CN113409460B - Machine learning type three-dimensional quantitative characterization method for clastic rock reservoir interlayer - Google Patents
Machine learning type three-dimensional quantitative characterization method for clastic rock reservoir interlayer Download PDFInfo
- Publication number
- CN113409460B CN113409460B CN202110680690.XA CN202110680690A CN113409460B CN 113409460 B CN113409460 B CN 113409460B CN 202110680690 A CN202110680690 A CN 202110680690A CN 113409460 B CN113409460 B CN 113409460B
- Authority
- CN
- China
- Prior art keywords
- interlayer
- clastic rock
- machine learning
- rock reservoir
- reservoir
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/05—Geographic models
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Geophysics (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Remote Sensing (AREA)
- Computer Graphics (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention discloses a clastic rock reservoir interlayer machine learning type three-dimensional quantitative characterization method, which accurately evaluates the spatial distribution and the rule of a clastic rock reservoir interlayer by utilizing the quantitative index of typical rock electrical parameters reflecting clastic rock reservoir interlayer characteristics and identifying the interlayer parameter type and the standard thereof through machine learning, provides more effective three-dimensional technical information for clastic rock oil and gas reservoir development, optimizes favorable blocks for clastic rock oil and gas reservoir development, improves the prediction accuracy of the residual oil enrichment favorable blocks, improves the oil and gas reservoir development efficiency and reduces the oil and gas reservoir development cost.
Description
Technical Field
The embodiment of the invention relates to the technical field of clastic rock reservoir oil and gas development and design, in particular to a clastic rock reservoir interlayer machine learning type three-dimensional quantitative characterization method.
Background
The quantitative characterization of the interlayer in the clastic rock reservoir is a world-level technical problem which is not fundamentally solved and is required to be solved for a long time in oil and gas reservoir development engineering. Due to the limitation of the resolution of well seismic data, the well seismic data cannot be directly and effectively used for describing the clastic rock reservoir interlayer and the space distribution thereof, and with the emergence of a digital high-resolution machine learning simulation technology, a technical guarantee is provided for describing the clastic rock reservoir interlayer distribution and a model. With the development of oil gas, the amount of residual oil gas which can be developed is less and less, and great breakthrough is difficult to achieve in the non-development area of the interlayer. Therefore, it has become a necessary trend to extend the development of residual oil to the interbed development zone. Clastic reservoir interbedding is a dominant factor affecting remaining oil distribution and retention. During long-term development, clastic rock reservoir interbedded layers are barriers for controlling fluid seepage and are one of the key contents for describing the residual oil in the development of oil and gas reservoirs.
In the prior art, the characteristic description of an interlayer disclosed by a core of a coring well can only be evaluated based on a clastic rock reservoir sedimentary geological model, but the type and distribution of the interlayer of a non-coring well and a non-well region cannot be represented, so that the characterization of the interlayer in the clastic rock reservoir cannot be effectively implemented, the prediction of the distribution of residual oil is inaccurate, and the development efficiency of an oil reservoir in the middle and later stages of development is low.
The novel method for quantitatively representing the clastic rock reservoir inner interlayer is urgently needed in the prior art, the clastic rock reservoir inner interlayer type and the space change of the clastic rock reservoir inner interlayer can be accurately determined, the interlayer and the residual oil distribution pattern are further determined, and accurate geological basis is provided for implementation of residual oil development measures, so that the method is favorable for predicting the residual oil space distribution rule, better guides the residual oil deep development, improves the efficiency and reduces the risk.
Disclosure of Invention
The invention aims to overcome the defects of the background technology and provide a machine learning type three-dimensional quantitative characterization method for clastic rock reservoir interlayers so as to accurately evaluate the spatial distribution and the rule of the clastic rock reservoir interlayers, improve the prediction accuracy of the residual oil enrichment favorable block and the development efficiency of an oil and gas reservoir and reduce the development cost of the oil and gas reservoir.
The invention provides a clastic rock reservoir interlayer machine learning type three-dimensional quantitative characterization method which comprises the following steps:
according to geological conditions and research target requirements, systematically observing and describing the core of a coring well in different sedimentary microphases in a target area, determining the type of an interlayer in a core clastic rock reservoir, establishing longitudinal series of comprehensive column charts of the core interlayer of each coring well, and determining parameters and reference values thereof obtained by machine learning, identifying and judging the interlayer;
establishing a matching relation between the type and thickness of each sedimentary microfacies inner interlayer of the clastic rock disclosed by the straight well core sample and the electrical property of sound waves, gamma rays and neutrons logging on the basis of the core interlayer comprehensive histogram of the coring well, and obtaining an electrical property value standard capable of effectively calculating the interlayer thickness by applying a machine learning method;
thirdly, identifying and judging the interlayer type drilled and encountered by the horizontal well through machine learning based on the matching relation between the interlayer type established by the vertical well and the electric property of the acoustic wave, gamma and neutron logging, establishing a single-well interlayer acoustic wave, gamma and neutron parameter model of the horizontal well, and solving the length and width of the interlayer plane spread;
fourthly, performing machine learning earthquake forward modeling according to the acoustic wave, gamma and neutron parameter models established for the vertical well and the horizontal well, and establishing an earthquake forward modeling interlayer model under the constraint of drilling interlayer model parameters;
fifthly, setting lithology and geostatistical random seismic inversion parameters and conditions by means of an interlayer space model established by the seismic forward modeling model, respectively performing interlayer seismic inversion simulation under a single parameter, searching for sensitive parameters by means of machine learning, and improving interlayer identification precision and resolution to perform interlayer simulation constrained by multiple sensitive parameters; carrying out seismic inversion of the dominant lithology machine learning method under the phase control constraint, establishing an interlayer space distribution model under the control of multiple sensitive parameters, and obtaining interlayer three-dimensional space scale parameters: thickness, length, width and the mutual butt joint and overlapping range;
and step six, learning an interlayer distribution model under the control of multiple sensitive parameters by applying a machine learning method, establishing a lithofacies model under different constraint conditions and a lithological inversion body constrained three-dimensional lithofacies modeling by adopting a sequential indication simulation method and a multi-point geostatistics method, establishing an interlayer three-dimensional model under the constraint of the lithofacies model, predicting the interlayer type and the spatial distribution characteristics in the clastic rock reservoir of the oil-gas reservoir development layer system, and providing quantitative evaluation parameter indexes for clastic rock reservoir evaluation and residual oil distribution prediction.
In the above technical solution, the first step is composed of the following items:
the selection criteria of the clastic rock reservoir interlayer machine learning quantitative characterization parameters are as follows: the logging parameter type is required to be capable of distinguishing the type of the interlayer in the clastic rock reservoir of the research block;
and secondly, the evaluation standard of the interlayer classification machine learning parameter quantitative value or the interlayer quantitative characterization parameter in the clastic rock reservoir can effectively and clearly distinguish various interlayers.
In the above technical solution, the step five is composed of the following items:
the interlayer classification machine learning earthquake forward modeling and machine learning earthquake inversion quantitative value in the clastic rock reservoir can effectively and clearly distinguish various interlayers and establish an interlayer three-dimensional space distribution model under the control of multiple sensitive parameters;
secondly, the interlayer classification machine in the clastic rock reservoir learns the quantitative values of the multiple sensitive parameters, so that various interlayers can be clearly distinguished, and an interlayer three-dimensional model under the constraint of a lithofacies model is established;
and thirdly, the results of clastic rock reservoir interlayer classification and three-dimensional space distribution can reflect the difference of various clastic rock reservoir residual oil enrichment main control influence factors.
The clastic rock reservoir interlayer machine learning type three-dimensional quantitative characterization method provided by the invention utilizes quantitative indexes of typical rock electrical parameters reflecting clastic rock reservoir interlayer characteristics, identifies the parameter type and the standard of an interlayer through machine learning, accurately evaluates the spatial distribution and the rule of the interlayer in the clastic rock reservoir, provides more effective three-dimensional technical information for clastic rock oil and gas reservoir development, optimizes favorable blocks for clastic rock oil and gas reservoir development, improves the prediction accuracy of the residual oil enrichment favorable blocks, improves the oil and gas reservoir development efficiency and reduces the oil and gas reservoir development cost.
Compared with the prior art, the invention has the following beneficial effects:
1) the research and evaluation method of the clastic rock reservoir inner interlayer is innovated, typical well seismic sensitive parameters reflecting the reservoir interlayer characteristics and quantitative indexes thereof are utilized, and the plane basic characteristics of the clastic rock reservoir inner interlayer in the same microphase and the clastic rock reservoir inner interlayer space distribution characteristics and rules of a certain layer of the clastic rock reservoir are accurately known by means of machine learning, so that more effective technical information is provided for clastic rock oil and gas reservoir development;
2) the oil and gas reservoir fine description efficiency of oil and gas reservoir development is high, the clastic rock reservoir in the target area is subjected to interlayer research by using a clastic rock reservoir interlayer classification machine learning evaluation method, the distribution range of clastic rock interlayers of all layers is found out, and on the basis, the clastic rock reservoir of all layers is evaluated by using an oil and gas reservoir evaluation method based on interlayer constraint, so that the oil and gas reservoir development efficiency is improved, and the clastic rock oil and gas reservoir development progress is accelerated;
3) the invention effectively fuses a large amount of logging parameters, seismic data and well-seismic forward and backward modeling data which are frequently used in clastic rock oil and gas reservoir development, establishes comprehensive sensitive parameter evaluation indexes of interlayers in clastic rock reservoirs by applying a machine learning method, distinguishes different interlayers in the same sedimentary microfacies of the clastic rock reservoirs by using the absolute average value of each index, establishes an interlayer three-dimensional model under the constraint of a petrographic model by learning an interlayer distribution model under the control of multiple sensitive parameters, optimizes favorable blocks of the clastic rock reservoir oil and gas reservoir development, improves the prediction accuracy of the favorable blocks, improves the efficiency of the oil and gas reservoir development and reduces the development cost of the oil and gas reservoir.
Drawings
Fig. 1 is a schematic flow chart of a clastic rock reservoir interlayer machine learning type three-dimensional quantitative characterization method provided by an embodiment of the invention.
Detailed Description
The application of the principles of the present invention will be further described with reference to the accompanying drawings and specific embodiments.
As shown in figure 1, the machine learning type three-dimensional quantitative characterization method for clastic rock reservoir interlayers disclosed by the invention comprises the following steps:
s110, systematically observing and describing the core of the coring well in different sedimentary microphase zones in the same oil and gas reservoir development block according to geological conditions and research target requirements, determining the type of the interlayer in the core clastic rock reservoir, and establishing a comprehensive column diagram of the core interlayer longitudinal sequence of each coring well; and determining parameters and reference values thereof required by the machine learning identification judgment interlayer.
The geological conditions at least comprise a research geological horizon, drilling coring data, logging data, rock types of corresponding horizons around the basin, outcrop and the like; research targets comprise the heterogeneity of interlayers and reservoirs, the distribution of interlayers and residual oil and the like; the longitudinal sequence comprehensive bar chart represents stratum sequence, thickness, lithology change, contact relation and the like in a plane area. The parameters required by the identification and judgment of the interlayer comprise at least one of rock type, color, bedding structure, deposition structure, interlayer thickness, attitude, position of the interlayer from bottom to top and distance of the core.
Alternatively, the core of the cored well may be described in terms of rock type, color, bedding structure, sedimentary formations, and thickness, attitude, type, location of interbeddings, etc. of the core.
Further, the selection criteria of the clastic rock reservoir interlayer machine learning quantitative characterization parameters are as follows: the logging parameter types are to be able to distinguish the type of the interlayer in the clastic rock reservoir of the research block.
Furthermore, the evaluation standard of the quantitative value of the interlayer classification machine learning parameter or the quantitative interlayer characterization parameter in the clastic rock reservoir can effectively and clearly distinguish various interlayers.
S120, based on the core interlayer comprehensive histogram of the coring well, establishing a matching relation between each sedimentary microfacies inner interlayer type of the clastic rock disclosed by the core sample of the straight well and the electrical property of the acoustic wave, gamma ray and neutron logging, and obtaining an electrical property value standard capable of effectively calculating the interlayer type by applying a machine learning method.
S130, based on the matching relation between the interlayer type established by the vertical well and the electrical property of the acoustic wave, gamma ray and neutron logging well, machine learning, identifying and judging the interlayer type drilled by the horizontal well, establishing a machine learning parameter model of the acoustic wave, gamma ray and neutron of the horizontal well layer, and obtaining the length and width of the interlayer plane spread.
Although the horizontal well and the vertical well are wells of different types and are drilled at different positions, the horizontal well and the vertical well are connected based on numerical values (standard values) of logging information of the same development area, and the logging numerical values of the horizontal well and the horizontal well are the same. Therefore, the interlayer type of the horizontal well drilling can be identified according to the interlayer logging electrical parameter model and the electrical value standard of the vertical well, and the interlayer logging electrical parameter model of the horizontal well is determined.
Because the track of the horizontal well usually extends along the layer, and the interlayer is also spread along the layer, the horizontal well can reveal the change of the plane (along the layer) of the interlayer spread, and the length and the width of the interlayer can be calculated.
S140, performing machine learning earthquake forward modeling according to the acoustic wave, gamma and neutron parameter models established by the vertical well and the horizontal well, and establishing a forward interlayer model under the restriction of the drilling interlayer model.
Due to the complexity of geological phenomena and the indirection of methods such as well logging, a single model cannot be used for identification, and the use of multiple models is more beneficial to identification.
S150, setting lithology and geostatistical random inversion parameters and conditions by means of an interlayer space model established by a forward model, respectively performing interlayer inversion simulation under the condition of machine learning single parameter, searching for sensitive parameters, improving interlayer identification precision and resolution ratio, performing interlayer simulation constrained by multiple sensitive parameters, performing lithology inversion under phase control constraint, establishing an interlayer space distribution model under the control of multiple sensitive parameters, and acquiring interlayer three-dimensional space scale parameters: thickness, length, width and the mutual butt joint and overlapping range.
Due to the fact that a single parameter is not accurate enough, accuracy of prediction can be improved through multi-parameter sensitivity analysis, and interlayer simulation of multi-sensitive parameter constraint can be conducted.
Furthermore, the interlayer classification machine learning earthquake forward modeling and machine learning earthquake inversion quantitative values in the clastic rock reservoir can effectively and clearly distinguish various interlayers and establish an interlayer three-dimensional space distribution model under the control of multiple sensitive parameters.
Furthermore, the interlayer classification machine in the clastic rock reservoir learns the quantitative values of the multiple sensitive parameters, so that various interlayers can be clearly distinguished, and an interlayer three-dimensional model under the constraint of a lithofacies model is established.
And furthermore, the results of clastic rock reservoir interlayer classification and three-dimensional space distribution can reflect the difference of various clastic rock reservoir residual oil enrichment main control influence factors.
S160, learning an interlayer distribution model under the control of multiple sensitive parameters by applying a machine learning method, establishing a lithofacies model under different constraint conditions and a lithological inversion body constrained three-dimensional lithofacies modeling by adopting a sequential indication simulation method and a multipoint geostatistics method, establishing an interlayer three-dimensional model under the constraint of the lithofacies model, and representing the interlayer type and the spatial distribution in the clastic rock reservoir.
The method for machine learning quantitative characterization of the clastic rock reservoir interlayer provided by the invention utilizes the quantitative index of typical rock-electricity parameters reflecting clastic rock reservoir interlayer characteristics, identifies the parameter type and the standard of the interlayer through machine learning, accurately evaluates the spatial distribution and the rule of the clastic rock reservoir interlayer, provides more effective three-dimensional technical information for clastic rock oil and gas reservoir development, optimizes favorable blocks for clastic rock oil and gas reservoir development, improves the prediction accuracy of the residual oil enrichment favorable blocks, improves the oil and gas reservoir development efficiency and reduces the oil and gas reservoir development cost.
According to geological conditions and research target requirements, systematically observing and describing the core of a coring well in different sedimentary microphases in a target area, determining the type of an interlayer in a core clastic rock reservoir, establishing longitudinal series of comprehensive column charts of the core interlayer of each coring well, and determining parameters and reference values thereof obtained by machine learning, identifying and judging the interlayer;
establishing a matching relation between the type and thickness of each sedimentary microfacies inner interlayer of the clastic rock disclosed by the straight well core sample and the electrical property of sound waves, gamma rays and neutrons logging on the basis of the core interlayer comprehensive histogram of the coring well, and obtaining an electrical property value standard capable of effectively calculating the interlayer thickness by applying a machine learning method;
thirdly, identifying and judging the interlayer type drilled and encountered by the horizontal well through machine learning based on the matching relation between the interlayer type established by the vertical well and the electric property of the acoustic wave, gamma and neutron logging, establishing a single-well interlayer acoustic wave, gamma and neutron parameter model of the horizontal well, and solving the length and width of the interlayer plane spread;
fourthly, performing machine learning earthquake forward modeling according to the acoustic wave, gamma and neutron parameter models established for the vertical well and the horizontal well, and establishing an earthquake forward modeling interlayer model under the constraint of drilling interlayer model parameters;
fifthly, setting lithology and geostatistical random seismic inversion parameters and conditions by means of an interlayer space model established by the seismic forward modeling model, respectively performing interlayer seismic inversion simulation under a single parameter, searching for sensitive parameters by means of machine learning, and improving interlayer identification precision and resolution to perform interlayer simulation constrained by multiple sensitive parameters; carrying out seismic inversion of the dominant lithology machine learning method under the phase control constraint, establishing an interlayer space distribution model under the control of multiple sensitive parameters, and obtaining interlayer three-dimensional space scale parameters: thickness, length, width and the mutual butt joint and overlapping range;
and step six, learning an interlayer distribution model under the control of multiple sensitive parameters by applying a machine learning method, establishing a lithofacies model under different constraint conditions and a lithological inversion body constrained three-dimensional lithofacies modeling by adopting a sequential indication simulation method and a multi-point geostatistics method, establishing an interlayer three-dimensional model under the constraint of the lithofacies model, predicting the interlayer type and the spatial distribution characteristics in the clastic rock reservoir of the oil-gas reservoir development layer system, and providing quantitative evaluation parameter indexes for clastic rock reservoir evaluation and residual oil distribution prediction.
The invention provides solid basic information related to the development characteristics of the interlayer in the clastic rock reservoir in the research area and the enrichment degree of the residual oil for the development and evaluation of the clastic rock reservoir, reduces the development range of the oil-gas reservoir and aims at the development target of the oil-gas reservoir, thereby improving the prediction accuracy of the target area to different degrees, avoiding the risk of failure of oil-gas drilling caused by the fact that the interlayer space distribution cannot provide accurate data because only the interlayer in the clastic rock reservoir at the coring well point is known, greatly improving the guarantee rate of the success of the adjustment of the well drilling of the clastic rock reservoir because the oil-gas enrichment degrees of the clastic rock reservoirs in different interlayers have great difference, accelerating the development progress of the clastic rock reservoir and greatly reducing the development cost of the oil-gas reservoir.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Those not described in detail in this specification are within the skill of the art.
Claims (3)
1. A clastic rock reservoir interlayer machine learning type three-dimensional quantitative characterization method is characterized by comprising the following steps:
according to geological conditions and research target requirements, systematically observing and describing core of coring wells in different sedimentary microphase zones in a target area, determining the type of interlayers in a core clastic rock reservoir, establishing longitudinal series of comprehensive histograms of the core interlayers of the coring wells, and determining parameters and reference values of the parameters, which are obtained by identifying the interlayers through machine learning;
establishing a matching relation between the type and thickness of each sedimentary microfacies inner interlayer of the clastic rock disclosed by the vertical well core sample and the electric properties of sound waves, gamma rays and neutron logging on the basis of the longitudinal series of comprehensive column graphs of the core interlayer of the coring well, and obtaining an electric property value standard capable of effectively calculating the thickness of the interlayer by applying a machine learning method;
thirdly, identifying and judging the interlayer type drilled and encountered by the horizontal well through machine learning based on the matching relation between the interlayer type established by the vertical well and the acoustic wave, gamma and neutron logging electrical property, establishing a single-well interlayer acoustic wave, gamma and neutron parameter model of the horizontal well, and obtaining the length and width of the interlayer plane spread;
fourthly, performing machine learning earthquake forward modeling according to acoustic wave, gamma and neutron parameter models established by the vertical well and the horizontal well, and establishing an earthquake forward interlayer model under the constraint of drilling interlayer model parameters;
fifthly, setting lithology and geostatistical random seismic inversion parameters and conditions by means of an interlayer space model established by the seismic forward modeling model, respectively performing interlayer seismic inversion simulation under a single parameter, searching for sensitive parameters by means of machine learning, and improving interlayer identification precision and resolution to perform interlayer simulation constrained by multiple sensitive parameters; carrying out seismic inversion of the dominant lithology machine learning method under the phase control constraint, establishing an interlayer space distribution model under the control of multiple sensitive parameters, and obtaining interlayer three-dimensional space scale parameters: thickness, length, width and the mutual butt joint and overlapping range;
and step six, learning an interlayer distribution model under the control of multiple sensitive parameters by applying a machine learning method, establishing a lithofacies model under different constraint conditions and a lithological inversion body constrained three-dimensional lithofacies modeling by adopting a sequential indication simulation method and a multi-point geostatistics method, establishing an interlayer three-dimensional model under the constraint of the lithofacies model, predicting the interlayer type and the spatial distribution characteristics in the clastic rock reservoir of the oil-gas reservoir development layer system, and providing quantitative evaluation parameter indexes for clastic rock reservoir evaluation and residual oil distribution prediction.
2. The clastic rock reservoir interbed machine-learning three-dimensional quantitative characterization method of claim 1, characterized in that: the first step is composed of the following items:
the selection criteria of the clastic rock reservoir interlayer machine learning quantitative characterization parameters are as follows: the logging parameter type is required to be capable of distinguishing the type of the interlayer in the clastic rock reservoir of the research block;
and secondly, the evaluation standard of the interlayer classification machine learning parameter quantitative value or the interlayer quantitative characterization parameter in the clastic rock reservoir can effectively and clearly distinguish various interlayers.
3. The clastic rock reservoir interbed machine-learning three-dimensional quantitative characterization method of claim 1 or 2, wherein: the step five is composed of the following items:
the interlayer classification machine learning earthquake forward modeling and machine learning earthquake inversion quantitative value in the clastic rock reservoir can effectively and clearly distinguish various interlayers and establish an interlayer three-dimensional space distribution model under the control of multiple sensitive parameters;
secondly, the interlayer classification machine in the clastic rock reservoir learns the quantitative values of the multiple sensitive parameters, so that various interlayers can be clearly distinguished, and an interlayer three-dimensional model under the constraint of a lithofacies model is established;
and thirdly, the results of clastic rock reservoir interlayer classification and three-dimensional space distribution can reflect the difference of various clastic rock reservoir residual oil enrichment main control influence factors.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110680690.XA CN113409460B (en) | 2021-06-18 | 2021-06-18 | Machine learning type three-dimensional quantitative characterization method for clastic rock reservoir interlayer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110680690.XA CN113409460B (en) | 2021-06-18 | 2021-06-18 | Machine learning type three-dimensional quantitative characterization method for clastic rock reservoir interlayer |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113409460A CN113409460A (en) | 2021-09-17 |
| CN113409460B true CN113409460B (en) | 2022-06-14 |
Family
ID=77681660
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110680690.XA Active CN113409460B (en) | 2021-06-18 | 2021-06-18 | Machine learning type three-dimensional quantitative characterization method for clastic rock reservoir interlayer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113409460B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103852787A (en) * | 2014-02-24 | 2014-06-11 | 长江大学 | Representation method for diagenetic seismic facies of sandstone reservoir |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103077558B (en) * | 2012-05-14 | 2015-12-09 | 中国石油化工股份有限公司 | The modeling method of fracture and vug carbonate reservoir large-scale solution cavity Reservoir Body distributed model |
| CN107807407B (en) * | 2017-09-30 | 2019-10-11 | 中国石油天然气股份有限公司 | A kind of petroleum zone efficiency evaluation method and apparatus |
| CN110929364A (en) * | 2018-09-20 | 2020-03-27 | 中国石油化工股份有限公司 | Quantitative evaluation method for microcracks of compact clastic rock reservoir |
-
2021
- 2021-06-18 CN CN202110680690.XA patent/CN113409460B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103852787A (en) * | 2014-02-24 | 2014-06-11 | 长江大学 | Representation method for diagenetic seismic facies of sandstone reservoir |
Non-Patent Citations (8)
| Title |
|---|
| 低渗透储层产能预测的测井优化建模;刘晓虹等;《西南石油大学学报(自然科学版)》;20110620;第第33卷卷(第03期);第115-120页 * |
| 复杂孔隙结构碳酸盐岩储层建模――以伊拉克米桑油田群B油田M组为例;陈培元等;《科学技术与工程》;20190418;第第19卷卷(第11期);第81-88页 * |
| 水平井参与下的油藏隔夹层描述技术及应用;夏竹等;《石油与天然气地质》;20181231;第第39卷卷(第06期);第1293-304页 * |
| 海上复杂碎屑岩储层油气藏地质建模关键技术;叶小明等;《中国海上油气》;20180703;第第30卷卷(第03期);第110-115页 * |
| 海相碎屑岩水平井隔夹层识别与表征――以哈得逊油田东河砂岩为例;余义常等;《中国矿业大学学报》;20180724;第第47卷卷(第06期);第1313-1324页 * |
| 综合多学科信息建模――以港东开发区二区六区块储层微相三维分布模型为例;尹艳树等;《天然气地球科学》;20070610;第第18卷卷(第03期);第408-411页 * |
| 致密碎屑岩裂缝性储层预测方法综述;张雨晴等;《科技导报》;20100728;第第28卷卷(第14期);第109-112页 * |
| 鄂尔多斯盆地LX地区山西组储层成岩演化及成岩相研究;王存武等;《沉积学报》;20160615;第第34卷卷(第03期);第594-605页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113409460A (en) | 2021-09-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US4646240A (en) | Method and apparatus for determining geological facies | |
| US9097821B2 (en) | Integrated workflow or method for petrophysical rock typing in carbonates | |
| CN105317375B (en) | Horizontal well is inducted into Target process and device | |
| US20180238148A1 (en) | Method For Computing Lithofacies Probability Using Lithology Proximity Models | |
| CN105005077A (en) | Thin layer thickness prediction method with combination of real drilling wells and virtual wells under rare well condition | |
| Harris | The role of geology in reservoir simulation studies | |
| Kamali et al. | 3D geostatistical modeling and uncertainty analysis in a carbonate reservoir, SW Iran | |
| Wang et al. | Application of horizontal wells in three-dimensional shale reservoir modeling: A case study of Longmaxi–Wufeng shale in Fuling gas field, Sichuan Basin | |
| Cuddy | The application of the mathematics of fuzzy logic to petrophysics | |
| CN112505754B (en) | Method for collaborative partitioning sedimentary microfacies by well-seismic based on high-precision sequence grid model | |
| CN112182966B (en) | Biological disturbance reservoir layer identification method based on multi-source logging data | |
| Jasim et al. | Specifying quality of a tight oil reservoir through 3-d reservoir modeling | |
| CN113409460B (en) | Machine learning type three-dimensional quantitative characterization method for clastic rock reservoir interlayer | |
| US11719851B2 (en) | Method and system for predicting formation top depths | |
| Olson et al. | Reservoir characterization of the giant Hugoton gas field, Kansas | |
| CN112147676A (en) | Method for predicting thickness of coal bed and gangue | |
| Ismagilov et al. | Machine learning approach to open hole interpretation and static modelling applied to a giant field | |
| Masoud et al. | Reservoir Characterization and Geostatistical Model of the Cretaceous and Cambrian-Ordovician Reservoir Intervals, Meghil Field, Sirte Basin, Libya | |
| Jageler et al. | Use of well logs and dipmeters in stratigraphic-trap exploration: geologic exploration methods | |
| RU2774819C1 (en) | Method for determining the electrical resistivity of terrigenous oil reservoirs from the data of electric logging of subvertical wells using artificial neural networks | |
| CN110927819B (en) | Crack development degree characterization method | |
| Carrizo et al. | An Integrated Petrophysical Characterization of a Siliciclastic Tight Gas Reservoirs in Neuquén Basin, Western Argentina | |
| Masaud et al. | Reservoir Characterization-Geostatistical Modeling of the Paleocene Zelten Carbonate Reservoir. Case study: Meghil Field, Sirte Basin, Libya | |
| Kolomytsev et al. | 3D Petrophysics for HAWE: Case Studies | |
| Sena et al. | Multiscale and multidisciplinary data-driven reservoir characterization of a fractured carbonate field in Kurdistan |
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 |