Life cycle assessment of Tehran Municipal solid waste during the COVID-19 pandemic and environmental impacts prediction using machine learning

This research-oriented project framework explores the environmental consequences of shifts in municipal solid waste (MSW) composition during the COVID-19 pandemic, using Tehran as a case study. The source study highlights a significant rise in plastic waste from 7.5% to 11%, which altered the overall environmental footprint. To evaluate these changes, a Life Cycle Assessment (LCA) was conducted using the ReCipe methodology across multiple waste management scenarios. The environmental burdens of these scenarios were ranked as follows: Sc-1 (increasing composting to 50%) > Sc-3 > Sc-4 > Sc-b2 > Sc-5 > Sc-2 (increasing recycling from 9% to 20%), indicating that maximizing recycling yielded the lowest environmental burden. To predict these impacts

dynamically, the researchers integrated machine learning models, specifically Artificial Neural Networks (ANN) and Gradient-Boosted Regression Trees (GBRT), achieving high prediction accuracy (R2). For M.Tech students, this framework provides research direction and implementation support for modeling waste management systems. It guides the structuring of LCA workflows and the integration of predictive ML algorithms to evaluate municipal waste strategies under fluctuating composition scenarios.

Message: Hi FE, I need help with “Life cycle assessment of Tehran Municipal solid waste during the COVID-19 pandemic and environmental impacts prediction using machine learning” in “Environmental Engineering”