- Library Home /
- Search Collections /
- Open Collections /
- Browse Collections /
- UBC Undergraduate Research /
- UBC Climate-Friendly Label recipe analysis, 2023-2024...
Open Collections
UBC Undergraduate Research
UBC Climate-Friendly Label recipe analysis, 2023-2024 : Student WorkLearn 2023-2024 Report Marfatia, Sharon
Abstract
Research Objectives and Methodology The core objective of Sharon's work was to refine and extend the environmental impact analysis of food services at UBC. This involved incorporating a new land use metric into the assessment framework, re-evaluating baselines for greenhouse gas (GHG) emissions, stress-weighted water use and embodied nitrogen. A multi-faceted approach was employed, leveraging both existing and dynamic data analysis techniques. Key methodologies included: • Enhancing environmental impact assessments by integrating land use factors with existing metrics. • Automating the classification of food items into GHG impact categories and standardizing unit measurements to streamline procurement data analysis. • Deploying machine learning models, specifically focusing on natural language processing (NLP), to classify and analyze UBC Food Services data, with the objective to use UBC Food Services data to predict CF label assignments at other venues where detailed recipe information is unavailable. Major Findings The application of these methodologies yielded several significant findings: • The introduction of a land use factor provided a more comprehensive reflection of food choices' environmental impacts. • Automation of data categorization and unit standardization substantially improved the efficiency of data analysis processes. • The NLP-based machine learning model demonstrated a robust capacity for classifying food service data (final test score of 0.7356 = 73.56%), a positive prospect towards deploying the label more effectively. Significant Conclusions As we move forward, it is clear that the insights and methodologies developed have the potential to significantly influence both the academic and operational landscapes of food services at UBC and beyond. The enhanced analytical capabilities have not only improved the precision of environmental impact assessments but have also paved the way for more informed decision-making regarding food procurement and sustainability practices. Disclaimer: “UBC SEEDS provides students with the opportunity to share the findings of their studies, as well as their opinions, conclusions and recommendations with the UBC community. The reader should bear in mind that this is a student project/report and is not an official document of UBC. Furthermore readers should bear in mind that these reports may not reflect the current status of activities at UBC. We urge you to contact the research persons mentioned in a report or the SEEDS Coordinator about the current status of the subject matter of a project/report.”
Item Metadata
Title |
UBC Climate-Friendly Label recipe analysis, 2023-2024 : Student WorkLearn 2023-2024 Report
|
Creator | |
Contributor | |
Date Issued |
2024-04
|
Description |
Research Objectives and Methodology The core objective of Sharon's work was to refine and extend the environmental impact analysis of food services at UBC. This involved incorporating a new land use metric into the assessment framework, re-evaluating baselines for greenhouse gas (GHG) emissions, stress-weighted water use and embodied nitrogen. A multi-faceted approach was employed, leveraging both existing and dynamic data analysis techniques. Key methodologies included: • Enhancing environmental impact assessments by integrating land use factors with existing metrics. • Automating the classification of food items into GHG impact categories and standardizing unit measurements to streamline procurement data analysis. • Deploying machine learning models, specifically focusing on natural language processing (NLP), to classify and analyze UBC Food Services data, with the objective to use UBC Food Services data to predict CF label assignments at other venues where detailed recipe information is unavailable. Major Findings The application of these methodologies yielded several significant findings: • The introduction of a land use factor provided a more comprehensive reflection of food choices' environmental impacts. • Automation of data categorization and unit standardization substantially improved the efficiency of data analysis processes. • The NLP-based machine learning model demonstrated a robust capacity for classifying food service data (final test score of 0.7356 = 73.56%), a positive prospect towards deploying the label more effectively. Significant Conclusions As we move forward, it is clear that the insights and methodologies developed have the potential to significantly influence both the academic and operational landscapes of food services at UBC and beyond. The enhanced analytical capabilities have not only improved the precision of environmental impact assessments but have also paved the way for more informed decision-making regarding food procurement and sustainability practices. Disclaimer: “UBC SEEDS provides students with the opportunity to share the findings of their studies, as well as their opinions, conclusions and recommendations with the UBC community. The reader should bear in mind that this is a student project/report and is not an official document of UBC. Furthermore readers should bear in mind that these reports may not reflect the current status of activities at UBC. We urge you to contact the research persons mentioned in a report or the SEEDS Coordinator about the current status of the subject matter of a project/report.”
|
Subject | |
Genre | |
Type | |
Language |
eng
|
Series | |
Date Available |
2024-07-30
|
Provider |
Vancouver : University of British Columbia Library
|
Rights |
Attribution-NonCommercial-NoDerivatives 4.0 International
|
DOI |
10.14288/1.0444920
|
URI | |
Affiliation | |
Peer Review Status |
Unreviewed
|
Scholarly Level |
Undergraduate
|
Rights URI | |
Aggregated Source Repository |
DSpace
|
Item Media
Item Citations and Data
Rights
Attribution-NonCommercial-NoDerivatives 4.0 International