(2cx) Real-Time Green CO2 Tracking with Artificial Intelligence in Biomass Co-Processing

This study presents an innovative Artificial Intelligence (AI)-based methodology for real-time green CO2emission tracking in biomass co-processing at oil refineries. This approach aims to reduce carbon intensity fuels and minimize environmental impact. The methodology includes data acquisition, preprocessing, feature extraction, and machine learning model selection, training, and validation. Various models like neural networks, support vector machines, and decision trees are evaluated considering process variables. The AI-driven system successfully analyzes green CO2 emissions in real-time, aiding in identifying trends, detecting anomalies, and optimizing processing conditions to reduce emissions while maintaining efficiency and product quality. This breakthrough approach provides significant potential in promoting more sustainable practices within the industry. Future work will focus on enhancing AI models and exploring their broader applications in biomass co-processing.

Research Interests: As society continues to decarbonize, addressing carbon emissions from hard-to-abate sectors such as transport and industry is a pressing challenge. My research centers on the data driven modeling the co-processing of biogenic feedstocks at oil refineries, a promising approach for reducing carbon intensity. The unique feature of our research lies in the application of Artificial Intelligence (AI) for real-time monitoring and optimization of green CO2 emissions during the co-processing operations. We propose an innovative methodology that utilizes various machine learning models, taking into account multiple process variables. Preliminary results show successful real-time tracking and analysis of green CO2 emissions, which allows for anomaly detection and process optimization. This research contributes to minimizing the environmental footprint of the oil refining industry while maintaining operational efficiency. We are also developing online monitoring tools for real-time tracking of "green molecules" in flue gas. Our work paves the way for other oil refineries and sectors aiming to implement co-processing and benefit from its insights.