CN114137610B - Low exploration area stratum and lithologic seismic evaluation method combining supervision and unsupervised learning - Google Patents
Low exploration area stratum and lithologic seismic evaluation method combining supervision and unsupervised learning Download PDFInfo
- Publication number
- CN114137610B CN114137610B CN202111404706.0A CN202111404706A CN114137610B CN 114137610 B CN114137610 B CN 114137610B CN 202111404706 A CN202111404706 A CN 202111404706A CN 114137610 B CN114137610 B CN 114137610B
- Authority
- CN
- China
- Prior art keywords
- learning
- seismic
- supervised
- unsupervised learning
- stratum
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 11
- 238000000034 method Methods 0.000 claims abstract description 39
- 238000012549 training Methods 0.000 claims abstract description 10
- 238000012847 principal component analysis method Methods 0.000 claims description 9
- 238000007637 random forest analysis Methods 0.000 claims description 7
- 210000002569 neuron Anatomy 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 4
- 238000010801 machine learning Methods 0.000 claims description 4
- 238000012360 testing method Methods 0.000 claims description 3
- 238000013517 stratification Methods 0.000 claims 2
- 230000001052 transient effect Effects 0.000 claims 1
- 238000013507 mapping Methods 0.000 description 3
- 238000012800 visualization Methods 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 239000000758 substrate Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Images
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. for interpretation or for event detection
- G01V1/30—Analysis
- G01V1/307—Analysis for determining seismic attributes, e.g. amplitude, instantaneous phase or frequency, reflection strength or polarity
-
- 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. for interpretation or for event detection
- G01V1/30—Analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
- G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
- G06N3/061—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using biological neurons, e.g. biological neurons connected to an integrated circuit
-
- 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
- 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
- G06N3/088—Non-supervised learning, e.g. competitive learning
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Molecular Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Acoustics & Sound (AREA)
- Environmental & Geological Engineering (AREA)
- Geology (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geophysics (AREA)
- Neurology (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention relates to a low exploration area stratum and lithologic seismic evaluation method combining supervised and unsupervised learning, which comprises the following steps: 1) Extracting seismic attributes reflecting geological features based on post-stack seismic data, and performing elastic parameter post-stack inversion to obtain an inversion result; 2) The feature dimension reduction method is utilized to reduce the dimension of the extracted high-dimension seismic feature; 3) Based on the feature after dimension reduction, clustering by adopting an unsupervised learning method; 4) Determining the application range of supervised learning by using an unsupervised learning result; 5) Adopting a supervised learning training model to quantitatively predict lithology of the seismic section; 6) And qualitatively evaluating the uncertainty of the supervised learning prediction by using the unsupervised learning result. Compared with the prior art, the method has the advantages that compared with a prediction method only using supervised learning, the method can well excavate the internal features of data, characterize the geological features and differences of stratum, and can also delineate the application range of supervised learning to qualitatively evaluate the prediction uncertainty.
Description
Technical Field
The invention relates to the field of geophysics, in particular to a low exploration area stratum and lithologic seismic evaluation method combining supervised and unsupervised learning.
Background
The low exploration area refers to a work area with insufficient seismic exploration data, and the seismic characterization of the geological features of the low exploration area often faces the challenges of insufficient well data, no representativeness, poor quality of the seismic data, fuzzy mapping relation of seismic response and geological features and the like.
Under the machine learning framework, training samples of a low exploration area are few and are not representative, and the supervised learning training model is used for easily causing overfitting, so that the whole earthquake work area is difficult to generalize, and the prediction result is inaccurate. The stratum and lithologic earthquake evaluation in a low exploration area are the problems to be solved in actual geophysical exploration, and the nonlinear mapping relation between the earthquake attribute and the geological feature needs to be excavated and mapped accurately, so that the accurate depiction of the geological feature is realized, the stratum division is guided, and the uncertainty of lithologic earthquake prediction is reduced.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a low exploration area stratum and lithologic earthquake evaluation method combining supervised and unsupervised learning.
The aim of the invention can be achieved by the following technical scheme:
a low exploration area stratum and lithologic seismic evaluation method combining supervised and unsupervised learning comprises the following steps:
1) Extracting seismic attributes reflecting geological features based on post-stack seismic data, and performing elastic parameter post-stack inversion to obtain inversion results, so as to form multidimensional seismic features for machine learning;
2) Performing dimension reduction on the extracted high-dimension seismic features by using a feature dimension reduction method to obtain sensitive seismic attributes;
3) Based on the feature after dimension reduction, an unsupervised learning method is adopted for clustering, and model parameters are optimized according to a method principle and a clustering result;
4) Determining the application range of supervised learning by using an unsupervised learning result;
5) For samples with similar data distribution, adopting a supervised learning training model to perform feature optimization and parameter optimization, taking samples with labels on the well to perform testing, and finally performing lithology quantitative prediction on the whole seismic section;
6) And qualitatively evaluating the uncertainty of the supervised learning prediction by using the unsupervised learning result.
In the step 1), the seismic attribute includes an instantaneous attribute and a time-frequency attribute.
In the step 2), the main component analysis method is adopted to reduce the dimension to obtain the sensitive seismic attribute.
In the step 3), clustering is performed by adopting a self-organizing map network SOM.
PCA dimension reduction is carried out on the multidimensional seismic features, original features with larger occupation in main components with front contribution are selected as input of a self-organizing map network SOM, the number of neurons of the self-organizing map network SOM is set, and the whole seismic section clustering is completed and visualization is completed.
And differentiating and representing the layering of each year and the difference from the substrate according to the color layering of the SOM clustering result of the self-organizing map network.
In the step 4), different clusters in the unsupervised result reflect different data characteristics, and samples with similar data distribution are used for supervised learning to obtain a better prediction effect, namely learning samples with similar cluster characteristics with the required prediction stratum are selected for supervised learning training.
In the step 5), under the constraint of the application range of the unsupervised learning, a random forest method in the supervised learning is adopted to train the model.
In the step 6), the larger the difference between the unsupervised learning result and the characteristic of the data on the well as the learning sample is, the larger the supervised learning prediction uncertainty is.
Compared with the prior art, the invention has the following advantages:
1. the invention fully plays the comprehensive processing capacity of unsupervised learning on multidimensional seismic information, extracts multi-seismic attributes (such as amplitude, frequency, phase and the like) and inverts elastic parameters on the seismic data, thereby improving the accuracy of intelligent division of strata with different geological features or physical attributes.
2. The invention applies the strategy of PCA+SOM combination, the PCA method can effectively reduce feature dimension, reduce noise and redundancy, relieve curse dimension problem caused by direct clustering on high-dimensional features, and the SOM method can further convert complex and nonlinear statistical relationship between high-dimensional data into low-dimensional simple geometric relationship, and maintain unchanged topological structure in the mapping process, thereby having good visuality and being beneficial to mining geological features and differences of stratum.
3. The invention applies the method of combining the supervised and the unsupervised learning, the unsupervised learning results restrict the application range of the supervised learning prediction, and the uncertainty of the supervised learning prediction is qualitatively evaluated, namely, in the area with large difference with the characteristics of the data (learning sample) on the well, the supervised learning prediction method is difficult to be applied, and the larger the difference is, the larger the prediction uncertainty is.
Drawings
FIG. 1 is a flow chart of a method for performing low exploration area formation and lithologic seismic evaluation by combining supervised learning and unsupervised learning.
Fig. 2 is a cross-sectional visualization of a cluster using the SOM method (color represents SOM cluster labels) using PCA method dimension reduction.
FIG. 3 is a graph of lithology prediction results for seismic sections using results of unsupervised learning to constrain supervised learning and training a model using a random forest approach.
Detailed Description
The invention will now be described in detail with reference to the drawings and specific examples.
Examples
The invention adopts a strategy of combining supervised and unsupervised learning, namely, unsupervised learning is assisted to supervise learning, the application range of supervised learning is delineated, the uncertainty of supervised learning is qualitatively evaluated, and the earthquake evaluation of stratum and lithology of a low exploration area is carried out.
As shown in FIG. 1, the invention discloses a low exploration area stratum and lithologic seismic evaluation method combining supervised and unsupervised learning, which comprises the following steps:
1) Extracting seismic attributes (such as instantaneous attributes, time-frequency attributes and the like) capable of reflecting geological features based on post-stack seismic data, and carrying out post-stack inversion of elastic parameters to provide multidimensional seismic information for later machine learning;
2) The problems of data redundancy and 'curse dimension' are easily caused by high-dimensional feature clustering, so that the extracted high-dimensional features are subjected to dimension reduction by a feature dimension reduction method (such as a principal component analysis method (PCA)) to obtain sensitive seismic attributes;
3) Based on the feature after dimension reduction, an unsupervised learning method such as SOM (self-organizing map network) is adopted for clustering, and model parameters are optimized according to the principle of the method and the clustering result. For example, when using SOM network clustering, the number of neurons can be adjusted according to the effect of clustering, 10×10 neurons being employed in this example. The unsupervised clustering result reflects the internal structural characteristics of the data, and adjacent neurons in the SOM network correspond to similar data characteristics, so that the method can be used for intelligently identifying strata with different geology or physical characteristics and plays a role in guiding horizon interpretation work.
4) And delineating the application range of the supervised learning by using the unsupervised learning result. Different clusters in the unsupervised result reflect different data characteristics, and the sample with similar data distribution is used for supervised learning, so that a better prediction effect can be obtained, namely, a learning sample with similar cluster characteristics with the required prediction stratum is selected for supervised learning training.
5) For the part of samples, a random forest method in supervised learning is adopted to train a model, characteristic optimization and parameter optimization are carried out, the samples with labels on the well are taken for testing, and then lithology quantitative prediction is carried out on the whole seismic section. Unsupervised learning can qualitatively evaluate the uncertainty of supervised learning prediction, i.e., the greater the feature difference from the data on the well (learning sample), the greater its prediction uncertainty.
Fig. 2 is a cross-sectional visualization of a cluster using the SOM method (color represents SOM cluster labels) using PCA method dimension reduction. The method comprises the following specific steps: PCA dimension reduction is carried out on the extracted seismic attributes and the seismic inversion result, the first four main components are taken, the contribution proportion of the four main components is ordered from large to small, the original characteristic of each main component with large proportion is taken as the input of an SOM clustering method, the number of SOM neurons is set to be 100, and the whole seismic section clustering is completed. Three distinct color layers appear in the SOM results of fig. 2, and the differences between the layers and the substrate are clearly distinguished from each other, which are well matched with geologic horizons independently interpreted by geologist, and prove that the SOM results can play an important role in highlighting geologic features and identifying horizons. In addition, SOMs are able to identify larger geologic structures, such as fault development herein.
FIG. 3 is a graph of lithology predictions for a seismic section using a random forest method training model under unsupervised learning constraints. The supervised learning is constrained by using unsupervised learning results, which indicate that the uphole data is not similar to the formation above the f1 horizon and the base features below the f4 horizon, and if the uphole label data is used for predicting the data of these areas, reasonable results are difficult to obtain, so that the random forest model prediction range from f1 to f4 horizons is defined by means of horizon constraint. In addition, the result of the unsupervised method can be used for carrying out qualitative assessment of the supervised learning prediction uncertainty, and data similar to the on-well features in the unsupervised learning result are mainly distributed between f2 and f3 layers, so that the prediction uncertainty below the f3 layer is high. From fig. 3, it can be seen that the random forest algorithm can perform fine lithology characterization, the transversal continuity above the f3 horizon is good, and the transversal continuity of the stratum prediction below the f3 horizon is poor, which accords with the unsupervised learning result.
Claims (7)
1. A low exploration area stratum and lithologic seismic evaluation method combining supervised and unsupervised learning is characterized by comprising the following steps:
1) Extracting seismic attributes reflecting geological features based on post-stack seismic data, and performing elastic parameter post-stack inversion to obtain inversion results, so as to form multidimensional seismic features for machine learning;
2) Performing dimension reduction on the extracted high-dimension seismic features by using a feature dimension reduction method to obtain sensitive seismic attributes;
3) Based on the feature after dimension reduction, an unsupervised learning method is adopted for clustering, and model parameters are optimized according to a method principle and a clustering result;
4) Determining the application range of supervised learning by using an unsupervised learning result;
5) For samples with similar data distribution, adopting a supervised learning training model to perform feature optimization and parameter optimization, taking samples with labels on the well to perform testing, and finally performing lithology quantitative prediction on the whole seismic section;
6) Qualitatively evaluating uncertainty of supervised learning prediction by using an unsupervised learning result;
in the step 4), different clusters in the unsupervised result reflect different data characteristics, and samples with similar data distribution are used for supervised learning to obtain a better prediction effect, namely learning samples with similar cluster characteristics with the required prediction stratum are selected for supervised learning training;
in the step 5), under the constraint of the application range of the unsupervised learning, a random forest method in the supervised learning is adopted to train the model.
2. The method of claim 1, wherein in step 1), the seismic attributes include transient and time-frequency attributes.
3. The method for evaluating the stratum and lithology earthquake of the low exploration area by combining supervised and unsupervised learning according to claim 1, wherein in the step 2), a principal component analysis method is adopted for dimension reduction to obtain sensitive earthquake attributes.
4. The method for evaluating the stratum and lithology earthquake of the low exploration area by combining supervised and unsupervised learning according to claim 1, wherein in the step 3), clustering is performed by adopting a self-organizing map network SOM.
5. The method for evaluating the stratum and lithology earthquake of the low exploration area by combining supervised and unsupervised learning according to claim 4, wherein the method is characterized in that the dimension reduction of PCA is carried out on multidimensional earthquake features, original features with larger occupation in main components with the front contribution are selected as the input of a self-organizing map network SOM, the number of neurons of the self-organizing map network SOM is set, and the whole earthquake section is clustered and visualized.
6. The method of claim 5, wherein the color stratification of SOM clustering results based on the self-organizing map is differentiated to represent the stratification of each year and the difference from the base.
7. The method for evaluating the stratum and lithology earthquake of the low exploration area by combining supervised and unsupervised learning according to claim 1, wherein in the step 6), the larger the difference between the characteristic of the data on the well as the learning sample in the unsupervised learning result is, the larger the uncertainty of the supervised learning prediction is.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111404706.0A CN114137610B (en) | 2021-11-24 | 2021-11-24 | Low exploration area stratum and lithologic seismic evaluation method combining supervision and unsupervised learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111404706.0A CN114137610B (en) | 2021-11-24 | 2021-11-24 | Low exploration area stratum and lithologic seismic evaluation method combining supervision and unsupervised learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114137610A CN114137610A (en) | 2022-03-04 |
| CN114137610B true CN114137610B (en) | 2023-05-02 |
Family
ID=80392170
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111404706.0A Active CN114137610B (en) | 2021-11-24 | 2021-11-24 | Low exploration area stratum and lithologic seismic evaluation method combining supervision and unsupervised learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114137610B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2023205841A1 (en) * | 2022-01-07 | 2024-08-01 | Solution Seeker As | A method of training a model for one or more production wells |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113095352A (en) * | 2021-03-01 | 2021-07-09 | 中国地质大学（武汉） | Oil-gas-containing property evaluation method for fracture-cavity type oil reservoir semi-supervised learning reservoir fused with static and dynamic characteristics |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7113869B2 (en) * | 2003-05-22 | 2006-09-26 | Schlumberger Technology Corporation | Method for prospect identification in asset evaluation |
| CN105259572B (en) * | 2015-07-23 | 2018-06-19 | 成都理工大学 | The seismic facies computational methods classified automatically based on seismic multi-attribute parametrical nonlinearity |
| CN106650766A (en) * | 2016-09-13 | 2017-05-10 | 电子科技大学 | Inherent feature analysis based three-dimensional body waveform classification method |
| EP3526629B1 (en) * | 2016-10-14 | 2020-11-25 | Chevron U.S.A. Inc. | System and method for seismic facies identification using machine learning |
| CN107688201B (en) * | 2017-08-23 | 2019-12-31 | 电子科技大学 | RBM-based seismic prestack signal clustering method |
| CN108732620B (en) * | 2018-03-09 | 2019-12-27 | 山东科技大学 | Multi-wave earthquake oil and gas reservoir prediction method under unsupervised and supervised learning |
| WO2020053197A1 (en) * | 2018-09-13 | 2020-03-19 | Shell Internationale Research Maatschappij B.V. | Method for predicting subsurface features from seismic using deep learning dimensionality reduction for segmentation |
| US11448792B2 (en) * | 2020-01-15 | 2022-09-20 | Energy And Environmental Research Center Foundation | Locating underground features with seismic data processing |
| CN111523376B (en) * | 2020-03-09 | 2023-07-28 | 浙江工业大学 | Self-interference micro-ring resonant cavity sensing classification identification method based on unsupervised learning |
-
2021
- 2021-11-24 CN CN202111404706.0A patent/CN114137610B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113095352A (en) * | 2021-03-01 | 2021-07-09 | 中国地质大学（武汉） | Oil-gas-containing property evaluation method for fracture-cavity type oil reservoir semi-supervised learning reservoir fused with static and dynamic characteristics |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114137610A (en) | 2022-03-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US5638269A (en) | Seismic trace analysis method utilizing a statistical calibration technique for deducing geologic properties | |
| CN111596364B (en) | Seismic sediment microphase combination analysis method based on high-precision sequence stratum grillwork | |
| US20040133531A1 (en) | Neural network training data selection using memory reduced cluster analysis for field model development | |
| CN111596978A (en) | Web page display method, module and system for lithofacies classification by artificial intelligence | |
| US20020188406A1 (en) | Method for facilitating monitoring, in the course of time, of the evolution of physical states in an underground formation | |
| CN116168224A (en) | Machine learning lithology automatic identification method based on imaging gravel content | |
| CA3177867A1 (en) | Structured representations of subsurface features for hydrocarbon system and geological reasoning | |
| CN114137610B (en) | Low exploration area stratum and lithologic seismic evaluation method combining supervision and unsupervised learning | |
| CN117452518B (en) | Reservoir lithology prediction method based on multidisciplinary data fusion clustering algorithm | |
| Ye et al. | Drilling formation perception by supervised learning: Model evaluation and parameter analysis | |
| Kuroda et al. | Interpretation of seismic multiattributes using a neural network | |
| Luo et al. | Automatic first-arrival picking method via intelligent Markov optimal decision processes | |
| Dramsch | Machine learning in 4D seismic data analysis | |
| CN113484907B (en) | Method for predicting distribution on different types of reservoir planes | |
| US20210374465A1 (en) | Methodology for learning a similarity measure between geophysical objects | |
| CN112394392B (en) | Method and device for evaluating distribution condition of hydrocarbon source rock | |
| CN115880455A (en) | Three-dimensional intelligent interpolation method based on deep learning | |
| CN115128671A (en) | Three-dimensional seismic facies automatic identification method based on deep learning technology | |
| Degterev | Multivariate Spatial Temporal Model of Gas Dynamic in Underground Gas Storage Based on Saturation Parameter from Well Logging Data | |
| Sadeghi et al. | Global stochastic seismic inversion using turning bands simulation and co-simulation | |
| CN110261906B (en) | Multi-parameter lithologic information fusion reservoir prediction method | |
| Maurya et al. | Geostatistical Inversion | |
| Carrillat et al. | From 3d seismic facies to reservoir simulation: an example from the Grane field | |
| Wang et al. | Lithological Reservoir Exploration Technology | |
| CN113671567B (en) | Method for predicting different types of reservoirs based on waveform classification and color fusion |
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 |