Predicting the oil production using the novel multivariate nonlinear model based on Arps decline model and kernel method

Improvement in Solar-Radiation Forecasting Based on Evolutionary KNEA Method and Numerical Weather Prediction

Accurate forecasting of solar radiation (Rs) is significant to photovoltaic power generation and agricultural management. The National Centers for Environmental Prediction (NECP) has released its latest Global Ensemble Forecast System version 12 (GEFSv12) prediction product; however, the capability of this numerical weather product for Rs forecasting has not been evaluated. This study intends to establish a coupling algorithm based on a bat algorithm (BA) and Kernel-based nonlinear extension of Arps decline (KNEA) for post-processing 1–3 d ahead Rs forecasting based on the GEFSv12 in Xinjiang of China. The new model also compares two empirical statistical methods, which were quantile mapping (QM) and Equiratio cumulative distribution function matching (EDCDFm), and compares six machine-learning methods, e.g., long-short term memory (LSTM), support vector machine (SVM), XGBoost, KNEA, BA-SVM, BA-XGBoost. The results show that the accuracy of forecasting Rs from all of the models decreases with the extension of the forecast period. Compared with the GEFS raw Rs data over the four stations, the RMSE and MAE of QM and EDCDFm models decreased by 20% and 15%, respectively. In addition, the BA-KNEA model was superior to the GEFSv12 raw Rs data and other post-processing methods, with R2 = 0.782–0.829, RMSE = 3.240–3.685 MJ m−2 d−1, MAE = 2.465–2.799 MJ m−2 d−1, and NRMSE = 0.152–0.173.

Modeling and forecasting United States oil production along with the social cost of carbon: conventional and unconventional oil

Purpose

The USA is one of the largest oil producers in the world. For this purpose, the authors model and predict the US conventional and unconventional oil production during the period 2000–2030.

Design/methodology/approach

In this research, the system dynamics (SD) model has been used. In this model, economic, technical, geopolitical, learning-by-doing and environmental (social costs of carbon) issues are considered.

Findings

The results of the simulation, after successfully passing the validation test, show that the US unconventional oil production rate under the optimistic scenario (high oil prices) in 2030 is about 12.62 million barrels/day (mb/day), under the medium oil price scenario is about 11.4 mb/day and under the pessimistic scenario (low oil price) is about 10.18 mb/day. The results of US conventional oil production forecasting under these three scenarios (high, medium and low oil prices) show oil production of 4.62, 4.26 and 3.91 mb/day, respectively.

Originality/value

The contribution of this study is important in several respects: First, by modeling SD that technical, economic, proven reserves and technology factors are considered, this paper models US conventional and unconventional oil production separately. In this modeling, nonlinear relationships and feedback loops are presented to better understand the relationships between variables. Second, given the importance of environmental issues, the modeling of social costs of CO2 emissions per barrel of oil is also presented and considered as a part of oil production costs. Third, conventional and unconventional US oil production by 2030 is forecast separately, the results of this study could help policymakers to develop unconventional oil and plan for energy self-sufficiency.

Integrated Hierarchy-Correlation Model for Evaluating Water-Driven Oil Reservoirs

With the increasing demands on energy and environmental domains, not only high oil production but also its accurate quantification has become one of the most important topics in academia and industry. This paper initially proposes a comprehensive workflow in which an integrated hierarchy-correlation model is used to thoroughly evaluate the influences of all relevant reservoir parameters on the ultimate oil recovery for water-flooding oil reservoirs. More specifically, the analytic hierarchy process, grey relation, and entropy weight are combined through the multiplicative weighting method to quantitatively describe the production parameters. Accordingly, novel multivariable linear and nonlinear correlations are developed to predict the production performance and validated through comparisons with numerical reservoir simulations. Seven factors, including five reservoir parameters, namely, permeability and its contrast, porosity, thickness, and saturation, and two production parameters, namely, the injection-production ratio and the operating pressure, have been identified as the most influential factors on recovery performances and thus are employed in the proposed correlations to predict the ultimate oil recovery factor. The results obtained by the proposed method are quite close to the real-time simulation data, while the accuracy is retained. The numerical results show that the recovery factors of water-flooding oil reservoirs are about 33.5-59.5%, and the corresponding linear and nonlinear correlation coefficients are 0.903 and 0.789, respectively. In comparison with the numerical simulation, the approximation error by the linear correlation is about 0.5%, which is lower than that of nonlinear correlation, for example, 12.3%. This study will be beneficial to analyze the reservoir-related parameters and provide a useful tool for rapid production performance evaluation of the water-flooding production scenario.

Four-dimensional evaluation and forecasting of marine carrying capacity in China: Empirical analysis based on the entropy method and grey Verhulst model

This study separates marine carrying capacity into four key dimensions, i.e., social, economic, resource, and ecological, and uses the entropy method to evaluate the carrying capacity of China's 11 coastal regions during the period 2007-2016. We then predict the values of marine carrying capacity in the subsequent five years (2017-2021) using the grey Verhulst model. Results reveal a significant disparity in marine carrying capacity among the 11 coastal regions of China, and social and ecological carrying capacities illustrate among the four subcategories. Pearl River Delta in the south has the highest marine carrying capacity value and shows an increasing trend, while Yangtze River Delta and Bohai Rim Region in the north are stable. With regard to the predicted values for 2017-2021, forecasting results illustrate that the industrial structure of China's coastal areas is gradually turning towards the mode of diversified and comprehensive utilization of marine resources.

A New Model for Predicting Rate of Penetration Using an Artificial Neural Network

The drilling rate of penetration (ROP) is defined as the speed of drilling through rock under the bit. ROP is affected by different interconnected factors, which makes it very difficult to infer the mutual effect of each individual parameter. A robust ROP is required to understand the complexity of the drilling process. Therefore, an artificial neural network (ANN) is used to predict ROP and capture the effect of the changes in the drilling parameters. Field data (4525 points) from three vertical onshore wells drilled in the same formation using the same conventional bottom hole assembly were used to train, test, and validate the ANN model. Data from Well A (1528 points) were utilized to train and test the model with a 70/30 data ratio. Data from Well B and Well C were used to test the model. An empirical equation was derived based on the weights and biases of the optimized ANN model and compared with four ROP models using the data set of Well C. The developed ANN model accurately predicted the ROP with a correlation coefficient (R) of 0.94 and an average absolute percentage error (AAPE) of 8.6%. The developed ANN model outperformed four existing models with the lowest AAPE and highest R value.

The conformable fractional grey system model

The fractional order grey models have appealed considerable interest of research in recent years due to its high effectiveness and flexibility in time series forecasting. However, the existing fractional order accumulation and difference are computationally complex, which leads to difficulties for theoretical analysis and applications. In this paper, new definitions of fractional accumulation and difference are proposed based on the definition of conformable fractional derivative, which are called the conformable fractional accumulation and difference. Then a novel conformable fractional grey model is proposed based on the conformable fractional accumulation and difference, and Brute Force method is introduced to optimize its fractional order. The feasibility and simplicity of the proposed model and the Brute Force method are shown in the numerical example. The conformable fractional grey model outperforms the existing fractional grey model and the autoregressive model in 1 to 3-step predictions with 21 benchmark data sets, and also outperforms the existing fractional grey model in predicting the natural gas consumption of 11 countries. The results indicate that the proposed conformable fractional grey model is more efficient in longer term prediction and non-smooth time series forecasting than the existing models.

Potential for Prediction of Water Saturation Distribution in Reservoirs Utilizing Machine Learning Methods

Machine learning technology is becoming increasingly prevalent in the petroleum industry, especially for reservoir characterization and drilling problems. The aim of this study is to present an alternative way to predict water saturation distribution in reservoirs with a machine learning method. In this study, we utilized Long Short-Term Memory (LSTM) to build a prediction model for forecast of water saturation distribution. The dataset deriving from monitoring and simulating of an actual reservoir was utilized for model training and testing. The data model after training was validated and utilized to forecast water saturation distribution, pressure distribution and oil production. We also compared standard Recurrent Neural Network (RNN) and Gated Recurrent Unit (GRU) which are popular machine learning methods with LSTM for better water saturation prediction. The results show that the LSTM method has a good performance on the water saturation prediction with overall AARD below 14.82%. Compared with other machine learning methods such as GRU and standard RNN, LSTM has better performance in calculation accuracy. This study presented an alternative way for quick and robust prediction of water saturation distribution in reservoir.

Estimation of electronic waste using optimized multivariate grey models

Rapid and revolutionary changes in technology and rising demand for consumer electronics have led to staggering rates of accumulation of electrical and electronic equipment waste, viz., WEEE or e-waste. Consequently, e-waste has become one of the fastest growing municipal solid waste streams in the United States making its efficient management crucial in supporting the efforts to create and sustain green cities. Accurate estimations on the amount of e-waste might help in increasing the efficiency of waste collection, recycling and disposal operations that have become more complicated and unpredictable. Early work focusing on prediction of e-waste generation includes a wide range of methodologies. Among these, grey forecasting models have drawn attention due to their capability to provide meaningful results with relatively small-sized or limited data. The performance of grey models heavily rely on their parameters. The purpose of this study is to present a novel forecasting technique for e-waste predictions with multiple inputs in presence of limited historical data. The proposed nonlinear grey Bernoulli model with convolution integral NBGMC(1,n) improved by Particle Swarm Optimization (PSO) demonstrates superior accuracy over alternative forecasting models. The proposed model and its findings are delineated with the help of a case study utilizing Washington State e-waste data. The results indicate that population density has a major impact on the generated e-waste followed by household income level. The findings also show that the e-waste generation forms a saturated distribution in Washington State. These results can help decision makers plan for more effective reverse logistics infrastructures that would ensure proper collection, recycling and disposal of e-waste.

Comparison of neuron-based, kernel-based, tree-based and curve-based machine learning models for predicting daily reference evapotranspiration

Accurately predicting reference evapotranspiration (ET0) with limited climatic data is crucial for irrigation scheduling design and agricultural water management. This study evaluated eight machine learning models in four categories, i.e. neuron-based (MLP, GRNN and ANFIS), kernel-based (SVM, KNEA), tree-based (M5Tree, XGBoost) and curve-based (MARS) models, for predicting daily ET0 with maximum/maximum temperature and precipitation data during 2001-2015 from 14 stations in various climatic regions of China, i.e., arid desert of northwest China (NWC), semi-arid steppe of Inner Mongolia (IM), Qinghai-Tibetan Plateau (QTP), (semi-)humid cold-temperate northeast China (NEC), semi-humid warm-temperate north China (NC), humid subtropical central China (CC) and humid tropical south China (SC). The results showed machine learning models using only temperature data obtained satisfactory daily ET0 estimates (on average R2 = 0.829, RMSE = 0.718 mm day-1, NRMSE = 0.250 and MAE = 0.508 mm day-1). The prediction accuracy was improved by 7.6% across China when information of precipitation was further considered, particularly in (sub)tropical humid regions (by 9.7% in CC and 12.4% in SC). The kernel-based SVM, KNEA and curve-based MARS models generally outperformed the others in terms of prediction accuracy, with the best performance by KNEA in NWC and IM, by SVM in QTP, CC and SC, and very similar performance by them in NEC and NC. SVM (1.9%), MLP (2.0%), MARS (2.6%) and KNEA (6.4%) showed relatively small average increases in RMSE during testing compared with training RMSE. SVM is highly recommended for predicting daily ET0 across China in light of best accuracy and stability, while KNEA and MARS are also promising powerful models.