CN114397711A - Unconventional tight sandstone reservoir porosity prediction method based on machine learning - Google Patents
Unconventional tight sandstone reservoir porosity prediction method based on machine learning Download PDFInfo
- Publication number
- CN114397711A CN114397711A CN202111442082.1A CN202111442082A CN114397711A CN 114397711 A CN114397711 A CN 114397711A CN 202111442082 A CN202111442082 A CN 202111442082A CN 114397711 A CN114397711 A CN 114397711A
- Authority
- CN
- China
- Prior art keywords
- data
- porosity
- machine learning
- steps
- tight sandstone
- 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000010801 machine learning Methods 0.000 title claims abstract description 29
- 238000012360 testing method Methods 0.000 claims abstract description 28
- 238000012549 training Methods 0.000 claims abstract description 22
- 239000011435 rock Substances 0.000 claims abstract description 17
- 238000004458 analytical method Methods 0.000 claims abstract description 14
- 238000002790 cross-validation Methods 0.000 claims abstract description 7
- 238000007781 pre-processing Methods 0.000 claims abstract description 3
- 239000000523 sample Substances 0.000 claims description 16
- 230000009467 reduction Effects 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 5
- 238000009933 burial Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 208000035126 Facies Diseases 0.000 claims description 3
- 239000012468 concentrated sample Substances 0.000 claims description 3
- 238000010219 correlation analysis Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000000513 principal component analysis Methods 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 2
- 229910052500 inorganic mineral Inorganic materials 0.000 abstract description 10
- 239000011707 mineral Substances 0.000 abstract description 10
- 238000011161 development Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 239000012530 fluid Substances 0.000 description 2
- 238000013508 migration Methods 0.000 description 2
- 230000005012 migration Effects 0.000 description 2
- 230000035699 permeability Effects 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000005056 compaction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V11/00—Prospecting or detecting by methods combining techniques covered by two or more of main groups G01V1/00 - G01V9/00
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V20/00—Geomodelling in general
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Geophysics (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention belongs to the technical field of compact sandstone mineral resource exploration, and particularly relates to an unconventional compact sandstone porosity prediction method based on machine learning. The invention comprises the following steps: step 1, extracting sample data for prediction from well core analysis test data and logging data; step 2, preprocessing data; step 3, training a plurality of porosity prediction models based on different mechanical learning methods; step 4, cross validation; step 5, optimizing each model; and 6, adding new data and re-optimizing the model. The method is based on the existing rock geophysical data, integrates various parameters, and realizes better prediction of the porosity of the compact sandstone reservoir.
Description
Technical Field
The invention belongs to the technical field of compact sandstone mineral resource exploration, and particularly relates to an unconventional compact sandstone porosity prediction method based on machine learning.
Background
Sedimentary mineral resources associated with sandstone porosity are abundant in sedimentary basins, including migration and enrichment of fluid minerals as well as precipitation and formation of solid minerals. People can establish a better sand porosity explanation model by using geophysical data, particularly logging data such as acoustic time difference, neutron porosity and density, and can be widely applied to exploration and development of conventional resources. However, with the breakthrough of unconventional resources, such as dense oil and gas, in recent years, the bottleneck of conventional resource exploration is gradually broken through. However, along with unconventional resources, which are often more complicated geological conditions, for tight sandstone, the main characteristic is low porosity and low permeability, which results in that the tight sandstone reservoir porosity prediction cannot be used for the establishment of a conventional reservoir porosity prediction model, and the prediction difficulty is higher due to the complex cause and influence factors of the low porosity and low permeability reservoir. However, accurate prediction of tight sandstone porosity is still a fundamental need to solve the mineral resource exploration and development problems closely related to tight sandstone porosity.
In recent years, as machine learning techniques and methods have become mature, strong capabilities have been developed in data processing, data analysis, pattern search, rule search, and the like. The processing of complex geological problems is just the comprehensive analysis and research of multi-level, multi-type and big data. Machine learning thus has the very ability and advantage of solving complex geological problems. Meanwhile, many geologists rapidly recognize the advancement of the method and continuously strengthen subject cooperation and technical fusion. However, in the field of tight sandstone, particularly for predicting the porosity of tight sandstone, a complete technical method system needs to be established, and the application of the machine learning method in the field of exploration and development of tight sandstone mineral resources is realized.
Disclosure of Invention
The invention aims to provide a compact sandstone reservoir porosity prediction method based on a machine learning method aiming at the problem that the porosity of the conventional unconventional compact sandstone reservoir is difficult to predict.
The technical scheme adopted by the invention is as follows:
a prediction method for unconventional tight sandstone porosity based on machine learning comprises the following steps: step 1, extracting sample data for prediction from well core analysis test data and logging data; step 2, preprocessing data; step 3, training a plurality of porosity prediction models based on different mechanical learning methods; step 4, cross validation; step 5, optimizing each model; and 6, adding new data and re-optimizing the model.
In the step 1, a data set consisting of the analysis and test porosity of the tight sandstone core sample and logging data related to the porosity of the rock is obtained, the analysis and test porosity of the core sample is used as a target set for supervised learning, and natural gamma, natural potential, sound wave time difference, neutron porosity, density, deep lateral resistivity and burial depth are used as feature sets.
Cleaning and statistically analyzing the data collected in the step 1, and removing abnormal points of porosity measurement and abnormal values obtained by logging parameters; and the statistical distribution of each type of parameter is statistically analyzed, the logging parameter characteristics of various rocks in different rock types, different sedimentary facies types and different diagenetic stages are divided, and the data characteristics and the data connotation are comprehensively mastered.
The step 2 comprises the following steps:
step 2.1, correcting the logging depth in the logging data and the core sample depth in the sample data, and performing matching correlation on the feature set and the target set;
step 2.2, normalizing the characteristic data of natural gamma, natural potential, acoustic wave time difference, neutron porosity, density, deep lateral resistivity and buried depth in the characteristic set;
and 2.3, performing dimension reduction treatment on the normalized feature set.
In the step 2.2, the normalization method adopts:
wherein: x is the number ofnormalIs normalized data of a feature data, xminRepresents the minimum value, x, in this characteristic datamaxRepresenting the maximum value in this characteristic data.
In the step 2.3, the correlation among the characteristic values is analyzed, the response mechanism of the actual physical significance of the logging data to the rock porosity is combined, and the correlation and principal component analysis of the characteristic data are analyzed to perform dimension reduction judgment and processing on the characteristic data set.
In the step 3, the feature set after the dimension reduction processing is averagely divided into 5 parts, and the corresponding target set is also divided into 5 parts; sequentially selecting one data i in the fifth step as a feature set F _ test (i) of the test set, wherein the corresponding target set is a target set T _ test (i) of the test set, and the rest 4 data form a feature set F _ train (i) and a target set T _ train (i) of the training set; selecting an optimal training result through multiple times of training; and selecting different machine learning algorithms, and training a porosity prediction model.
In the step 4, each training model is evaluated according to the cross validation result of each trained model.
In the step 5, the evaluation indexes comprise mean square error MSE, root mean square error RMSE, mean absolute error MAE and R2。
The MSE is calculated as follows:
the RMSE is calculated as follows:
the MAE calculation method comprises the following steps:
wherein R is2The calculation method of (2) is as follows:
wherein, yiActually analyzing and testing the porosity for the concentrated sample;
in order to predict the result for the model,
the average of the model predictions is used.
Compared with the prior art, the invention has the beneficial effects that:
(1) the unconventional tight sandstone porosity prediction method based on machine learning improves the prediction accuracy of the tight sandstone porosity, and reduces the mineral resource exploration in the tight sandstone, especially the cost of the oil-gas exploration of the tight sandstone;
(2) the unconventional tight sandstone porosity prediction method based on machine learning introduces a multi-parameter comprehensive tight sandstone porosity prediction method, and the introduced parameters reflect different information of tight sandstone, including rock component information, rock burial compaction information, rock density information and the like, which are related to the rock porosity. The porosity is more accurately predicted through the integration of multiple information;
(3) the unconventional tight sandstone porosity prediction method based on machine learning can be applied to research on fluid migration channels and enrichment capacity in tight sandstone in a sedimentary basin, can also be directly applied to exploration and development of tight sandstone mineral resources, and provides strong scientific support for research on enrichment rules of the mineral resources, prediction of favorable zones and mining practice.
Drawings
Fig. 1 is a flow chart of a method for predicting porosity of tight sandstone based on machine learning according to the present invention.
FIG. 2 is a graph of the comparison of the porosity of a core sample in a certain oilfield block in an analysis test and a machine learning predicted porosity.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
As shown in fig. 1, the method for predicting unconventional tight sandstone porosity based on machine learning provided by the invention comprises the following steps:
step 1, acquiring a tight sandstone core sample analysis testing porosity and logging data related to the rock porosity from core sample analysis testing data and logging data of a certain oil field to form a data set, taking the core sample analysis testing porosity as a target set for supervision and learning, and taking natural gamma, natural potential, acoustic wave time difference, neutron porosity, density, deep lateral resistivity and burial depth as feature sets; the more the tight sandstone drilling core analysis test data and logging data are, the more comprehensive the more beneficial the machine learning and prediction results are, in order to master the data characteristics by the system, the data collected in the step 1 are cleaned and statistically analyzed, abnormal points of porosity measurement, abnormal values obtained by logging parameters and the like are removed, in order to master the data characteristics by the system, the statistical distribution of each type of parameters is statistically analyzed, the logging parameter characteristics of various rocks of tight sandstones of different rock types, different sedimentary facies types, different diagenetic stages and the like are divided, the data characteristics and the data connotation are comprehensively mastered, and the basis is provided for the subsequent model training;
and 3, normalizing the characteristic data of natural gamma, natural potential, sound wave time difference, neutron porosity, density, deep lateral resistivity and buried depth in the characteristic set. The normalization method comprises the following steps:
wherein xnormalIs normalized data of a feature data, xminRepresents the minimum value, x, in this characteristic datamaxRepresents the maximum value, x;
and 4, performing dimension reduction treatment on the normalized feature set. Performing dimension reduction judgment and processing on the characteristic data set by analyzing the correlation among the characteristic values, combining the response mechanism of the actual physical meaning of the logging data to the rock porosity and analyzing the correlation and principal component analysis of the characteristic data;
step 5, averagely dividing the feature set subjected to the dimension reduction into 5 parts, and dividing the corresponding target set into 5 parts;
and 7, evaluating each training model according to the cross validation result of each trained model. The main evaluation indexes include Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and R2. The MSE is calculated as follows:
the RMSE is calculated as follows:
the MAE calculation method comprises the following steps:
wherein R is2The calculation method of (2) is as follows:
wherein, yiActually analyzing and testing the porosity for the concentrated sample;
in order to predict the result for the model,
average value of model prediction results; and m is selected.
And 8, applying the obtained optimal model as a porosity explanation model of the tight sandstone in a research area, and solving the problem that the unconventional tight sandstone porosity is difficult to predict.
And 9, adding new data and re-optimizing the model.
The evaluation indexes of the training result model based on different algorithms in this example are as follows:
TABLE 1 evaluation index based on different algorithm training models
As shown in FIG. 2, the left side shows the prediction result based on the random forest algorithm, and the right side shows the prediction result based on the K-neighborhood algorithm. The result shows that the training result model based on the K-proximity method and the random forest algorithm shows a good prediction effect.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (10)
1. A method for predicting unconventional tight sandstone porosity based on machine learning is characterized by comprising the following steps: the method comprises the following steps: extracting sample data for prediction from the well core analysis test data and the well logging data; step (2), preprocessing data; step (3), training a plurality of porosity prediction models based on different mechanical learning methods; step (4), cross validation; step (5), optimizing each model; and (6) adding new data and re-optimizing the model.
2. The method for predicting unconventional tight sandstone porosity based on machine learning of claim 1, wherein the method comprises the following steps: in the step (1), a data set is formed by acquiring the analysis and test porosity of the tight sandstone core sample and logging data related to the porosity of the rock, the analysis and test porosity of the core sample is used as a target set for supervised learning, and natural gamma, natural potential, sound wave time difference, neutron porosity, density, deep lateral resistivity and burial depth are used as feature sets.
3. The method for predicting unconventional tight sandstone porosity based on machine learning of claim 2, wherein the method comprises the following steps: cleaning and statistically analyzing the data collected in the step (1), and removing abnormal values obtained from porosity measurement abnormal points and logging parameters; and the statistical distribution of each type of parameter is statistically analyzed, the logging parameter characteristics of various rocks in different rock types, different sedimentary facies types and different diagenetic stages are divided, and the data characteristics and the data connotation are comprehensively mastered.
4. The method for predicting unconventional tight sandstone porosity based on machine learning of claim 3, wherein the method comprises the following steps: the step (2) comprises the following steps:
step (2.1), correcting the logging depth in the logging data and the core sample depth in the sample data, and performing matching correlation on the feature set and the target set;
step (2.2), carrying out normalization processing on characteristic data of natural gamma, natural potential, acoustic wave time difference, neutron porosity, density, deep lateral resistivity and buried depth in the characteristic set;
and (2.3) performing dimension reduction treatment on the normalized feature set.
5. The method for predicting unconventional tight sandstone porosity based on machine learning of claim 4, wherein the method comprises the following steps: in the step (2.2), the normalization method adopts:
wherein: x is the number ofnormalIs normalized data of a feature data, xminRepresents the minimum value, x, in this characteristic datamaxRepresenting the maximum value in this characteristic data.
6. The method for predicting unconventional tight sandstone porosity based on machine learning of claim 5, wherein the method comprises the following steps: in the step (2.3), through analyzing the correlation among the characteristic values, combining the response mechanism of the actual physical meaning of the logging data to the rock porosity, and through analyzing the correlation and principal component analysis of the characteristic data, the dimension reduction judgment and processing are carried out on the characteristic data set.
7. The method for predicting unconventional tight sandstone porosity based on machine learning of claim 6, wherein the method comprises the following steps: in the step (3), the feature set after the dimension reduction processing is averagely divided into 5 parts, and the corresponding target set is also divided into 5 parts; sequentially selecting one data i in the fifth step as a feature set F _ test (i) of the test set, wherein the corresponding target set is a target set T _ test (i) of the test set, and the rest 4 data form a feature set F _ train (i) and a target set T _ train (i) of the training set; selecting an optimal training result through multiple times of training; and selecting different machine learning algorithms, and training a porosity prediction model.
8. The method for predicting unconventional tight sandstone porosity based on machine learning of claim 7, wherein the method comprises the following steps: in the step (4), each training model is evaluated according to the cross validation result of each trained model.
9. The method for predicting unconventional tight sandstone porosity based on machine learning of claim 8, wherein the method comprises the following steps: in the step (5), the evaluation indexes comprise mean square error MSE, root mean square error RMSE, mean absolute error MAE and R2。
10. The method for predicting unconventional tight sandstone porosity based on machine learning of claim 9, wherein the method comprises the following steps: the MSE is calculated as follows:
the RMSE is calculated as follows:
the MAE calculation method comprises the following steps:
wherein R is2The calculation method of (2) is as follows:
wherein, yiActually analyzing and testing the porosity for the concentrated sample;
in order to predict the result for the model,
the average of the model predictions is used.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111442082.1A CN114397711A (en) | 2021-11-30 | 2021-11-30 | Unconventional tight sandstone reservoir porosity prediction method based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111442082.1A CN114397711A (en) | 2021-11-30 | 2021-11-30 | Unconventional tight sandstone reservoir porosity prediction method based on machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114397711A true CN114397711A (en) | 2022-04-26 |
Family
ID=81225580
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111442082.1A Pending CN114397711A (en) | 2021-11-30 | 2021-11-30 | Unconventional tight sandstone reservoir porosity prediction method based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114397711A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118568629A (en) * | 2024-05-31 | 2024-08-30 | 中国矿业大学 | Rock porosity prediction method based on small sample while-drilling data inversion |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110824556A (en) * | 2019-10-22 | 2020-02-21 | 中国石油天然气股份有限公司 | Rock physical model building method and application of unconventional tight sandstone reservoir |
| CN110852527A (en) * | 2019-11-20 | 2020-02-28 | 成都理工大学 | Reservoir physical property parameter prediction method combining deep learning |
| CN111324990A (en) * | 2020-03-19 | 2020-06-23 | 长江大学 | Porosity prediction method based on multilayer long-short term memory neural network model |
| CN112576244A (en) * | 2020-11-17 | 2021-03-30 | 中海油田服务股份有限公司 | Porosity calculation method and device |
| US20210293139A1 (en) * | 2020-03-20 | 2021-09-23 | Saudi Arabian Oil Company | Systems and Methods for the Determination of Lithology Porosity from Surface Drilling Parameters |
-
2021
- 2021-11-30 CN CN202111442082.1A patent/CN114397711A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110824556A (en) * | 2019-10-22 | 2020-02-21 | 中国石油天然气股份有限公司 | Rock physical model building method and application of unconventional tight sandstone reservoir |
| CN110852527A (en) * | 2019-11-20 | 2020-02-28 | 成都理工大学 | Reservoir physical property parameter prediction method combining deep learning |
| CN111324990A (en) * | 2020-03-19 | 2020-06-23 | 长江大学 | Porosity prediction method based on multilayer long-short term memory neural network model |
| US20210293139A1 (en) * | 2020-03-20 | 2021-09-23 | Saudi Arabian Oil Company | Systems and Methods for the Determination of Lithology Porosity from Surface Drilling Parameters |
| CN112576244A (en) * | 2020-11-17 | 2021-03-30 | 中海油田服务股份有限公司 | Porosity calculation method and device |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118568629A (en) * | 2024-05-31 | 2024-08-30 | 中国矿业大学 | Rock porosity prediction method based on small sample while-drilling data inversion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110619353B (en) | Multi-scale logging curve automatic identification method based on deep learning | |
| CN112343587A (en) | Ultra-low permeability reservoir dominant seepage channel identification and characterization method | |
| CN109800954B (en) | Reservoir evaluation method based on logging data | |
| CN113537585B (en) | Oil field production increasing measure recommendation method based on random forest and gradient lifting decision tree | |
| CN101266299A (en) | Method for forecasting oil gas utilizing earthquake data object constructional features | |
| CN114818076B (en) | Machine learning-based fault closed hydrocarbon column height evaluation method | |
| US20230160304A1 (en) | Method and system for predicting relative permeability curve based on machine learning | |
| CN109543915B (en) | Method for identifying total organic carbon content of hydrocarbon source rock in whole well section based on logging information | |
| CN110308497B (en) | Method for fusing different types of reservoir body models of fracture-cavity oil reservoir | |
| CN115438823A (en) | Borehole wall instability mechanism analysis and prediction method and system | |
| CN112253087A (en) | Biological disturbance reservoir physical property calculation method based on multi-source logging data | |
| CN110988997A (en) | Hydrocarbon source rock three-dimensional space distribution quantitative prediction technology based on machine learning | |
| CN110671092A (en) | Oil gas productivity detection method and system | |
| CN117251802B (en) | Heterogeneous reservoir parameter prediction method and system based on transfer learning | |
| CN116911216B (en) | Reservoir oil well productivity factor assessment and prediction method | |
| CN111155980B (en) | Water flow dominant channel identification method and device | |
| CN115629188B (en) | Core productivity simulation experiment system | |
| Carrasquilla et al. | Using facies, data mining and artificial intelligence concepts in the evaluation of a carbonate reservoir in Campos basin, Southeastern Brazil | |
| CN114397711A (en) | Unconventional tight sandstone reservoir porosity prediction method based on machine learning | |
| CN114462323A (en) | Oil reservoir flow field characterization method based on multi-attribute field fusion | |
| CN108875109B (en) | Method and system for predicting abnormal formation pressure | |
| CN114153002A (en) | Three-dimensional geological modeling method and device for natural fracture of reservoir, electronic equipment and medium | |
| CN113344729B (en) | Residual oil submergence digging method based on small sample learning | |
| CN117235628B (en) | Well logging curve prediction method and system based on hybrid Bayesian deep network | |
| CN105528732B (en) | Method for predicting productivity of gas testing well |
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 |