Sources

The data utilized in this project originates from the United States Environmental Protection Agency (EPA) Greenhouse Gas Reporting Program (GHGRP), specifically the “Emissions from Production & Transformation Processes by Chemical” records as published in 2023 EPA. This dataset comprises facility-reported, chemical-level emissions of fluorinated greenhouse gases within the electronics manufacturing sector, including key variables such as chemical name, facility identifier, reporting year, and total annual emissions measured in metric tons. To ensure analytical rigor, we performed thorough data cleaning, excluding any entries with missing chemical names or emission values and standardizing categorical fields for modeling purposes. All variable names were harmonized and formatted for clarity and consistency in downstream statistical analysis. The resulting clean dataset serves as the foundation for both exploratory analysis and predictive modeling, enabling a detailed investigation into the factors that drive greenhouse gas emissions at the chemical and facility level within the electronics industry.