Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Discovery Horizons

University of Regina

$141,000.00

Machine learning approach for sustainable clothing and textile waste management: Evidence-based policy and circular economy framework in the fashion industry

FY 2024-25

Summary
The rise of fast fashion has strained the Canadian waste management system. Unlike paper and plastic recycling, managing post-consumer clothing and textile (CT) waste is more challenging due to its heterogeneous nature. Various plastics, metals, adhesives, as well as blends of synthetic and natural fibres, can all be found in a single item of clothing. Currently, we do not have a viable engineering and business management framework to collect, process, and recycle of end-of-life CT. More importantly, the social and regulatory aspects of the CT management framework are lagging. Social stigma of second-hand clothing, inconsistent perceived monetary and aesthetic values, and the lack of a resilient market are some of the key socio-economic barriers. The long-term goal of this project is to develop an evidence-based policy and a comprehensive circular economy (CE) framework in the fashion industry using a big data approach. The specific objectives are: (i) Conducting a comprehensive literature review on CT waste management framework across the globe using bibliometric analysis, (ii) Developing an interactive Canadian thrift database using semi-structured interviews, post-purchase customer surveys, and field sampling, (iii) Creating a machine learning model on CT generation and recycling behaviours using distinct time series and lagged inputs, and (iv) Informing policy-makers with data-driven recommendations and guidelines based on the proposed CT waste management framework. We believe the lag in development of a circular fashion system is at least in part due to the absence of a transdisciplinary approach, which is the key theme of this proposal. In this study, the complex and interrelated end-of-life CT generation behaviors in different geographic regions and sociocultural conditions are modelled using RNN-LSTM, with the goal to establish national wide data-driven CT management policy. This project aims to combine expertise from engineering, textiles, human ecology, social and behavioral sciences, and business. Managing CT domestically supports a healthy CE and reduces the burden placed on importing countries of second-hand clothing, reducing health risks to marginalized groups, and mitigating business ethical issues of waste importation/exportation. The proposed work will bring research institutions and non-government organizations together, creating new science and streamlining our efforts on interdisciplinary HQP training.
Program
Discovery Horizons
Location
Saskatchewan, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
DH-2023-00488
Name nom
Ng, Kelvin Tsun Wai
Department département
Environmental Systems Engineering - University of Regina
Organization id
17
Institution établissement
University of Regina
Province en
Saskatchewan
Province fr
Saskatchewan
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2023
Award amount
141000
Program id
DH
Program name en
Discovery Horizons
Program name fr
Horizons de la découverte
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
nan
Area of application code
9999
Area of application group en
Not available
Area of application group fr
Non disponible
Area of application en
Not available
Area of application fr
Non disponible
Research subject code
9999
Research subject group en
Not available
Research subject group fr
Non disponible
Research subject en
Not available
Research subject fr
Non disponible
Field of research list codes
RDF2080101
Field of research list names en
Residual materials management
Field of research list names fr
Gestion des matières résiduelles
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Machine learning approach for sustainable clothing and textile waste management: Evidence-based policy and circular economy framework in the fashion industry
Keywords
Post-consumer clothing and textile waste; Data driven waste policy in end-of-life textile sector; Circular economy in Canadian fashsion industry; RNN-LSTM modeling using K-fold validation and distinct time-series; Interaction of odorous molecules with textile fibres ; Sensory detection of body odor emanating from fabrics; Holistic scenario mapping and social justice; Recycling opportunities and disposal behaviors of second-hand clothing; Gender stereotyping and cultural appropriation in Fashsion
Application summary
The rise of fast fashion has strained the Canadian waste management system. Unlike paper and plastic recycling, managing post-consumer clothing and textile (CT) waste is more challenging due to its heterogeneous nature. Various plastics, metals, adhesives, as well as blends of synthetic and natural fibres, can all be found in a single item of clothing. Currently, we do not have a viable engineering and business management framework to collect, process, and recycle of end-of-life CT. More importantly, the social and regulatory aspects of the CT management framework are lagging. Social stigma of second-hand clothing, inconsistent perceived monetary and aesthetic values, and the lack of a resilient market are some of the key socio-economic barriers. The long-term goal of this project is to develop an evidence-based policy and a comprehensive circular economy (CE) framework in the fashion industry using a big data approach. The specific objectives are: (i) Conducting a comprehensive literature review on CT waste management framework across the globe using bibliometric analysis, (ii) Developing an interactive Canadian thrift database using semi-structured interviews, post-purchase customer surveys, and field sampling, (iii) Creating a machine learning model on CT generation and recycling behaviours using distinct time series and lagged inputs, and (iv) Informing policy-makers with data-driven recommendations and guidelines based on the proposed CT waste management framework. We believe the lag in development of a circular fashion system is at least in part due to the absence of a transdisciplinary approach, which is the key theme of this proposal. In this study, the complex and interrelated end-of-life CT generation behaviors in different geographic regions and sociocultural conditions are modelled using RNN-LSTM, with the goal to establish national wide data-driven CT management policy. This project aims to combine expertise from engineering, textiles, human ecology, social and behavioral sciences, and business. Managing CT domestically supports a healthy CE and reduces the burden placed on importing countries of second-hand clothing, reducing health risks to marginalized groups, and mitigating business ethical issues of waste importation/exportation. The proposed work will bring research institutions and non-government organizations together, creating new science and streamlining our efforts on interdisciplinary HQP training.