Machine learning inversion solution: a tool to identify faults shear slip from sensed ground deformation
Saeed Salimzadeh A * and Dane Kasperczyk AA
Saeed is a Senior Research Scientist at Subsurface Engineering and Technology team at CSIRO Energy, Clayton, Australia. He obtained his PhD in Geomechanics at University of New South Wales (UNSW Sydney) in 2014, and since has been working in international research institutes at Imperial College London, Technical University of Denmark, and CSIRO Australia. Saeed is an expert in reservoir geomechanics for measurement, monitoring and verification (MMV) purposes. He has developed the hydraulic fracturing simulator CSMP-HF, as well as the machine lLearning inversion solution (MLIS), and has supervised many Master and PhD students. |
Dane is a Senior Engineer leading the subsurface technologies team in the CSIRO Energy Resources group, he holds degrees from University of Melbourne in Civil Engineering and Science (Earth Sciences). For the past decade, he has worked on research and projects related to fracture mechanics modelling, hydraulic fracturing environmental risk probabilities and preconditioning for block cave, sublevel cave, and underground mines. Through this he has developed capability in subsurface monitoring using tiltmeters that has seen applicable use for mining, CO2 sequestration and subsurface energy storage. |
Abstract
Geological energy storage and carbon sequestration activities should consider the stability of surrounding faults and induced seismicity potential. In order to ensure the efficacy of storage medium, it is crucial to possess a comprehensive understanding of the movement of pressure plumes within geological features by monitoring the potential impact on the deformation of geological layers as well as the ground surface. In this study, we propose a new tool (machine learning inversion solution, MLIS) capable of identifying opening (dilation) and shearing behaviour of faults and fractures pressurised by a fluid plume. While geo-storage of energy and CO2 is mainly dominant with the dilational deformation, any fault slippage generates shear deformation. Combination of the two creates a mixed-mode deformation detectable via an array of tiltmeters, fibre-optic strain sensors, or Interferometric Synthetic Aperture Radar (InSAR). MLIS utilises surrogate models trained specifically for dilation and shear deformations, together with Bayesian inversion and differential evolution optimisation to identify the set of unknown parameters that gives the best fit to the observed data.
Keywords: differential evolution, dilational fractures, distributed strain sensing (DSS), faults reactivations, geological carbon storage, ML inversion solution, shear loading, tiltmeters.
Saeed is a Senior Research Scientist at Subsurface Engineering and Technology team at CSIRO Energy, Clayton, Australia. He obtained his PhD in Geomechanics at University of New South Wales (UNSW Sydney) in 2014, and since has been working in international research institutes at Imperial College London, Technical University of Denmark, and CSIRO Australia. Saeed is an expert in reservoir geomechanics for measurement, monitoring and verification (MMV) purposes. He has developed the hydraulic fracturing simulator CSMP-HF, as well as the machine lLearning inversion solution (MLIS), and has supervised many Master and PhD students. |
Dane is a Senior Engineer leading the subsurface technologies team in the CSIRO Energy Resources group, he holds degrees from University of Melbourne in Civil Engineering and Science (Earth Sciences). For the past decade, he has worked on research and projects related to fracture mechanics modelling, hydraulic fracturing environmental risk probabilities and preconditioning for block cave, sublevel cave, and underground mines. Through this he has developed capability in subsurface monitoring using tiltmeters that has seen applicable use for mining, CO2 sequestration and subsurface energy storage. |
