Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Alliance Grants

McMaster University

$100,000.00

Adaptive Multi-Source Transfer Learning Approaches for Environmental Challenges

FY 2023-24

Summary
The prediction of water and environmental processes, such as river ice events and water/wastewater treatment, can be a daunting challenge due to dynamic complexity and data scarcity. For example, the early breakup of ice cover in a mid-winter breakup (MWB) is a rare, dangerous to measure, and potentially catastrophic river ice event. While MWBs in Canada are increasing in frequency due to climate change, their prediction is significantly challenged by the availability of data and the complexity of river ice dynamics. Membrane, a relatively new and highly effective technology for water and wastewater treatment, is also difficult to model. The dynamic and nonstationary nature of membrane processes often leads to shifts in fouling behavior, making it fundamentally challenging to rely solely on historical data for accurate predictions. The goal of this project is to develop novel Transfer Learning (TL) approaches tailored for MWB forecasting and membrane fouling prediction. This research will be conducted in collaboration with an international collaborator in the UK, who has secured funding for the development of TL approaches for river ice jam and wastewater inflow rate prediction. By integrating the applicant's expertise in environmental modeling and the international collaborator's expertise in machine learning, new TL models tailored for MWB and membrane modeling will be developed, evaluated and implemented. This work will advance the fields of river ice modeling and membrane fouling modeling by providing reliable predictions of rare and/or undesirable events and thus helping industries and different levels of government in Canada improve their effectiveness in managing water and environmental risks. It will also facilitate the integration of advanced AI technologies and the automation of decision-making in the water and wastewater sector.
Program
Alliance Grants
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
587158-2023
Name nom
Li, Zoe Z
Department département
Civil Engineering
Organization id
27
Institution établissement
McMaster University
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2023
Competition year année de concours
2023
Award amount
100000
Program id
ALLRP
Program name en
Alliance Grants
Program name fr
Subventions Alliance
Group en
RESEARCH PARTNERSHIPS
Group fr
PARTENARIATS DE RECHERCHE
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
400
Area of application group en
Environment
Area of application group fr
Environnement
Area of application en
Environment
Area of application fr
Environnement
Research subject code
2717
Research subject group en
Information technology
Research subject group fr
Modelling and simulation studies
Research subject en
Technologie de l'information
Research subject fr
Études de modélisation et de simulation
Application title
Adaptive Multi-Source Transfer Learning Approaches for Environmental Challenges
Keyword
environmental systems; imbalanced data; machine learning; multi-source data; river ice modeling; transfer learning; wastewater modeling
Application summary
The prediction of water and environmental processes, such as river ice events and water/wastewater treatment, can be a daunting challenge due to dynamic complexity and data scarcity. For example, the early breakup of ice cover in a mid-winter breakup (MWB) is a rare, dangerous to measure, and potentially catastrophic river ice event. While MWBs in Canada are increasing in frequency due to climate change, their prediction is significantly challenged by the availability of data and the complexity of river ice dynamics. Membrane, a relatively new and highly effective technology for water and wastewater treatment, is also difficult to model. The dynamic and nonstationary nature of membrane processes often leads to shifts in fouling behavior, making it fundamentally challenging to rely solely on historical data for accurate predictions. The goal of this project is to develop novel Transfer Learning (TL) approaches tailored for MWB forecasting and membrane fouling prediction. This research will be conducted in collaboration with an international collaborator in the UK, who has secured funding for the development of TL approaches for river ice jam and wastewater inflow rate prediction. By integrating the applicant's expertise in environmental modeling and the international collaborator's expertise in machine learning, new TL models tailored for MWB and membrane modeling will be developed, evaluated and implemented. This work will advance the fields of river ice modeling and membrane fouling modeling by providing reliable predictions of rare and/or undesirable events and thus helping industries and different levels of government in Canada improve their effectiveness in managing water and environmental risks. It will also facilitate the integration of advanced AI technologies and the automation of decision-making in the water and wastewater sector.