Grant: Engage Grants Program
McGill University
$25,000.00
A new framework for nonlinear input variable selection coupled with ensemble-wavelet-machine learning methods with uncertainty assessments for urban water demand forecasting
EF 2013-14
Résumé
In Canada, increasing water demands and decreasing supplies have prompted many water utilities to seek outnew methods of optimizing their water supply and infrastructure planning and management to ensure thedelivery of high quality potable water to their customer base now, and into the future, while ensuring thesustainability of surrounding ecosystems. An effective and low cost method that can help optimize and ensurethe sustainability of water supplies is highly accurate and reliable urban water demand forecasting. Suchforecasts provide water managers, such as program managers with the City of Ottawa's (COO) EnvironmentalServices and Planning and Growth Management departments, with the ability to optimize day to day operationsand make informed, sustainable decisions when planning future water infrastructure maintenance andexpansion. The industrial partnership between the COO and Professor Adamowski's research team at McGillUniversity will allow for the development of new state-of-the-art urban water demand forecasting methodsbased on coupling wavelet transform, machine learning, and uncertainty assessment methods. These highlyaccurate and reliable forecasting methods will significantly advance the COO's water demand forecastingcapabilities in all of the different sectors of the city, and will have a significant impact in helping to improve:water treatment plant operation, maintenance and pump scheduling; reservoir recharge rates; pressure zonemonitoring; contingency planning; water conservation program development and evaluation; supply systemdevelopment and expansion; and establishing effective water rates. The models that will be developed andprovided to the COO are expected to lead the industry in urban water demand forecasting techniques withinCanada, and can serve as an excellent example for other utilities nationwide that are interested in sustainablyoptimizing their drinking water systems.
Programme
Engage Grants Program
Bénéficiaire
Emplacement
Quebec, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
450689-2013
Name nom
Adamowski, Jan
Department département
Bioresource Engineering
Organization id
61
Institution établissement
McGill University
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2013
Competition year année de concours
2013
Award amount
25000
Program id
EGP
Program name en
Engage Grants Program
Program name fr
Programme de subventions d'engagement partenariat
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1552
Committee name en
Quebec Internal Decision Committee
Committee name fr
Comité de décision interne pour le Québec
Area of application code
1206
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Engineering
Area of application fr
Génie
Research subject code
1007
Research subject group en
Civil engineering
Research subject group fr
Génie civil
Research subject en
Water resources and supply
Research subject fr
Ressources et approvisionnement en eau
Partie
1
Nb partie
1
Application title
A new framework for nonlinear input variable selection coupled with ensemble-wavelet-machine learning methods with uncertainty assessments for urban water demand forecasting
Keyword
NSERC
Application summary
In Canada, increasing water demands and decreasing supplies have prompted many water utilities to seek outnew methods of optimizing their water supply and infrastructure planning and management to ensure thedelivery of high quality potable water to their customer base now, and into the future, while ensuring thesustainability of surrounding ecosystems. An effective and low cost method that can help optimize and ensurethe sustainability of water supplies is highly accurate and reliable urban water demand forecasting. Suchforecasts provide water managers, such as program managers with the City of Ottawa's (COO) EnvironmentalServices and Planning and Growth Management departments, with the ability to optimize day to day operationsand make informed, sustainable decisions when planning future water infrastructure maintenance andexpansion. The industrial partnership between the COO and Professor Adamowski's research team at McGillUniversity will allow for the development of new state-of-the-art urban water demand forecasting methodsbased on coupling wavelet transform, machine learning, and uncertainty assessment methods. These highlyaccurate and reliable forecasting methods will significantly advance the COO's water demand forecastingcapabilities in all of the different sectors of the city, and will have a significant impact in helping to improve:water treatment plant operation, maintenance and pump scheduling; reservoir recharge rates; pressure zonemonitoring; contingency planning; water conservation program development and evaluation; supply systemdevelopment and expansion; and establishing effective water rates. The models that will be developed andprovided to the COO are expected to lead the industry in urban water demand forecasting techniques withinCanada, and can serve as an excellent example for other utilities nationwide that are interested in sustainablyoptimizing their drinking water systems.