Future Production Rates Research Articles

Integrating Petrophysical, Hydrofracture, and Historical Production Data with Self-Attention-Based Deep Learning for Shale Oil Production Prediction

Summary As the energy industry increasingly turns to unconventional shale reservoirs to meet global demands, the development of advanced predictive models for shale oil production has become imperative. The inherent complexity of shale formations, coupled with the intricacies of hydraulic fracturing, poses significant challenges to efficient resource extraction. Our study leverages a substantial data set from the Ordos Basin to develop an advanced predictive model, integrating 18 parameters that blend static petrophysical attributes and dynamic factors, including hydraulic fracturing parameters and real-time pump pressure data. This holistic approach enables our self-attention (SA) model to accurately forecast future production rates by processing the complex interplay between reservoir characteristics and operational inputs. In testing across three wells, the model achieved average accuracies of 99.28% for daily oil production (DOP) and 99.25% for daily liquid production (DLP) over 20 days, surpassing traditional long short-term memory (LSTM) and gated recurrent unit (GRU) models, proving its efficacy in fractured well production forecasting. Furthermore, using the initial 30 days of production data as input, the model demonstrated its capability to predict DOP and DLP over a one-year period, achieving prediction accuracies of 96.2% for DOP and 99.6% for DLP rates. Our model’s profound implications for the shale industry include establishing a quantifiable link between key factors and production forecasts, guiding the optimization of controllable aspects, and serving as a decision-support tool for more efficient and cost-effective oil recovery.

Methods Used to Estimate Reservoir Pressure Performance: A Review

Reservoir pressure plays a significant role in all reservoir and production engineering studies. It is crucial to characterize petroleum reservoirs: by detecting fluid movement, computing oil in place, and calculating the recovery factor. Knowledge of reservoir pressure is essential for predicting future production rates, optimizing well performance, or planning enhanced oil recovery strategies. However, applying the methods to investigate reservoir pressure performance is challenging because reservoirs are large, complex systems with irregular geometries in subsurface formations with numerous uncertainties and limited information about the reservoir's structure and behavior. Furthermore, many computational techniques, both numerical and analytical, have been utilized to examine reservoir pressure performance. This paper summarizes the concepts and applications of traditional and novel ways to investigate reservoir pressure changes over time. It provides a comprehensive review that assists the reader in recognizing and distinguishing between various techniques for obtaining an accurate description of reservoir pressure behavior during production, such as the reservoir simulation method, material balance equation approach, time-lapse seismic data, and modern artificial intelligence methods. Thus, the central concept of these procedures and a list of the authors' research are discussed.

Prediction of Wells Performance and Producing Life Applying Production Decline Analysis

Analyzing the production data became a common method in modern reservoir engineering practice, which is used to dynamically indicate the reservoir's characteristics, predict long-term performance, and determine the reservoir's criteria through daily production analysis. Input data required to analyze production data is production rate and sometimes flow pressure (if any). The decline curve analysis method analyzes well production data to history matching and forecasts the future well performance. The decline curve analysis (DCA) method is a non-linear regression method for production history matching and prediction. In this study, we used the DCA method to analyze eight oil wells' production data produced from the Mishrif reservoir in an Iraqi oil field. This work dealt with the prediction of the reservoir’s performance and future production rate using the DCA method tool integrated with IPM- MBAL software. Production decline rate trend analysis was performed by generating standard curves utilizing exponential, hyperbolic, and harmonic decline model equations based on historical production data. Afterward, a production forecast model was built for production to 2025. The producing life for each well at the economic flow rate (300 bbl/Day) is estimated. Results from the production forecast showed that the exponential and hyperbolic decline models yielded 54.057 MMSTB and 80.73 MMSTB, respectively. The decline rates for hyperbolic and exponential models till 2025 were estimated as 4614.25 STB/Day and 1153.1STB/Day.

Oil and Gas Production Forecasting Using Decision Trees, Random Forst, and XGBoost

Oil and gas production forecasting has always been a hot topic in the petroleum industry. Production forecasting in this sector aims to estimate future production rates, facilitating operational planning, production optimization, and resource allocation for companies. Scientists have traditionally attempted to forecast oil and gas production using methods such as Numerical Reservoir Simulation (NRS) and Decline Curve Analysis (DCA). However, these methods present challenges including time-consuming processes lasting hours or even days, uncertain accuracy, reliance on accurate static models, and uncertainty in dynamic model parameters. In this research, aim to address these limitations by leveraging machine learning models for production forecasting. These models enable faster and more precise decision-making by accurately predicting future outcomes based on historical data. Our study employs three models: Decision Trees (DTR), Random Forest (RFR), and XGBoost. In this reserch utilize the Python programming language and a dataset from wells in New York State, USA. Experimental results demonstrate that the RFR model achieves the highest accuracy (99%) for oil and gas production compared to the XGBoost and DTR models.

Geological and dynamic similarity for reservoir state prediction by well connectivity

For decades, computational reservoir modeling remained the main instrument for assessing reservoir state during the operations, and for the forecasting of future production rates. The recent development of reduced-order physics modeling and pure data-driven solutions made it possible to monitor and forecast the reservoir state in a more prompt way. In this work, we propose a new data-driven approach aimed at assessing inter-well connectivity. The solution is based on a machine learning (ML) forecasting model for production parameters (production rates, bottom-hole pressure) and the extraction of feature importances by additive explanation. Resulted inter-well connectivity coefficients are used as edges weights in well connectivity graphs. The validation of the proposed solution was performed by the comparison with Capacity Resistance Model performance and static geological similarity between wells derived from well logs analysis. Two case studies on benchmark reservoir models from clastic and carbonate environments are presented to ensure reliability of the proposed solution.

The effects of tree planting on allergenic pollen production in New York City

Planting low-pollen trees could reduce aeroallergen exposure in cities, but the effects of historical tree planting on contemporary airborne pollen exposure remains largely unexplored. Whether tree selection decisions can effectively reduce airborne pollen will depend in part on which taxa are the most important sources of allergenic pollen and the extent to which they are intentionally planted vs. unplanted (i.e., recruiting naturally). Here, we use airborne pollen measurements to examine which taxa are of allergenic importance in New York City (NYC), and then combine two tree surveys with allometric equations to determine pollen production for several taxa. Future changes in pollen production as a function of growth, mortality, and recruitment are then simulated using i-Tree Eco Forecast. The most important producers of allergenic pollen in NYC are Quercus, Platanus, Morus, and Betula; they comprise 71% of airborne pollen measured and 93% of estimated pollen production (107 quadrillion pollen grains; however, pollen production was not estimated for all taxa). Previous municipal planting decisions have resulted in the high abundance of Platanus × acerifolia; it accounts for 34% of total street tree basal area and has an estimated annual pollen production of 27.7 ± 6.4 quadrillion grains. In contrast, Morus and Betula are generally unplanted, indicating that tree planting decisions will have smaller effects on their future pollen production rates in NYC. Quercus trees produced an estimated 68.2 ± 12.3 quadrillion pollen grains and accounted for almost 25% of airborne pollen collected, but were very abundant in parks and were mostly unplanted, suggesting that planting has not and will not have a major effect on city-wide pollen production. Overall, this study demonstrates that tree planting decisions can have important and long-lasting consequences for city-wide pollen production but only for species that are both primarily planted and large producers of allergenic pollen.

Bioenergy production side-streams availability assessment as decision making driver for sustainable valorisation technologies development. Case study: Bioethanol and biodiesel industries

Recently, biorefineries have emerged globally as an attractive alternative to conventional fuel production, but costs still need to be competitive. Latest policy actions such as the Green Deal or the Circular Economy Action Plan encourage maximising the biomass-to-products value chain through the use of all valuable compounds available in side-streams to the full extent. Side-streams from corn and rapeseed-based biofuels industries represent excellent sources of bioactive compounds and proteins, mainly under-utilised as animal feed without uncovering their full potential at industrial sectors such as food supplement, speciality chemicals, cosmetics, and household products. The main objective of the research conducted is to pave the way for side-streams valorisation technologies upgrading and market penetration by assessing current availability and future production rates of corn oil, thin stillage, rapeseed meal and other biodiesel and bioethanol production side-streams. Through a bibliographic analysis of peer-reviewed articles and grey literature, key information and valuable data are presented. It is possible to conclude that trends in biofuel markets (supported by regional regulations) lead to increased biofuel production, as well as increased availability of the specified side-streams. Corn oil is produced at a rate of 60 million L/year on average in Europe, a total of 1.6 billion L of thin stillage is produced each year, and rapeseed meal is generated at a global rate of 68 million tons per year. Future research to trigger further developments and investments could dive into the types and regional availability of relevant active compounds found in the selected side-streams.

The Prediction of Future Oil Wells Production from Decline Curve Pattern

The production decline analysis is a traditional method of identifying wells production pattern and predicting its performance and life based on real production data. The study of the application the production decline curves using one of the empirical models either the exponential, hyperbolic or the harmonic decline curves which occur often in the later life of production units has been done. Decline curve analysis applies oil production versus time plots to extrapolate an estimation of the future production rates for wells. Production data were plotted in different ways to identify a representative decline model. In this study, the historical data were provided from five oil wells of the 4th pay formation reservoir in Zubair field in southern Iraq (Basrah region). These data were used to estimate the total future recovery of petroleum and the end of a productive life to the economic limit. The relationships between production rate, time, and cumulative production for each well were studied. The production data points for each well were analyzed separately to evaluate the effect of the change in the production and reservoir conditions on the remaining reserves. The typical decline curve was applied in each oil well and the estimation of total reserves isn‘t changing with the time or by the workover action.

Prediction of Shale-Gas Production at Duvernay Formation Using Deep-Learning Algorithm

SummaryDecline–curve analysis (DCA) is an easy and fast empirical regression method for predicting future well production. However, applying DCA to shale–gas wells is limited by long transient flow, a unique completion design, and high–density drilling. Recently, a long short-term-memory (LSTM) algorithm has been widely applied to the prediction of time–series data. Because shale–gas–production data are time–series data, the LSTM algorithm can be applied to predict future shale–gas production. After information for 332 shale–gas wells in Alberta, Canada, is obtained from a commercial database, the data are preprocessed in seven steps, including cutoffs for well list, data cleaning, feature extraction, train and test sets split, normalization, and sorting for input into the LSTM model. The LSTM model is trained in 405 seconds by two features of production data and a shut–in (SI) period from 300 wells. The two–feature case shows a better prediction accuracy than both the one–feature case (i.e., production data only) and the hyperbolic DCA, where the three methods are tested on unseen data from 15 wells. The two–feature case can predict future production rates according to the SI period and provide a stable result for available time–series data.

Analysis of gas production data via an intelligent model: application to natural gas production

Predicting the future oil and gas production rate and evaluating oil/gas reserves are very challenging issues. Many engineers have found decline curve analysis a useful approach (Ahmed, 2010; Arps, 1945; Ebrahimi, 2010; Fetkovich, 1980; Gentry, 1972; Li and Horne, 2005; Ling and He, 2012; Oghena, 2012; Shirman, 1999; Zheng and Fei, 2008). The production rate or cumulative production at a constant bottom-hole pressure declines with time (Ahmed, 2010). Since mechanisms affecting the production are constant throughout the lifetime of a reservoir, extrapolating decline curves is used to forecast the future production rate. To do so, initial production rate, the decline curvature, and its rate should be considered (Ahmed, 2010). Arps’s equations are fundamental for the most heuristic and conventional decline curve analysis models (Arps, 1945). Arps demonstrated that the hyperbolic family of equations can express mathematically the curvature behaviour of the production rate versus time curve. The Arps (Arps, 1945) equations are divided into three categories, including exponential, hyperbolic, and harmonic decline curve models. Fetkovich (Fetkovich, 1980) proposed type curves for analysing decline curves. The procedure of type curve matching is summarized by the visual matching with log-log paper that includes pre-plotted curves of production data. Each of the curves has characteristics which can be shown when plotting them on Cartesian, semi-log and log-log scales as shown in Figure 1.

Engineering approach to allocate and evaluate performance influencing factors for ready mixed concrete batch plant under different effects

Growth of construction motion in the world specially Egyptian construction areas and ready mixed concrete production growth mainly in mega projects such as real estate projects, tourism projects and infrastructure projects, which they want high quality ready mixed concrete. The main objective of this paper is to analyze a clear understanding for measuring any concrete batch plant performance ratio by using analysis of collected data from more real concrete batch plants and determining the most effective factors that have great affect on concrete batch plants performance ratio. Predicting the actual future performance ratio and production rates for any concrete batch plant according to groups of effective factors is the essential sector which is suggest in this study using smart modeling analysis. Improve performance ratio of concrete batch plant was selected because of its importance in construction field by studying and analyzing the most effective factors. The study will be done by collecting and studying large detailed data through start of 2012 till the end of 2016 and it will be illustrated the time, quantities, distances and factors which affecting concrete batch plants performance ratio. This paper will be divided into main three groups, which are illustrated as follows: (1) It was mentioned the designing tables which is divided into three levels: (A) Field data recording sheet; (B) Field data processing sheet and (C) Field data analysis sheet to observe the most convincing variables that has large affect on concrete batch plant performance ratio. It was analyzed and checked the concrete batch plant performance ratio by optimizing its most effective variables. (2) It was mentioned how to analyze and use the collected detailed data from field and classified their variables affecting concrete batch plant performance ratio and getting the relation between concrete batch plant performance ratio and each variable separately considering all remaining variables are obviated then all statistical analysis were mentioned, all relations were proved to get proportion correlation for each variable. (3) It was summarized the conclusion. Finally this paper serve construction stakeholders to achieve a competitive level of time and quality for effective construction management.

Data-driven inverse modeling with a pre-trained neural network at heterogeneous channel reservoirs

This paper develops a reliable and efficient data-integration method, based on artificial neural networks (ANN) incorporated with a stacked autoencoder (SAE) in a deep neural network's framework. To handle scale-different static and dynamic data of heterogeneous channel reservoirs, the workflow suggests an unsupervised pre-training process coupled with ANN-based inverse modeling. The performances of the proposed neural network, i.e. the training efficiency, the predictability of future production rates and the computing time, are compared to those with an optimal ANN and the impact of hidden neurons are discussed. The pre-trained neural network demonstrates a reliable estimation of reservoir properties with the spatial characteristics of a true channel reservoir while the ANN fails with respect to the spatial heterogeneity. The pre-trained neural network decreases the mean absolute error of future oil production rates up to 9.1% which is less than 25% of the comparison case's level, i.e. the optimal ANN model. Its efficiency is validated by a computing time 14 times faster than that of the optimal ANN workflow. The pre-trained neural network evaluates the spatial characteristics of reservoir properties and facies models in a reasonable manner and is thus able to predict the water production rates and also the breakthrough time accurately. This pre-trained neural network manifests its applicability with robustness as an efficient method to integrate static and dynamic data.

A learning-based data-driven forecast approach for predicting future reservoir performance

Quantification of the predictive uncertainty of subsurface models has long been investigated. The traditional workflow is to calibrate prior models to match observed data, and then use the posterior models to simulate future system performance. Not only are these procedures computationally expensive, but they also have issues in maintaining geological model constraints during the calibration step. Data space inversion (DSI) was introduced recently to predict future system performance without the iterative history matching or model calibration step. In general, DSI approaches seek to establish a statistical relationship between the observed and forecast variables, as well as to quantify the predictive uncertainty of the forecast variables, by using an ensemble of uncalibrated prior models. Existing DSI approaches all require a number of complex transformation and mapping operations, which may deter their widespread use. In this study, we introduce a new and simpler DSI approach, the learning-based, data-driven forecast approach (LDFA), by combining dimension reduction and machine learning techniques to quickly provide accurate forecast results and reliably quantify corresponding uncertainty in the results. Our LDFA framework is demonstrated using two supervised learning algorithms, artificial neural network (ANN) and support vector regression (SVR), on two representative examples from reservoir engineering and geological carbon storage. Results suggest that our approach provides accurate forecast results (e.g., future oil production rate or cumulative injected CO2) and reasonable predictive uncertainty intervals. Our framework is generic and may be applied to other surface and subsurface problems.

Statistical model for predicting and improving ready mixed concrete batch plants’ performance ratio under different influences

Producers of ready mixed concrete think of improving concrete batch plants’ performance ratio to provide the construction market with high quality standards, save cost and time. Ready mixed concrete (RMC) is a mixture of different materials, which is delivered to customer in unhardened state and freshly mixed. Major objective of this study was to provide a clear understanding for predicting and improving the concrete batch plants’ performance ratio by use analysis of large collected data from more and different concrete batch plants and determining the most effective factors that have a great effect on concrete batch plants’ performance ratio. Predicting the actual future performance ratio and production rates for any concrete batch plant according to a groups of effective factors is the essential sector which is suggested in this paper using smart modeling analysis. Improving the performance ratio of concrete batch plant is selected because of its importance in construction field by studying and analyzing the most effective factors. The study will be done by collecting and studying large detailed data through start of 2012 till the end of 2016 and it will illustrate the time, quantities, distances and factors which affect concrete batch plants’ performance ratio. This paper is divided into six main groups, which are illustrated as follows: (1) It concludes the historical information about concrete batch plants and RMC, and introduces the objective of this paper and the most convincing definitions for productivity and Performance Ratio (PR). (2) It explains general information for ready mixed concrete batch plants, classifies plant types for determining criteria of pumping method and declares the modeling techniques, concept of standard performance, measuring productivity difficulties, productivity cycles, factors affecting equipment productivity, applications of construction productivity, concrete placement process, concrete equipment selection and methods of construction. Factors affecting concrete batch plants’ performance ratio were mentioned and it discussed the related studies for problem statement. (3) It mentions the concrete batch plant classifications, advantages and disadvantages of ready mix concrete batch plants, mixing process and the methodology. It analyzes and improves the concrete batch plant performance ratio using optimizing of its most effective variables. (4) It introduces and analyzes all variables data at the same time using input phase by Statistics Package for Social Science (SPSS) software; then the estimated model was developed in the final form. Stepwise forms of the model were done using SPSS to reduce and simplify the proposed model for getting the alternative simplified formulas and neglect the variables that have lowest and negligible effect. On the other hand, correlation matrix was done to indicate what will be impacted on concrete batch plant performance ratio when each variable changes. (5) It introduces an application of general and simplified models for a real case study on Suez power station project, which uses ready mixed concrete with theoretical capacity equal to 160m3/h. The case study will be conducted to validate and verify the applications of the proposed general and simplified models to give optimum expressway for ready mixed concrete construction projects. (6) It introduces conclusions, recommendations and suggests future studies.

A Framework for Conversion of Plastic Waste into Fuels and Chemicals: A Review of the Waste Current Situation in Libya

Pyrolysis of waste plastics is one of the routes used for waste minimization, which has been gaining interest in recent years as a feedstock method.In this work, the two universal problems: plastics waste and fuel shortage have been addressed simultaneously. The process of converting PP and PE plastics waste in Libya into fuel and chemicals was overviewed. Data concerning Plastic Industry in Libya was collected to which some projection of the future production rate and waste rate has been estimated.Keywords: Plastic waste; recycling of polymers; waste management.

Lithium availability and future production outlooks

Lithium is a highly interesting metal, in part due to the increasing interest in lithium-ion batteries. Several recent studies have used different methods to estimate whether the lithium production can meet an increasing demand, especially from the transport sector, where lithium-ion batteries are the most likely technology for electric cars. The reserve and resource estimates of lithium vary greatly between different studies and the question whether the annual production rates of lithium can meet a growing demand is seldom adequately explained. This study presents a review and compilation of recent estimates of quantities of lithium available for exploitation and discusses the uncertainty and differences between these estimates. Also, mathematical curve fitting models are used to estimate possible future annual production rates. This estimation of possible production rates are compared to a potential increased demand of lithium if the International Energy Agency’s Blue Map Scenarios are fulfilled regarding electrification of the car fleet. We find that the availability of lithium could in fact be a problem for fulfilling this scenario if lithium-ion batteries are to be used. This indicates that other battery technologies might have to be implemented for enabling an electrification of road transports.

Studies on the Estimation and Prospective Recovery of Coal Bed Methane from Raniganj Coalfield, India

Faster depletion of liquid hydrocarbons reserves makes coal bed methane a potential energy source. In the present investigation, coal samples were collected from a coal bed methane reservoir and proximate analysis was carried out to determine the ash content, volatile matter, and moisture content. Permeability and porosity of the coal was obtained to determine the gas content and flow characteristic of gas through the coal bed. Reserve and recoverable gas from the coal bed methane field under study was estimated from the adsorption-desorption experiments and simulation study. Future production rate of gas and water and dewatering time were predicted using Fekete coal bed methane software.

Prediction of Reservoir Performance Applying Decline Curve Analysis

Decline curve analysis is a technique can be applied to a single well, and total reservoir. Decline analysis routinely used by engineers to estimate initial hydrocarbon in place, hydrocarbon reserves at some abandonment conditions, and forecasting future production rate. The remaining reserve depends on the production points that selected to represent the real well behavior, the way of dealing with the production data, and the human errors that might happen during the life of the field. In this study the actual oil rate technique is applied under decline curve analysis (D.C.A) program, and screening data points to calculate remaining and recoverable reserves. Index Terms—Decline curve, production history, initial decline rate, remaining reserve, scenario.

Impact of a possible future global hydrogen economy on Arctic stratospheric ozone loss

The potential role of molecular hydrogen (H2) as a future alternative energy carrier has generated widespread interest. The possible amount of additional hydrogen emission into the atmosphere in a hydrogen-based economy depends on future hydrogen production and leakage rates throughout the complete process chain. However, the expected emissions are highly uncertain. Based on the current literature an upper limit is estimated. Additional hydrogen emissions yield enhanced water vapor concentrations in the stratosphere which will have an impact on stratospheric temperatures and on polar ozone loss. Both stratospheric water vapor and ozone are important drivers of climate change. The potential environmental risks are described and assessed to be low compared to the environmental benefits.

Debottlenecking and Computational-Fluid-Dynamics Studies of High-and Low-Pressure Production Separators

Summary Efficient and effective oil/water/gas separation is required for success of many production operations. A major oil producer was experiencing difficulties with the oil/water/gas separation equipment on an offshore platform and improvements were required to meet both present and future production rates. Both high-pressure (HP) and low-pressure (LP) separators on a major oil production platform were studied to determine the design limitations for foamy service and basic sediment and water (BS&W) levels. Computational-fluid-dynamics (CFD) studies were completed to show the volumetric utilization and flow-pattern improvements made with the design changes. Both HP and LP separators showed substantial foam and poor efficiency because of poor inlet-device design, plugging, and other general vessel-design limitations. Debottlenecking efforts determined that, while the inlet device was somewhat ineffective, major improvements could be made from changes to perforated plate baffles, fluid-level adjustments, and weir placement and operations. CFD calculations performed on both vessels indicated similar problems. The perforated plate baffles with improper design lead to countercurrent flow through the baffles, making them less effective in flow control and distribution. Fluid-level settings for the weir height affected the velocity differences between fluid layers and contributed to promotion of recirculation within the vessel, which lead to low volumetric utilization. With adjustments to vessel internal equipment and changes to fluid-phase levels, CFD calculations showed that overall vessel volumetric utilization was improved by 22% for the HP vessel and by 38% for the LP vessel. CFD results also showed the changes to the flow patterns accompanying these improvements. Vessels with the proposed changes were operating effectively with substantially higher throughputs and meeting the expected BS&W levels for operations of the downstream oil-processing equipment. Details about the vessel internals, flow properties, and other changes required to accomplish these improvements will be discussed.