The identification of underground formation lithology can serve as a basis for petroleum exploration and development. This study integrates Extreme Gradient Boosting (XGBoost) with Bayesian Optimization (BO) for formation lithology identification and comprehensively evaluated the performance of the proposed classifier based on the metrics of the confusion matrix, precision, recall, F1-score and the area under the receiver operating characteristic curve (AUC). The data of this study are derived from Daniudui gas field and the Hangjinqi gas field, which includes 2153 samples with known lithology facies class with each sample having seven measured properties (well log curves), and corresponding depth. The results show that BO significantly improves parameter optimization efficiency. The AUC values of the test sets of the two gas fields are 0.968 and 0.987, respectively, indicating that the proposed method has very high generalization performance. Additionally, we compare the proposed algorithm with Gradient Tree Boosting-Differential Evolution (GTB-DE) using the same dataset. The results demonstrated that the average of precision, recall and F1 score of the proposed method are respectively 4.85%, 5.7%, 3.25% greater than GTB-ED. The proposed XGBoost-BO ensemble model can automate the procedure of lithology identification, and it may also be used in the prediction of other reservoir properties.

Fracture aperture change under stress has long been considered as one of primary causes of stress sensitivity of fractured gas reservoirs. However, little is known about the evolution of the morphology of fracture apertures on flow property in loading and unloading cycles. This paper reports a stress sensitivity experiment on carbonate core plugs in which Computed Tomography (CT) technology is applied to visualize and quantitatively evaluate morphological changes to the fracture aperture with respect to confining pressure. Fracture models were obtained at selected confining pressures on which pore-scale flow simulations were performed to estimate the equivalent absolute permeability. The results showed that with the increase of confining pressure from 0 to 0.6 MPa, the fracture aperture and equivalent permeability decreased at a greater gradient than their counterparts after 0.6 MPa. This meant that the rock sample is more stress-sensitive at low effective stress than at high effective stress. On the loading path, an exponential fitting was found to fit well between the effective confining pressure and the calculated permeability. On the unloading path, the relationship is found partially reversible, which can evidently be attributed to plastic deformation of the fracture as observed in CT images.

The Enhanced Geothermal System (EGS) constructs an artificial thermal reservoir by hydraulic fracturing to extract heat economically from hot dry rock. As the core element of the EGS heat recovery process, mass and heat transfer of working fluid mainly occurs in fractures. Since the direction of the natural and induced fractures are generally perpendicular to the minimum principal stress in the formation, as an effective stimulation approach, horizontal well production could increase the contact area with the thermal reservoir significantly. In this paper, the thermal reservoir is developed by a dual horizontal well system and treated as a fractured porous medium composed of matrix rock and discrete fracture network. Using the local thermal non-equilibrium theory, a coupled THM mathematical model and an ideal 3D numerical model are established for the EGS heat extraction process. EGS heat extraction capacity is evaluated in the light of thermal recovery lifespan, average outlet temperature, heat production, electricity generation, energy efficiency and thermal recovery rate. The results show that with certain reservoir and production parameters, the heat production, electricity generation and thermal recovery lifespan can achieve the commercial goal of the dual horizontal well system, but the energy efficiency and overall thermal recovery rate are still at low levels. At last, this paper puts forward a series of optimizations to improve the heat extraction capacity, including production conditions and thermal reservoir construction design.

Natural gas hydrates, crystalline solids whose gas molecules are so compressed that they are denser than a typical fluid hydrocarbon, have extensive applications in the areas of climate change and the energy crisis. The hydrate deposit located in the Shenhu Area on the continental slope of the South China Sea is regarded as the most promising target for gas hydrate exploration in China. Samples taken at drilling site SH2 have indicated a high abundance of methane hydrate reserves in clay sediments. In the last few decades, with its relatively low energy cost, the depressurization gas recovery method has been generally regarded as technically feasible and the most promising one. For the purpose of a better acquaintance with the feasible field operational factors and processes which control the production behavior of a real 3D geological CH₄-hydrate deposit, it is urgent to figure out the effects of the parameters such as well type, well spacing, bottom hole pressure, and perforation intervals on methane recovery. One years’ numerical simulation results show that under the condition of 3000 kPa constant bottom hole pressure, 1000 m well spacing, perforation in higher intervals and with one horizontal well, the daily peak gas rate can reach 4325.02 m³ and the cumulative gas volume is 1.291 × 10⁶ m³. What’s more, some new knowledge and its explanation of the curve tendency and evolution for the production process are provided. Technically, one factor at a time design (OFAT) and an orthogonal design were used in the simulation to investigate which factors dominate the productivity ability and which is the most sensitive one. The results indicated that the order of effects of the factors on gas yield was perforation interval > bottom hole pressure > well spacing.