E.M. Myshakin | Search USGS

USGS2023

Machine learning application to assess occurrence and saturations of methane hydrate in marine deposits offshore India

Artificial Neural Networks (ANN) were used to assess methane hydrate occurrence and saturation in marine sediments offshore India. The ANN analysis classifies the gas hydrate occurrence into three types: methane hydrate in pore space, methane hydrate in fractures, or no methane hydrate. Further, predicted saturation characterizes the volume of gas hydrate with respect to the available void volume. Log data collected at six wells, which were drilled during the India National Gas Hydrate Program Expedition 02 (NGHP-02), provided a combination of well log measurements that were used as input for machine learning (ML) models. Well log measurements included density, porosity, electrical resistivity, natural gamma radiation, and acoustic wave velocity. Combinations of well logs used in the ML models provide good overall balanced accuracy (0.79 to 0.86) for the prediction of the gas hydrate occurrence and good accuracy (0.68 to 0.92) for methane hydrate saturation prediction in the marine accumulations against reference data. The accuracy scores indicate that the ML models can successfully predict reservoir characteristics for marine methane hydrate deposits. The results indicate that the ML models can either augment physics-driven methods for assessing the occurrence and saturation of methane hydrate deposits or serve as an independent predictive tool for those characteristics.

Journal Interpretation↗

USGS2020

An international code comparison study on coupled thermal, hydrologic and geomechanical processes of natural gas hydrate-bearing sediments

Geologic reservoirs containing gas hydrate occur beneath permafrost environments and within marine continental slope sediments, representing a potentially vast natural gas source. Numerical simulators provide scientists and engineers with tools for understanding how production efficiency depends on the numerous, interdependent (coupled) processes associated with potential production strategies for these gas hydrate reservoirs. Confidence in the modeling and forecasting abilities of these gas hydrate reservoir simulators (GHRSs) grows with successful comparisons against laboratory and field test results, but such results are rare, particularly in natural settings. The hydrate community recognized another approach to building confidence in the GHRS: comparing simulation results between independently developed and executed computer codes on structured problems specifically tailored to the interdependent processes relevant for gas hydrate-bearing systems. The United States Department of Energy, National Energy Technology Laboratory (DOE/NETL), sponsored the first international gas hydrate code comparison study, IGHCCS1, in the early 2000s. IGHCCS1 focused on coupled thermal and hydrologic processes associated with producing gas hydrates from geologic reservoirs via depressurization and thermal stimulation. Subsequently, GHRSs have advanced to model more complex production technologies and incorporate geomechanical processes into the existing framework of coupled thermal and hydrologic modeling. This paper contributes to the validation of these recent GHRS developments by providing results from a second GHRS code comparison study, IGHCCS2, also sponsored by DOE/NETL. IGHCCS2 includes participants from an international collection of universities, research institutes, industry, national laboratories, and national geologic surveys. Study participants developed a series of five benchmark problems principally involving gas hydrate processes with geomechanical components. The five problems range from simple geometries with analytical solutions to a representation of the world’s first offshore production test of methane hydrates, which was conducted with the depressurization method off the coast of Japan. To identify strengths and limitations in the various GHRSs, study participants submitted solutions for the benchmark problems and discussed differing results via teleconferences. The GHRSs evolved over the course of IGHCCS2 as researchers modified their simulators to reflect new insights, lessons learned, and suggested performance enhancements. The five benchmark problems, final sample solutions, and lessons learned that are presented here document the study outcomes and serve as a reference guide for developing and testing gas hydrate reservoir simulators.

Journal of Marine and Petroleum Geology↗