Although time-lapse seismic data has been used to great success in the history matching of reservoir fluid properties (i.e. saturation in reservoir simulators), it has been used far less effectively for benchmarking geomechanical behaviour. The reason for this is twofold.
Firstly, hydromechanical models are typically large, complex and highly nonlinear with considerably large runtimes. Secondly, isolating and extracting quantifiable mechanical information from seismic data is difficult. However, by not attempting to utilise numerical history matching techniques, are we making the most out of the geomechanical information stored in time-lapse seismic data?
In this Thesis I have attempted to answer this question by conducting a synthetic history matching study. I generate a hydromechanical model of a typical high pressure high temperature production scenario in the North Sea and utilise seismic history matching in
an attempt to constrain the properties of the overburden and improve the models predictive capabilities. The study focuses primarily on overburden calibration as overburden timeshifts are not complicated by fluid effects, as in the reservoir, and hence can be considered as a purely geomechanical effect. Also the matching process is attempted utilising only a small, feasible number of model perturbations.
Before seismic history matching can be successfully attempted it is important to have an in depth working knowledge of the model behaviour. Therefore, I conduct a multi-method Global Sensitivity Analysis (GSA) on over 4000 model perturbations, to evaluate the potential geomechanical information content of seismic time-shifts. Specifically, which model parameters cause the majority of the variation to overburden time-shifts. The results show that the majority of the variation in modelled shifts can be attributed to the Young's Modulus and Biot coefficient. These parameters appear the most influential for both near-offset time-shifts and the time-shift offset behaviour. However, the Poisson's ratio also becomes influential when considering the time-shift offset behaviour at long offsets. The results of the GSA also highlight that the over-parametrisation of material
properties in the model can lead to unnecessary complexity in the model space. The simplification of complex rock properties (i.e. simplification of nonlinear relationships to single constants) will not significantly affect model performance whilst making seismic
history matching more achievable.
A robust history matching study also requires the consideration of all forms of uncertainty. One of the main causes of uncertainty in the process is that of the relationship between effective stress and seismic velocity i.e. the rock physics model. I analyse a handful
of the most popular rock physics models and assess their behaviour and stability when applied to a large dry core dataset of different lithologies. The results show that most models are robust, well constrained and do a suitably good job at fitting velocity-stress data taken from core samples in a laboratory environment. However, slight discrepancies between different model approximations for the same core sample can cause significantly different time-lapse velocity predictions. The results also show that models are difficult
to parameterise without the availability of velocity-stress core data. Attempting to do so can lead to even greater discrepancies in their time-lapse velocity predictions. The results also support the current belief that the velocity-stress core data may not be a good
representation of the velocity-stress dependence of the subsurface
I utilise an iterative emulator based approach to history matching which makes it possible to perform a robust history match with a small number of model realisations. I utilise the results of the GSA to define the model parameters in which to focus the history match and also utilise the results of the rock physics model analysis to define suitable uncertainties. The results of the emulation process show it is possible to perform a successful history match utilising only a small number of model perturbations and to constrain the
uncertainty in the most influential model parameters. The process is improved significantly when both near-offset time-shifts and the time-shift offset behaviour are considered simultaneously in the matching process. It becomes apparent that the matching process and hence final solution is limited by the number of model realisations, iterations and the extent of the available seismic data. The greater the number of realisations, the more accurate the emulators whilst the more seismic observations, the more data available in which to test predicted models. Also, it becomes increasingly clear that the uncertainty in rock physics modelling dominates the matching process. Taking into consideration it's
uncertainty makes it extremely difficult to confidently constrain any properties of the hydromechanical
model from time-lapse seismic data. It becomes increasingly apparent that there is a great need to improve our understanding of rock behaviour (i.e. rock physics) before the seismic history matching of mechanical behavior becomes suitably accurate and
economically appealing.
