To store CO2 in depleted oil and gas fields or saline aquifers, a detailed site assessment is typically done manually, which is time-consuming and costly, as there are large number of older wells with poor quality records. The study presented here will leverage cloud computing and artificial intelligence (AI) tools like Optical Character Recognition (OCR) and Natural Language Processing (NLP) to automate the legacy well assessment for efficient decision-making in storage site selection, thus reducing human effort. Results from our preliminary tests show that with this approach one can extract 80% of the desired information from various data sources including hand-written well reports and analyze information to accelerate CO2 storage risk level estimation.

Machine Learning (ML) has proved successful in various applications and delivered tremendous value across numerous domains. ML turns data into knowledge and intelligence, that can be used to make the right business decisions. The application of ML in the energy industry is increasing rapidly. This includes but is not limited to manufacturing, refining, energy distribution, and other related domains. Due to the unique and diverse domain requirements, various ML and AI solutions in the energy industry must be extensively customized. These specific requirements usually lead to different approaches to solutions and further introduce difficulties in developing, deploying, and scaling. These difficulties lead to higher costs and longer cycle time in productization. To reduce cost and save time, there is a growing business need to develop, deploy, and scale these energy industry ML applications in an agile way. To achieve this goal, we developed a full-stack ML development framework, which makes it easier to develop and deploy (energy industry) ML solutions with high efficiency, reproducibility, and scalability. It has been demonstrated that projects using this full-stack ML development framework successfully saved both turnaround time and costs.