Daily Gas Research Articles

Simulation Study on Reservoir Stimulation of Multihorizontal Wells for Gas Hydrate Production in Low-Permeability Reservoirs.

The feasibility of hydrate exploitation technology has been verified by two rounds of trial productions in the South China Sea, but it is also faced with the problem of low gas production efficiency. Therefore, this paper proposed four different hydrate production cases with multihorizontal wells and established simulation models. Then, the influence patterns of reservoir stimulation and offset distances on hydrate dissociation, saturation change, and pressure distribution were studied. To understand hydrate dissociation behaviors and production performances, the coupling effects of multihorizontal wells were discussed. Through simulation, the following conclusions could be drawn: (1) hydrate reservoir stimulation could effectively increase gas production. In these four production models, the cumulative gas production in Case C (multihorizontal wells + reservoir stimulation) was 5.27 times that of Case A (only multihorizontal wells) in 330 days. However, in Case D with screen completions, the gas output was 15.58% less compared with Case C. (2) Different offset distances of horizontal wells had a relatively minor impact on the cumulative gas yield and daily gas capacity. In addition, the variation range of hydrate saturation changed with offset distances of horizontal wells, indicating that hydrate dissociation occurred mainly around horizontal wells and fractures. (3) Considering interwells coupling, the daily gas rate and cumulative gas production of inner wells were higher than outer wells, and the cumulative gas volume increased by 6.4% in 330 days. Temporally and spatially, the hydrate saturation variation between wells was significantly faster than the outward expansion from the horizontal wells. Moreover, nearer to the axis of the horizontal wells, the variation in the hydrate saturation was more pronounced. These results could provide theoretical data to optimize marine hydrate development with multihorizontal wells.

Differential Pressure Power Generation in UGS: Operational Optimization Model and Its Implications for Carbon Emission Reduction

Underground Gas Storage (UGS) is an important facility for natural gas peak adjustment and ensuring the balance between energy supply and demand. The daily gas injection and production capacity of large UGS can reach several hundred million or even billions of cubic meters, and the energy consumed by the injection and production equipment is not to be underestimated, which also contains a large amount of pressure energy that can be utilized for power generation. In this context, the optimization of low-carbon operation of UGS is of great practical significance in engineering. In this study, an innovative UGS system operation optimization method is proposed to integrate a natural gas differential pressure generator set in the UGS system. Considering the complex interconnections among multiple storage areas, multiple wells and wellsites, and the hydro-thermodynamic constraints during the operation of injection and production pipeline network, and with the objective of minimizing the carbon emission, the UGS integrated with Differential Pressure Power Generation System (UGSIDPPGS) is established. In order to solve this complex model, this paper designs an optimization solution framework based on variational assignment, which effectively avoids the problem of falling into inferior solutions during the solution process. The optimization model is applied to the case study of a large-scale depleted gas reservoir in China, and the optimal operation schemes under three scenarios are successfully obtained. The results show that the UGSIDPPGS optimization model, not only effectively utilizes the pressure energy, generates up to 56.908×106kW·h per month, and reduces the CO2 emission by 56,738 tons, but also achieves the low-carbon and economic operation of the UGS. In conclusion, the operation strategy proposed in this study is of great value for optimizing the operation of UGS, and provides practical guidance and suggestions for the low carbon and environmental protection of UGS and the utilization of new energy sources.

OPTIMIZATION SYSTEM FOR LOCAL CONTROL OF COMPRESSOR STATION

The article was devoted to the characteristics of using a compressor to process gas deposits. It is an important principle that the liquid is lifted to the surface of the earth by the energy of the gas compressed from the layer during processing. The structure of the well, the diameter of the exploitation belt, and the fountain pipes should be determined in such a way that there is little pressure in the well and in the trunk. Fountain pipes should not be lowered from the barrier to reducing pressure in the well's trunk and saving metal consumption. Depending on the daily gas volume of oil deposits, the gradient of pressure in the bed and the duration of the gas-water border should have been known. The change in those parameters depends primarily on the energy of the bed. The exploitation of the oil bed can lead to gas and flooding. The gas tank is the force that enables the liquid to move. In the compressor regime, however, the main energy is the energy of six gases. The compressor lifts the liquid to the surface of the earth, mainly because of air or gas. Keywords: gas compressor, field operation compress, compressor characteristics, formation water, wellbore pressure.

Novel Gas Supply System for Multi-Chamber Tri-Gas Cell Culture: Low Gas Consumption and Wide Concentration Range

Gas plays a crucial role in cell culture as cells require a specific gas environment to maintain their growth, reproduction, and function. Here, we propose a gas supply system for tri-gas multi-channel cell incubators to meet the specific needs of various cells. The system utilizes a circulating gas supply method powered by air pumps for each chamber. Gas inflow from the cylinder is independently controlled by Mass Flow Controllers (MFCs), and a quantitative step-by-step adjustment control strategy is employed to calculate the volume of different gases being introduced. Through mixing simulations and experiments, we identified the SV static mixer with an L/D ratio of 2.5 as the optimal choice. To evaluate the concentration accuracy and gas consumption of the gas system, we conduct gas mixing and distribution experiments under different conditions. The results show that the system could achieve a concentration range of 0–100% for O2 with an accuracy of ±0.5%, and a concentration range of 0–10% for CO2 with an accuracy of ±0.1%. The daily gas consumption during cultivation is 3570 mL of N2, 330 mL of CO2, and 115 mL of O2, significantly lower than conventional incubators. Overall, our system can effectively manage dynamic gas concentration changes, particularly in high O2 concentration environments. It offers advantages such as low gas consumption, a wide concentration range, and high accuracy compared to existing incubators.

Town gas daily load forecasting based on machine learning combinatorial algorithms: A case study in North China

Town gas daily load forecasting based on machine learning combinatorial algorithms: A case study in North China

Blockchain-Enhanced Hydrogen Fuel Production and Distribution for Sustainable Energy Management

Renewable energy projects, particularly wind and solar farms, have garnered significant attention as a potential solution to global energy challenges. Despite the energy production obstacles, the steady availability of fossil fuels continues to compete due to established distribution systems, as societies increasingly rely on electricity. Hydrogen fuel emerges as a promising avenue for energy production, storage, and distribution, involving converting surplus renewable electricity into hydrogen through electrolysis, storing it, and distributing it. Our novel approach leverages blockchain technology to enhance the efficiency and traceability of hydrogen fuel production, offering a unique synergy of transparency, security, and decentralized governance. We showcase its viability and effectiveness using the ERC-1155 token standard to tokenize renewable resources and convert them into hydrogen fuel. Within our tokenized fuel blockchain architecture, we simulate the forecasted growth in hydrogen production and vehicle demand, highlighting our approach's efficiency, traceability, and transparency. This integration showcases the potential for a sustainable hydrogen fuel ecosystem. The gas consumption data analysis indicates that the daily gas consumption remains below 194 million Gas for refilling 3245 vehicles (including the cost of one-time contract deployment), demonstrating the feasibility and efficiency of our approach.

Wellbore salt-deposition risk prediction of underground gas storage combining numerical modeling and machine learning methodology

Strengthening the construction of underground gas storage (UGS) is significant for securing national energy and achieving carbon neutrality. However, salt deposition occurs in the wellbore affecting the safety of UGS seriously. How to predict the salt-deposition risk in UGS wells accurately and quickly is still challenging. This work aims at establishing a fast and convenient framework of wellbore salt-deposition risk prediction in UGS wells. Firstly, the influence of the production parameters on wellbore salt-deposition is analyzed by an in-house simulator. Further, an intelligent diagnostic model of salt-deposition risk is proposed based on the machine learning algorithm. The effect of salt deposition on reservoir is analyzed by reservoir salt-deposition simulation model. Finally, downhole video survey is used to validate the modeling accuracy of diagnostic model. Results indicate that the contribution ratio of daily gas production and water-gas-ratio to wellbore salt deposition is 3:2. After the salt deposition, the reduction in water saturation and the permeability of near wellbore areas are 77.14 % and 98.91 %. The modeling accuracy of diagnostic model is 97 %, which is applied in the Y UGS successfully. The proposed framework can predict the salt-deposition risk of UGS wells in real time to help engineers control salt clogging issues.

STUDY OF THE EFFECTIVENESS OF THE APPLICATION OF COMPLEX GEOLOGICAL AND TECHNOLOGICAL MEASURES ON THE EXAMPLE OF GAS-CONDENSATE GENERATION IN THE CENTRAL PART OF THE PRIAXIAL ZONE OF THE DNIPROV-DNETZ BASIN

The field development system is the basis of hydrocarbon production, as it ensures the achievement of the necessary technical and economic indicators. Therefore, a high-perfor- mance development system is necessary to ensure maximum profit in the shortest possible time. Empirical studies, analysis and assessment of the effect of implementing a complex of geological and technological measures on the operational facility of a gas condensate field in the central part of the peri-axial zone of the Dnieper-Donets Basin were carried out in order to find methods for improving the existing gas and gas condensate field development systems and increasing gas extraction rates. It is shown that due to hydraulic fracturing, drilling and transfer of wells to the production facility during the five years of production of the produced gas, it is 7.8 % more than in the previous 21 hours, the rate of development of the field from 2015 to 2019 increased from 2.52 %. to 7.9 %, the average well yield increased by 83 % with an increase in the operational fund by 55 %. The results of studies of the effect of the application of geo- logical-technological measures are shown in the form of graphical dependences of the change in the rate of sampling on the number of production wells over time, the rate of daily gas sampling on the number of conducted geological-technological measures on the researched operational object over time. It has been determined that the main driver of the increase in gas production is the hydraulic fracturing of the formation in most of the operational wells, thanks to which the average increase in the output of the wells is 425 %. According to the results of geological and industrial data processing and analysis of changes in the rate of daily gas extraction over time, the effect of the performed operations is divided into three time segments lasting 15–18 months. The decrease in the duration of the effect from the increase in the fund of production wells and the conduct of hydraulic fracturing of the reservoir is due to the decrease in the volume of reservoir energy, therefore the investigated complex of measures will have the greatest effect when implemented at the initial stage of the development of a reservoir with similar geological parameters.

Multi-parameter modeling for prediction of gas–water production in tight sandstone reservoirs

Tight sandstone reservoirs are significant sources of natural gas reserves. As traditional reserves become increasingly scarce and costly, optimizing the development of these reservoirs becomes crucial. This study introduces a novel two-phase gas–water flow model for single wells, incorporating both Darcy and non-Darcy flow equations. These equations are derived from mass conservation and momentum principles for both gas and water phases. Using data from a real tight gas well, our model, which includes stress-sensitive phases for gas and water, outperforms traditional Darcy flow models. Specifically, the average relative deviations in daily production rates were 0.1815% for gas and − 0.2677% for water, which are significantly smaller compared to traditional Darcy flow models. Further application of the non-Darcy flow model reveals strategies to enhance well performance. For example, mitigating liquid lock damage within a 2 m radius near the well could restore the permeability from 0.045 to 0.143 mD, thereby tripling the daily gas production. This non-Darcy flow model is easy to implement and shows significant potential in forecasting production yields in tight sandstone reservoirs, highlighting its importance in the petroleum and natural gas industry.

Investigation on critical erosion of gas production channel for sand carrying during injection and production process in gas storage

Gas wells on underground gas storage typically are operated in high-load mode, with a large working displacement injection and high-strength production. Erosion-corrosion caused by solid particles could cause serious damage to the gas well, leading to tubing column failure and security risks. The influence factors on the tubing column geometry, the fluid properties and particle properties were investigated by the indoor erosion experiments and numerical simulation respectively. Five different erosion models were applied to predict the erosion rate. The Generic model was selected to calculate the influencing value by a range of parameters after comparing the predicted results with the experimental data. The results indicated that the sand production rate, the gas production rate and the production pressure played a crucial role on the tubing column erosion. The error of Generic model is less than 20%. The product of the quadratic power of daily gas production, the negative quadratic power of production pressure and the first power of sand production rate was directly proportional to the erosion rate of tubing column. The sequence of the maximum erosion rate on different sites from high to low was obtained: No-Go Landing Nipple, Safety Valve, integral Y-type wellhead. The erosion effect on Y-type wellhead should be considered emphatically considering the long-term operation. The chart of Critical Erosion Coefficient (C value) was established according to the design criterion of API RP 14E, which is suitable for gas storage production channel. The reasonable C value should be set as 180.0 to ensure the gas storage to meet the service life. Meanwhile, the recommendatory C value range was set between 175.0 and 200.0 for considering the maximum productivity of gas storage. The research results provided a key guidance for judging the service safety of injection-production channel in gas storage.

Modeling microwave heating for enhanced shale gas recovery: Fully coupled two-phase flows with heat transfer and electromagnetism in deformable reservoirs

To investigate the mechanisms of fluid migration during shale gas extraction under microwave irradiation, we developed a coupled Electromagnetic-Thermal-Hydraulic-Mechanical (ETHM) model. This model accounts for changes in fracture permeability due to variations in temperature, gas pressure, and methane desorption. The impact of microwave power on both gas production and the alteration of reservoir geological properties under microwave stimulation was investigated. Simulation results revealed that with a microwave injection power of 4,000 W, cumulative gas production increased by 45 %, reaching 64.9 million cubic meters. Additionally, the influence of initial water saturation and the diffusion damping coefficient on both gas and water production was examined. The findings show that cumulative water production was 33 % higher when microwave heating was applied compared to scenarios without microwave stimulation. An increase in initial water saturation led to a decrease in daily gas production during the early stages of extraction. Under microwave irradiation, the methane adsorption capacity at data acquisition point MP2 decreased to 0.0075 m3/kg, representing a 69 % reduction compared to conditions without microwave stimulation. Our analysis also found that daily gas production is highly sensitive to the diffusion damping coefficient. The diffusion attenuation effect had a notably negative impact on improving the recovery rate of shale gas reservoirs. In a word, this research holds significant implications for understanding the trends in gas and water production as well as the sensitivity of geological parameters during microwave-assisted thermal recovery of shale gas.

Laboratory Investigation of Biogas Production Using Cow Dungs and Kitchen Wastes Otta

Laboratory Investigation of Biogas Production Using Cow Dungs and Kitchen Wastes Otta

Upper limit estimate to wellhead flowing pressure and applicable gas production for a downhole throttling technique in high-pressure–high-temperature gas wells

In recent years, China has explored and exploited several high-pressure deep gas fields. Normally, high-pressure gas wells are gathered and processed through multichoke manifolds on well sites, creating hazards such as high wellhead flowing pressure (Pt) and high risk for on-site operation personnel. Moreover, downhole chokes have been used in place of surface chokes. In doing this, the Joule–Thomson (JT) effect is geothermally regulated, alleviating the formation of hydrates in surface facilities. However, its applicability to high-pressure gas wells is less explored. In an effort to guide its use, the objective of this study is to set selection criteria in terms of the allowable wellhead Pt and gas flow rate. First, isenthalpic lines are separately estimated for dry gas and high liquid hydrocarbon (LHC) content gas condensate at various inlet temperatures with the use of commercial software. Next, by analysis of the resulting isenthalpic curves, several results are obtained on the JT inversion curves and throttling process through a choke. Third, building on these insights, a method for projecting the maximum Pt is presented, leading to a value of 52.5 MPa. Finally, multiparameter models are separately run for two deep gas wells (8100 m and 5000 m), reinforcing the result of the pressure upper limit while maintaining a maximum daily gas production of 14 E4 m3. Both upper limits with a maximum Pt of 52.5 MPa and daily gas production of 14 E4 m3 are corroborated with field data records. These findings are vital to the selection of a viable high-pressure gas well for applying the downhole throttling technique.

Evaluation of Recovery of Tight Sandstone Gas Reservoirs Based on a Seepage Steady-State Model

As an important indicator for measuring the effectiveness and level of oil and gas field development, recovery rate has always been a focus in the research of oil and gas fields. Reservoirs of tight sandstone gas formations have significant characteristics of low porosity, high permeability, and high water content, which leads to greater difficulty in their development and makes it challenging to evaluate the recovery rate. Newtonian mechanics, as an important component of the mechanical system, is an innovative application of classical mechanics in the field of seepage mechanics when applied to the two-phase flow of gas and water. Firstly, starting from the perspective of mechanics analysis, we derive a steady-state model for gas–water two-phase infiltration and obtain the productivity equation based on this model. Then, according to the steady-state model, we establish a method to calculate the effective control radius of gas reservoirs under different production conditions and reservoir physical properties. Finally, using Matlab 2018a programming based on the productivity equation, we calculate the gas recovery under different conditions during constant pressure drop production and constant production rate production. The results indicate that the effective control radius of the reservoir decreases with an increase in the economic ultimate daily gas production, increases with an increase in production pressure difference, slightly decreases with an increase in startup pressure gradient, and correspondingly increases with an increase in microtube radius and quantity. Regardless of whether it is production with a fixed pressure drop or production with a fixed production rate, the gas recovery decreases as the production pressure drop and bottomhole abandonment pressure increase, but it increases as the proportion of the single-well control radius increases. In production with a fixed pressure drop, the gas recovery remains consistent across different reservoir quality indices. However, in production with a fixed production rate, the gas recovery initially increases rapidly and then gradually slows down as the reservoir quality index increases, and there is an obvious critical permeability (0.1 mD). The research findings are based on the mechanical analysis of porous media, delving into the laws governing fluid flow during infiltration. The derived infiltration model can be used to calculate the effective control radius and evaluate recovery rates, providing practical guidance for reservoir development.

Determining Appropriate Numbers and Times of Daily Measurements Using GreenFeed System to Estimate Ruminal Methane Emission of Meat Goats.

The study was conducted to determine appropriate numbers and times of daily gas measurements to estimate total daily methane (CH4) emission of meat goats using a GreenFeed system (GFS). A replicated 4 (four measurement protocols) × 4 (four periods) Latin square design was employed with 16 Boer wethers in a confinement pen setting. Measurement protocols entailed three (G-3T; 0600-0700, 1400-1500, and 2200-2300 h), four (G-4T; 0700-0800, 1300-1400, 1900-2000, and 0100-0200 h), and six (G-6T; 0800-0900, 1200-1300, 1600-1700, 2000-2100, 0000-0100, and 0400-0500 h) times for daily measurement periods in GFS. The fourth protocol was continuous measurement over 24 h with animals in an open-circuit respiration calorimetry system (CS). Oat hay was given in individual feeders, and a small predetermined quantity of a pelleted concentrate supplement (bait) was dispensed by the GFS or manually offered for the CS. Overall, total dry matter (DM) intake (614, 625, 635, and 577 g/day for CS, G-3T, G-4T, and G-6T, respectively; SEM = 13.9) and digestible DM intake (359, 368, 374, and 320 CS, G-3T, G-4T, and G-6T, respectively; SEM = 15.9) were lower for CS than for G-3T, G-4T, and G-6T (p < 0.05), but these variables were not different among the GFS protocols. There was a significant (p < 0.001) effect of measurement protocol on CH4 emission in g/day (11.1, 25.6, 27.3, and 26.7 for CS, G-3T, G-4T, and G-6T, respectively; SEM = 1.11), g/kg DM intake (19.3, 46.4, 43.9, and 42.4 for CS, G-3T, G-4T, and G-6T, respectively; SEM = 2.03), and g/kg body weight (0.49, 1.11, 1.18, and 1.16 for CS, G-3T, G-4T, and G-6T, respectively; SEM = 0.052), with values being much lower for CS than for G-3T, G-4T and G-6T. Conversely, CH4 emission was similar among the GFS protocols despite differences in the time and number of daily visits (2.03, 2.76, and 3.75 visits for G-3T, G-4T, and G-6T, respectively; SEM = 0.114; p < 0.001). Pearson correlation (r) analysis indicated a moderate to high (p < 0.05) correlation between CS and G-3T (r = 0.62 for CH4 in g/day and r = 0.59 for CH4 in g/kg BW), CS and G-4T (r = 0.67 for CH4 in g/day and r = 0.76 for CH4 in g/kg BW), and CS and G-6T (r = 0.70 for CH4 in g/day and r = 0.75 for CH4 in g/kg BW). However, the correlation coefficient for CH4 in g/kg DM intake was low between CS and G-3T (r = 0.11) and CS and G-6T (r = 0.31) but slightly greater between CS and G-4T (r = 0.47). In conclusion, the results suggest that CH4 emissions using GFS in a confinement setting were greater compared with the CS in goats, but CH4-emission estimation using the GFS correlated with the CH4 emission in the CS system with a stronger relationship for the four times of daily measurements.

Daily natural gas load prediction method based on APSO optimization and Attention-BiLSTM.

As the economy continues to develop and technology advances, there is an increasing societal need for an environmentally friendly ecosystem. Consequently, natural gas, known for its minimal greenhouse gas emissions, has been widely adopted as a clean energy alternative. The accurate prediction of short-term natural gas demand poses a significant challenge within this context, as precise forecasts have important implications for gas dispatch and pipeline safety. The incorporation of intelligent algorithms into prediction methodologies has resulted in notable progress in recent times. Nevertheless, certain limitations persist. However, there exist certain limitations, including the tendency to easily fall into local optimization and inadequate search capability. To address the challenge of accurately predicting daily natural gas loads, we propose a novel methodology that integrates the adaptive particle swarm optimization algorithm, attention mechanism, and bidirectional long short-term memory (BiLSTM) neural networks. The initial step involves utilizing the BiLSTM network to conduct bidirectional data learning. Following this, the attention mechanism is employed to calculate the weights of the hidden layer in the BiLSTM, with a specific focus on weight distribution. Lastly, the adaptive particle swarm optimization algorithm is utilized to comprehensively optimize and design the network structure, initial learning rate, and learning rounds of the BiLSTM network model, thereby enhancing the accuracy of the model. The findings revealed that the combined model achieved a mean absolute percentage error (MAPE) of 0.90% and a coefficient of determination (R2) of 0.99. These results surpassed those of the other comparative models, demonstrating superior prediction accuracy, as well as exhibiting favorable generalization and prediction stability.

Numerical Evaluation of Commingled Production Potential of Marine Multilayered Gas Hydrate Reservoirs Using Fractured Horizontal Wells and Thermal Fluid Injection

Multilayered reservoirs with coexisting free gas and hydrates are primary targets for commercialization, nevertheless, the extremely low permeability greatly limits their extraction efficiency. Herein, multilayer commingled production using horizontal wells stimulated by hydraulic fracturing and thermal fluid injection was proposed to enhance productivity, and the effects of key factors on co-production performance were numerically examined, with the reservoir located in the Shenhu Area as the geological background. The results indicated that due to severe interlayer contradictions, the stimulation capabilities of using fracturing or thermal fluid injection alone were limited, in particular, the extraction of hydrates severely lagged behind. However, their combination exhibited tantalizing productivity due to strengthened inter-well interaction. Reducing the fracture spacing was more effective than increasing fracture conductivity in shortening the production cycle, and intensive fractures with adequate flow capacity were suggested for gas enhancement and water control. When the fracture spacing was reduced from 30 to 5 m and the fracture conductivity increased from 10 to 100 D·cm, the horizontal section length for commercial production (average daily gas production of 50,000 m3 and recovery ratio of 0.7) was reduced from 1758 to 146 m, which is lower than the on-site horizontal section length of 250–300 m. Therefore, the proposed development mode is promising for the commingled production of gas and hydrates.

Full-cycle prediction of gas production variations in gas wells using different production methods

Gas production from gas wells is affected by formation pressure and wellbore outflow during gas production. To increase the daily gas production and obtain smooth and efficient gas production gas wells, methods such as wellbore shut-in pressure recovery and foam injection and drainage for gas production are usually adopted. In this paper, the gas-carrying liquid model, capacity prediction model, and pressure recovery model are utilized to establish a full-cycle production prediction method for newly developed gas wells. Combining the initial development pressure, gas production, and water production parameters of the gas well, the gas production prediction is obtained for the next few years. Meanwhile, the implementation time of the forced drainage method is calculated and obtained.

The practice and knowledge of Maokou-Qixia Formation depth: Acid fracturing in the Hechuan Tongnan regione

The Maokou Qixia Formation in the Hechuan Tongnan region is characterized by tight reservoirs, high pressure, high temperature, high sulfur content, multiple layers, and strong heterogeneity, Mainly using highly deviated wells in conjunction with general acidification to achieve production, although certain stimulation effects have been achieved, there are also problems such as uneven acid distribution, poor targeted acid fracturing technology, large production differences between wells, and rapid production decline. In order to improve the development effectiveness of the Hechuan Tongnan area, based on the physical characteristics of the Maokou Qixia Formation reservoir in the Hechuan Tongnan area, Combining the influencing factors and process research of deep acid fracturing transformation, through experimental evaluation of acid corrosion effect and crack simulation, a set of deep acid fracturing transformation process with alternating injection of “high and low viscosity gelling acid+turning acid” as the core has been explored and formed. This technological achievement has increased the volume of vertical and horizontal acid fracturing transformation, and has been applied in HS6 on-site for 5 levels, with a tested daily gas production of 118.2×104 m3, The production increase effect is significant, with 100% effective rate for deep acid fracturing transformation and 100% effective rate for production increase. This provides a theoretical basis and technical guidance for the deep acid fracturing transformation of the Maokou Qixia Formation in the Hechuan Tongnan region.

TimeNet: Time2Vec attention-based CNN-BiGRU neural network for predicting production in shale and sandstone gas reservoirs

With the continuous growth in global population and productivity, the demand for natural gas, the cleanest fossil fuel, is expected to increase significantly. Accurate daily gas production forecasting of shale and sandstone reservoirs ensures a reliable gas supply. However, the complex and non-linear gas data (reservoir and production data) makes this difficult. To address these challenges, we propose a novel model named TimeNet, which utilizes a mix of convolutional neural networks (CNN), bidirectional gated recurrent units (BiGRU), attention mechanisms (AM), and Time2Vec. Time2Vec is integrated to automatically capture important complex and non-linear temporal information and mitigate burdensome time series pre-processing. The CNN layer extracts spatial features influencing gas production, while the BiGRU captures high-level temporal features and irregular trends in the time series data. The AM helps in understanding embedded information for accurate learning. Each component of the TimeNet model serves a distinct function in the prediction task, optimizing its strengths. Testing on two real-world datasets from the Fenchuganj conventional sandstone gas field and the Marcellus shale gas field confirms the proposed model's effectiveness. Comparative analysis demonstrates the superior performance of the proposed model on the two datasets, exhibiting an R2 of 97.25 % and 97.57 % in shale and sandstone gas, respectively.