Abstract This paper demonstrates a novel approach to tracking greenhouse gas emissions of artificial lift equipment, to support data and data driven decision making in delivering a circular carbon economy. Leveraging the outcome of insights and new datasets through implementing nybl's proprietary novel "Science-Based Artificial Intelligence" to Electrical Submersible Pump (ESP) Lift.ai to wells in the context of Environmental Sustainability and Governance (ESG) in real-world applications. Identifying opportunities to integrate advanced data analytics, Machine Learning (ML) and Artificial intelligence (AI) to improve operational efficiency, production, transparency and reducing downtime, and environmental and social impacts of ESPs, which can also be applied to other rotating, reciprocal and cavitational equipment in the future. Utilizing these techniques in a novel approach will increase transparency and allow active, rather than reactive, ESG efforts and enable data-driven decision-making in this space with limited additional Remote Telemetry Units (RTUs) associated costs - with further opportunities for sites where additional RTU related investments are warranted to drive increased insight.