Geological CO₂ storage must operate within pressure and stress limits that preserve caprock, fault, and well integrity while sustaining climate-relevant injection. Existing reviews often treat multiphysics simulation, machine learning, and physics-informed learning separately, which obscures the different evidence required for stability screening, first slip, aseismic deformation, dynamic rupture, monitoring analytics, and containment consequences. This structured critical review integrates direct CO₂ storage observations, laboratory studies, injection analogues, multiphysics numerical methods, data-driven machine learning, and scientific machine learning within a target-specific evidence framework. We compare continuum, discontinuum, interface, and diffuse fracture formulations; one-way, staggered, and monolithic coupling; field and laboratory validation; seismic, deformation, pressure, and fiber optic monitoring; and physics-informed neural networks, neural operators, and reduced-order models. The synthesis herein identifies the strongest evidence base for pressure and deformation modeling and seismic signal processing, for which repeated field or operational applications and task-specific evaluation are available. By contrast, prospective fault slip and seismicity forecasting remain at a limited evidence level because of uncertain in situ stress, fault connectivity, CO₂-conditioned friction, monitoring detection limits, model discrepancy, and scarce cross-site validation. We propose task-appropriate metrics, explicit method maturity criteria, a validation ladder, and a staged, human-supervised digital twin roadmap. Machine learning and physics-informed methods are most credible as bounded complements to verified simulators and monitoring systems, and operational readiness should be judged by uncertainty-calibrated prospective evidence rather than algorithm novelty.

Geological CO₂ storage is essential to pathways to carbon neutrality, but its deployment depends on trustworthy estimates of storage capacity, injectivity, trapping, reactive evolution, and containment. Digital rock physics can provide these estimates from X-ray and electron microscopy images, yet every result depends on image segmentation, which converts grayscale data into pore, mineral, fracture, and fluid phases. This review evaluates classical methods, machine learning, deep learning, transformers, and foundation models according to whether they support reliable storage decisions rather than image overlap scores alone. Evidence is synthesized from imaging of dry rocks, CO₂–brine experiments, multiscale studies of carbonates and shales, and analyses of fractured rocks. We introduce a framework with seven dimensions: class accuracy, boundary fidelity, topology, morphology, calibrated uncertainty, sensitivity of physical properties, and consequences for engineering decisions. The evidence shows that visually similar segmentations can yield substantially different predictions of permeability, connected porosity, residual trapping, reactive surface area, and leakage paths when errors occur at critical pore throats, fluid interfaces, or fractures. We therefore recommend selecting methods according to storage task and lithology, validating them on independent samples, propagating ensembles of plausible segmentations, using metrics that account for topology, and comparing predictions with laboratory measurements. The central message is simple: segmentation should be treated as both a measurement process and a form of risk control. Segmentation with auditable and quantified uncertainty can reduce false site acceptance or rejection, improve injection and monitoring design, and strengthen geological CO₂ storage as a technology for carbon neutrality.

Geological CO₂ storage is essential to pathways to carbon neutrality, but its deployment depends on trustworthy estimates of storage capacity, injectivity, trapping, reactive evolution, and containment. Digital rock physics can provide pore-scale inputs to these estimates from X-ray and electron microscopy images, but translation to formation-scale performance requires additional geological, fluid, and operational information. Each image-derived result depends on image segmentation, which converts grayscale data into pore, mineral, fracture, and fluid phases. This review evaluates classical methods, machine learning, deep learning, transformers, and foundation models according to whether they support reliable storage decisions rather than image overlap scores alone. Evidence is synthesized from imaging of dry rocks, CO₂–brine experiments, multiscale studies of carbonates and shales, and analyses of fractured rocks. We introduce a framework with seven dimensions: class accuracy, boundary fidelity, topology, morphology, calibrated uncertainty, sensitivity of physical properties, and consequences for engineering decisions. The evidence shows that visually similar segmentations can yield substantially different predictions of permeability, connected porosity, residual trapping, reactive surface area, and leakage paths when errors occur at critical pore throats, fluid interfaces, or fractures. We therefore recommend selecting methods according to storage task and lithology, validating them on independent samples, propagating ensembles of plausible segmentations, using metrics that account for topology, and comparing predictions with laboratory measurements. The central message is simple: segmentation should be treated as both a measurement process and a form of risk control. Segmentation with auditable and quantified uncertainty has the potential to improve the inputs to site screening, injection design, and monitoring. These project-level benefits are proposed consequences requiring upscaling and project-specific validation, not outcomes demonstrated by this review.

Predictive monitoring of injection operations requires evidence that warning rules transfer across fault conditions and loading rates. We develop a seven-variable representation of mechanical, hydraulic, and acoustic measurements and retrospectively evaluate source-calibrated Watch, Mitigate, and Hold indicators over 60, 30, and 10 s horizons. A separate Mahalanobis gate measures similarity to the source states. The original cohort comprises 18 pressure-stage events from two rough specimens and one smooth specimen; an independent archive adds six slow-creep stage peaks from a fourth specimen. A pump-based reconstruction reproduces every original event and model input. In the original rough-to-smooth transfer, Watch and Mitigate intercepted 6/6 events, with median warning time s of 16.5 and 3.5 s. In reverse transfer, both indicators intercepted 12/12 events but produced 22.9 and 42.2 s/event of pre-horizon alert activity. Deleting one smooth-source event changed support coverage in the final 30 s to 19.7–88.6%. On the independent specimen, the unchanged rough-source Watch indicator intercepted 5/6 peaks, whereas Mitigate and Hold intercepted none. The smooth-source Mitigate indicator intercepted 6/6 peaks but was active before its horizon for 72.8 s/event. Despite these contrasting outcomes, the source-domain gates included 99.7–100.0% of external states. The contributions are reproducible event construction, source-only policy evaluation, calibration sensitivity analysis, and an independent laboratory transfer test. The results show that high empirical support does not establish transferable warning thresholds. They motivate further advisory evaluation with separate prediction and support outputs. Four specimens, retrospective processing, and the absence of field validation do not establish operational readiness.

Geological CO₂ storage must operate within pressure and stress limits that preserve caprock, fault, and well integrity while sustaining climate relevant injection. Existing reviews often treat multiphysics simulation, machine learning, and physics informed learning separately, which obscures the different evidence required for stability screening, first slip, aseismic deformation, dynamic rupture, monitoring analytics, and containment consequences. This structured critical review integrates direct CO₂ storage observations, laboratory studies, injection analogues, multiphysics numerical methods, data driven machine learning, and scientific machine learning within a target specific evidence framework. We compare continuum, discontinuum, interface, and diffuse fracture formulations; one way, staggered, and monolithic coupling; field and laboratory validation; seismic, deformation, pressure, and fiber optic monitoring; and physics informed neural networks, neural operators, and reduced order models. The synthesis shows that pressure and deformation modeling and seismic signal processing are comparatively mature, whereas prospective fault slip and seismicity forecasting remain limited by uncertain in situ stress, fault connectivity, CO₂ conditioned friction, monitoring detection limits, model discrepancy, and scarce cross site validation. We propose task appropriate metrics, an explicit validation ladder, and a staged, human supervised digital twin roadmap. Machine learning and physics informed methods are most credible as bounded complements to verified simulators and monitoring systems, and operational readiness should be judged by uncertainty calibrated prospective evidence rather than algorithm novelty.