CN113589363B - Novel oil gas prediction method integrating artificial neural network and geostatistics - Google Patents
Novel oil gas prediction method integrating artificial neural network and geostatistics Download PDFInfo
- Publication number
- CN113589363B CN113589363B CN202010370977.8A CN202010370977A CN113589363B CN 113589363 B CN113589363 B CN 113589363B CN 202010370977 A CN202010370977 A CN 202010370977A CN 113589363 B CN113589363 B CN 113589363B
- Authority
- CN
- China
- Prior art keywords
- neural network
- artificial neural
- reservoir
- data
- logging
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000012549 training Methods 0.000 claims abstract description 9
- 238000012935 Averaging Methods 0.000 claims abstract description 3
- 238000010219 correlation analysis Methods 0.000 claims abstract description 3
- 230000000704 physical effect Effects 0.000 claims description 14
- 239000004215 Carbon black (E152) Substances 0.000 claims description 11
- 229930195733 hydrocarbon Natural products 0.000 claims description 11
- 150000002430 hydrocarbons Chemical class 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000007619 statistical method Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000011282 treatment Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 abstract description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 4
- 238000012545 processing Methods 0.000 description 5
- 230000002195 synergetic effect Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000004927 fusion Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 125000001183 hydrocarbyl group Chemical group 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 208000035126 Facies Diseases 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. analysis, for interpretation, for correction
- G01V1/282—Application of seismic models, synthetic seismograms
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. analysis, for interpretation, for correction
- G01V1/30—Analysis
- G01V1/306—Analysis for determining physical properties of the subsurface, e.g. impedance, porosity or attenuation profiles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/40—Seismology; Seismic or acoustic prospecting or detecting specially adapted for well-logging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V2210/00—Details of seismic processing or analysis
- G01V2210/60—Analysis
- G01V2210/66—Subsurface modeling
- G01V2210/665—Subsurface modeling using geostatistical modeling
- G01V2210/6652—Kriging
Abstract
The invention provides a new oil gas prediction method integrating an artificial neural network and geostatistics, which comprises the following steps: step 1, averaging intervals of earthquake and logging data; step 2, kendall correlation analysis of earthquake and logging data is carried out; step 3, training an artificial neural network at the well point; step 4, carrying out seismic logging combined geological statistics to obtain three-dimensional distribution of physical parameters of the reservoir; step 5, training a second artificial neural network at the well point; and 6, carrying out three-dimensional prediction of oil gas. The novel oil gas prediction method integrating the artificial neural network and the geostatistics combines the artificial neural network method and the geostatistical method, can process a large amount of data from different academic sources in a highly nonlinear mode, can integrate various data information, and fully plays respective advantages of the artificial intelligence technology and the geostatistical technology.
Description
Technical Field
The invention relates to the technical field of seismic data processing and interpretation, in particular to a novel oil gas prediction method integrating an artificial neural network and geostatistics.
Background
In the field of petroleum exploration and development, there are several methods to integrate data of different disciplines, and a detailed reservoir model is built to predict oil and gas. The data can be divided into geological data, drilling and logging data, oil and gas production data and seismic data according to discipline types, wherein the seismic data is a vital information source in an exploration stage and a development stage, because the seismic data not only has a large-area three-dimensional covering capacity, but also has a dense grid density. In order to predict and analyze the reservoir parameter distribution of a beneficial zone, a reliable relationship needs to be established between reservoir properties and seismic data. Conventionally, reservoir physical parameters can be deduced from seismic data using deterministic petrophysical analysis techniques as well as statistical analysis techniques. However, artificial intelligence methods are a new option beyond traditional methods, such as artificial neural network methods, in making three-dimensional predictions of reservoir parameters. Artificial intelligence methods are capable of processing multiple types of data in a highly non-linear manner even though the inherent links between data sources do not appear to be very close. Because the artificial neural network approach is not limited to a particular discipline, data from different discipline sources may be processed, such as associating sedimentary and production data with geological and geophysical data. This greatly increases the ability to handle practical problems, and is more flexible when three-dimensionally predicting reservoir parameters such as sedimentary facies, permeability, porosity, and hydrocarbon saturation, which often do not have a direct link to seismic data, and typically require analysis of many seismic attributes to do so. Geostatistics is one of the most important methods in three-dimensional prediction of reservoir parameters, which follow statistical laws when data is utilized, and can give a spatial distribution of the parameters. Therefore, the advantages of the artificial neural network method and the geostatistical method can be developed by combining the two methods, the advantages of the artificial neural network are that the data-driven background can process a large amount of data from different departments in a highly nonlinear manner, even if the connection between the data is difficult to clearly describe, and the traditional method is difficult to go on without clear connection between the data.
In application number: 201710388429.6, in a chinese patent application, relates to a method for acquiring log curve data of an oil and gas well, and in particular to a method for predicting log curve based on a radial basis function neural network model, which comprises an old well to be predicted and at least one new well of the same oil and gas field as the old well, wherein a plurality of log curves of the known new well are obtained, an artificial neural network technique is used to build a prediction model, and then the prediction model and the log curve of the known new well are used to predict the log curve of the old well lacking the log curve. However, this technique only predicts well point locations, and of course only uses log data, and it is not practical to want to make three-dimensional predictions at locations where no well is drilled. At this time, the logging data and the seismic data are utilized simultaneously, and the method of comprehensively utilizing the artificial neural network and the geostatistics can embody stronger advantages.
Therefore, the invention discloses a novel oil gas prediction method integrating an artificial neural network and geostatistics, and solves the technical problems.
Disclosure of Invention
The invention aims to provide a novel method for oil gas prediction by using a geostatistical method to expand fusion attributes into a three-dimensional space and further fusion an artificial neural network for oil gas prediction and geostatistical.
The aim of the invention can be achieved by the following technical measures: the novel oil gas prediction method integrating the artificial neural network and the geostatistics comprises the following steps: step 1, averaging intervals of earthquake and logging data; step 2, performing Kendall correlation analysis of earthquake and logging data; step 3, training an artificial neural network at the well point; step 4, carrying out seismic logging combined geological statistics to obtain three-dimensional distribution of physical parameters of the reservoir; step 5, training a second artificial neural network at the well point; and 6, carrying out three-dimensional prediction of oil gas.
The aim of the invention can be achieved by the following technical measures:
in step 1, seismic attributes related to reservoir physical properties are extracted around the well, time-depth conversion is performed in a certain interval, an arithmetic average is obtained, and the same arithmetic average processing is performed on the well log data.
In step 2, statistical analysis of the logging data and the seismic attributes is performed by using Kendal-level correlation coefficients, and the seismic attributes closely related to the logging reservoir physical parameters are found out.
In step 3, these seismic attributes are input, an artificial neural network is trained at the well point, and output as reservoir physical parameters.
In step 4, the reservoir physical property parameters obtained by logging are used as hard data, the reservoir physical property parameters obtained by an artificial neural network are used as soft data, and three-dimensional calculation of the reservoir physical property parameters is performed by using a geostatistical method of synergetic kriging, so that three-dimensional distribution of various reservoir physical property parameters is obtained by calculation.
In step 5, training a second artificial neural network at the well point, inputting the second artificial neural network as three-dimensional reservoir physical property parameters, and outputting the second artificial neural network as the condition of oil and gas.
In step 6, a second artificial neural network is used to predict the three-dimensional spatial distribution of the hydrocarbon.
The novel oil gas prediction method integrating the artificial neural network and the geostatistics is established on the basis of integrating earthquake, well logging and geological data by the artificial neural network algorithm, and the integration attribute is expanded to a three-dimensional space by using the geostatistics method, so that oil gas prediction is performed. Firstly, utilizing a specific artificial neural network algorithm to fuse input earthquake, logging and geological data, and obtaining a new attribute related to oil gas based on a data driving technology. And then based on the obtained new attribute, carrying out three-dimensional spatial prediction by utilizing a geostatistical method of synergetic kriging so as to carry out oil and gas prediction. For oil exploration development, the method is a powerful tool for fusing various data information, and the advantages of the artificial intelligence technology and the geostatistical technology are fully exerted.
Drawings
FIG. 1 is a flow chart of an embodiment of a new method of hydrocarbon prediction incorporating artificial neural networks and geostatistics of the present invention;
FIG. 2 is a graph of typical seismic attributes versus logging parameters in accordance with an embodiment of the invention;
FIG. 3 is a schematic diagram of an artificial neural network for reservoir physical parameters and hydrocarbon prediction in accordance with an embodiment of the invention;
FIG. 4 is a schematic diagram of three-dimensional reservoir property parameter distribution obtained via geostatistical methods in accordance with one embodiment of the present invention;
FIG. 5 is a graph showing a three-dimensional distribution of oil and gas predicted by a combination of artificial neural network and geostatistical methods in accordance with one embodiment of the present invention.
Detailed Description
The foregoing and other objects, features and advantages of the invention will be apparent from the following more particular description of preferred embodiments, as illustrated in the accompanying drawings.
As shown in FIG. 1, FIG. 1 is a flow chart of the novel method for predicting oil gas by combining artificial neural network and geostatistics.
In step 101, seismic attributes related to reservoir physical properties are extracted around the well, time-depth conversion is performed in a certain interval, an arithmetic average is obtained, and the same arithmetic average process is performed on the well log data. This may highlight the geological features of the entire interval. The flow proceeds to step 102.
In step 102, statistical analysis of the log data and seismic attributes is performed using Kendall (one of the well-known three correlation coefficients, named Maur i ce Kendal l in statistics) rank correlation coefficients to find seismic attributes that are closely related to the physical parameters of the logging reservoir. The flow proceeds to step 103.
At step 103, these seismic attributes are input, an artificial neural network is trained at the well point, and output as reservoir physical parameters. The flow proceeds to step 104.
In step 104, the reservoir physical property parameters obtained by logging are used as hard data, the reservoir physical property parameters obtained by an artificial neural network are used as soft data, and three-dimensional calculation of the reservoir physical property parameters is performed by using a geostatistical method of synergetic kriging. By using the method, the three-dimensional distribution of various reservoir physical parameters can be calculated. This is a unique new way of fusion of seismic and logging information. The flow proceeds to step 105.
At step 105, a second artificial neural network is trained at the well point, input as three-dimensional reservoir physical parameters, and output as a hydrocarbon-bearing condition. The flow proceeds to step 106.
In step 106, a second artificial neural network is used to predict the three-dimensional spatial distribution of the hydrocarbon. The method is a brand new three-dimensional artificial neural network oil gas prediction method. The flow ends.
In one embodiment of the invention, FIG. 2 is a representative plot of seismic attributes versus logging parameters. The seismic attribute is an impedance attribute obtained through sparse pulse inversion, and the logging parameter is an acoustic logging speed curve. The seismic attribute input into the artificial neural network is a three-dimensional seismic attribute calculated based on three-dimensional seismic data, and here, seismic wave impedance data obtained by sparse pulse inversion are shown. In the seismic data processing stage, a three-dimensional depth migration processing technique is used. In the sparse pulse inversion process, the assistance of logging data is not used, so that the independence between the seismic attribute and the logging parameters is ensured. The log shown here is an acoustic logging speed profile, a typical reservoir physical parameter.
FIG. 3 is an artificial neural network for reservoir physical parameters and hydrocarbon predictions. In the (a) plot, the input layer is a seismic attribute (X1, X2, X3, X4, or more other seismic attributes), and the output layer is a reservoir physical parameter (L, which may represent an acoustic logging speed value, a porosity logging value, a resistivity logging value, an SP logging value, etc.); in the graph (b), the input layer is a reservoir physical property parameter (L1, L2, L3, L4, or more other reservoir physical property parameters), and the output layer is an oil-gas prediction result (O, representing the oil-gas content of each reservoir such as oil, gas, water, and dry layer). Figure 3 shows two artificial neural networks. One is to use the input seismic attribute to obtain reservoir physical parameters, the other is to use the input reservoir physical parameters to obtain oil and gas prediction results, and neither artificial neural network contains hidden layers. Although the two layers together can be a two-layer artificial neural network, the two layers are separated here because of the important step of inserting geostatistical computation in between.
FIG. 4 is a three-dimensional reservoir property parameter distribution (two-dimensional cross-sectional display) obtained via geostatistical methods. The reservoir physical parameter here is porosity. In fig. 4, a three-dimensional distribution (shown here in cross-section) of the physical reservoir parameters of impedance is obtained using a geostatistical method such as the synergistic kriging. In the collaborative kriging method, physical parameters of a logging reservoir are used as hard data, and physical parameters of the reservoir obtained by an artificial neural network are used as soft data. It can be seen that the three-dimensional distribution of reservoir physical parameters is more specific than using the logging data alone, and the results obtained are more consistent with the actual logging information and higher resolution than using the seismic data alone.
FIG. 5 is a three-dimensional plot of oil and gas predicted jointly via an artificial neural network and geostatistical methods. Only the distribution of hydrocarbon-bearing reservoirs is shown here, with non-reservoir, dry and aquifer treatments being transparentized. FIG. 5 shows the actual results of hydrocarbon prediction using artificial neural networks and geostatistics. The two methods are combined to exert respective advantages, the advantages of geostatistics are that point data are subjected to three-dimensional expansion, the advantages of an artificial neural network are that a data driving mechanism of the artificial neural network can process a large amount of data from different departments in a highly nonlinear mode, even if the connection between the data is difficult to describe clearly, and the traditional method is difficult to go on under the premise that the connection between the data is not clear.
Geostatistics is one of the most important methods in three-dimensional prediction of reservoir parameters, which follow statistical laws when data is utilized, and can give a spatial distribution of the parameters. According to the novel oil gas prediction method integrating the artificial neural network and the geostatistics, the artificial neural network method and the geostatistical method are combined, the advantages of the two methods can be brought into play, the advantages of the artificial neural network are that the data driving background of the artificial neural network can process a large amount of data from different academic sources in a highly nonlinear mode, even if the connection between the data is difficult to clearly describe, the traditional method is difficult to go on under the premise that the connection between the data is not clear.
Claims (3)
1. The novel oil gas prediction method integrating the artificial neural network and the geostatistics is characterized by comprising the following steps of:
step 1, averaging intervals of earthquake and logging data;
step 2, kendall correlation analysis of earthquake and logging data is carried out;
step 3, training an artificial neural network at the well point;
step 4, carrying out seismic logging combined geological statistics to obtain three-dimensional distribution of physical parameters of the reservoir;
step 5, training a second artificial neural network at the well point;
step 6, carrying out three-dimensional prediction of oil gas;
in step 1, seismic attributes related to reservoir physical properties are extracted around a well, arithmetic average values are obtained after time-depth conversion is carried out in a certain interval, and the same arithmetic average value obtaining treatment is carried out on logging data;
in step 2, statistical analysis of logging data and seismic attributes is performed by using Kendall grade correlation coefficients, and the seismic attributes closely related to logging reservoir physical parameters are found out;
in step 3, training an artificial neural network at the well point, inputting the artificial neural network as the seismic attribute closely related to the physical parameters of the logging reservoir, and outputting the artificial neural network as the physical parameters of the reservoir;
in step 5, training a second artificial neural network at the well point, inputting the second artificial neural network as three-dimensional reservoir physical property parameters, and outputting the second artificial neural network as the condition of oil and gas.
2. The new oil gas prediction method integrating an artificial neural network and geostatistics according to claim 1, wherein in step 4, reservoir physical parameters obtained by logging are used as hard data, reservoir physical parameters obtained by the artificial neural network are used as soft data, three-dimensional calculation of the reservoir physical parameters is performed by using a collaborative kriging geostatistical method, and three-dimensional distribution of various reservoir physical parameters is calculated.
3. The new method for predicting hydrocarbon by combining artificial neural network and geostatistics according to claim 1, wherein in step 6, the second artificial neural network is used to predict the three-dimensional spatial distribution of hydrocarbon.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010370977.8A CN113589363B (en) | 2020-04-30 | 2020-04-30 | Novel oil gas prediction method integrating artificial neural network and geostatistics |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010370977.8A CN113589363B (en) | 2020-04-30 | 2020-04-30 | Novel oil gas prediction method integrating artificial neural network and geostatistics |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113589363A CN113589363A (en) | 2021-11-02 |
CN113589363B true CN113589363B (en) | 2024-03-19 |
Family
ID=78238031
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010370977.8A Active CN113589363B (en) | 2020-04-30 | 2020-04-30 | Novel oil gas prediction method integrating artificial neural network and geostatistics |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113589363B (en) |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102884448A (en) * | 2010-05-06 | 2013-01-16 | 埃克森美孚上游研究公司 | Windowed statistical analysis for anomaly detection in geophysical datasets |
CN103376468A (en) * | 2012-04-18 | 2013-10-30 | 中国石油化工股份有限公司 | Reservoir parameter quantitative characterization method based on neural network function approximation algorithm |
CN104635265A (en) * | 2014-12-31 | 2015-05-20 | 中国石油天然气集团公司 | Controllable neural network-type method for predicting reservoir permeability |
CN104914467A (en) * | 2015-05-22 | 2015-09-16 | 中国石油天然气股份有限公司 | Classification model channel extracting seismic facies clustering analysis method |
CN105005079A (en) * | 2015-07-14 | 2015-10-28 | 北京博达瑞恒科技有限公司 | Well logging curve inversion method |
CN106842301A (en) * | 2016-12-22 | 2017-06-13 | 中国石油天然气股份有限公司 | The quantitative judge and Forecasting Methodology of a kind of tuffaceous sandstone Favorable Reservoir |
CN106873033A (en) * | 2017-03-13 | 2017-06-20 | 中国海洋石油总公司 | A kind of method of many attribute earthquake information fusion FRACTURE PREDICTIONs based on neutral net |
CN106991509A (en) * | 2017-05-27 | 2017-07-28 | 重庆科技学院 | Log Forecasting Methodology based on radial basis function neural network model |
CN109799533A (en) * | 2018-12-28 | 2019-05-24 | 中国石油化工股份有限公司 | A kind of method for predicting reservoir based on bidirectional circulating neural network |
WO2019174366A1 (en) * | 2018-03-12 | 2019-09-19 | 山东科技大学 | Seismic data-based oil and gas reservoir distribution-oriented convolutional neural network learning and predicting method |
RU2717740C1 (en) * | 2019-05-28 | 2020-03-25 | Федеральное государственное бюджетное учреждение науки Институт физики Земли им. О.Ю. Шмидта Российской академии наук | Open porosity prediction method in the space between wells |
CN110954948A (en) * | 2018-09-27 | 2020-04-03 | 中国石油化工股份有限公司 | Physical property parameter inversion method and system for rock physical constraint reservoir |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
MX2015005627A (en) * | 2012-12-05 | 2016-02-03 | Landmark Graphics Corp | Systems and methods for 3d seismic data depth conversion utilizing artificial neural networks. |
-
2020
- 2020-04-30 CN CN202010370977.8A patent/CN113589363B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102884448A (en) * | 2010-05-06 | 2013-01-16 | 埃克森美孚上游研究公司 | Windowed statistical analysis for anomaly detection in geophysical datasets |
CN103376468A (en) * | 2012-04-18 | 2013-10-30 | 中国石油化工股份有限公司 | Reservoir parameter quantitative characterization method based on neural network function approximation algorithm |
CN104635265A (en) * | 2014-12-31 | 2015-05-20 | 中国石油天然气集团公司 | Controllable neural network-type method for predicting reservoir permeability |
CN104914467A (en) * | 2015-05-22 | 2015-09-16 | 中国石油天然气股份有限公司 | Classification model channel extracting seismic facies clustering analysis method |
CN105005079A (en) * | 2015-07-14 | 2015-10-28 | 北京博达瑞恒科技有限公司 | Well logging curve inversion method |
CN106842301A (en) * | 2016-12-22 | 2017-06-13 | 中国石油天然气股份有限公司 | The quantitative judge and Forecasting Methodology of a kind of tuffaceous sandstone Favorable Reservoir |
CN106873033A (en) * | 2017-03-13 | 2017-06-20 | 中国海洋石油总公司 | A kind of method of many attribute earthquake information fusion FRACTURE PREDICTIONs based on neutral net |
CN106991509A (en) * | 2017-05-27 | 2017-07-28 | 重庆科技学院 | Log Forecasting Methodology based on radial basis function neural network model |
WO2019174366A1 (en) * | 2018-03-12 | 2019-09-19 | 山东科技大学 | Seismic data-based oil and gas reservoir distribution-oriented convolutional neural network learning and predicting method |
CN110954948A (en) * | 2018-09-27 | 2020-04-03 | 中国石油化工股份有限公司 | Physical property parameter inversion method and system for rock physical constraint reservoir |
CN109799533A (en) * | 2018-12-28 | 2019-05-24 | 中国石油化工股份有限公司 | A kind of method for predicting reservoir based on bidirectional circulating neural network |
RU2717740C1 (en) * | 2019-05-28 | 2020-03-25 | Федеральное государственное бюджетное учреждение науки Институт физики Земли им. О.Ю. Шмидта Российской академии наук | Open porosity prediction method in the space between wells |
Non-Patent Citations (2)
Title |
---|
《测井约束与神经网络联合反演储层预测技术》;余为维 等;《地球物理学进展》;第31卷(第5期);第2232-2238页 * |
《用神经网络和地质统计学综合多元信息进行储层预测》;李东安 等;《石油与天然气地质》;第31卷(第4期);第493-503页 * |
Also Published As
Publication number | Publication date |
---|---|
CN113589363A (en) | 2021-11-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Rajabi et al. | Intelligent approaches for prediction of compressional, shear and Stoneley wave velocities from conventional well log data: A case study from the Sarvak carbonate reservoir in the Abadan Plain (Southwestern Iran) | |
El Ouahed et al. | Application of artificial intelligence to characterize naturally fractured zones in Hassi Messaoud Oil Field, Algeria | |
NO340044B1 (en) | Procedure for creating facies probability cubes based on geological interpretation | |
CN105005079B (en) | A kind of well log inversion method | |
CN103389513A (en) | Method for increasing seismic data resolution by applying sonic logging information constraint inversion | |
Fegh et al. | Permeability prediction and construction of 3D geological model: application of neural networks and stochastic approaches in an Iranian gas reservoir | |
Sarkheil et al. | Fractures distribution modeling using fractal and multi-fractal–neural network analysis in Tabnak hydrocarbon field, Fars, Iran | |
Maschio et al. | A framework to integrate history matching and geostatistical modeling using genetic algorithm and direct search methods | |
Tariq et al. | Development of new correlation of unconfined compressive strength for carbonate reservoir using artificial intelligence techniques | |
Ouadfeul et al. | Shale gas reservoirs characterization using neural network | |
Hadavand et al. | A practical methodology for integration of 4D seismic in steam-assisted-gravity-drainage reservoir characterization | |
Cranganu et al. | Using Gene Expression Programming to estimate sonic log distributions based on the natural gamma ray and deep resistivity logs: A case study from the Anadarko Basin, Oklahoma | |
Newgord et al. | Bakken well performance predicted from shale capacity | |
Sun et al. | Structure of an artificial-intelligence-assisted reservoir characterization and field development protocol | |
CN113589363B (en) | Novel oil gas prediction method integrating artificial neural network and geostatistics | |
Djebbas et al. | Integrating hydraulic flow unit concept and adaptive neuro-fuzzy inference system to accurately estimate permeability in heterogeneous reservoirs: Case study Sif Fatima oilfield, southern Algeria | |
Samimi et al. | SENSITIVITY & UNCERTAINTY ANALYSIS OF ORIGINAL OIL-IN-PLACE IN CARBONATE RESERVOIR MODELING, A CASE STUDY. | |
Zellou et al. | Integrated fractured reservoir characterization using neural networks and fuzzy logic: three case studies | |
Kuroda et al. | Analysis of porosity, stratigraphy, and structural delineation of a Brazilian carbonate field by machine learning techniques: A case study | |
Rezaee et al. | Shale gas rock properties prediction using artificial neural network technique and multi regression analysis, an example from a North American shale gas reservoir | |
Isaiah et al. | Performing reservoir simulation with Neural Network enhanced data | |
Schiozer et al. | Integration of history matching and uncertainty analysis | |
Hou et al. | Estimation of reservoir porosity using probabilistic neural network and seismic attributes | |
Boisvert et al. | A methodology to construct training images for vein-type deposits | |
Kazemi et al. | Optimal parameter updating in assisted history matching using streamlines as a guide |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |