A novel framework for predicting non-stationary production time series of shale gas based on BiLSTM-RF-MPA deep fusion model

Shale gas, as an environmentally friendly fossil energy resource, has gained significant commercial development and shows immense potential. However, accurately predicting shale gas production faces substantial challenges due to the complex law of decline, nonlinear and non-stationary features in production data, which greatly repair the robustness of current models in predicting shale gas production time series. To address these challenges and improve accuracy in production forecasting, this paper introduces a novel and innovative approach: a hybrid proxy model that combines the bidirectional long short-term memory(BiLSTM) neural network and random forest(RF) through deep learning. The BiLSTM neural network is adept at capturing long-term dependencies, making it suitable for understanding the intricate relationships between input and output variables in shale gas production.On the other hand, RF serves a dual purpose: reducing model variance and addressing the concept drift problem that arises in non-stationary time series predictions made by BiLSTM. By integrating these two models, the hybrid approach effectively captures the inherent dependencies present in long and nonstationary production time series, thereby reducing model uncertainty. Furthermore, the combination of BiLSTM and RF is optimized using the recently-proposed marine predators algorithm(MPA) to fine-tune hyperparameters and enhance the overall performance of the proxy model. The results demonstrate that the proposed BiLSTM-RF-MPA model achieves higher prediction accuracy and demonstrates stronger generalization capabilities by effectively handling the complex nonlinear and non-stationary characteristics of shale gas production time series. Compared to other models such as LSTM, BiLSTM, and RF, the proposed model exhibits superior fitting and prediction performance, with an average improvement in performance indicators exceeding 20%. This innovative framework provides valuable insights for forecasting the complex production performance of unconventional oil and gas reservoirs, which sheds light on the development of data-driven proxy models in the field of subsurface energy utilization.

Production Capacity Prediction Method of Shale Oil Based on Machine Learning Combination Model

The production capacity of shale oil reservoirs after hydraulic fracturing is influenced by a complex interplay involving geological characteristics,engineering quality,and well conditions.These relationships,nonlinear in nature,pose challenges for accurate description through physical models.While field data provides insights into real-world effects,its limited volume and quality restrict its utility.Complementing this,numerical simulation models offer effective support.To harness the strengths of both data-driven and model-driven approaches,this study established a shale oil production capacity prediction model based on a machine learning combination model.Leveraging fracturing development data from 236 wells in the field,a data-driven method employing the random forest algorithm is implemented to identify the main controlling factors for different types of shale oil reservoirs.Through the combination model integrating support vector machine(SVM)algorithm and back propagation neural network(BPNN),a model-driven shale oil production capacity prediction model is developed,capable of swiftly responding to shale oil development performance under varying geological,fluid,and well conditions.The results of numerical experiments show that the proposed method demonstrates a notable enhancement in R2 by 22.5%and 5.8%compared to singular machine learning models like SVM and BPNN,showcasing its superior precision in predicting shale oil production capacity across diverse datasets.

A Biogas Production Model from the Combination of Pig Manure and Cow Dung in N’Zérékoré City, Republic of Guine

This present research work focuses on the valorization of pig droppings for production of biogas in mono digestion and co-digestion with proportions of cow dung from the urban commune of N’Zérékoré. It was carried out in December 2020 in the Physics laboratory of the University of N’Zérékoré. The anaerobic digestion process took 25 days in an almost constant ambient temperature of 25˚C. Five digesters were loaded on 12/06/2020, two of which with 1 kg of pig dung and 1 kg of cow dung both in mono-digestion. The 3 other digesters in co-digestion with different proportions of pig manure and cow dung. The substrate in each digester is diluted in 2 liters of water, with a proportion of (1/2). The main results obtained are: 1) the evolution of the temperature and pH during digestion process, 2) the average biogas productions 0.61 liters for (D1);1.20 liter for (D2);1.65 liter for (D3);1.51 liter for (D4) and 1.31 liter for (D5). The cumulative amounts of biogas are respectively: D1 (7.95 liters), D2 (15.60 liters), D3 (21.50 liters), D4 (19.65 liters) and D5 (17.05 liters). The total cumulative production is 81.75 liters at the end of the process. The originality of this research work is that the proposed model examines the relation between the daily biogas production and the variation of temperature, pH and pressure. The combustibility test showed the biogas produced during the first week was no combustible (contains less than 50% methane). Combustion started from the biogas produced from the 15th day and it is from the 20th day that a significant amount of stable yellow/blue flame was observed. The results of this study show the combination of pig manure and cow dung presents advantages for optimal biogas production.

Consistency of Water Production Function Models of Two Crops

On basis of test information, the research performed analysis on water production function models of two crops, which indicated that water model of crops in whole growth stage and water model of crops indifferent growth stages have consistency as well as differences, providing references for optimization of irrigation water. Meanwhile, the research analyzed the deficiency of optimization on irrigation water for crops just by Jensen model.

Hydrogen production via steam reforming of bio-oil model compounds over supported nickel catalysts

The steam reforming of four bio-oil model compounds（acetic acid,ethanol,acetone and phenol） was investigated over Ni-based catalysts supported on Al2O3 modified by Mg,Ce or Co in this paper.The activation process can improve the catalytic activity with the change of high-valence Ni（Ni2O3,NiO） to low-valence Ni（Ni,NiO）.Among these catalysts after activation,the Ce-Ni/Co catalyst showed the best catalytic activity for the steam reforming of all the four model compounds.After long-term experiment at 700°C and the S/C ratio of 9,the Ce-Ni/Co catalyst still maintained excellent stability for the steam reforming of the simulated bio-oil（mixed by the four compounds with the equal masses）.With CaO calcinated from calcium acetate as CO2 sorbent,the catalytic steam reforming experiment combined with continuous in situ CO2 adsorption was performed.With the comparison of the case without the adding of CO2 sorbent,the hydrogen concentration was dramatically improved from 74.8% to 92.3%,with the CO2 concentration obviously decreased from 19.90% to 1.88%.

Technological Options to Ameliorate Waste Treatment of Intensive Pig Production in China:An Analysis Based on Bio-Economic Model

Ameliorating waste treatment by technological improvements affects the economic and the ecological-environment benefits of intensive pig production. The objective of the research was to develop and test a method to determine the technical optimization to ameliorate waste treatment methods and gain insight into the relationship between technological options and the economic and ecological effects. We developed an integrated bio-economic model which incorporates the farming production and waste disposal systems to simulate the impact of technological improvements in pig manure treatment on economic and environmental benefits for the case of a pilot farm in Beijing, China. Based on different waste treatment technology options, three scenarios are applied for the simulation analysis of the model. The simulation results reveal that the economic-environmental benefits of the livestock farm could be improved by reducing the cropland manure application and increasing the composting production with the current technologies. Nevertheless, the technical efficiency, the waste treatment capacity and the economic benefits could be further improved by the introduction of new technologies. It implies that technological and economic support policies should be implemented comprehensively on waste disposal and resource utilization to promote sustainable development in intensive livestock production in China.

Shale gas production evaluation framework based on data-driven models

Increasing the production and utilization of shale gas is of great significance for building a clean and low-carbon energy system.Sharp decline of gas production has been widely observed in shale gas reservoirs.How to forecast shale gas production is still challenging due to complex fracture networks,dynamic fracture properties,frac hits,complicated multiphase flow,and multi-scale flow as well as data quality and uncertainty.This work develops an integrated framework for evaluating shale gas well production based on data-driven models.Firstly,a comprehensive dominated-factor system has been established,including geological,drilling,fracturing,and production factors.Data processing and visualization are required to ensure data quality and determine final data set.A shale gas production evaluation model is developed to evaluate shale gas production levels.Finally,the random forest algorithm is used to forecast shale gas production.The prediction accuracy of shale gas production level is higher than 95%based on the shale gas reservoirs in China.Forty-one wells are randomly selected to predict cumulative gas production using the optimal regression model.The proposed shale gas production evaluation frame-work overcomes too many assumptions of analytical or semi-analytical models and avoids huge computation cost and poor generalization for numerical modelling.

Saline Water Irrigation Scheduling Through a Crop-Water-Salinity Production Function and a Soil-Water-Salinity Dynamic Model

Using a crop-water-salinity production function and a soil-water-salinity dynamic model, optimal irrigation scheduling was developed to maximize net return per irrigated area. Plot and field experiments were used to obtain the crop water sensitivity index, the salinity sensitivity index, and other parameters. Using data collected during 35 years to calculate the 10-day mean precipitation and evaporation, the variation in soil salinity concentrations and in the yields of winter wheat and cotton were simulated for 49 irrigation scheduling that were combined from 7 irrigation schemes over 3 irrigation dates and 7 salinity concentrations of saline irrigation water (fresh water and 6 levels of saline water). Comparison of predicted results with irrigation data obtained from a large area of the field showed that the model was valid and reliable. Based on the analysis of the investment cost of the irrigation that employed deep tube wells or shallow tube wells, a saline water irrigation schedule and a corresponding strategy for groundwater development and utilization were proposed. For wheat or cotton, if the salinity concentration was higher than 7.0 g L-1 in groundwater, irrigation was needed with only fresh water; if about 5.0 g L-1, irrigation was required twice with fresh water and once with saline water; and if not higher than 3.0 g L-1, irrigation could be solely with saline water.

Improving remote sensing-based net primary production estimation in the grazed land with defoliation formulation model

Remote sensing(RS) technologies provide robust techniques for quantifying net primary productivity(NPP) which is a key component of ecosystem production management. Applying RS, the confounding effects of carbon consumed by livestock grazing were neglected by previous studies, which created uncertainties and underestimation of NPP for the grazed lands. The grasslands in Xinjiang were selected as a case study to improve the RS based NPP estimation. A defoliation formulation model(DFM) based on RS is developed to evaluate the extent of underestimated NPP between 1982 and 2011. The estimates were then used to examine the spatiotemporal patterns of the calculated NPP. Results show that average annual underestimated NPP was 55.74 gC·m^(-2)yr^(-1) over the time period understudied, accounting for 29.06% of the total NPP for the Xinjiang grasslands. The spatial distribution of underestimated NPP is related to both grazing intensity and time. Data for the Xinjiang grasslands show that the average annual NPP was 179.41 gC·m^(-2)yr^(-1), the annual NPP with an increasing trend was observed at a rate of 1.04 gC·m^(-2)yr^(-1) between 1982 and 2011. The spatial distribution of NPP reveals distinct variations from high to low encompassing the geolocations of the Tianshan Mountains, northern and southern Xinjiang Province and corresponding with mid-mountain meadow, typical grassland, desert grassland, alpine meadow, and saline meadow grassland types. This study contributes to improving RS-based NPP estimations for grazed land and provides a more accurate data to support the scientific management of fragile grassland ecosystems in Xinjiang.

Modeling China's offshore production sharing contracts using meta analysis

Production sharing contracts have been used in the development of China’s offshore petroleum resources since 1982, but the mechanism in which the fiscal terms impact project economics is complicated and not well understood. The purpose of this paper is to model China’s offshore production sharing contracts using a probabilistic approach. Cash flows and economic indicators are used for a typical offshore oilfield development, and meta-models are constructed to analyze the basic features of the fiscal system. Applications of the models in contract negotiation are discussed.

Constructing the Ontology for Modeling the Fish Production in Pearl River Basin

This paper puts forward a construction method based on ontology for the Pearl River Basin fish production, to facilitate the domain knowledge analysis and information retrieval. By converting the concepts and terms in domain ordinally, the fish production ontology was constructed with the definition of classes, properties, instances, and relationships. The developed ontology model of the fish production knowledge is proposed and applied in the system of fish diseases diagnosis primarily. The research lays the semantic foundation for the further efficient knowledge management and practical application.

Coupling Relationship Analysis on Households′ Production Behaviors and Their Influencing Factors in Nature Reserves:A Structural Equation Model

A households′production behavior directly influences the quality of the environment and determines the successful development of nature reserves.Meanwhile,the households′production behaviors are complicated by interrelated factors,such as protection attitudes,resource endowment,and family wealth.This research evaluated households near the Crested Ibis National Nature Reserve in Shaanxi Province,acquiring data from 436 households around Yang County and Ningshan County in the south slope of Qinling Mountains,China.Based on the collected data,we developed a structural equation model to evaluate the coupling relationships among households′ protection attitudes,production behaviors,resource endowment,and family wealth.The results showed that:1) households with great resource endowment had more negative attitudes,probably due to their greater protection costs;2) the households with higher education levels had worse protection attitudes;3) the households with more family wealth were likely to use fewer fertilizers,pesticides,and firewood;4) the households with more resource endowment showed less production and management behaviors;5) the enhancement of households' attitudes improved production behaviors to protection the environment,but the effects were not statistically significant.Our results provide a basis for the government's protection policy making,exploring the effective management measures that are beneficial for both nature reserve management and community development.

Response of Growing Season Gross Primary Production to El Nino in Different Phases of the Pacific Decadal Oscillation over Eastern China Based on Bayesian Model Averaging

Gross primary production(GPP) plays a crucial part in the carbon cycle of terrestrial ecosystems.A set of validated monthly GPP data from 1957 to 2010 in 0.5°× 0.5° grids of China was weighted from the Multi-scale Terrestrial Model Intercomparison Project using Bayesian model averaging(BMA).The spatial anomalies of detrended BMA GPP during the growing seasons of typical El Nino years indicated that GPP response to El Nino varies with Pacific Decadal Oscillation(PDO) phases: when the PDO was in the cool phase,it was likely that GPP was greater in northern China(32°–38°N,111°–122°E) and less in the Yangtze River valley(28°–32°N,111°–122°E);in contrast,when PDO was in the warm phase,the GPP anomalies were usually reversed in these two regions.The consistent spatiotemporal pattern and high partial correlation revealed that rainfall dominated this phenomenon.The previously published findings on how El Nino during different phases of PDO affecting rainfall in eastern China make the statistical relationship between GPP and El Nino in this study theoretically credible.This paper not only introduces an effective way to use BMA in grids that have mixed plant function types,but also makes it possible to evaluate the carbon cycle in eastern China based on the prediction of El Nino and PDO.

RECONFIGURABLE PRODUCTION LINE MODELING AND SCHEDULING USING PETRI NETS AND GENETIC ALGORITHM

In response to the production capacity and functionality variations, a genetic algorithm （GA） embedded with deterministic timed Petri nets（DTPN） for reconfigurable production line（RPL） is proposed to solve its scheduling problem. The basic DTPN modules are presented to model the corresponding variable structures in RPL, and then the scheduling model of the whole RPL is constructed. And in the scheduling algorithm, firing sequences of the Petri nets model are used as chromosomes, thus the selection, crossover, and mutation operator do not deal with the elements in the problem space, but the elements of Petri nets model. Accordingly, all the algorithms for GA operations embedded with Petri nets model are proposed. Moreover, the new weighted single-objective optimization based on reconfiguration cost and E/T is used. The results of a DC motor RPL scheduling suggest that the presented DTPN-GA scheduling algorithm has a significant impact on RPL scheduling, and provide obvious improvements over the conventional scheduling method in practice that meets duedate, minimizes reconfiguration cost, and enhances cost effectivity.

Multiproduct and multistage integrated production planning model and algorithm based on an available production capacity network

This research attempts to devise a multistage and multiproduct short-term integrative production plan that can dynamically change based on the order priority and virtual occupancy for application in steel plants. Considering factors such as the delivery time, varietal compatibility between different products, production capacity of variety per hour, minimum or maximum batch size, and transfer time, we propose an available production capacity network with varietal compatibility and virtual occupancy for enhancing production plan implementation and quick adjustment in the case of dynamic production changes. Here available means the remaining production capacity after virtual occupancy.To quickly build an available production capacity network and increase the speed of algorithm solving, constraint selection and cutting methods with order priority were used for model solving. Finally, the genetic algorithm improved with local search was used to optimize the proposed production plan and significantly reduce the order delay rate. The validity of the proposed model and algorithm was numerically verified by simulating actual production practices. The simulation results demonstrate that the model and improved algorithm result in an effective production plan.

Uncertain Multidisciplinary Design Optimization on Next Generation Subsea Production System by Using Surrogate Model and Interval Method

The innovative Next Generation Subsea Production System(NextGen SPS)concept is a newly proposed petroleum development solution in ultra-deep water areas.The definition of NextGen SPS involves several disciplines,which makes the design process difficult.In this paper,the definition of NextGen SPS is modeled as an uncertain multidisciplinary design optimization(MDO)problem.The deterministic optimization model is formulated,and three concerning disciplines—cost calculation,hydrodynamic analysis and global performance analysis are presented.Surrogate model technique is applied in the latter two disciplines.Collaborative optimization(CO)architecture is utilized to organize the concerning disciplines.A deterministic CO framework with two disciplinelevel optimizations is proposed firstly.Then the uncertainties of design parameters and surrogate models are incorporated by using interval method,and uncertain CO frameworks with triple loop and double loop optimization structure are established respectively.The optimization results illustrate that,although the deterministic MDO result achieves higher reduction in objective function than the uncertain MDO result,the latter is more reliable than the former.

Towards Production and Energy Coupling System Modeling and Simulation for Energy Optimization in the Process Industry

The production and energy coupling system is used to mainly present energy flow, material flow, information flow, and their coupling interaction. Through the modeling and simulation of this system, the performance of energy flow can be analyzed and optimized in the process industry. In order to study this system, the component based hybrid Petri net methodology (CpnHPN) is proposed, synthesizing a number of extended Petri net methods and using the concept of energy place, material place, and information place. Through the interface place in CpnHPN, the component based encapsulation is established, which enables the production and energy coupling system to be built, analyzed, and optimized on the multi-level framework. Considering the block and brief simulation for hybrid system, the CpnHPN model is simulated with Simulink/Stateflow. To illustrate the use of the proposed methodology, the application of CpnHPN in the energy optimization of chlorine balance system is provided.

Modeling and Analysis on Production Yield and Energy Consumption of Pelleting Process

The existing studies on the pelleting process were reviewed, and then the forming process of pelleting was introduced. Furthermore, the models describing the production yield and energy consumption of pelleting were presented. Based on the models, the influence of the pelleting structure parameters, die speed on the production yield and energy consumption were discussed. The results showed that larger pellet mill was preferred and the proper speed of the die should be selected to increase the production yield and reduce the energy consumption.

Production Management Modelling Based on MAS

Modelling based on multi-agent system （MAS） was built for the current production management and process of Shenyang Songyang Paper Cup Co., Ltd. It can transmit the information instantly via order agent （OA）, manager agent （MA）, production agent （PA）, and service agent （SA）, and realize information sharing. The PA is also built on MAS, and it includes two agents, task agent （TA）, and resource agent （RA）. It has been found that the modelling is superior to the old one. It can improve the working flow and production efficiency, and shorten the time of delivery.

Analysis and Forecast of MSW Production Based on the ARIMA Model in Beijing

Based on the data of MSW generation in Beijing from 2004 to 2012,an ARIMA model of time series analysis was established. By contrast of the modeling results of different yearly data,the forecast period was identified to be 10 years. The yearly production of MSW from 2015 to 2025 was forecasted by using SPSS 16. 0 software. Result shows that the forecasting effect of ARIMA( 1,0,1) model is relatively good,and it can be applied to prediction of MSW production in Beijing. In the next 10 years,the amount of MSW produced in Beijing is increasing,but the growth rate is not large. Is expected to 2025,the production of MSW will reach more than 9 million tons. Taking into account the MSW return,it is inferred that the production of MSW in Beijing in 2025 will be close to 10 million tons. In order to reduce the pressure of subsequent waste disposal facilities in Beijing,the government can increase the intensity of the recycling of waste materials.