Date of Award
2024
Document Type
Thesis
Degree Name
Master of Science (MS)
Department
Computer Science
Committee Chair
Tathagata Mukherjee
Committee Member
Chaity Banerjee Mukherjee
Committee Member
Sundar Christopher
Research Advisor
Tathagata Mukherjee
Subject(s)
Data sets--Management, Machine learning, Environmental justice
Abstract
Equity and Environmental Justice (EEJ) advocates for unbiased distribution of environmental impacts across communities, regardless of social and economic characteristics. After extreme events like natural disasters, EEJ gains importance due to evident disparities in impact among communities. Addressing these injustices requires comprehensive datasets and analytical methods for quantification and resolution. While AI and advanced data analysis offer promising solutions, creating AI-ready EEJ datasets is challenging due to heterogeneity in the data surrounding EEJ. In this work, we focus on curating novel datasets for EEJ targeting a few recent extreme events - Maui Wildfire, Hurricane Harvey, and Hurricane Ida. We demonstrate the utility of the datasets using preliminary analysis with machine learning and AI enabled methods. Succinctly, we created masks to identify EEJ issues and generated nuanced insights employing machine learning, image processing and statistical methods. This study has the potential to empower authorities in data-driven policy-making, disaster management, and resource allocation, addressing the actual needs of affected communities.
Recommended Citation
Parajuli, Paridhi, "Curation and analysis of AI ready environmental justice datasets : a proof-of-concept study" (2024). Theses. 661.
https://louis.uah.edu/uah-theses/661