Reservoir parameter estimation using a hybrid neural. In this paper, we presented two approaches for modeling of survival data with different degrees of censoring. Predicting permeability from porosity using artificial neural. Artificial neural network modeling of dissolved oxygen in reservoir. A machine learningoriented spiking neural networks. The volume is the first comprehensive book in the area of intelligent reservoir characterization written by leading experts in academia and industry. Application of artificial neural networks for calibration. This allowed direct simulation of the trained neural network to obtain an updated reservoir parameters. Artificial neural network and inverse solution method for. Then, a suitable neural network architecture is selected and trained using input and. Resermine is a decision making platform for surveillance. In petroleum applications, the methodology developed can be a substitute for objects basedalgorithms when facies geometry and reservoir continuity are too complex to be modeled by simple object such as channels.
The rate of censorship in each of these models was considered from 20% up 80%. Abstract a combined approach of a dynamic programming algorithm and artificial. Reservoir simulation is an area of reservoir engineering that, combining physics, mathematics, and computer programming to a reservoir model allows the analysis and the prediction of the fluid behavior in the reservoir over time it can be simply considered as the process of mimicking the behavior of fluid flow in a. Novel connectionist learning methods, evolving connectionist systems, neurofuzzy systems, computational neurogenetic modeling, eeg data analysis, bioinformatics, gene data analysis, quantum neurocomputation, spiking neural networks, multimodal information processing in the brain, multimodal neural network. Development and application of reservoir models and. This paper presents a study aimed at forecasting water level of reservoir using neural network approaches. Reservoir systems operation model using simulation and neural. The available porosity and permeability data needed to build a reservoir simulation model are old and sparse. We develop a proxy model based on deep learning methods to accelerate the simulations of oil reservoirsby three orders of. In addition to neuronal and synaptic state, snns incorporate the concept of time into their operating model. Stochastic reservoir simulation using neural networks trained. The program is intended to be used in lessons of neural networks.
There is a range of artificial neural network architectures designed and used in various fields. Historically, the most common type of neural network software was intended for researching neural network structures and algorithms. Neurovis is an interactive neural network visualizer and tutorial. Numerous research works among which some related books e. Dissolved oxygen do in water column is essential for microorganisms and a significant indicator of the state of aquatic ecosystems. Available well logs and cores were used as inputs to the hybrid model.
The deep learning textbook is a resource intended to help students and practitioners enter the field of machine learning in general and deep learning in particular. Geochemical equilibrium determination using an artificial. Special issue on neural network applications to reservoirs. Download interactive neural network simulator for free. In this study, a deep learning neural network was developed to estimate the petrophysical characteristics required building a full field earth model for a large reservoir. In many cases, complex simulation models are available, but direct incorporation of them into an optimization framework is computationally prohibitive. Rating is available when the video has been rented. The online version of the book is now complete and will remain available online for free. The simulation model, shown in figure 1, is a portion of a very large geological model developed by castro 3.
Neural networkbased simulationoptimization model for. One is the pantai pakam timur field, located in northern sumatra, indonesia, where the data from only two wells were available and the other is iwafune oki field, located in the sea of japan, eastern japan, where wells were concentrated in the central part of the field. The proposed hybrid model fuzzy neural network fnn combines the learning ability of artificial neural networks and the transparent nature of fuzzy logic. Oil reservoir simulation, artificial neural networks. Accelerating physicsbased simulations using endtoend neural. Whitacre t and yu x a neural network receiver for emmwd baseband communication systems proceedings of the 2009 international joint conference on neural networks, 18121816 alavi a, cavanagh b, tuxworth g, meedeniya a, mackaysim a and blumenstein m automated classification of dopaminergic neurons in the rodent brain proceedings of the 2009. A montecarlo simulation study was performed to compare predictive accuracy of cox and neural network models in simulation data sets. The primary purpose of this type of software is, through simulation, to gain a better understanding of the behavior and the properties of neural networks.
Each processing node behaves like a biological neuron and performs two. The development of artificial neural networks began approximately 50 years ago, inspired by a desire to understand the human brain and emulate its functioning. In the algorithm, a few simulation runs of different reservoir realizations are first made using 3level fractional factorial design. Accelerating physicsbased simulations using neural network. Machine learning in reservoir production simulation and forecast. Pdf artificial neural networks for predicting petroleum quality. In the suggested model, multireservoir operating rules are derived using a neural network from the results of simulation. Some focus on the biologically realistic simulation of neurons, while others on highlevel spiking network functionality. Predicting reservoir water level using artificial neural. Applying machine learning algorithms to oil reservoir. In petroleum applications, the methodology developed can be a substitute for objects basedalgorithms when facies geometry and reservoir continuity are too.
Journal of petroleum science and engineering, elsevier, 2014, insu01084932, 123, pp. Additionally, a reasonable and effective reservoir operating plan is essential for realizing reservoir function. Reservoir computing emerges as a solution, o ering a generic. The water quality of reservoirs is one of the key factors in the operation and water quality management of reservoirs. We employed matlabs neural network fitting toolbox to train a proxy neural network model. The neural simulation language nsl, developed by alfredo weitzenfeld, michael arbib, and amanda alexander, provides a simulation environment for modular brain modeling. A new approach to reservoir characterization using deep. Im exploring reservoir computing more precisely, echo states network. Reservoir computing, recurrent neural network learning architectures, agent architectures, machine learning applications. Arti cial neural network as a proxy arti cial neural network ann is a. One is the pantai pakam timur field, located in northern sumatra, indonesia, where the data from only two wells were available and the other is iwafune oki field, located in the sea of japan, eastern japan, where wells were concentrated in the central part of. Genetic algorithms combined to ann applied to reservoir simulation and. Machine learning in reservoir production simulation and forecast serge a.
The application of rom to a realistic reservoir simulation model is illustrated and the ability of the rom to provide accurate predictions for cases that di. Artificial neural network modeling of dissolved oxygen in. Mar 22, 20 download interactive neural network simulator for free. In the suggested model, multi reservoir operating rules are derived using a neural network from the results of simulation. I cant find good explication for number of drop of transient states. Terekhov neurok techsoft, llc, moscow, russia email. Levenbergmarquardt training algorithm was used for training a neural network architecture with one hidden layer and thirty hidden neurons. This paper demonstrates the use of the k fold cross validation technique to obtain confidence bounds on an anns accuracy statistic from a finite sample set. To this end, new automated procedures are established. The training of the neural network is done using a supervised learning approach with the back propagation algorithm. The fundamental building block of a neural network is the neuron. Dynamical systems are essentially functions with an added time component, the same. It contains stateoftheart techniques to be applied in reservoir geophysics, well logging, reservoir geology, and reservoir engineering.
Machine learning in reservoir production simulation and. The performance is analyzed using a simulation model for the. Application of artificial neural networks for calibration of. Machine learning applied to 3d reservoir simulation. The idea is that not all neurons are activated in every iteration of propagation as is the case in a typical multilayer perceptron network, but only when its membrane potential reaches a certain value.
The network used in this study employs an architecture called backpropagation that is good at. Neural computations such as artificial neural networks ann have aroused considerable interest over the last decades, and are being successfully applied across a wide range of problem areas, to domains as diverse as medicine, finance. Well tops guided prediction of reservoir properties using modular neural network concept. Performance evaluation of artificial neural network approaches in forecasting reservoir inflow. T1 geochemical equilibrium determination using an artificial neural network in compositional reservoir flow simulation.
For multireservoir operating rules, a simulationbased neural network model is developed in this study. What is the realitionship between deep learning methods and. This model was then used to predict porosity and permeability for the reservoir and these values were then included in a reservoir simulation model. The book inspires geoscientists entrenched in first principles and engineering concepts to think. Physicsbased models and data models tahar aifa to cite this version. A system and method for modeling technology to predict accurately wateroil relative permeability uses a type of artificial neural network ann known as a generalized regression neural network grnn the ann models of relative permeability are developed using experimental data from waterflood core test samples collected from carbonate reservoirs of arabian oil fields three groups of data sets. Neurovis an interactive introduction to neural networks.
Artificial neural networks ann or connectionist systems are. See more ideas about artificial neural network, ai machine learning and deep learning. Datadriven reservoir modeling introduces new technology and protocols intelligent systems that teach the reader how to apply data analytics to solve realworld, reservoir engineering problems. For multi reservoir operating rules, a simulation based neural network model is developed in this study. Performing reservoir simulation with neural network. Us8510242b2 us12733,357 us73335708a us8510242b2 us 8510242 b2 us8510242 b2 us 8510242b2 us 73335708 a us73335708 a us 73335708a us 8510242 b2 us8510242 b2 us 8510242b2 authority us united states prior art keywords relative permeability reservoir data neural network test prior art date 20070831 legal status the legal status is an assumption and is not a. A neural net can be learned to collect multiple point statistics from various training images, these statistics are then used to generate stochastic models conditioned to actual data. Predicting permeability from porosity using artificial.
N2 the application of chemical method for hydrocarbons extraction has attracted increasing interest in the reservoir simulation community. Here, each circular node represents an artificial neuron and an arrow represents a connection from the output of one artificial neuron to the input of another. Also, it may consist of a single layer of neurons with each neuron feeding its output signal back to the inputs of all the other. Voltages recorded from the output of the two layer reservoir network. An artificial neural network is an interconnected group of nodes, inspired by a simplification of neurons in a brain. In the simulation study, four different models were considered. Spiking neural networks snns are artificial neural networks that more closely mimic natural neural networks. The development of spiking neural network simulation software is a critical component enabling the modeling of neural systems and the development of biologically inspired algorithms. Computer runs may be performed at an early stage of the reservoir study to estimate sensitivity of calculated reservoir performance to variations in the various required input data. A feedforward network approximates a mathematical function, whereas rnns approximate dynamical systems. Reservoir systems operation model using simulation and.
This paper demonstrates the use of the k fold cross validation technique to obtain confidence bounds. To overcome this problem, in this study, a backpropagation neural network is trained to approximate the simulation model developed for the chennai city water supply problem. Modeling and simulation, computational systems biology, bioinformatics. The deep learning textbook can now be ordered on amazon. We develop a proxy model based on deep learning methods to accel erate the simulations. A recurrent neural network differs from feed forward neural network in a way that it has at least one feedback loop. A case study from western onshore, india soumi chaki, akhilesh k. Current state of reservoir simulation and modeling of shale. The reservoir is an important hydraulic engineering measure for human utilization and management of water resources. Performance evaluation of artificial neural network. How to tune this variable and what is the impact of this one on the reservoir. Stochastic reservoir simulation using neural networks. The basic element of a backpropagation neural network is the processing node. Pdf artificial intelligence application in reservoir characterization.
Fuzzy neural network modeling of reservoir operation. Nsl is an objectoriented language offering objectoriented protocols applicable to all levels of neural simulation. Optimal operation of multireservoir system using dynamic. Auckland university of technology, auckland, new zealand fields of specialization. Reservoir modeling uses all available information which includes at a minimum logs data, and fluid and rock properties. Many spiking neural network frameworks exist, each with a unique set of use cases. The simulation model itself can be a useful tool in allocating effort and expense in determination of reservoir fluid and rock data. Reservoir computing is a framework for computation derived from recurrent neural network theory that maps input signals into higher dimensional computational spaces through the dynamics of a fixed, nonlinear system called a reservoir. Fundamentals of higher order neural networks for modeling and.
In this work an adaptive strategy is used to build fast proxy models for the npv, and then optimizing the proxy model using a pattern search algorithm. What is the realitionship between deep learning methods. In this study, a feedforward neural network with backpropagation learning algorithm was used. In this context, we have developed an artificial neural network based model to predict macroporosity of sandstones. Recurrent networks o er more biological plausibility and theoretical computing power, but exacerbate the aws of feedforward nets. Prediction of reservoir properties by monte carlo simulation. Neural computations such as artificial neural networks ann have. The book describes how to utilize machinelearningbased algorithmic protocols to reduce large quantities of difficulttounderstand data down to actionable, tractable quantities. Nonlinear survival regression using artificial neural network. Fundamentals of higher order neural networks for modeling and simulation. Optimal operation of multireservoir system using dynamic programming and neural network h.
Generate field productivity maps by integrating reservoir simulation data with analytics production analysis access all subsurface data pertaining to each field and cluster information. Reservoir properties from well logs using neural networks. Lens the light, efficient neural network simulator 2. Shahabs book mohaghegh, datadriven reservoir modeling, 2017, the topdown model. Simulating reservoir operation using a recurrent neural. Optimal operation of multi reservoir system using dynamic programming and neural network h. The arti cial neural network paradigm is a major area of research within a. Monte carlo simulation and artificial neural network are applied to two areas for predicting the distribution of reservoirs. After the input signal is fed into the reservoir, which is treated as a black box, a simple readout mechanism is trained to read the state of the reservoir. To explore the application of a deep learning algorithm on the field of reservoir operations, a recurrent neural network rnn, long shortterm memory lstm, and. The proxy model is generated by training an arti cial neural network ann. These rnns are useful because they have superior theoretical computational power. In this chapter, the authors provide fundamental principles of higher order neural units honus and higher order neural networks honns for modeling and.
Basically both are neural networks but one which recurrently executing its layers is reservoir computing while the one with feed forward approach is simple neural network. Applying machine learning algorithms to oil reservoir production optimization mehrdad gharib shirangi stanford university. A spiking neural network considers temporal information. The present study aims at the application of the hybrid model, which consists of artificial neural network and fuzzy logic in the reservoir operating policy during critical periods. Reservoir parameter estimation using a hybrid neural network. Reservoir characterization from 3d seismic data using. Neural computations such as artificial neural networks ann have aroused considerable interest over the last decades, and are being successfully applied across a wide range of problem areas, to domains as diverse as medicine, finance, engineering, geology and physics, to problems of complex dynamics and complex behaviour prediction, classification or control. In essence the neuron is simply a model for a multivariate function whose input variables are weighted by a weight vector. The idea is that neurons in the snn do not fire at each propagation cycle as it happens with typical multilayer perceptron networks, but rather fire only when a membrane. Soft computing for reservoir characterization and modeling.
1499 1117 775 112 391 884 797 254 202 137 516 102 826 535 394 21 1501 901 413 109 493 581 1265 127 1075 432 862 752 165 638 1415 696 962 255 1228 1443 1256 1159 1321 105 919 346 1019 970