ORCID

0000-0001-9125-7802

Keywords

Recycling, AI, ML, LCA, Cart-tagging, Waste Management

Abstract

Municipal solid waste management requires balancing environmental performance, operational efficiency, and community participation. Proper recycling contamination in single-family units is a persistent barrier to material recovery, reducing the effectiveness of local programs by increasing recycling contamination. This dissertation develops an integrated, data-driven framework that combines behavioral modeling of communities via statistical analysis and machine learning (ML), and life cycle assessment (LCA) to support decision-making in residential waste management. The first component examines household recycling behavior using data from Orange County, Florida’s Recycling Quality Improvement Program (RQIP). Cart-tagging results were integrated with socio-demographic data from the U.S. Census to predict contamination patterns and participation rates, as well as responses of various communities to a 4 week cart tagging program. Machine learning models identified key predictors, including home ownership, education, and income, revealing that outreach and contamination-reduction strategies should be spatially tailored rather than uniformly applied. The second component evaluates environmental and economic trade-offs among alternative curbside collection systems in four southern U.S. counties. The LCA results show that lower garbage collection frequency reduces both cost and greenhouse gas emissions at the cost of garbage bin overflow into the recycling bin, increasing the contamination, while switching to the dual stream recycling (DSR) from single stream recycling (SSR) improves material quality at higher operational cost. Food waste diversion provides additional environmental benefits but depends on local infrastructure capacity. A third, ongoing phase involves the deployment of cameras at a regional transfer station to capture visual data for contamination detection and to evaluate the effect of targeted messaging strategies, as well as testing methods to detect batteries and battery containing items, which pose fire risk at the material recovery facilities (MRFs) and the transfer stations. Observations indicate improvements in contamination reduction through combined positive and corrective messaging.

Completion Date

2025

Semester

Fall

Committee Chair

Jiannan Chen

Degree

Doctor of Philosophy (Ph.D.)

College

College of Engineering and Computer Science

Department

Department of Civil, Environmental and Construction Engineering

Format

PDF

Identifier

DP0029724

Document Type

Thesis

Campus Location

Orlando (Main) Campus

Download

Share

COinS