Adaptive Optimization Strategies for Surfactant Cyclic Injection in Tight Oil Reservoirs Jianwei Dou, Miao Zhang, Qian Sun, Chunhua Lu, Yunqi Cui, Junjian Li SPE Journal, 2026 Summary The surfactant huff ’n’ puff process, or cyclic surfactant injection, is a promising technique for enhancing oil recovery from tight reservoirs. The effectiveness of this process is highly dependent on the design of cycle parameters such as injection rate, surfactant concentration, soaking duration, and production time. This study is the first to apply reinforcement learning (RL) to cyclic surfactant injection, introducing a framework that adaptively optimizes operational parameters across multiple cycles in response to the reservoir’s evolving state to enhance recovery efficiency. For comparison, a cyclewise particle swarm optimization (PSO) optimizes parameters independently for each cycle, while a fixed-strategy PSO is implemented as the baseline. Numerical simulations were conducted for a multifractured horizontal well in tight formations. The model incorporated the coupled effects of interfacial tension (IFT) reduction and wettability alteration through a K-value-based approach. A long short-term memory (LSTM) proxy model was trained using synthetic data generated by a history-matched numerical model. Net present value (NPV) is used as the objective function for all optimization strategies. Results indicate that both adaptive optimization strategies, RL and cyclewise PSO, outperform the fixed-strategy PSO. Cyclewise PSO leads to higher oil recovery in the early cycles but shows a sharp decline in later stages, potentially resulting in early termination. RL-based strategy maintains more stable production over successive cycles, allowing for extended economic operation and a higher overall NPV. Cyclewise PSO may be preferred for development plans aimed at fast returns, while the RL approach is more suited to long-term project goals. Cycle-to-cycle comparisons reveal the main reasons from the underlying physics perspective that explain the differences between RL and cyclewise PSO results. The improved enhanced oil recovery (EOR) performance of the RL strategy over extended cycles is attributed to higher early-cycle surfactant concentrations that enhance oil mobility and areal sweep efficiency, while increased injection volumes in later cycles maintain productivity, sustain the sweep advantage, and further reduce residual oil saturation.
Investigation of Surfactant Huff-n-Puff Injection for Enhanced Oil Recovery in Unconventional Reservoirs: An Integrated Experimental and Numerical Simulation Approach Coupled with the HLD-NAC Methodology Chunhua Lu, Miao Zhang, Yilei Hua, Ming Liu, Hanqiao Jiang, Junjian Li Energy and Fuels, 2024 Surfactant huff-n-puff (HnP) injection processes have become one of the most attractive enhanced oil recovery (EOR) protocols to effectively produce unconventional oil reservoirs. In this paper, the mechanism of surfactant-enhanced tight oil recovery is comprehensively investigated by experimental and numerical simulation. Imbibition experiments are employed to elucidate the impact of surfactants on enhancing the tight core recovery. Core-scale numerical simulation models are applied to match experimental data to characterize the effects of surfactants on oil and water flow capabilities. We model the microemulsion phase behavior of an optimized surfactant formulation using hydrophilic–lipophilic difference and the net-average curvature (HLD-NAC) equation, which are used to quantitatively characterize the interfacial tension (IFT) reduction, wettability alteration, and oil solubilization effects. A numerical simulation model is structured to assess the production increments of the surfactant huff-n-puff injection for a multistage fractured horizontal well in the Jimusar J305 block as a case study. An extensive parametric study is conducted employing it as a base case model. Results show that the adsorption capacity of the surfactant on the reservoir rock has a strong impact on the wettability alteration and oil production increment. For the huff-n-puff surfactant injection design considerations, the top three factors impacting oil recovery improvement are the injection volume, concentration, and number of cycles, while injection time, production time/stage, and soaking time show a less significant impact. The recovery rate of the surfactant huff-n-puff EOR ranged from 2.55 to 17.12%. The use of the HLD-NAC equation enables the characterization of microemulsion phase behavior, which makes the simulation results reliable for field practices.
Simulation and optimization of hydraulic fracturing in shale reservoirs: A case study in the Permian Lucaogou formation, China Chunhua Lu, Hanqiao Jiang, Jinlong Yang, Haitong Yang, Baoyang Cheng, Miao Zhang, Jixiang He, Junjian Li Energy Reports, 2022 Long horizontal sections, small well spacings, and dense cutting are the main methods for shale reservoir development. However, there are still significant differences in oil production after large-scale fracturing of horizontal wells due to reservoir heterogeneity. This study presents a fracturing design method based on sweet spot mapping to determine the adaptability of reservoir quality and fracturing scale in order to improve the fracturing effect. First, geomechanics model is constructed utilizing logs and core laboratory tests. Then, comprehensive sweet spot mapping is captured through the two-level fuzzy comprehensive evaluation method, which considered the reservoir physical quality and engineering quality. The sweet spot divides the reservoir into three types: type I (good), type II (moderate), and type III (poor). Finally, fracturing simulation and reservoir numerical simulation are performed to optimize the fracturing parameters for different types of sweet spots. Results show that there is a strong correlation between type I sweet spot and productivity. Increasing drilling rate for type I sweet spot can improve productivity. The 5-year cumulative oil production of segmented way based on sweet spot types is 4005 m3 higher than that of uniform segmented way. Reasonable stage lengths of type I, II, and III sweet spot are 66.67 m, 50 m and 40 m, respectively, and cluster spacing is between 10 m and 12 m. Reasonable single-stage fracturing fluid volume for type I and type II sweet spot is 2200 m3, and type III is 1900 m3. Specifically, the results of applying the optimized parameters to actual well demonstrate that the design scheme has a 5-year cumulative oil production of 7026 m3 and NPV of $1.01 million higher than the actual scheme. This method will be helpful for engineers in developing a reasonable fracturing plan for shale oil in future operations.
Analysis of controlling factors at separate imbibition stages for ultra-low-permeability reservoirs Hailong Dang, Hanqiao Jiang, Binchi Hou, Xiaofeng Wang, Tao Gao, Chengjun Wang, Chunhua Lu Energies, 2021 Spontaneous imbibition is an important mechanism in naturally fractured reservoirs. In our previous studies on the effect of imbibition efficiency of ultra-low permeability reservoirs, we mostly focused on the relationship between macroscopic core recovery rate and influential factors. Additionally, we also mainly focused on the factors that control the final imbibition recovery for ultra-low permeability reservoirs. Through a large number of experiments, it was found that the factors affecting imbibition are different in separate stages. However, the relative importance of those factors in different imbibition stages was hardly studied. In this work, we tested six key factors, i.e., the core length, RQI, salinity, interfacial characteristics, initial oil saturation, and oil viscosity, in natural sandstone samples from Chang 6 in the Zichang area. Based on experimental results, we divided the imbibition process into three stages (i.e., the early stage, the middle stage, and the late stage) to quantify the effects of the controlling factors. The results show that the relative importance of the controlling factors is changing during the imbibition process. The weight of importance is obtained for those factors at each stage. In addition, a comparative model is established for the dual-porosity media from Chang 6 formation. The results show that the increase of the rock size can extend the imbibition period for the early and middle stages. Moreover, the weight of importance for the initial oil saturation, interfacial characteristics, and salinity are also analyzed in three imbibition stages. This study provides theoretical support to guide water injection in ultra-low-permeability reservoirs and to understand the formation of energy supplements and oil recovery during the imbibition process.
