Abstract
Data-driven machine learning (ML) is a groundbreaking way to address some of the biggest problems we tackle to combat climate change, like monitoring carbon sequestration. These solutions are crucial to responding to climate targets set in international agreements, like the Paris Agreement, with emissions of carbon dioxide (CO2) in the world still on the rise and practicable methods to capture, utilize and store carbon urgently needed. This work highlights the advancements and potentials of machine learning enhancing carbon sequestration tracking, emphasizing both the possibilities and challenges that accompany this approach and the implications for the future of carbon capture and sequestration. Monitoring sequestered carbon dioxide has many advantages from the perspective of machine learning. Thus, even data analysis can be automated, leading to less expensive and less time-consuming methods than the legacy systems for monitoring.