Multilayer Neural Network with Multi-Valued Neurons in time series forecasting of oil production
NeurocomputingPublished 18 November 2015
Igor Aizenberg, Leonid Sheremetov, Luis Alfonso Villa‐Vargas, Jorge Martínez-Muñoz
Citations113
SJR quartileQ1
SJR score1.47
SNIP1.94
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
It is shown that MLMVN can be efficiently applied to univariate and multivariate multi-step ahead prediction of reservoir dynamics and several aspects of the application of ANN models to time series forecasting that could be of the interest for pattern recognition community are studied.
Abstract
In this paper, we discuss the long-term time series forecasting using a Multilayer Neural Network with Multi-Valued Neurons (MLMVN). This is a complex-valued neural network with a derivative-free backpropagation learning algorithm. We evaluate the proposed approach using a real-world data set describing the dynamic behavior of an oilfield asset located in the coastal swamps of the Gulf of Mexico. We show that MLMVN can be efficiently applied to univariate and multivariate one-step- and multi-step ahead prediction of reservoir dynamics. This paper is not only intended for proposing to use a complex-valued neural network for forecasting, but to deeper study some important aspects of the application of ANN models to time series forecasting that could be of the particular interest for pattern recognition community.
Keywords
Computer ScienceDecision SciencesEngineering
NeurocomputingTime series forecasting using a hybrid ARIMA and neural network model
4,350 Citations2003G.Peter Zhang
Experimental results with real data sets indicate that the combined model can be an effective way to improve forecasting accuracy achieved by either of the models used separately.
Journal of Statistical SoftwareAutomatic Time Series Forecasting: The<b>forecast</b>Package for<i>R</i>
3,448 Citations2008Rob J. Hyndman, Yeasmin Khandakar
Two automatic forecasting algorithms that have been implemented in the forecast package for R, based on innovations state space models that underly exponential smoothing methods, are described.
Automatic time series forecasting: the forecast package for R
1,011 Citations2017Rob J. Hyndman, Yeasmin Khandakar
IEEE Transactions on Neural NetworksTuning of the structure and parameters of a neural network using an improved genetic algorithm
787 Citations2003F.H.F. Leung, Hak‐Keung Lam +2 more
Journal of Intelligent & Robotic SystemsTime Series Prediction and Neural Networks
316 Citations2001R. Frank, N. Davey +1 more
It is shown that the heuristics can provide useful information in defining the appropriate network architecture and the resulting generalisation performance of the trained feed-forward neural network predictors is analysed.
NeurocomputingImprovement of Auto-Regressive Integrated Moving Average models using Fuzzy logic and Artificial Neural Networks (ANNs)
292 Citations2008Mehdi Khashei, Mehdi Bijari +1 more
Empirical results of financial markets forecasting indicate that the hybrid models exhibit effectively improved forecasting accuracy so that the model proposed can be used as an alternative to financial market forecasting tools.
Journal of Petroleum Science and EngineeringDesign of neural networks using genetic algorithm for the permeability estimation of the reservoir
242 Citations2007Mohsen Saemi, Morteza Ahmadi +1 more
A new method for the auto-design of neural networks was used, based on genetic algorithm (GA), which was evaluated by a case study in South Pars gas field in Persian Gulf and improved the effectiveness of forecasting when ANN is applied to a permeability predicting problem from well logs.
Studies in computational intelligenceComplex-Valued Neural Networks with Multi-Valued Neurons
225 Citations2011Igor Aizenberg
This book on the multi-valued neuron (MVN) and MVN-based neural networks covers MVN theory, learning, and applications.
Soft ComputingMultilayer Feedforward Neural Network Based on Multi-valued Neurons (MLMVN) and a Backpropagation Learning Algorithm
209 Citations2006Igor Aizenberg, Claudio Moraga
It is shown that using a traditional architecture of multilayer feedforward neural network (MLF) and the high functionality of the MVN, it is possible to obtain a new powerful neural network.
Computers & Operations ResearchAn investigation of neural networks for linear time-series forecasting
197 Citations2001Guoqiang Peter Zhang
It is often difficult in reality to determine whether the underlying data generating process is linear or nonlinear, so if neural networks can compete with traditional forecasting models for linear data with noise, they can be used in even broader situations for forecasting researchers and practitioners.
Expert Systems with ApplicationsEvolving neural network using real coded genetic algorithm for daily rainfall–runoff forecasting
194 Citations2008A. Sedki, Driss Ouazar +1 more
The results showed that the GA-based neural network model gives superior predictions and the well-trained neural network can be used as a useful tool for runoff forecasting.
IEEE Transactions on Neural NetworksBlur Identification by Multilayer Neural Network Based on Multivalued Neurons
146 Citations2008Igor Aizenberg, Dmytro Paliy +2 more
The MLMVN is used to identify both type and parameters of the point spread function, whose precise identification is of crucial importance for the image deblurring, and the simulation results show the high efficiency of the proposed approach.
Journal of Petroleum TechnologyRecent Developments in Application of Artificial Intelligence in Petroleum Engineering
136 Citations2005Shahab D. Mohaghegh
This article covers some of the most recent and advanced uses of intelligent systems in the oil and gas industry and discusses their potential role in the industry’s future.
Neural Computing and ApplicationsTime series forecasting by evolving artificial neural networks with genetic algorithms, differential evolution and estimation of distribution algorithm
133 Citations2011Juan Peralta Donate, Xiaodong Li +2 more
CNN based on multi-valued neuron as a model of associative memory for grey scale images
131 Citations2003Naum N. Aizenberg, Igor Aizenberg
A mathematical model of multivalued neural elements that can be used as an alternative to the basic cellular neural network (CNN) element and an efficient learning algorithm for the neural element and associative memory are presented.
IEEE Transactions on Neural NetworksNeuron-adaptive higher order neural-network models for automated financial data modeling
115 Citations2002Ming Zhang, Shuxiang Xu +1 more
These models are shown to be capable of automatically finding not only the optimum model, but also the appropriate order for specific financial data, and are more acceptable to financial experts than classical (closed box) neural networks.
NeurocomputingMultilayer Neural Network with Multi-Valued Neurons in time series forecasting of oil production
113 Citations2015Igor Aizenberg, Leonid Sheremetov +2 more
It is shown that MLMVN can be efficiently applied to univariate and multivariate multi-step ahead prediction of reservoir dynamics and several aspects of the application of ANN models to time series forecasting that could be of the interest for pattern recognition community are studied.
Neural NetworksHow embedded memory in recurrent neural network architectures helps learning long-term temporal dependencies
110 Citations1998Tsung-Nan Lin, Bill G. Horne +1 more
This work gives empirical justification to the hypothesis that similar improvements in learning long-term dependencies can be achieved with other classes of recurrent neural network axchitectures simply by increasing the order of the embedded memory.
IEEJ Transactions on Electronics Information and SystemsComplex-valued Neural Networks
103 Citations2011Akira Hirose
SPE/DOE Improved Oil Recovery SymposiumHow Artificial Intelligence Methods Can Forecast Oil Production
53 Citations2002William W. Weiss, Robert Balch +1 more
Applied Soft ComputingPerception-based approach to time series data mining
51 Citations2007Ildar Batyrshin, Leonid Sheremetov
It is shown how different methods developed so far in TSDM for manipulation of perception- based information can be used for development of a fuzzy perception-based TSDD approach, grounded in computing with words and perceptions permitting to formalize human perception-Based inference mechanisms.
Advances in soft computingA Feedforward Neural Network based on Multi-Valued Neurons
49 Citations2006Igor Aizenberg, Claudio Moraga +1 more
It is shown that using aTraditional feedforward architecture and a high functionality multi-valued neuron, it is possible to obtain a new powerful neural network that does not require a derivative of the activation function and its functionality is higher than the functionality of traditional feedforward networks containing the same number of layers and neurons.
NeurocomputingDisaggregation & aggregation of time series components: A hybrid forecasting approach using generalized regression neural networks and the theta method
42 Citations2010Marina Theodosiou
A hybrid forecasting method is proposed which leverages from statistical and neural network techniques to perform multi-step ahead forecasting and demonstrates that the proposed method can outperform standard statistical techniques in the literature.
Pattern Recognition LettersA novel associative model for time series data mining
38 Citations2013Itzamá López-Yáñez, Leonid Sheremetov +1 more
A novel non-linear forecasting technique based on the Gamma classifier, which is inspired on the Alpha-Beta associative memories, which are both supervised pattern recognition models, for time series data mining.
Journal of Petroleum Science and EngineeringData-driven forecasting of naturally fractured reservoirs based on nonlinear autoregressive neural networks with exogenous input
33 Citations2014Leonid Sheremetov, A. Cosultchi +3 more
It is shown that the NARX network can be efficiently applied to multivariate multi-step ahead prediction of reservoir dynamics and preliminary clustering of the time series can increase the precision of the forecasting.
International Journal of Chemical Engineering and ApplicationsPrediction of Reservoir Performance Applying Decline Curve Analysis
32 Citations2013Khulud Rahuma, H. Mohamed +2 more
IFAC Proceedings VolumesTime Series Forecasting: Applications to the Upstream Oil and Gas Supply Chain
31 Citations2013Leonid Sheremetov, Arturo González-Sánchez +2 more
This paper describes different models which are used for forecasting in the time series context of petroleum engineering and mainly focuses on a feedforward neural network model and a Gamma classifier, taking the alpha and beta operators as basis for the gamma operator.
SPE Western Regional MeetingNeural-Network Approach To Predict Well Performance Using Available Field Data
28 Citations2001Zhong Hai He, Linyu Yang +2 more
Journal of Statistical SoftwareA Web-Based Simulator for Sample Size and Power Estimation in Animal Carcinogenicity Studies
25 Citations2002Ho‐Jin Moon, J. Jack Lee +2 more
A Web-based statistical tool for sample size and power estimation in animal carcinogenicity studies is presented and can be used to provide a design with sufficient power for detecting a dose-related trend in the occurrence of a tumor of interest when competing risks are present.
SPE Intelligent Energy InternationalProduction Monitoring Using Artificial Intelligence, APLT Asset
24 Citations2012Gerardo Olivares, C.. Escalona +1 more
Expert Systems with ApplicationsPredicting time series of railway speed restrictions with time-dependent machine learning techniques
21 Citations2013Olga Fink, Enrico Zio +1 more
The proposed approach is verified on a case study predicting the occurrence of railway operation disruptions based on discrete-event data, which is represented by a binary time series and proves to be superior to MLP.
International Journal of Computer ApplicationsProduction Forecasting of Petroleum Reservoir applying Higher-Order Neural Networks (HONN) with Limited Reservoir Data
21 Citations2013Chithra ChakraNC, Ki‐Young Song +2 more
A new neural approach called higher-order neural network (HONN) to forecast the oil production of a petroleum reservoir is presented, which overcomes the limitation of the conventional neural network.
University of Hertfordshire Research Archive (University of Hertfordshire)Time Series Prediction and Neural Networks
14 Citations1999N. Davey, S.P. Hunt +1 more
SPE Eastern Regional MeetingForecasting US Natural Gas Production into year 2020: a comparative study.
12 Citations2004A Medina García, Shahab D. Mohaghegh
Predictive Data-Mining Technologies for Oil-Production Prediction in Petroleum Reservoir
10 Citations2007Luis Carlos Ferreira da Silva, R. C. M. Portella +2 more
Lecture notes in computer scienceMultilayer Neural Network with Multi-Valued Neurons in Time Series Forecasting of Oil Production
7 Citations2014Igor Aizenberg, Leonid Sheremetov +1 more