Production Forecasts Research Articles

Research on the Multiscale Microscopic Pore Structure of a Coalbed Methane Reservoir

Coal rock pores are the space in which coalbed gas is stored and flows. Accurately characterizing the pore structure of coalbed gas is the foundation of coalbed gas reserve assessment and production forecasting. Traditional experimental methods are unable to characterize the multi-scale pore structure characteristics of coal rock. In this paper, a multi-scale pore structure characterization method is proposed by coupling various experimental methods, including low-pressure nitrogen gas adsorption experiments, X-ray computed tomography (XCT) imaging technology, and scanning electron microscopy (SEM). Using Zhengzhuang coalbed gas as an example, the micro-pore structure of coalbed gas reservoirs is characterized and depicted from a multi-scale perspective. The results indicate that a single experimental approach can only partially reveal the microstructure of coal rock pores. The combined use of multiple methods can accurately reveal the full-scale microstructure of coal rock pores. The pore structure of the experimental coal rock samples exhibits multi-scale characteristics, with a complex variety of pore types, including inorganic pores, organic pores, and fractures. Organic pores are predominant, with a small number of inorganic pores, and their sizes range from 2 nm to 50 μm. Mineral particles and fractures are observed at both the nanoscale and microscale, exhibiting typical multi-scale characteristics, with quartz being the predominant mineral.

New product family demand planning: AddressingSKU‐level spread bias

AbstractNew product supply chain planning is challenging, primarily due to the lack of historical demand data. Rarely, however, do the academic literature or companies differentiate the demand forecasting process for new products from existing ones, despite their increased reliance on judgmental estimates. This research focuses on how judgmental errors lead to an under‐estimation of the difference between the highest‐ and lowest‐demand stock‐keeping units (SKUs), and consequently negatively impact supply chain planning for new product family introductions. A generalized empirical model and accompanying discrete event simulation are developed and applied to data from a major consumer packaged goods (CPG) firm during the launch of a new cosmetics product family. This application allows us to identify a focal type of judgmental error (identified as the SKU‐level spread bias) inherent to new product forecasting and to provide a new theoretical understanding of how this type of bias harms supply chain performance. Via an empirically driven theory‐building approach that iterates between the simulation outcomes and existing literature, SKU‐level spread bias is demonstrated to harm demand forecasts and, thereby, supply chain plans. Our unique theory‐building approach advances theory by identifying planner SKU‐level spread bias as a new source of bias that firms should seek to mitigate when introducing new product families.

Digitalization, Industry 4.0, Data, KPIs, Modelization and Forecast for Energy Production in Hydroelectric Power Plants: A Review

Intelligent water usage is required in order to target the challenging goals for 2030 and 2050. Hydroelectric power plants represent processes wherein water is exploited as a renewable resource and a source for energy production. Hydroelectric power plants usually include reservoirs, valves, gates, and energy production devices, e.g., turbines. In this context, monitoring and maintenance policies together with control and optimization strategies, at the different levels of the automation hierarchy, may represent strategic tools and drivers for energy efficiency improvement. Nowadays, these strategies rely on different basic concepts and elements, which must be assessed and investigated in order to provide a reliable background. This paper focuses on a review of the state of the art associated with these basic concepts and elements, i.e., digitalization, Industry 4.0, data, KPIs, modelization, and forecast.

Demand forecasting of technological products considering re-purchasing and dynamic pricing: a modified diffusion model

Demand forecasting of technological products considering re-purchasing and dynamic pricing: a modified diffusion model

Prediction of Electricity Generation Using Onshore Wind and Solar Energy in Germany

Renewable energy production is one of the most important strategies to reduce the emission of greenhouse gases. However, wind and solar energy especially depend on time-varying properties of the environment, such as weather. Hence, for the control and stabilization of electricity grids, the accurate forecasting of energy production from renewable energy sources is essential. This study provides an empirical comparison of the forecasting accuracy of electricity generation from renewable energy sources by different deep learning methods, including five different Transformer-based forecasting models based on weather data. The models are compared with the long short-term memory (LSTM) and Autoregressive Integrated Moving Average (ARIMA) models as a baseline. The accuracy of these models is evaluated across diverse forecast periods, and the impact of utilizing selected weather data versus all available data on predictive performance is investigated. Distinct performance patterns emerge among the Transformer-based models, with Autoformer and FEDformer exhibiting suboptimal results for this task, especially when utilizing a comprehensive set of weather parameters. In contrast, the Informer model demonstrates superior predictive capabilities for onshore wind power and photovoltaic (PV) power production. The Informer model consistently performs well in predicting both onshore wind and PV energy. Notably, the LSTM model outperforms all other models across various categories. This research emphasizes the significance of selectively using weather parameters for improved performance compared to employing all parameters and a time reference. We show that the suitability and performance of a prediction model can vary significantly, depending on the specific forecasting task and the data that are provided to the model.

Effect of production system uncertainties on production forecast, energy demand, and carbon emissions

Effect of production system uncertainties on production forecast, energy demand, and carbon emissions

Skin Factor Consideration in Decline Curve Analysis

Summary This paper introduces an approach for the impact of skin factor on the decline curve analysis of hydraulically fractured reservoirs. The objective is to consider this impact in the production forecasting and the ultimate recovery estimation. The approach focuses on reducing the uncertainties that could be raised from this impact on the production history and increasing the accuracy of the predicted flow rates. It proposes an easy and promising tool for the decline curve analysis that could be applied confidently to different oil- and gas-producing wells and different reservoirs. This approach utilizes the rate-normalized flow rate derivative β behavior of the fractured reservoirs. This derivative demonstrates a constant behavior with time for each flow regime when the production history has not undergone the impact of the skin factor. However, the constant behavior no longer exists when this impact has influenced the production history. Instead, a power-law type model governs the relationship between the flow rate derivative and production time. New analytical flow rate decline curve models, exponential-type, are derived from the flow rate derivative power-law type models for the flow regimes. Different models for calculating the skin factor are developed for the three linear flow regimes that could be observed during the transient state flow conditions. The proposed flow rate models are used to simulate the production history and forecast the future performance. Moreover, the hydraulic fracture conductivity can be calculated using these models as well as the flow rate loss caused by skin factor. Several case studies are examined by the proposed approach where the production history is used to characterize the dominant flow regimes. The study has reached several observations and conclusions. The impact of skin factor is seen clearly throughout transient state flow regimes; however, this impact declines sharply before reaching pseudosteady-state flow (boundary-dominated flow regime). The impact of the skin factor alternates the constant behavior of the flow rate derivative with time to a power-law type relationship. A straight line of a slope (0.5) is diagnosed during hydraulic fracture and formation linear flow regime on the log-log plot of the flow rate derivative β and time, while the bilinear flow regime demonstrates a straight line of a slope (0.25). Because of the skin factor, exponential decline curve models replace the power-law type models of the flow rate during the abovementioned flow regimes. These models exhibit an excellent match between the calculated flow rate and the production history. The maximum flow rate loss occurs during very early production time even though the skin factor during this time is less than the intermediate production time. This study presents a novel approach for the decline curve analysis taking into account the impact of skin factor. The novelty is represented by considering the flow regimes in the production forecasting of hydraulically fractured reservoirs. This approach is smoothly applied to predict the future performance with no need to know the wellbore and reservoir parameters. It can be used to predict the declining flow rate for a constant or varied bottomhole flowing pressure.

Well-Log-Based Reservoir Property Estimation With Machine Learning: A Contest Summary

Well logs are processed and interpreted to estimate in-situ reservoir properties, which are essential for reservoir modeling, reserve estimation, and production forecasting. While the traditional methods are mostly based on multimineral physics or empirical formulae, machine learning provides an alternative data-driven approach that requires much less a-priori geological or petrophysical information. From October 2021 to March 2022, the Petrophysical Data-Driven Analytics Special Interest Group (PDDA SIG) of the Society of Petrophysicists and Well Log Analysts (SPWLA) hosted a machine-learning contest aiming to develop data-driven models for estimating reservoir properties, including shale volume, porosity, and fluid saturation, based on a common set of well logs, including gamma ray, bulk density, neutron porosity, resistivity, and sonic. Log data from nine wells from the same field, together with the interpreted reservoir properties by petrophysicists, were provided as training data, and five additional wells were provided as blind test data. During the contest, various data-driven models were developed by the contestants to predict the three reservoir properties with the provided training data set. The top five performing models from the contest, on average, beat the performance of the benchmarked Random Forest model by 45% in the root-mean-square error (RMSE) score. In the paper, we will review these top-performing solutions, including their preprocessing techniques, feature engineering, and machine-learning models, and summarize their advantages and conditions.

An efficient data-driven global sensitivity analysis method of shale gas production through convolutional neural network

The shale gas development process is complex in terms of its flow mechanisms and the accuracy of the production forecasting is influenced by geological parameters and engineering parameters. Therefore, to quantitatively evaluate the relative importance of model parameters on the production forecasting performance, sensitivity analysis of parameters is required. The parameters are ranked according to the sensitivity coefficients for the subsequent optimization scheme design. A data-driven global sensitivity analysis (GSA) method using convolutional neural networks (CNN) is proposed to identify the influencing parameters in shale gas production. The CNN is trained on a large dataset, validated against numerical simulations, and utilized as a surrogate model for efficient sensitivity analysis. Our approach integrates CNN with the Sobol' global sensitivity analysis method, presenting three key scenarios for sensitivity analysis: analysis of the production stage as a whole, analysis by fixed time intervals, and analysis by declining rate. The findings underscore the predominant influence of reservoir thickness and well length on shale gas production. Furthermore, the temporal sensitivity analysis reveals the dynamic shifts in parameter importance across the distinct production stages.

Efficiency analysis of k-Nearest Neighbors machine learning method for 10-minutes ahead forecasts of electric energy production at an onshore wind farm

Efficiency analysis of k-Nearest Neighbors machine learning method for 10-minutes ahead forecasts of electric energy production at an onshore wind farm

A Machine Learning-Based Electricity Consumption Forecast and Management System for Renewable Energy Communities

The energy sector is currently undergoing a significant shift, driven by the growing integration of renewable energy sources and the decentralization of electricity markets, which are now extending into local communities. This transformation highlights the pivotal role of prosumers within these markets, and as a result, the concept of Renewable Energy Communities is gaining traction, empowering their members to curtail reliance on non-renewable energy sources by facilitating local energy generation, storage, and exchange. Also in a community, management efficiency depends on being able to predict future consumption to make decisions regarding the purchase, sale and storage of electricity, which is why forecasting the consumption of community members is extremely important. This study presents an innovative approach to manage community energy balance, relying on Machine Learning (ML) techniques, namely eXtreme Gradient Boosting (XGBoost), to forecast electricity consumption. Subsequently, a decision algorithm is employed for energy trading with the public grid, based on solar production and energy consumption forecasts, storage levels and market electricity prices. The outcomes of the simulated model demonstrate the efficacy of incorporating these techniques, since the system showcases the potential to reduce both the community electricity expenses and its dependence on energy from the centralized distribution grid. ML-based techniques allowed better results specially for bi-hourly tariffs and high storage capacity scenarios with community bill reductions of 9.8%, 2.8% and 5.4% for high, low, and average photovoltaic (PV) generation levels, respectively.

Leveraging Circular Economy Metrics for Data-Driven Forecasting of Solid Waste Production in Europe

This study integrates circular economy (CE) metrics with machine learning techniques, specifically XGBoost and Shapley additive explanations (SHAP), to forecast municipal solid waste (MSW) in the EU, analyzing data from 2010 to 2020. It examines key economic and consumption indicators, including GDP per capita and energy consumption, along with CE metrics such as resource productivity, the municipal waste recycling rate, and the circular material use rate. The model demonstrates high predictive accuracy, with an R2 of 99% for in-sample data and 75% for out-of-sample data. The results indicate a significant correlation between a higher GDP per capita and an increased gross municipal waste per capita (GMWp). Conversely, lower energy consumption is associated with reduced GMWp. Notably, the circular material use rate emerges as a crucial factor for sustainability, with increased use significantly decreasing the GMWp. In contrast, a higher resource productivity correlates with an increased GMWp, suggesting complex implications for waste generation. The recycling rate, while impactful, shows a more modest effect compared to the other factors. The culminating insights from this study emphasize the need for sustainable, integrated waste management and support the adoption of circular economy-aligned policies. They underscore the efficacy of merging CE metrics with advanced predictive models to bolster regional sustainability efforts.

Analysis of Precipitation Zone Forecasts and Examination of Numerical Forecasts for Two Heavy Rainfall Processes in June 2019 in Jiangxi, China 2019

Warm zone rainstorms and frontal rainstorms are two types of rainstorms that often occur in the rainy season in Jiangxi (located in the eastern part of China). The ability to correctly identify the type of rainstorms is important for accurate forecasting of rainstorms. Two heavy rainstorms took place in Jiangxi province. The first heavy rainstorm occurred from 20:00 BJT (Beijing Time) on 6 June to 20:00 BJT on 9 June (referred to as the “6.9” process) and another heavy rainstorm occurred from 20:00 BJT on 21 June to 20:00 BJT on 22 June (referred to as the “6.9” process), 2019. We analyzed the two rainstorms’ processes by using ground-based observation data, NCEP/FNL reanalysis data, ECMWF and CMA-SH9 numerical forecasting products. The results show that: “6.9” process is a warm area rainstorm, and a strong northeast cold vortex exists at 500 hPa geopotential height. The northwesterly flow behind the northeast cold vortex trough is stronger. The position of the northern edge of the subtropical high pressure is more south than that at “6.22” process. The rainstorm is in the precipitation zone of the warm temperature ridge over 925 hPa geopotential height, and with more convective character than “6.22” process. The process of “6.22” is a frontal rainstorm. The convective character of precipitation is weaker. The rainstorm precipitation zones are in a strong temperature front area at 925 hPa geopotential height and there is a tendency for vertical convection to develop into oblique upward convection in the late stage of the rainstorm. The precipitation location and intensity forecast by CMA-SH9 at the “6.9” process is better than that of ECMWF, while ECMWF’s prediction of the precipitation zone and weather condition of the “6.22” process is better.

On approaches to solving problems when modeling polymer flooding at the Kalamkas oil field

Background: Currently, polymer flooding is one of the most effective methods for increasing reservoir recovery, accordingly and modeling this process is of particular relevance.
 Aim: The purpose of hydrodynamic modeling is to predict the distribution of parameters, technological indicators, and simulate all possible development scenarios. Based on the simulation results, decisions are made on the profitability of projects.
 Materials and methods: There are a number of significant problems in the process of hydrodynamic modeling, one of which is adaptation. Difficulties with adaptation are mainly associated with the incorrect determination of filtration – capacitive properties, which is directly caused by the lack of core research data. The main physical parameters that determine the filtration-capacitive properties of reservoir rocks are porosity, permeability, relative phase permeabilities, and saturation. These properties are critical for accurate fluid flow modeling and production forecasting. However, the lack of core data limits our understanding of these properties and affects the quality of model fit.
 Due to the insufficient data on the oil field in this Vostok site of horizon Ю-1 of the Kalamkas field, the approved initial geological reserves differ from the reserves according to the model by approximately 20%. For a more accurate adaptation of the hydrodynamic model, the availability of current initial geological reserves is significantly insufficient.
 Results: In this article, a number of approaches were applied to solve the above-mentioned problem in the hydrodynamic modeling of polymer flooding in the Kalamkas oil field, and as a result, the results obtained were demonstrated.
 Conclusion: Hydrodynamic modeling allows us to conduct numerical experiments to optimize the parameters of polymer flooding, helps to study their influence and select the optimal ratio to improve the efficiency of the flooding process.

A novel structure adaptive discrete grey Bernoulli prediction model and its applications in energy consumption and production

It is well known that energy forecasts play an important role in guiding energy policy, economic development and technological progress. Therefore, based on the purpose of energy consumption and production forecasting, this paper proposes a novel structure adaptive discrete grey Bernoulli model, which is innovative in terms of both accumulated generating operator and model structure. In terms of accumulated generating operator, a new fractional order accumulated generating operator is proposed in this paper. The new accumulated generating operator has a different information priority by adjusting the values of the parameters. In terms of model structure, a novel discrete grey Bernoulli model is proposed in this paper. The novel model is well adapted to time series data containing nonlinear information, and can well mine and utilize the information contained in the original data. In addition, the Particle Swarm Optimization (PSO) algorithm was chosen to optimize the model parameters based on algorithm comparison experiments. This enables the model to flexibly adapt to a variety of complex data and has the ability of structure adaptive. Moreover, this paper conducts comparative experiments between the novel model and eight other forecasting algorithms for time series data. The numerical results show that the novel model has better forecasting performance for the data of China’s total energy consumption, China’s total electricity generation and China’s total domestic electricity consumption. In addition, for the model reliability problem caused by the optimization algorithm, the stability and accuracy of the model are verified by Monte Carlo simulation and probability density visualization analysis. Finally, the proposed model predicts the future development trend of energy consumption and production in China.

Behaviour of small scale dispersed PV generation

The spread over of the small scale PhotoVoltaic plants requires a central production forecast. The regional meteorological information is not suitable for individual production calculation. We investigated the behaviour of the PV plants in different regions. We have also been looking for the relation between daily irradiation and energy production. We start from a basic assumption then we visualize the appropriate series of data and we calculate the correlation or other factors. Finally we confirm or neglect the initial idea. The geographical extent has significant effect on the daily cumulated production curve. The co-running of the daily power peak in a region is really strict but it has no correlation with the daily irradiation. The daily irradiation is proportional with the daily electricity production. The individual production forecast is not really viable that is why aggregation is necessary. The area of the whole country must be handled by regions.

Controlled power distributed photovoltaic system using solar energy forecast

The use of renewable energy sources to supply electricity in customer grids is a current practise in developed countries and, particularly, in the case of distributed solar energy generation grids. Even though, the environmental benefits of the practise drive to economic incentives to increase the renewable energies. However, because of the unsteady behaviour of the renewable electric energy sources [1], as wind energy and solar photovoltaic production, the increment in the use of these sources produces severe fluctuations in the electric grids. Then, their electric supply to the electric grid is limited and at the same time, an accurate renewable energy production forecast is required. In this work, the feasibility of a new approach to reduce this problem is tested by the application (on a yearly basis) of a simulator of a production-storage controlled system, namely FOTOV, to be applied in the design of a photovoltaic (PV) installation

Effect of Saharan dust episodes on the accuracy of photovoltaic energy production forecast in Hungary (Central Europe)

In order to meet global sustainability goals, in particular, the rapid decarbonisation of the energy sector in combination with geopolitical energy security issues, as well as further improvement in regional air quality-the so-called renewable energy sources are becoming increasingly critical and important. Photovoltaic power (PV) generation is clearly the most widely deployed (non-hydro) renewable energy source globally, which still has a significant growth potential in many countries, including Hungary.However, due to the intermittent nature and the strong dependency of photovoltaic power production on meteorological factors, continuous adjustment of electric power in the electric grid is needed. This, in turn, requires the most accurate forecast of the photovoltaic energy to be produced in the ultra-short term (15 min) and short term (1 day) in order to minimise last-minute and high-price energy acquisition or unplanned kicks-in of gas-fired auxiliary power plants.In this paper, we evaluate the impacts of large-scale dust transport episodes on the accuracy of forecasts of PV power generation. The numbers and intensities of Saharan dust storm events reaching Central Europe have increased over the last decade, hitting a new record in 2022 with 16 (!) African dust episodes observed over Hungary. We have shown that the semi-direct effect of atmospheric dust particles on high-level cloud formation rather than their direct irradiance-reducing effect is responsible for the reduced accuracies of e short-term (24-h) PV energy production forecasts during these events.

Evaluation of Daily Temperature Extremes in the ECMWF Operational Weather Forecasts and ERA5 Reanalysis

In weather forecasting and climate monitoring, daily maximum and minimum air temperatures (TMAX and TMIN) are fundamental for operational and research purposes, from early warning of extreme events to climate change studies. This study provides an integrated evaluation of TMAX and TMIN from two European Centre for Medium-range Weather Forecasts (ECMWF) products: ERA5 reanalysis (1980–2019) and operational weather forecasts (2017–2021). Both products are evaluated using in situ observations from the Global Historical Climatology Network (GHCN). While the analyses span globally, emphasis is given to four key regions: Europe, East and West United States, and Australia. Results reveal a general underestimation of TMAX and overestimation of TMIN in both operational forecasts and ERA5, highlighting the limitation of the ECMWF model in estimating the amplitude of the diurnal cycle of air temperature. ERA5′s accuracy has improved over the past decade, due to enhanced constrain of land–atmosphere analysis streaming from more and higher-quality satellite data. Furthermore, ERA5 outperforms one-day-ahead weather forecasts, indicating that non-real-time dependent studies should rely on ERA5 instead of real-time operational forecasts. This study underscores the importance of ongoing research in model and data assimilation, considering the relevance of daily temperature extremes forecasting and reanalysis for operational meteorology and climate monitoring.

An artificial-intelligence-based petrophysical property predictor for compositional volatile oil reservoir using three-phase production data

When considering multiphase flow scenarios, the interpretation of petrophysical properties poses significant challenges for production forecasts and reservoir modeling. The findings of the numerical modeling were therefore subject to uncertainty because characteristics like relative permeability and capillary pressure curve were hardly ever bound by interpretations. The uncertainty may result in inaccurate predictions of reservoir performance and skewed perceptions of the reservoir. Due to the difficulty in directly interpreting such property from the available field data and the expensive cost of coring, analyses or experimental measurements to determine relative permeability and capillary pressure were infrequently carried out. Such a gap would be filled by a straightforward yet rigorous method. In this study, we develop production projections for a wide range of three-phase compositional volatile oil reservoirs. Then, we used an artificial neural network to figure out how petrophysical characteristics and production data relate to one another. The artificial neural network model was adjusted, and the final trained model was tested blindly to determine how well it predicted permeability, multiphase relative permeability, and capillary pressure data. For the testing scenarios, consistency is seen between the predicted values and the original ones, despite some mispredictions being present. To provide production projections that can be compared to those from the reservoir model that include the initial petrophysical characteristic, the anticipated properties are then propagated into reservoir models. The comparison findings show that for 65/59/34 out of 74 testing scenarios, the reservoir model with artificial neural network-predicted features can anticipate oil/gas/water output with < 20% inaccuracy. With the developed artificial neural network tool, the reservoir engineers can evaluate the three-phase relative permeability surface from rate-transient data conveniently improving the accuracy of the relative permeability data implemented by history matching or from core experiments which sometimes are extremely expensive. The findings of this study can help for a better understanding of the relationships between three-phase rate-transient data and the relative permeability surface as well as the horizontal/vertical permeability.