• Automated the retrieval, aggregation, and elimination of duplicates of 100+ million rows of pollutant emissions data through Python and API pull requests in a singular runtime, improving data collection efficiency by 7,500%+
• Utilized Pandas and NumPy for data cleaning, schema validation, and transformation on metrics from 1,200+ facilities
• Analyzed day-ahead prices, marginal costs, heat rates, and capacity factors to forecast power plant outages under varying ambient air temperatures, supporting ongoing research paper on protecting energy systems against climate change