Grant: Engage Grants Program
University of British Columbia
$11,750.00
Online machine learning methods for hydrological problems
FY 2012-13
Summary
Machine learning methods from the field of artificial intelligence, having greatly improved our ability to
discover and model nonlinear relations, have been increasingly used in solving hydrological problems.
Unfortunately, maintaining an operational nonlinear regression model in a real environment is extremely
difficult logistically, as new data arrive continually, and updating the model by retraining using all available
data is often prohibitively expensive computationally. This proposal aims to develop ""online learning"" models,
which can inexpensively update the nonlinear regression models as new data arrive continually, and to apply
these models to forecasting streamflow and other environmental variables.
Program
Engage Grants Program
Recipient
Location
British Columbia, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
441782-2012
Name nom
Hsieh, William
Department département
Earth and Ocean Sciences
Organization id
2
Institution établissement
University of British Columbia
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2012
Competition year année de concours
2012
Award amount
11750
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
1554
Committee name en
Pacific Internal Decision Committee
Committee name fr
Comité de décision interne pour le Pacifique
Area of application code
702
Area of application group en
Transportation systems and services
Area of application group fr
Services et systèmes de transport
Area of application en
Water
Area of application fr
Maritime
Research subject code
4500
Research subject group en
Hydrology
Research subject group fr
Hydrologie
Research subject en
Hydrology
Research subject fr
Hydrologie
Partie
1
Nb partie
1
Application title
Online machine learning methods for hydrological problems
Keyword
NSERC
Application summary
Machine learning methods from the field of artificial intelligence, having greatly improved our ability to
discover and model nonlinear relations, have been increasingly used in solving hydrological problems.
Unfortunately, maintaining an operational nonlinear regression model in a real environment is extremely
difficult logistically, as new data arrive continually, and updating the model by retraining using all available
data is often prohibitively expensive computationally. This proposal aims to develop ""online learning"" models,
which can inexpensively update the nonlinear regression models as new data arrive continually, and to apply
these models to forecasting streamflow and other environmental variables.