The central topic of this seminar is modeling approaches to facilitate resource conservation and a just energy transition. Potential subtopics are an emerging technology’s potential for scaling, life-cycle assessment for measuring social and environmental impacts, uncertainty quantification, and economic modeling for the energy transition. Our goal is to create an intimate, collaborative space for students, postdocs, scientists, and PIs within the Stanford techno-economic modeling and systems modeling community. These seminars will provide an opportunity to disseminate insights from your studies, connect with fellow researchers, and strengthen bonds across the community.

This week's speaker is:

Zhenlin (Richard) Chen, Ph.D. Candidate, Stanford University

"Advancing oil and gas emissions assessment through large language model data extraction"

Talk Abstract: This innovative research demonstrates how Large Language Models can transform data accessibility in the oil and gas industry. By harnessing the capabilities of advanced AI, the study presents a framework that efficiently extracts crucial operational information from diverse literature sources, addressing the industry's long-standing challenge of fragmented and costly data access.
The approach shows remarkable improvements in both efficiency and cost-effectiveness compared to traditional manual methods, while maintaining high accuracy. This breakthrough has far-reaching implications for environmental stewardship in the sector, potentially democratizing access to critical information that supports emissions reduction strategies, enhances climate modeling, and improves investment decision-making.
By creating a more organized and accessible database of industry operations, this framework contributes significantly to the oil and gas sector's environmental commitments and energy transition efforts.

Zhenlin (Richard) Chen is a Ph.D. candidate at Stanford's Adam Brandt lab, focuses on greenhouse gas emissions from oil and gas. His work primarily revolves around evaluating ground sensor technologies for methane detection and quantification ability. His methodological approach blends engineering principles, field data collection, and applied statistics. Chen is exploring AI-driven frameworks, particularly large language models, to refine energy data extraction and enhance the OPGEE model through private data fine-tuning and reinforcement learning. His emphasis remains on domain-specific tasks, aiming for efficiency in terms of latency and cost. He pursued his undergraduate studies in environmental science at Cornell University and holds a master's in Atmosphere and Energy Engineering from Stanford.