabilistically forecast the point-of-consumption free residual chlorine (FRC) concentration using water quality data from six refugee and IDP settlements. These models were then used to generate point-of-distribution FRC targets based on the risk of insufficient FRC at the point-of consumption. Overall, the ensemble ANN approach produced accurate risk-based FRC targets, though the ensemble forecasts were underdispersed. Three approaches for overcoming the underdispersion were considered: post-processing ensemble predictions, training the ANNs using cost-sensitive learning, and multi-objective training of the ANNs. Of these approaches, the multi-objective training yielded the best results.","abstract_html":"Waterborne illnesses are a leading health concern in refugee and internally displaced person (IDP) settlements where waterborne pathogens often spread through household recontamination of stored water. Ensuring sufficient chlorine residual is important for protecting drinking water against recontamination and ensuring water remains safe up to the point-of-consumption. This thesis investigated the use of ensembles of artificial neural networks (ANNs) to probabilistically forecast the point-of-consumption free residual chlorine (FRC) concentration using water quality data from six refugee and IDP settlements. These models were then used to generate point-of-distribution FRC targets based on the risk of insufficient FRC at the point-of consumption. Overall, the ensemble ANN approach produced accurate risk-based FRC targets, though the ensemble forecasts were underdispersed. Three approaches for overcoming the underdispersion were considered: post-processing ensemble predictions, training the ANNs using cost-sensitive learning, and multi-objective training of the ANNs. Of these approaches, the multi-objective training yielded the best results.","abstract_has_math":false,"creators":["De Santi, Michael Vincent"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Khan, Usman T.","Ali, Syed Imran"],"committee_chairs":[],"committee_members":[],"year":2021,"date_issued":"2021-11-15","date_published":"2021-11-15","updated_at":"2026-07-24T06:34:00Z","subjects":["Artificial intelligence"],"languages":["en"],"rights":["Author owns copyright, except where explicitly noted. Please contact the author directly with licensing requests."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/10315/38799","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Khan, Usman T.","Ali, Syed Imran"]},{"key":"dc:creator","label":"Author","values":["De Santi, Michael Vincent"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2021-11-15T15:56:22Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2021-11-15T15:56:22Z"]},{"key":"dc:date.issued","label":"Date","values":["2021-11-15"]},{"key":"dc:type","label":"Dc Type","values":["Electronic Thesis or Dissertation"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Artificial intelligence"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Author owns copyright, except where explicitly noted. Please contact the author directly with licensing requests."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/10315/38799"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Waterborne illnesses are a leading health concern in refugee and internally displaced person (IDP) settlements where waterborne pathogens often spread through household recontamination of stored water. Ensuring sufficient chlorine residual is important for protecting drinking water against recontamination and ensuring water remains safe up to the point-of-consumption. This thesis investigated the use of ensembles of artificial neural networks (ANNs) to probabilistically forecast the point-of-consumption free residual chlorine (FRC) concentration using water quality data from six refugee and IDP settlements. These models were then used to generate point-of-distribution FRC targets based on the risk of insufficient FRC at the point-of consumption. Overall, the ensemble ANN approach produced accurate risk-based FRC targets, though the ensemble forecasts were underdispersed. Three approaches for overcoming the underdispersion were considered: post-processing ensemble predictions, training the ANNs using cost-sensitive learning, and multi-objective training of the ANNs. Of these approaches, the multi-objective training yielded the best results."]},{"key":"dc:title","label":"Title","values":["Forecasting Chlorine Residual for Water Safety Using Artificial Neural Networks Ensembles in Humanitarian Water Systems"]}]}],"canonical_facts":{"dc:contributor.advisor":["Khan, Usman T.","Ali, Syed Imran"],"dc:creator":["De Santi, Michael Vincent"],"dc:date.accessioned":["2021-11-15T15:56:22Z"],"dc:date.available":["2021-11-15T15:56:22Z"],"dc:date.issued":["2021-11-15"],"dc:description.abstract":["Waterborne illnesses are a leading health concern in refugee and internally displaced person (IDP) settlements where waterborne pathogens often spread through household recontamination of stored water. Ensuring sufficient chlorine residual is important for protecting drinking water against recontamination and ensuring water remains safe up to the point-of-consumption. This thesis investigated the use of ensembles of artificial neural networks (ANNs) to probabilistically forecast the point-of-consumption free residual chlorine (FRC) concentration using water quality data from six refugee and IDP settlements. These models were then used to generate point-of-distribution FRC targets based on the risk of insufficient FRC at the point-of consumption. Overall, the ensemble ANN approach produced accurate risk-based FRC targets, though the ensemble forecasts were underdispersed. Three approaches for overcoming the underdispersion were considered: post-processing ensemble predictions, training the ANNs using cost-sensitive learning, and multi-objective training of the ANNs. Of these approaches, the multi-objective training yielded the best results."],"dc:identifier.uri":["http://hdl.handle.net/10315/38799"],"dc:language":["en"],"dc:rights":["Author owns copyright, except where explicitly noted. Please contact the author directly with licensing requests."],"dc:subject":["Artificial intelligence"],"dc:title":["Forecasting Chlorine Residual for Water Safety Using Artificial Neural Networks Ensembles in Humanitarian Water Systems"],"dc:type":["Electronic Thesis or Dissertation"]},"updated_at":"2026-07-24T06:34:00Z"}