Artificial intelligence and in particular artificial neural networks ann. Pdf artificial neural networks for predicting petroleum quality. For multireservoir operating rules, a simulationbased neural network model is developed in this study. Recurrent networks o er more biological plausibility and theoretical computing power, but exacerbate the aws of feedforward nets. In the suggested model, multi reservoir operating rules are derived using a neural network from the results of simulation. Simulating reservoir operation using a recurrent neural. Artificial neural networks learn the nature of the dependency between input and output variables. Available well logs and cores were used as inputs to the hybrid model. In this paper we propose an empirical analysis of deep recurrent neural networks rnns with stacked layers. 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. The reservoir is an important hydraulic engineering measure for human utilization and management of water resources. Abstract the use of artificial neural networks ann for reservoir analysis now makes it possible to predict important reservoir properties from combinations of data such as well logs, production data, seismic data, etc. A sequence of 25 normalized 5 min rainfalls was applied as inputs to predict the runoff. Mohaghegh 2000 noted pattern recognition as one of the neural networks strengths.
Read the latest articles of journal of petroleum science and engineering at, elseviers. While the larger chapters should provide profound insight into a paradigm of neural networks e. Each link has a weight, which determines the strength of one nodes influence on another. Such approach requires independent programming to implements 4d reservoir modeling systems and thus introduces a new research area with great development potential. Deltav neural is easy to understand and use, allowing process engineers to produce extremely accurate results even without prior knowledge of neural network theory. 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. In the suggested model, multireservoir operating rules are derived using a neural network from the results of simulation. Machine learning in reservoir production simulation and. 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. Machine learning applied to 3d reservoir simulation marco a. The available porosity and permeability data needed to build a reservoir simulation model are old and sparse. Softcomputingforreservoircharacterizationandmodeling. The architecture of the artificial neural network that is used in gros. Location of the study area and the rain gauge stations network.
Machine learning in reservoir production simulation and forecast. Reservoir computing with untrained convolutional neural. Ebook kalman filtering and neural networks as pdf download. It contains stateoftheart techniques to be applied in reservoir geophysics, well logging, reservoir geology, and reservoir engineering. Additionally, a reasonable and effective reservoir operating plan is essential for realizing reservoir function.
Shahabs book mohaghegh, datadriven reservoir modeling, 2017, the topdown model. An artificial neural network consists of a collection of simulated neurons. Neural networkbased simulationoptimization model for. The most common formulation used in reservoir simulation is the. The operation of the network is illustrated with two simple onedimensional examples which can be followed through with hand calculations to give an insight into the operation of the network. Mohaghegh 2000 noted pattern recognition as one of the neural network s strengths. Reservoir systems operation model using simulation and. Machine learning models to support reservoir production optimization. An introduction naveen kuppuswamy, phd candidate, a. Application of machine learning and artificial intelligence in. Soft computing for reservoir characterization and modeling. Such tools offer the user to obtain precise simulations of a given computational paradigm, as well as publishable. Stateoftheart coverage of kalman filter methods for the design of neural networks this selfcontained book consists of seven chapters by expert contributors that discuss kalman filtering as applied to the training and use of neural networks. Spe member price usd 120 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.
Artificial neural network for 4d reservoir modeling system. Predicting reservoir water level using artificial neural network. Machine learning applied to 3d reservoir simulation. Geochemical equilibrium determination using an artificial neural network in compositional reservoir flow simulation. Monte carlo simulation and artificial neural network are applied to two areas for predicting the distribution of reservoirs. We develop a proxy model based on deep learning methods to accel erate the simulations. Neural networks can discover highly complex relationships between several variables that are presented to the network. We have demonstrated the benefits of committee neural networks where predictions are redundantly combined. A neural net can be learned to collect multiple point statistics.
Physicsbased models and data models introduction neural computations such as artificial neural networks ann have aroused considerable interest over the last decades e. Graupe, 2007, and are being successfully applied across. For developing the ann models, three alternative networks i. A new approach to reservoir characterization using deep. Abstract a combined approach of a dynamic programming algorithm and artificial. Reservoir properties from well logs using neural networks. In the algorithm, a few simulation runs of different reservoir realizations are first made using 3level fractional factorial design. Neural networks is the archival journal of the worlds three oldest neural modeling societies. Simulation of petroleum reservoir performance refers to the construction and operation of a model whose behavior assumes the appearance of actual reservoir behavior. Data driven reservoir modeling, also known as topdown model tdm, is an alternative to the.
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. A subscription to the journal is included with membership in each of these societies. Reservoir computing, recurrent neural network learning architectures, agent architectures, machine learning applications. 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. A reservoir computing system consists of a reservoir part represented as a sparsely connected recurrent neural network and a readout part represented as a simple regression model. Saptono 35 mapping the gas column in an aquifer gas. Those of you who are up for learning by doing andor have. Hjelmfelt and wang 1993ac developed a neural network based on the unit hydrograph theory. Artificial neural network and inverse solution method for. Pdf a neural network based general reservoir operation scheme. This paper presents an artificial neural network ann approach for forecasting of reservoir water level using ten daily data of inflow, water level and release. Reservoir parameter estimation using a hybrid neural network.
This paper forms the second part of the series on application of arti. Seismic characterization prediction of reservoir properties by monte carlo simulation and artificial neural network in the exploration stage k. 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. A neural network approach to geostatistical simulation. Multiple linear regression and artificial neural networks. A neural network based general reservoir operation scheme. To explore the application of a deep learning algorithm on the field of reservoir operations, a recurrent neural network rnn, long shortterm memory. Performing reservoir simulation with neural network enhanced data. Both models offer avenues for predicting reservoir capacity at gauged sites without the expense of timeseries based simulation alternatives. Hou 15 application of neural networks in determining petrophysical properties from seismic survey b. Then, a suitable neural network architecture is selected and trained using input and. Although the traditional approach to the subject is almost always linear, this.
Deep neural networks predicting oil movement in a development unit. Optimal operation of multi reservoir system using dynamic programming and neural network h. This model was then used to predict porosity and permeability for the reservoir and these values were then included in a reservoir simulation model. These optimizations are very demanding computationally due. Hydrologic applications by the asce task committee on application of arti. Falguni parekh2 pg student, water resources engineering and management institute, faculty of technology and engineering, the maharaja sayajirao university of baroda. Basic applied reservoir simulation, textbook series request pdf. We employed matlabs neural network fitting toolbox to train a proxy neural network model. Application of artificial neural networks for calibration of.
Optimal operation of multireservoir system using dynamic. Highly inspired from natural computing in the brain and recent advances in neurosciences, they derive their strength and interest from an ac. Datadriven reservoir modeling society of petroleum engineers. Professor shahab mohaghegh, being one of the most innovative and experienced thought leaders in the field of datadriven modeling in the upstream, has written a comprehensive and readable book that finally puts to bed the persistent complaints in the industry. Performing reservoir simulation with neural network. Multiple linear regression and artificial neural networks models for generalized reservoir storageyieldreliability function for reservoir planning. Cascade, elman and feedforward back propagation were evaluated. Reservoir systems operation model using simulation and neural. 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. Optimal operation of multireservoir system using dynamic programming and neural network h. The online version of the book is now complete and will remain available online for free. This textbook is only one of the tools to teach the reservoir simulation techniques at the university and in post graduate courses efficiently. The book describes how to utilize machinelearningbased algorithmic protocols to reduce large quantities of difficulttounderstand data down to. Predicting reservoir water level using artificial neural network shilpi rani1, dr.
Applying machine learning algorithms to oil reservoir. Accelerating physicsbased simulations using neural network. A schematic diagram of this process is shown in figure 1. Application of artificial neural networks for reservoir. The training of the neural network is done using a supervised learning approach with the back propagation algorithm. For multi reservoir operating rules, a simulation based neural network model is developed in this study. Application of artificial neural networks for calibration. The readers have to work with a sophisticated reservoir simu lator to deepen their theoretical knowledge too. Mathematical model computer codes numerical model physical model figure 1.
In quantitative geological modeling with an artificial neural network approach, time information can be considered as input variable to better describe dynamic evolution patterns of reservoir parameters. Reservoir computing has attracted much attention for its easy training process as well as its ability to deal with temporal data. Caudill presented a comprehensive description of neural networks in a series of papers caudill, 1987, 1988, 1989. In many cases, complex simulation models are available, but direct incorporation of them into an optimization framework is computationally prohibitive. Reservoir simulation process reservoir simulation is briefly. Modeling and simulation, computational systems biology, bioinformatics. Journal of petroleum science and engineering neural network. Stochastic reservoir simulation using neural networks.
The book inspires geoscientists entrenched in first principles and engineering concepts to think. Pdf deep neural networks predicting oil movement in a. Introduction webster defines simulate as to assume the appearance of without reality. The performance is analyzed using a simulation model for the. International journal of modeling and simulation for the petroleum industry, 9 1. Cardoso 1 introduction the optimization of subsurface. Pdf a neural network based general reservoir operation. Reduced order reservoir simulation with neuralnetwork based hybrid model. Prediction of reservoir properties by monte carlo simulation. Falguni parekh2 pg student, water resources engineering and management institute, faculty of technology and engineering, the maharaja sayajirao university of baroda, samiala391410, vadodara, gujarat, india1 offg. The paper gives a brief overview of neural networks and describes a feedforward, backpropagation network for geostatistical simulation. Machine learning in reservoir production simulation and forecast serge a. 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.
Oil reservoir simulation, artificial neural networks. Reservoir computing emerges as a solution, o ering a generic. A critical analysis claudio gallicchio and alessio micheli department of computer science, university of pisa largo bruno pontecorvo 3 56127 pisa, italy abstract. For porosity prediction we have made a study initially with a single neural network and then by the cm approach. Deltav neural gives you a practical way to create virtual sensors for measurements previously available only through the use of lab analysis or online analyzers. 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. If a random recurrent neural network rnn possesses certain algebraic properties, training only a linear readout from it is often sufficient to.
This allowed direct simulation of the trained neural network to obtain an updated reservoir parameters. Preliminary concepts by the asce task committee on application of arti. It can be simply considered as the process of mimicking the behavior of fluid flow in a. Stochastic reservoir simulation using neural networks trained on outcrop data. Reservoir modeling uses all available information which includes at a minimum logs data, and fluid and rock properties. This course has a supplemental book located in our spe bookstore entitled datadriven reservoir modeling.
Can we upscale original problem of reservoir simulation to the level of functional dependence between observed outputs e. 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. 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. In this twopart series, the writers investigate the role of arti. Reduced order reservoir simulation with neuralnetwork based. A neural network approach to geostatistical simulation pdf.
Performing reservoir simulation with neural network enhanced. This paper considers the development of a computationally fast model for simulation of. It introduces the basic concepts of soft computing techniques including neural networks, fuzzy logic and evolutionary computing applied to reservoir characterization. Terekhov neurok techsoft, llc, moscow, russia email. Datadriven reservoir modeling reservoir analytics is defined as the. Applying machine learning algorithms to oil reservoir production optimization mehrdad gharib shirangi stanford university abstract in well control optimization for an oil reservoir described by a set of geological models, the expectation of net present value npv is optimized. Levenbergmarquardt training algorithm was used for training a neural network architecture with one hidden layer and thirty hidden neurons. The arti cial neural network paradigm is a major area of research within a. A neural network is characterized by its architecture that represents the pattern of connection between nodes, its method of determining the connection weights, and the activation function fausett 1994. Reservoir parameter estimation using a hybrid neural. The deep learning textbook can now be ordered on amazon. Reservoir computing by felix grezes a dissertation submitted to the graduate faculty in computer science in partial ful llment of the requirements for the degree of doctor of philosophy, the city university of new york.
Each neuron is a node which is connected to other nodes via links that correspond to biological axonsynapsedendrite connections. Development and application of reservoir models and. This study opened up several possibilities for rainfallrunoff application using neural networks. For instances, permeability prediction with artificial neural network modeling from well logs 2, reservoir parameter estimation using a hybrid neural network 3, application of fuzzy logic and. Pdf geochemical equilibrium determination using an. This paper presents a study aimed at forecasting water level of reservoir using neural network approaches. Predicting reservoir water level using artificial neural. 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. Optimal design of the neural network modules and the size of the training set. Current state of reservoir simulation and modeling of shale. The better solutions found by the ga were tested with. Auckland university of technology, auckland, new zealand fields of specialization. Wo2009032220a1 artificial neural network models for.
1600 358 563 607 766 195 735 1278 594 590 284 134 1610 1359 468 1284 1622 417 1060 415 983 488 1391 274 663 863 1568 7 461 1263 1337 138 655 718 1331 1410 1298 762 735