|Theme||Visible||Selectable||Appearance||Zoom Range (now: 0)|
A comprehensive intelligent decision support system (IDSS) for unconventional field development design is presented in this paper. The proposed IDSS combines data-driven models with physics-based reservoir engineering methods and it is a stack of three AI layers: Predictive, Prescriptive and Cognitive. The predictive unit receives physical reservoir parameters as input and predicts the outcome for thousands of possible designs under different subsurface scenarios by using advanced machine learning and deep learning methods. The prescriptive unit searches between these outcomes and finds the most optimum solutions based on the project goals and risks using optimization techniques. Finally, the cognitive unit tries to understand the utility function of expert decision makers and finds the best solution from the optimum subset. For this paper, we focus on the predictive unit results.
Because of the time it takes to setup reservoir simulations, reservoir engineers can only test tens of well designs amongst thousands of possibilities for a particular project, which results in suboptimal outcome. Using the IDSS technology, we enable analyzing thousands of options in less than a week and consequently the optimum field development design can be achieved, which can decrease average cost per barrel of production by 15%.
This is the first study on a cognition-driven decision support system in the upstream oil and gas industry. Unlike conventional field development, for unconventional oil and gas fields the development process is a high-dimensional decision-making problem. In such problems, a cognition-driven DSS is a necessary tool for mitigating human error. The success of cognitive DSS, especially for a complex problem such as unconventional field development, paves the way towards wider usage of this technology in the oil and gas industry.
A Decision Support System (DSS) is an information system used to support organizations and businesses to make informed decisions. If this system uses artificial intelligence (AI) techniques extensively, it is called Artificial Intelligence DSS (AIDSS) or Intelligence DSS (IDSS). Nowadays, DSS and IDSS systems are widely used in healthcare, finance, environment, security among many others. The oil and gas industry also utilizes DSS and IDSS for different purposes and business problems. Korovin and Kalayev (2015) listed some of the DSS systems in the oil and gas industry.
Borehole microseismic monitoring is a widely used method in the oil and gas industry to monitor hydraulic fracturing operations. Sometimes, the quality of acquired microseismic data is relatively poor due to lack of proper survey design. The authors provide a comprehensive and thorough workflow, using multiple criteria decision analysis (MCDA), to optimize microseismic acquisition design. The result of this work is a software application, that will help the user determine optimized locations for placing receivers in observation wellbores.
Presentation Date: Monday, September 25, 2017
Start Time: 2:15 PM
Presentation Type: ORAL
Accurate microseismic event locations require an accurate velocity model. A common technique for deriving the velocity model involves tomographically inverting perforation shot traveltimes. The approach requires known perforation locations, an initial velocity model and a perf shot aperture large enough to span the velocity medium. In contrast, we developed a velocity modeling approach based on the vertical slowness and polarization angle of microseismic events with unknown locations.
We applied the technique to a microseismic dataset and compared the results with those derived from a tomography-based solution. The slowness-polarization velocity model is very similar to the tomographic velocity model. However, the VTI (vertical transverse isotropy) slowness-polarization velocity model is 16% more like the acquired sonic log in the deeper part of the array.
Presentation Date: Monday, October 17, 2016
Start Time: 1:50:00 PM
Presentation Type: ORAL
Wide azimuth and multicomponent vertical seismic profile (VSP) data provide reliable estimation of subsurface anisotropy at and near the well location. In this work, we apply prestack waveform inversion to the wide-azimuth multicomponent VSP data, acquired at the Wattenberg Field, located in Denver Basin of northeastern Colorado, USA, to characterize the subsurface formations for azimuthal anisotropy. The waveform inversion used a multi-objective method based on the non-dominated sorting genetic algorithm as the optimization tool, and P- and S-wave velocities and density from the well-log were used as constraints to invert data for the subsurface orthorhombic anisotropic properties. In addition, the inversion was run using sliding windows from shallow-to-deep in which as the shallow depths were successfully inverted, they were fixed and used as constraints to invert for the anisotropic model parameters at deeper depths. By comparing the waveform inversion results with an independent study that used a joint slowness-polarization approach to invert the same data, we conclude that the waveform inversion is a reliable tool for inverting the wide-azimuth multicomponent VSP data for estimating the subsurface anisotropic earth properties at much higher resolution than the joint slowness-polarization inversion.
Presentation Date: Tuesday, October 18, 2016
Start Time: 4:10:00 PM
Presentation Type: ORAL
Anisotropy parameters provide vital information for surface and borehole seismic data processing, imaging and interpretation. The objective of this research is to introduce a reliable technique, for estimating local seismic anisotropy using both P- and SV-wave from VSP data in VTI media where the overburden is heterogeneous.
The technique uses P- and SV-wave vertical slowness components and polarization angles in VTI media to estimate Thomsen parameter δ and anellipticity parameter ƞ. The proposed method is applied to a synthetic VSP data with anisotropic properties. The estimated δ and ƞ parameters, using both P- and SV-wave data, show better correlation with anisotropy parameters in the model compared to the technique that only uses P- wave data.
Salt rock is characterized by its very low porosity and permeability along with excellent mechanical deformability. These characteristics make it a good cap rock for many structural petroleum reservoirs, a good geological hydrocarbon storage, and a suitable host rock for poisonous and hazardous wastes. Over the past few decades, different laboratory experiments have revealed the complexity and variety of mechanical behaviors of salt rocks. Although the elasto-plastic mechanical properties of salt rock highly depend on its stress state and temperature, but they can also change with its composition. Therefore, different salt rocks around the world show wide ranges of mechanical behaviors and it necessitates more experimental data from different geological regions. In this study 26 rock salt samples, with two different levels of impurities, from the Central Iranian salt rock were collected and examined. A set of rock mechanics experiments, including uniaxial compression test, triaxial compression test, and dipole ultrasonic velocity measurements at elevated temperatures, were fulfilled. It was found that the amount of impurities significantly affect the rock salt mechanical behavior. The results suggest that unconfined compressive strength increases as the temperature increases, but the triaxial compressive strength and the ultrasonic wave velocities demonstrate more complex patterns.
The estimation of seismic velocity is one of the crucial steps for seismic depth imaging in laterally inhomogeneous layers. This task is more challenging for incompetent units overlying the reservoir layer in shallow depth. Gachsaran Formation is a cap rock of the Asmari oil-bearing formation and plays an important role in geophysical studies of Middle Eastern oilfields. According to the complex geological structure and stratigraphy of Gachsaran, which is due to the high tectonic activity of the basin and special lithological and rheological properties of Gachsaran, estimation of seismic velocity is crucial and full of challenges. In the present paper, the relationships between seismic velocity and structural components have been analyzed. The Gachsaran Formation from Aghajari structure (Aghajari oilfield / SW Iran) has been selected for this study. Newly acquired and high quality 3D seismic data provided new insight about the relationships between structural characteristics and seismic velocity.