Leak Detection in Carbon Sequestration Projects Using Machine LearningMethods: Cranfield Site,Mississippi,USA

摘要

Due to international commitments on carbon capture and storage(CCS),an increase in CCS projects isexpected in the near future.Saline aquifers and depleted hydrocarbon reservoirs with good seals and locatedin tectonically stable zones make an excellent storage formation option for geological carbon sequestration.However,stored carbon dioxide(CO2)takes a long time to convert into diagenetically stable form.Hence,ensuring the CO2 does not leak from these reservoirs in this time period is the key to any successful CCSproject.Numerous methods are developed over the past couple of decades to identify the leaks which utilizesvarious types of geophysical,geochemical and engineering data.We demonstrate the automated leakagedetection in CCS projects using pressure data obtained from Cranfield reservoir,Mississippi,USA.Ourdataset consists of CO2 injection rates and pressure monitoring data obtained from a pressure pulse test.We first demonstrate the differences between the pressure pulse signal in case of a baseline pulse test and apulse test with an artificially induced leak onsite.We then use machine learning techniques to automaticallydifferentiate between the two tests.The results indicate that even simple deep learning architectures such asmulti-layer feedforward network(MFNN)can identify a leak using pressure data and can be used to raisean early warning flag.