CN116433059A - Intelligent evaluation method and device for shale oil dessert - Google Patents
Intelligent evaluation method and device for shale oil dessert Download PDFInfo
- Publication number
- CN116433059A CN116433059A CN202111677300.XA CN202111677300A CN116433059A CN 116433059 A CN116433059 A CN 116433059A CN 202111677300 A CN202111677300 A CN 202111677300A CN 116433059 A CN116433059 A CN 116433059A
- Authority
- CN
- China
- Prior art keywords
- shale oil
- dessert
- evaluation model
- type
- seismic
- 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.)
- Pending
Links
- 239000003079 shale oil Substances 0.000 title claims abstract description 224
- 235000021185 dessert Nutrition 0.000 title claims abstract description 215
- 238000011156 evaluation Methods 0.000 title claims abstract description 54
- 238000013210 evaluation model Methods 0.000 claims abstract description 87
- 238000012549 training Methods 0.000 claims abstract description 72
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 42
- 235000011850 desserts Nutrition 0.000 claims abstract description 20
- 238000000034 method Methods 0.000 claims abstract description 18
- 238000010801 machine learning Methods 0.000 claims abstract description 17
- 238000012360 testing method Methods 0.000 claims abstract description 13
- 238000004590 computer program Methods 0.000 claims description 26
- 230000006870 function Effects 0.000 claims description 19
- 238000007781 pre-processing Methods 0.000 claims description 10
- 239000004576 sand Substances 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 8
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims description 7
- 229910052799 carbon Inorganic materials 0.000 claims description 7
- 230000015572 biosynthetic process Effects 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000003066 decision tree Methods 0.000 claims description 4
- 238000007477 logistic regression Methods 0.000 claims description 4
- 238000007637 random forest analysis Methods 0.000 claims description 4
- 238000012706 support-vector machine Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 3
- 239000010410 layer Substances 0.000 description 39
- 238000010586 diagram Methods 0.000 description 22
- 239000011435 rock Substances 0.000 description 7
- 239000004215 Carbon black (E152) Substances 0.000 description 4
- 238000009826 distribution Methods 0.000 description 4
- 229930195733 hydrocarbon Natural products 0.000 description 4
- 150000002430 hydrocarbons Chemical class 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000004927 fusion Effects 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 239000011148 porous material Substances 0.000 description 2
- BVKZGUZCCUSVTD-UHFFFAOYSA-L Carbonate Chemical compound [O-]C([O-])=O BVKZGUZCCUSVTD-UHFFFAOYSA-L 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 239000011229 interlayer Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Mining
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The invention discloses an intelligent evaluation method and device for shale oil desserts, wherein the method comprises the following steps: dividing dessert types of shale oil layer sections in the well according to known logging interpretation results and oil testing conditions to form dessert type labels; extracting a parawell seismic channel containing dessert type labels, and calculating the seismic attribute of a shale oil layer section to form a training data set; constructing a shale oil dessert evaluation model by using a machine learning algorithm, wherein the input of the shale oil dessert evaluation model is the seismic attribute of a shale oil interval, and the output is the dessert type of the shale oil interval; training the shale oil dessert evaluation model according to the training data set to obtain a trained shale oil dessert evaluation model; inputting the seismic attribute of the untagged seismic trace shale oil layer section into a trained shale oil dessert evaluation model, and predicting the dessert type of the untagged seismic trace shale oil layer section. The method and the device can improve the accuracy of the predicted result, reduce the difference of the predicted result and improve the operation efficiency.
Description
Technical Field
The invention relates to the technical field of geophysical oil and gas exploration, in particular to an intelligent evaluation method and device for shale oil desserts.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
As hydrocarbon exploration continues deeper, conventional hydrocarbon resource exploration has gradually turned to unconventional hydrocarbon exploration. At present, shale oil dessert evaluation mainly focuses on: hydrocarbon source rock quality, reservoir dessert quality, engineered dessert quality, and source rock characteristics (thickness, total organic carbon), reservoir lithology, physical properties (pores, fissures), oleaginous properties, brittleness, ground stress characteristics. Shale oil is classified into clastic rock type, carbonate rock type and mixed accumulation type, and the key parameters of geophysical evaluation of each type are different.
The existing shale oil dessert evaluation method comprises two types of methods, namely parameter comprehensive evaluation and model comprehensive evaluation. The parameter comprehensive evaluation method mainly comprises the steps of superposing all evaluation parameters into a graph, taking intersections of regional distribution of all evaluation parameter standards, and determining the distribution of shale oil dessert areas by combining the continuous distribution area and economy of the regions. The model comprehensive evaluation method is that according to shale oil layer comprehensive evaluation parameter standard and drilling oil test condition, the weighting coefficient of each single parameter of the evaluation area is calculated, then the dessert comprehensive evaluation coefficient is calculated by weighting accumulation, and the higher the comprehensive evaluation coefficient is, the higher the evaluation level of the dessert area is.
However, the above two types of methods have the following disadvantages: the accuracy of the prediction result is low, the difference of the prediction result is large, and the operation efficiency is low.
Disclosure of Invention
The embodiment of the invention provides an intelligent evaluation method for shale oil desserts, which is used for improving the accuracy of predicted results, reducing the difference of the predicted results and improving the operation efficiency, and comprises the following steps:
dividing dessert types of shale oil layer sections in the well according to known logging interpretation results and oil testing conditions to form dessert type labels;
extracting a parawell seismic channel containing dessert type labels, and calculating the seismic attribute of a shale oil layer section to form a training data set;
constructing a shale oil dessert evaluation model by using a machine learning algorithm, wherein the input of the shale oil dessert evaluation model is the seismic attribute of a shale oil interval, and the output is the dessert type of the shale oil interval;
training the shale oil dessert evaluation model according to the training data set to obtain a trained shale oil dessert evaluation model;
inputting the seismic attribute of the untagged seismic trace shale oil layer section into a trained shale oil dessert evaluation model, and predicting the dessert type of the untagged seismic trace shale oil layer section.
The embodiment of the invention also provides an intelligent evaluation device for shale oil desserts, which is used for improving the accuracy of the predicted result, reducing the difference of the predicted result and improving the operation efficiency, and comprises the following steps:
the dessert type label forming module is used for dividing the dessert type of the shale oil layer section in the well according to the known logging interpretation result and the oil test condition to form a dessert type label;
the training data set forming module is used for extracting a parawell seismic channel containing dessert type labels, calculating the seismic attribute of the shale oil layer section and forming a training data set;
the construction module is used for constructing a shale oil dessert evaluation model by utilizing a machine learning algorithm, wherein the input of the shale oil dessert evaluation model is the seismic attribute of a shale oil layer section, and the output is the dessert type of the shale oil layer section;
the training module is used for training the shale oil dessert evaluation model according to the training data set to obtain a trained shale oil dessert evaluation model;
the prediction module is used for inputting the seismic attribute of the untagged seismic trace shale oil layer section into the trained shale oil dessert evaluation model and predicting the dessert type of the untagged seismic trace shale oil layer section.
The embodiment of the invention also provides computer equipment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the intelligent evaluation method of the shale oil dessert is realized when the processor executes the computer program.
The embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program realizes the intelligent evaluation method of the shale oil dessert when being executed by a processor.
The embodiment of the invention also provides a computer program product, which comprises a computer program, and the computer program realizes the intelligent evaluation method of the shale oil dessert when being executed by a processor.
Compared with the technical scheme in the prior art, the embodiment of the invention divides the dessert types of shale oil layer sections in the well according to the known logging interpretation result and the oil test condition to form dessert type labels; extracting a parawell seismic channel containing dessert type labels, and calculating the seismic attribute of a shale oil layer section to form a training data set; the organic fusion of multiple information can be realized; constructing a shale oil dessert evaluation model by using a machine learning algorithm, wherein the input of the shale oil dessert evaluation model is the seismic attribute of a shale oil interval, and the output is the dessert type of the shale oil interval; training the shale oil dessert evaluation model according to the training data set to obtain a trained shale oil dessert evaluation model; inputting the seismic attribute of the untagged seismic trace shale oil layer section into a trained shale oil dessert evaluation model, and predicting the dessert type of the untagged seismic trace shale oil layer section; therefore, various seismic attributes are comprehensively considered, calculation of each single parameter is avoided, accuracy of the predicted result can be improved, difference of the predicted result is reduced, and operation efficiency is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
fig. 1 is a schematic flow chart of an intelligent evaluation method for shale oil desserts, which is provided in an embodiment of the invention;
FIG. 2 is a diagram of one embodiment of the types of desserts for shale oil intervals provided in an embodiment of the present invention;
FIG. 3 is a diagram of one embodiment of a training data set provided in an embodiment of the present invention;
FIG. 4 is a diagram of a specific example of a method for intelligently evaluating shale oil desserts provided in an embodiment of the present invention;
FIG. 5 is a diagram of one embodiment of the input of a shale oil dessert assessment model provided in an embodiment of the present invention;
FIG. 6 is a graph of one embodiment of predicted shale oil dessert results provided in an embodiment of the present invention;
FIG. 7 is a diagram of a specific example of a method for intelligently evaluating shale oil desserts provided in an embodiment of the present invention;
fig. 8 is a schematic structural diagram of an intelligent evaluation device for shale oil desserts, which is provided in an embodiment of the invention;
fig. 9 is a diagram of a specific example of an intelligent evaluation apparatus for shale oil desserts according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention will be described in further detail with reference to the accompanying drawings. The exemplary embodiments of the present invention and their descriptions herein are for the purpose of explaining the present invention, but are not to be construed as limiting the invention.
The embodiment of the invention provides an intelligent evaluation method of shale oil desserts, and fig. 1 is a flow diagram of the intelligent evaluation method of shale oil desserts, as shown in fig. 1, and the method comprises the following steps:
step 101: dividing dessert types of shale oil layer sections in the well according to known logging interpretation results and oil testing conditions to form dessert type labels;
step 102: extracting a parawell seismic channel containing dessert type labels, and calculating the seismic attribute of a shale oil layer section to form a training data set;
step 103: constructing a shale oil dessert evaluation model by using a machine learning algorithm, wherein the input of the shale oil dessert evaluation model is the seismic attribute of a shale oil interval, and the output is the dessert type of the shale oil interval;
step 104: training the shale oil dessert evaluation model according to the training data set to obtain a trained shale oil dessert evaluation model;
step 105: inputting the seismic attribute of the untagged seismic trace shale oil layer section into a trained shale oil dessert evaluation model, and predicting the dessert type of the untagged seismic trace shale oil layer section.
As can be seen from the flow shown in FIG. 1, compared with the technical proposal in the prior art, the embodiment of the invention divides the dessert types of shale oil layer sections in the well according to the known logging interpretation result and the oil test condition to form dessert type labels; extracting a parawell seismic channel containing dessert type labels, and calculating the seismic attribute of a shale oil layer section to form a training data set; the organic fusion of multiple information can be realized; constructing a shale oil dessert evaluation model by using a machine learning algorithm, wherein the input of the shale oil dessert evaluation model is the seismic attribute of a shale oil interval, and the output is the dessert type of the shale oil interval; training the shale oil dessert evaluation model according to the training data set to obtain a trained shale oil dessert evaluation model; inputting the seismic attribute of the untagged seismic trace shale oil layer section into a trained shale oil dessert evaluation model, and predicting the dessert type of the untagged seismic trace shale oil layer section; therefore, various seismic attributes are comprehensively considered, calculation of each single parameter is avoided, accuracy of the predicted result can be improved, difference of the predicted result is reduced, and operation efficiency is improved.
In specific implementation, firstly, the dessert type of shale oil layer sections in the well is divided according to known logging interpretation results and oil testing conditions, and a dessert type label is formed. Fig. 2 is a diagram showing a specific example of the dessert type of a shale oil interval provided in the embodiment of the present invention, in this example, taking a certain tight oil stratum as an example, the dessert type of the shale oil interval may include: multi-stage sand superposed thick layer type (I type), thick sand and thin mud mutual layer type (II type), shale type (III type) containing thin sand interlayer.
After the dessert type label is formed, a parawell seismic trace containing the dessert type label is extracted, and the seismic attribute of the shale oil layer section is calculated to form a training data set.
In one embodiment, the seismic attributes of the shale oil interval include one or any combination of the following seismic attributes: amplitude, frequency, phase, curvature, coherence, fracture density, fracture orientation, sand thickness, total organic carbon, porosity, lithology, brittleness, oil content, formation pressure.
In one embodiment, each row in the training dataset represents a sample, wherein a sample comprises known seismic attributes and corresponding known dessert types; each column represents a feature, which may be, for example, a certain seismic attribute of the shale oil interval or a dessert type of the shale oil interval.
FIG. 3 is a diagram of a specific example of a training dataset provided in an embodiment of the present invention, in which the training dataset may have, for example, 90 samples, each row representing a sample, and each column representing a feature; wherein a sample may comprise, for example, known seismic attributes and corresponding known dessert types; one of the features may include, for example: line number, tie line number, well name, reservoir thickness, reservoir porosity, root mean square amplitude, poisson's ratio, brittleness, source rock thickness, source rock total organic carbon content, dessert type.
Fig. 4 is a diagram of a specific example of the intelligent evaluation method for shale oil desserts provided in the embodiment of the present invention, as shown in fig. 4, in this example, the flow shown in fig. 1 may further include the following steps:
step 401: the training data set is preprocessed.
In one embodiment, the training data set is preprocessed according to one or any combination of the following preprocessing methods: outlier rejection, feature value range adjustment, type feature encoding, feature combination, and preference.
After the training data set is formed, a shale oil dessert evaluation model is constructed by utilizing a machine learning algorithm, wherein the input of the shale oil dessert evaluation model is the seismic attribute of the shale oil interval, and the output is the dessert type of the shale oil interval.
FIG. 5 is a diagram of a specific example of the input of a shale oil dessert evaluation model provided in an embodiment of the present invention, in which the input of the shale oil dessert evaluation model may include, for example, one or any combination of the following seismic properties of the shale oil layer section: source rock TOC, sand thickness, porosity, oiliness, brittleness, cracking, pore pressure.
In one embodiment, the machine learning algorithm includes any one of a random forest algorithm, a decision tree algorithm, a logistic regression algorithm, a support vector machine algorithm, and a neural network algorithm.
After the shale oil dessert evaluation model is built by utilizing a machine learning algorithm, training the shale oil dessert evaluation model according to a training data set to obtain a trained shale oil dessert evaluation model.
In one embodiment, training the shale oil dessert evaluation model according to the training data set to obtain a trained shale oil dessert evaluation model, comprising: selecting a known cross entropy function as a cost function, and measuring the difference between the predicted dessert type and the known dessert type; and according to the difference between the predicted dessert type and the known dessert type, carrying out parameter optimization on the shale oil dessert evaluation model by adopting a random gradient descent algorithm, and determining the optimized parameters of the shale oil dessert evaluation model when the value of the cost function reaches the target value to obtain the trained shale oil dessert evaluation model.
After the trained shale oil dessert evaluation model is obtained, the seismic attribute of the untagged seismic trace shale oil layer section is input into the trained shale oil dessert evaluation model, and the dessert type of the untagged seismic trace shale oil layer section is predicted.
Fig. 6 is a specific example graph of a predicted result of a shale oil dessert in an embodiment of the present invention, as shown in fig. 6, in this example, a dessert type distribution diagram of a certain tight oil stratum is predicted by taking the tight oil stratum as an example, mu53, li92 shown in fig. 6 and other numbers shown in fig. 6 are all well numbers, the accuracy of blind well verification is 90%, and the predicted result basically accords with geological knowledge of the region, so that the shale oil dessert evaluation method provided in the embodiment of the present invention can be applied to guiding exploration and development well position deployment.
A specific example is given below to illustrate a specific application of the intelligent evaluation method for shale oil desserts according to the embodiment of the invention. Fig. 7 is a diagram of a specific example of an intelligent evaluation method for shale oil desserts according to an embodiment of the present invention, as shown in fig. 7, in this example:
and dividing the dessert types of shale oil layer sections in the well according to known logging interpretation results and oil testing conditions to form dessert type labels.
Extracting a parawell seismic channel containing dessert type labels, and calculating the seismic attribute of a shale oil layer section to form a training data set; wherein the seismic attributes of the shale oil interval comprise one or any combination of the following seismic attributes: amplitude, frequency, phase, curvature, coherence, fracture density, fracture orientation, sand thickness, total organic carbon, porosity, lithology, brittleness, oil content, formation pressure.
Preprocessing the training data set to obtain a processed training data set; wherein the training data set is preprocessed according to one or any combination of the following preprocessing methods: outlier rejection, feature value range adjustment, type feature encoding, feature combination, and preference.
And constructing a shale oil dessert evaluation model by using a machine learning algorithm, wherein the input of the shale oil dessert evaluation model is the seismic attribute of the shale oil interval, and the output is the dessert type of the shale oil interval.
Training the shale oil dessert evaluation model according to the training data set to obtain a trained shale oil dessert evaluation model; the training of the shale oil dessert evaluation model according to the training data set to obtain a trained shale oil dessert evaluation model may include: selecting a known cross entropy function as a cost function, and measuring the difference between the predicted dessert type and the known dessert type; and according to the difference between the predicted dessert type and the known dessert type, carrying out parameter optimization on the shale oil dessert evaluation model by adopting a random gradient descent algorithm, and determining the optimized parameters of the shale oil dessert evaluation model when the value of the cost function reaches the target value to obtain the trained shale oil dessert evaluation model.
Inputting the seismic attribute of the untagged seismic trace shale oil layer section into a trained shale oil dessert evaluation model, and predicting the dessert type of the untagged seismic trace shale oil layer section.
The embodiment of the invention also provides an intelligent evaluation device for shale oil desserts, which is described in the following embodiment. Because the principle of the device for solving the problems is similar to that of the intelligent evaluation method of the shale oil dessert, the implementation of the device can be referred to the implementation of the intelligent evaluation method of the shale oil dessert, and repeated parts are not repeated.
An embodiment of the invention provides an intelligent evaluation device for shale oil desserts, and fig. 8 is a schematic structural diagram of the intelligent evaluation device for shale oil desserts, as shown in fig. 8, and the device comprises the following modules:
the dessert type label forming module 81 is used for dividing the dessert type of the shale oil layer section in the well according to the known logging interpretation result and the oil test condition to form a dessert type label;
a training data set forming module 82 for extracting parawell seismic traces containing dessert type tags, calculating seismic attributes of shale oil intervals, and forming a training data set;
the construction module 83 is configured to construct a shale oil dessert evaluation model by using a machine learning algorithm, where an input of the shale oil dessert evaluation model is a seismic attribute of a shale oil interval, and an output is a dessert type of the shale oil interval;
the training module 84 is configured to train the shale oil dessert evaluation model according to the training data set, so as to obtain a trained shale oil dessert evaluation model;
the prediction module 85 is configured to input the seismic attribute of the untagged seismic trace shale oil interval into a trained shale oil dessert evaluation model, and predict the dessert type of the untagged seismic trace shale oil interval.
In one embodiment, the seismic attributes of the shale oil interval include one or any combination of the following seismic attributes: amplitude, frequency, phase, curvature, coherence, fracture density, fracture orientation, sand thickness, total organic carbon, porosity, lithology, brittleness, oil content, formation pressure.
Fig. 9 is a diagram of a specific example of the intelligent evaluation apparatus for shale oil dessert provided in the embodiment of the present invention, as shown in fig. 9, in this example, the intelligent evaluation apparatus for shale oil dessert shown in fig. 8 further includes:
the preprocessing module 91 is configured to preprocess the training data set before the training module 84 trains the shale oil dessert evaluation model according to the training data set.
In one embodiment, the preprocessing module 91 is specifically configured to preprocess the training data set according to one or any combination of the following preprocessing methods: outlier rejection, feature value range adjustment, type feature encoding, feature combination, and preference.
In one embodiment, the machine learning algorithm includes any one of a random forest algorithm, a decision tree algorithm, a logistic regression algorithm, a support vector machine algorithm, and a neural network algorithm.
In one embodiment, training module 84 is specifically configured to: selecting a known cross entropy function as a cost function, and measuring the difference between the predicted dessert type and the known dessert type; and according to the difference between the predicted dessert type and the known dessert type, carrying out parameter optimization on the shale oil dessert evaluation model by adopting a random gradient descent algorithm, and determining the optimized parameters of the shale oil dessert evaluation model when the value of the cost function reaches the target value to obtain the trained shale oil dessert evaluation model.
The embodiment of the invention also provides computer equipment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the intelligent evaluation method of the shale oil dessert is realized when the processor executes the computer program.
The embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program realizes the intelligent evaluation method of the shale oil dessert when being executed by a processor.
The embodiment of the invention also provides a computer program product, which comprises a computer program, and the computer program realizes the intelligent evaluation method of the shale oil dessert when being executed by a processor.
Compared with the technical scheme in the prior art, the embodiment of the invention divides the dessert types of shale oil layer sections in the well according to the known logging interpretation result and the oil test condition to form dessert type labels; extracting a parawell seismic channel containing dessert type labels, and calculating the seismic attribute of a shale oil layer section to form a training data set; the organic fusion of multiple information can be realized; constructing a shale oil dessert evaluation model by using a machine learning algorithm, wherein the input of the shale oil dessert evaluation model is the seismic attribute of a shale oil interval, and the output is the dessert type of the shale oil interval; training the shale oil dessert evaluation model according to the training data set to obtain a trained shale oil dessert evaluation model; inputting the seismic attribute of the untagged seismic trace shale oil layer section into a trained shale oil dessert evaluation model, and predicting the dessert type of the untagged seismic trace shale oil layer section; therefore, various seismic attributes are comprehensively considered, calculation of each single parameter is avoided, accuracy of the predicted result can be improved, difference of the predicted result is reduced, and operation efficiency is improved.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (15)
1. An intelligent evaluation method for shale oil desserts is characterized by comprising the following steps:
dividing dessert types of shale oil layer sections in the well according to known logging interpretation results and oil testing conditions to form dessert type labels;
extracting a parawell seismic channel containing dessert type labels, and calculating the seismic attribute of a shale oil layer section to form a training data set;
constructing a shale oil dessert evaluation model by using a machine learning algorithm, wherein the input of the shale oil dessert evaluation model is the seismic attribute of a shale oil interval, and the output is the dessert type of the shale oil interval;
training the shale oil dessert evaluation model according to the training data set to obtain a trained shale oil dessert evaluation model;
inputting the seismic attribute of the untagged seismic trace shale oil layer section into a trained shale oil dessert evaluation model, and predicting the dessert type of the untagged seismic trace shale oil layer section.
2. The intelligent evaluation method of shale oil dessert of claim 1, wherein the seismic attributes of shale oil interval comprise one or any combination of the following seismic attributes:
amplitude, frequency, phase, curvature, coherence, fracture density, fracture orientation, sand thickness, total organic carbon, porosity, lithology, brittleness, oil content, formation pressure.
3. The intelligent shale oil dessert assessment method of claim 1, further comprising, prior to training the shale oil dessert assessment model according to the training dataset:
the training data set is preprocessed.
4. The intelligent shale oil dessert assessment method of claim 3, wherein the training data set is pre-processed according to one or any combination of the following pre-processing methods:
outlier rejection, feature value range adjustment, type feature encoding, feature combination, and preference.
5. The intelligent shale oil dessert evaluation method of claim 1, wherein the machine learning algorithm comprises any one of a random forest algorithm, a decision tree algorithm, a logistic regression algorithm, a support vector machine algorithm, and a neural network algorithm.
6. The intelligent evaluation method of shale oil dessert according to claim 1, wherein training the shale oil dessert evaluation model according to the training data set to obtain a trained shale oil dessert evaluation model comprises:
selecting a known cross entropy function as a cost function, and measuring the difference between the predicted dessert type and the known dessert type;
and according to the difference between the predicted dessert type and the known dessert type, carrying out parameter optimization on the shale oil dessert evaluation model by adopting a random gradient descent algorithm, and determining the optimized parameters of the shale oil dessert evaluation model when the value of the cost function reaches the target value to obtain the trained shale oil dessert evaluation model.
7. Intelligent evaluation device of shale oil dessert, characterized by, include:
the dessert type label forming module is used for dividing the dessert type of the shale oil layer section in the well according to the known logging interpretation result and the oil test condition to form a dessert type label;
the training data set forming module is used for extracting a parawell seismic channel containing dessert type labels, calculating the seismic attribute of the shale oil layer section and forming a training data set;
the construction module is used for constructing a shale oil dessert evaluation model by utilizing a machine learning algorithm, wherein the input of the shale oil dessert evaluation model is the seismic attribute of a shale oil layer section, and the output is the dessert type of the shale oil layer section;
the training module is used for training the shale oil dessert evaluation model according to the training data set to obtain a trained shale oil dessert evaluation model;
the prediction module is used for inputting the seismic attribute of the untagged seismic trace shale oil layer section into the trained shale oil dessert evaluation model and predicting the dessert type of the untagged seismic trace shale oil layer section.
8. The intelligent shale oil dessert evaluation device of claim 7, wherein the seismic attributes of shale oil intervals comprise one or any combination of the following seismic attributes:
amplitude, frequency, phase, curvature, coherence, fracture density, fracture orientation, sand thickness, total organic carbon, porosity, lithology, brittleness, oil content, formation pressure.
9. The intelligent shale oil dessert evaluation device of claim 7, further comprising a preprocessing module for, prior to the training module training the shale oil dessert evaluation model according to the training data set:
the training data set is preprocessed.
10. The intelligent shale oil dessert evaluation device of claim 9, wherein the preprocessing module is specifically configured to preprocess the training data set according to one or any combination of the following preprocessing methods:
outlier rejection, feature value range adjustment, type feature encoding, feature combination, and preference.
11. The intelligent shale oil dessert evaluation device of claim 7, wherein the machine learning algorithm comprises any one of a random forest algorithm, a decision tree algorithm, a logistic regression algorithm, a support vector machine algorithm, and a neural network algorithm.
12. The intelligent shale oil dessert evaluation device of claim 7, wherein the training module is specifically configured to:
selecting a known cross entropy function as a cost function, and measuring the difference between the predicted dessert type and the known dessert type;
and according to the difference between the predicted dessert type and the known dessert type, carrying out parameter optimization on the shale oil dessert evaluation model by adopting a random gradient descent algorithm, and determining the optimized parameters of the shale oil dessert evaluation model when the value of the cost function reaches the target value to obtain the trained shale oil dessert evaluation model.
13. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the shale oil dessert intelligent assessment method of any of claims 1 to 6 when the computer program is executed.
14. A computer readable storage medium, characterized in that it stores a computer program, which when executed by a processor, implements the shale oil dessert intelligent evaluation method of any of claims 1 to 6.
15. A computer program product, characterized in that it comprises a computer program which, when executed by a processor, implements the intelligent evaluation method of shale oil desserts according to any of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111677300.XA CN116433059A (en) | 2021-12-31 | 2021-12-31 | Intelligent evaluation method and device for shale oil dessert |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111677300.XA CN116433059A (en) | 2021-12-31 | 2021-12-31 | Intelligent evaluation method and device for shale oil dessert |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116433059A true CN116433059A (en) | 2023-07-14 |
Family
ID=87085985
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111677300.XA Pending CN116433059A (en) | 2021-12-31 | 2021-12-31 | Intelligent evaluation method and device for shale oil dessert |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116433059A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117272841A (en) * | 2023-11-21 | 2023-12-22 | 西南石油大学 | Shale gas dessert prediction method based on hybrid neural network |
-
2021
- 2021-12-31 CN CN202111677300.XA patent/CN116433059A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117272841A (en) * | 2023-11-21 | 2023-12-22 | 西南石油大学 | Shale gas dessert prediction method based on hybrid neural network |
CN117272841B (en) * | 2023-11-21 | 2024-01-26 | 西南石油大学 | Shale gas dessert prediction method based on hybrid neural network |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108573320B (en) | Method and system for calculating final recoverable reserves of shale gas reservoir | |
Aminian et al. | Application of artificial neural networks for reservoir characterization with limited data | |
CN112684497B (en) | Seismic waveform clustering method and device | |
CN110284873B (en) | Method and device for detecting oil well reservoir properties | |
CN110320557B (en) | Multi-scale geological feature detection fusion method based on deep learning and evolutionary learning | |
Sarkheil et al. | Fractures distribution modeling using fractal and multi-fractal–neural network analysis in Tabnak hydrocarbon field, Fars, Iran | |
Mohaghegh et al. | Data-driven reservoir management of a giant mature oilfield in the Middle East | |
CN113033648A (en) | Method for realizing logging interpretation by using machine learning algorithm | |
Song et al. | Potential for vertical heterogeneity prediction in reservoir basing on machine learning methods | |
Chahar et al. | Data-driven approach for hydrocarbon production forecasting using machine learning techniques | |
Masoudi et al. | Net pay determination by artificial neural network: Case study on Iranian offshore oil fields | |
CN114529110A (en) | Lithofacies inversion method and system based on deep neural network model | |
US20180306030A1 (en) | Method for improving reservoir performance by using data science | |
Chang et al. | SegLog: Geophysical logging segmentation network for lithofacies identification | |
CN116433059A (en) | Intelligent evaluation method and device for shale oil dessert | |
WO2019199723A1 (en) | Predictions in unconventional plays using machine learning | |
Hou et al. | Data-driven optimization of brittleness index for hydraulic fracturing | |
CN110118994B (en) | Continental facies hydrocarbon source rock quantitative prediction method based on seismic inversion and machine learning | |
CN111472763A (en) | Stratum thickness prediction method and device | |
Sun et al. | Structure of an artificial-intelligence-assisted reservoir characterization and field development protocol | |
Khilrani et al. | Contrasting machine learning regression algorithms used for the estimation of permeability from well log data | |
WO2022186182A1 (en) | Prediction device, prediction method, and recording medium | |
Egorov et al. | Applying machine learning methods to search for missing net pay zones in mature oilfields wells | |
Luo et al. | Multi-level reservoir identification with logs based on machine learning | |
EP3579026B1 (en) | Method of characterising a subsurface region using multiple point statistics |
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 |