Forecasting and Volume Estimation of Municipal Solid Waste Using Machine Learning

Published in B.Tech-M.Tech Dual Degree Project • IIT Bombay, 2025

Overview

This thesis addresses two interconnected challenges in waste management: forecasting MSW generation using economic indicators across countries, and estimating waste volumes from single RGB images using monocular depth inference—together forming a closed-loop data-driven framework for waste monitoring.

Motivation

Effective solid waste management requires knowing how much waste is generated, where it originates, and what it comprises. We build:

  1. Forecasting models that infer waste generation from stable socioeconomic variables.
  2. Low-cost volume estimation systems that operate on-site without expensive hardware.

Volume Analysis

Recommended citation: Goyal, A. (2025). "Forecasting and Volume Estimation of Municipal Solid Waste Using Machine Learning". IIT Bombay.