CN114397711A - Unconventional tight sandstone reservoir porosity prediction method based on machine learning - Google Patents
Unconventional tight sandstone reservoir porosity prediction method based on machine learningDownload PDFInfo
- Publication number
- CN114397711A CN114397711ACN202111442082.1ACN202111442082ACN114397711ACN 114397711 ACN114397711 ACN 114397711ACN 202111442082 ACN202111442082 ACN 202111442082ACN 114397711 ACN114397711 ACN 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
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 OR CALCULATING; 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
Description
Translated fromChinese技术领域technical field
本发明属于致密砂岩矿产资源勘探技术领域，具体涉及一种基于机器学习的非常规致密砂岩孔隙度进行预测方法。The invention belongs to the technical field of tight sandstone mineral resource exploration, in particular to a method for predicting the porosity of unconventional tight sandstone based on machine learning.
背景技术Background technique
在沉积盆地中，与砂岩孔隙度有关的沉积矿产资源非常丰富，包括流体矿产的运移和富集也包括固体成矿的沉淀与形成等。人们通过运用地球物理数据，尤其是声波时差、中子孔隙度、密度等测井数据，可以建立较好的砂体孔隙度解释模型，并广泛应用于常规资源的勘探和开发中。但随着近几年在非常规资源，如致密油气等领域的突破，我们也逐渐突破了常规资源勘探的瓶颈。但是，伴随着非常规资源的往往是更复杂的地质条件，对致密砂岩来讲，其最主要的特征是低孔低渗，这导致致密砂岩储层孔隙度预测无法照搬常规储层孔隙度预测模型的建立方法，并且由于低孔低渗储层的成因和影响因素复杂，导致其预测难度更大。但是，对致密砂岩孔隙度的准确预测依然是解决与其紧密相关的矿产资源勘探和开发问题的根本需求。In sedimentary basins, sedimentary mineral resources related to sandstone porosity are very abundant, including the migration and enrichment of fluid minerals and the precipitation and formation of solid mineralization. By using geophysical data, especially logging data such as acoustic transit time, neutron porosity, and density, a better interpretation model of sand body porosity can be established, which is widely used in the exploration and development of conventional resources. However, with breakthroughs in unconventional resources, such as tight oil and gas, in recent years, we have gradually broken through the bottleneck of conventional resource exploration. However, unconventional resources are often accompanied by more complex geological conditions. For tight sandstone, the most important feature is low porosity and low permeability, which makes the prediction of tight sandstone reservoir porosity impossible to copy conventional reservoir porosity prediction. The modeling method and the complex formation and influencing factors of low-porosity and low-permeability reservoirs make its prediction more difficult. However, accurate prediction of tight sandstone porosity is still the fundamental requirement to solve the closely related mineral resource exploration and development problems.
近年来，随着机器学习技术和方法的日趋成熟，在数据处理、数据分析、模式搜索和规律寻找等方面表现出较强的能力。对复杂地质问题的处理正是对多层次、多类型、大数据的综合分析和研究。因此，机器学习恰好具有解决复杂地质问题的能力和优势。同时，很多地质学家也迅速认识到该方法的先进性，均在不断加强学科合作和技术融合。但是在致密砂岩领域，尤其是对致密砂岩孔隙度的预测问题，尚需要建立一套完整的技术方法体系，实现机器学习方法在致密砂岩矿产资源勘探和开发领域的应用。In recent years, with the maturity of machine learning technology and methods, it has shown strong capabilities in data processing, data analysis, pattern search and rule finding. The treatment of complex geological problems is the comprehensive analysis and research of multi-level, multi-type and big data. Therefore, machine learning happens to have the ability and advantage to solve complex geological problems. At the same time, many geologists have quickly recognized the advanced nature of this method, and are constantly strengthening disciplinary cooperation and technical integration. However, in the field of tight sandstone, especially the prediction of tight sandstone porosity, it is still necessary to establish a complete set of technical method system to realize the application of machine learning method in the field of tight sandstone mineral resource exploration and development.
发明内容SUMMARY OF THE INVENTION
本发明的目的在于，针对目前非常规致密砂岩储层孔隙度较难预测的问题，提出一种基于机器学习方法致密砂岩储层孔隙度预测方法，该方法基于现有的岩石地球物理数据，综合多种参数，实现了对致密砂岩储层孔隙度较好的预测。The purpose of the present invention is to propose a method for predicting the porosity of tight sandstone reservoirs based on the machine learning method, aiming at the problem that the porosity of unconventional tight sandstone reservoirs is difficult to predict at present. A variety of parameters are used to achieve better prediction of the porosity of tight sandstone reservoirs.
本发明采用的技术方案：The technical scheme adopted in the present invention:
一种基于机器学习的非常规致密砂岩孔隙度进行预测方法，包括如下步骤：步骤1、从钻井岩心分析测试数据和测井数据中提取用于预测的样本数据；步骤2、数据预处理；步骤3、基于不同机械学习方法，训练多个孔隙度预测模型；步骤4、交叉验证；步骤5、优化各个模型；步骤6、新数据的加入和模型的重新优化。A method for predicting the porosity of unconventional tight sandstone based on machine learning, comprising the following steps: step 1, extracting sample data for prediction from drilling core analysis test data and logging data;
所述步骤1中，获取致密砂岩岩心样品分析测试孔隙度和与岩石孔隙度有关的测井数据组成数据集，并以岩心样品分析测试孔隙度作为监督学习的目标集，以自然伽马、自然电位、声波时差、中子孔隙度、密度和深侧向电阻率以及埋藏深度为特征集。In the step 1, the tight sandstone core sample analysis test porosity and the logging data related to the rock porosity are obtained to form a data set, and the core sample analysis test porosity is used as the target set of supervised learning. Potential, acoustic transit time, neutron porosity, density and deep lateral resistivity, and burial depth are feature sets.
对步骤1中收集到的数据进行清洗和统计分析，对孔隙度测量异常点、测井参数获取的异常值进行移出；统计分析每类参数的统计分布，划分不同岩石类型、不同沉积相类型、不同成岩阶段的各类岩石测井参数特征，全面掌握数据特征和数据内涵。The data collected in step 1 is cleaned and statistically analyzed, and the abnormal points of porosity measurement and the abnormal values obtained by logging parameters are removed; the statistical distribution of each type of parameters is statistically analyzed, and different rock types, different sedimentary facies types, Logging parameter characteristics of various rocks in different diagenetic stages, and comprehensively master data characteristics and data connotations.
所述步骤2中，包括如下步骤：In the
步骤2.1、校正测井数据中的测井深度和样品数据中的岩心样品深度，将特征集和目标集进行匹配关联；Step 2.1. Correct the logging depth in the logging data and the core sample depth in the sample data, and match and associate the feature set with the target set;
步骤2.2、对特征集中的自然伽马、自然电位、声波时差、中子孔隙度、密度、深侧向电阻率和埋藏深度这些特征数据进行归一化处理；Step 2.2, normalize the characteristic data of natural gamma, natural potential, acoustic time difference, neutron porosity, density, deep lateral resistivity and burial depth in the feature set;
步骤2.3、对归一化后的特征集进行降维处理。Step 2.3. Perform dimensionality reduction processing on the normalized feature set.
所述步骤2.2中，归一化方法采用：In the step 2.2, the normalization method adopts:
其中：xnormal为一特征数据归一化后的数据，xmin代表这一特征数据中的最小值，xmax代表这一特征数据中最大值。Among them: xnormal is the normalized data of a feature data, xmin represents the minimum value in the feature data, and xmax represents the maximum value in the feature data.
所述步骤2.3中，通过对各特征值之间的相关性进行分析，结合各测井数据的实际物理意义对岩石孔隙度的响应机理，通过分析特征数据的相关性及主成分分析，对特征数据集进行降维判断和处理。In the step 2.3, by analyzing the correlation between the characteristic values, combined with the actual physical meaning of each logging data to the response mechanism of the rock porosity, by analyzing the correlation of the characteristic data and the principal component analysis, the characteristic data is analyzed. The dataset is subjected to dimensionality reduction judgment and processing.
所述步骤3中，将降维处理后的特征集平均分为5份，将对应的目标集也分为相应的5份；依次选择第五步中的一份数据i作为测试集的特征集F_test(i)，对应的目标集为测试集的目标集T_test(i)，其余4份数据组成训练集合的特征集F_train(i)和目标集T_train(i)；通过多次训练，选择最优的训练结果；选择不同的机器学习算法，训练对个孔隙度预测模型。In the step 3, the feature set after dimensionality reduction processing is divided into 5 parts on average, and the corresponding target set is also divided into corresponding 5 parts; one piece of data i in the fifth step is selected as the feature set of the test set in turn. F_test(i), the corresponding target set is the target set T_test(i) of the test set, and the remaining 4 pieces of data form the feature set F_train(i) and target set T_train(i) of the training set; through multiple trainings, select the best training results; choose different machine learning algorithms to train a pair of porosity prediction models.
所述步骤4中，根据每个已经训练模型的交叉验证结果，对每个训练模型进行评价。In the
所述步骤5中，评价指标包括均方误差MSE、均方根误差RMSE、平均绝对误差MAE和R2。In the step 5, the evaluation indicators include mean square error MSE, root mean square error RMSE, mean absolute error MAE and R2 .
所述MSE的计算方法如下：The calculation method of the MSE is as follows:
其中RMSE的计算方法如下：The calculation method of RMSE is as follows:
其中MAE的计算方法如下：The calculation method of MAE is as follows:
其中R2的计算方法如下：where R2 is calculated as follows:
其中，yi为测试集中样品实际分析测试孔隙度；
与现有技术相比，本发明的有益效果在于：Compared with the prior art, the beneficial effects of the present invention are:
(1)本发明提供的一种基于机器学习的非常规致密砂岩孔隙度进行预测方法，提高了致密砂岩孔隙度的预测准确度，降低了致密砂岩中的矿产资源勘探，尤其是致密砂岩油气勘探的成本；(1) A method for predicting unconventional tight sandstone porosity based on machine learning provided by the present invention improves the prediction accuracy of tight sandstone porosity and reduces mineral resource exploration in tight sandstone, especially oil and gas exploration in tight sandstone the cost of;
(2)本发明提供的一种基于机器学习的非常规致密砂岩孔隙度进行预测方法，引入了多参数综合预测致密砂岩孔隙度的方法，引入的各参数反映致密砂岩的不同信息，包括岩石组分信息、岩石埋藏压实信息、岩石密度信息等，这些信息均与岩石孔隙度相关联。通过多信息的综合，对孔隙度进行了更准确预测；(2) The present invention provides a method for predicting the porosity of unconventional tight sandstone based on machine learning, which introduces a method for comprehensively predicting the porosity of tight sandstone with multiple parameters. The parameters introduced reflect different information of tight sandstone, including rock groups. information, rock burial compaction information, rock density information, etc., all of which are related to rock porosity. Through the synthesis of multiple information, the porosity is more accurately predicted;
(3)本发明提供的一种基于机器学习的非常规致密砂岩孔隙度进行预测方法，该预测可应用于沉积盆地中致密砂岩中流体迁移通道和富集能力的研究，也可直接应用与致密砂岩矿产资源的勘探和开发中，为矿产资源的富集规律研究、有利区预测和开采实践提供较强的科学支撑。(3) A method for predicting the porosity of unconventional tight sandstone based on machine learning provided by the present invention, the prediction can be applied to the study of fluid migration channels and enrichment capacity of tight sandstone in sedimentary basins, and can also be directly applied to tight sandstones in sedimentary basins. In the exploration and development of sandstone mineral resources, it provides strong scientific support for the study of the enrichment law of mineral resources, the prediction of favorable areas and the mining practice.
附图说明Description of drawings
图1为本发明实现基于机器学习预测致密砂岩孔隙度的方法流程图。Fig. 1 is a flow chart of the method for implementing prediction of tight sandstone porosity based on machine learning in the present invention.
图2为某油田区块岩心样品分析测试孔隙度与机器学习预测孔隙度对比图。Figure 2 is a comparison diagram of the porosity measured by core sample analysis in an oilfield block and the porosity predicted by machine learning.
具体实施方式Detailed ways
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
在本发明的描述中，需要说明的是，术语“中心”、“上”、“下”、“左”、“右”“竖直”、“水平”、“内”、“外”等指示的方位或位置关系为基于附图所示的方位或位置关系，仅是为了便于描述本发明和简化描述，而不是指示或暗示所指的装置或元件必须具有特定的方位、以特定的方位构造和操作，因此不能理解为对本发明的限制。此外，术语“第一”、“第二”、“第三”仅用于描述目的，而不能理解为指示或暗示相对重要性。In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer" and the like indicate The orientation or positional relationship is based on the orientation or positional relationship shown in the accompanying drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred device or element must have a specific orientation or be constructed in a specific orientation. and operation, and therefore should not be construed as limiting the present invention. Furthermore, the terms "first", "second", and "third" are used for descriptive purposes only and should not be construed to indicate or imply relative importance.
在本发明的描述中，需要说明的是，除非另有明确的规定和限定，术语“安装”、“相连”、“连接”应做广义理解，例如，可以是固定连接，也可以是可拆卸连接，或一体地连接；可以是机械连接，也可以是电连接；可以是直接相连，也可以通过中间媒介间接相连，可以是两个元件内部的连通。对于本领域的普通技术人员而言，可以具体情况理解上述术语在本发明中的具体含义。In the description of the present invention, it should be noted that the terms "installed", "connected" and "connected" should be understood in a broad sense, unless otherwise expressly specified and limited, for example, it may be a fixed connection or a detachable connection Connection, or integral connection; can be mechanical connection, can also be electrical connection; can be directly connected, can also be indirectly connected through an intermediate medium, can be internal communication between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood in specific situations.
如图1所示，本发明提供的一种基于机器学习的非常规致密砂岩孔隙度进行预测方法，包括如下步骤：As shown in Figure 1, a method for predicting the porosity of unconventional tight sandstone based on machine learning provided by the present invention includes the following steps:
步骤1，从某一油田的岩心样品分析测试数据和测井数据中获取致密砂岩岩心样品分析测试孔隙度和与岩石孔隙度有关的测井数据组成数据集，并以岩心样品分析测试孔隙度作为监督学习的目标集，以自然伽马、自然电位、声波时差、中子孔隙度、密度和深侧向电阻率以及埋藏深度为特征集；致密砂岩钻孔岩心分析测试数据和测井数据越多、越全面对机器学习和预测结果越有利，为了系统掌握数据特征，对步骤1中收集到的数据要进行清洗和统计分析，对孔隙度测量异常点、测井参数获取的异常值等要进行移出，为了系统掌握数据特征，统计分析每类参数的统计分布，划分不同岩石类型、不同沉积相类型、不同成岩阶段等致密砂岩的各类岩石测井参数特征，全面掌握数据特征和数据内涵，为后续的模型训练做基础；Step 1: Obtain the tight sandstone core sample analysis and test porosity and the logging data related to the rock porosity from the core sample analysis test data and logging data of a certain oilfield to form a data set, and use the core sample analysis and test porosity as the data set. A target set for supervised learning, characterized by natural gamma, spontaneous potential, acoustic transit time, neutron porosity, density and deep lateral resistivity, and burial depth; more test data and logging data for tight sandstone borehole core analysis , The more comprehensive the machine learning and prediction results, the better. In order to systematically grasp the data characteristics, the data collected in step 1 should be cleaned and statistically analyzed, and the abnormal points of porosity measurement and the abnormal values obtained by logging parameters should be analyzed. Move out, in order to systematically grasp the data characteristics, statistically analyze the statistical distribution of each type of parameters, classify the characteristics of various rock logging parameters of tight sandstones such as different rock types, different sedimentary facies types, and different diagenetic stages, and comprehensively grasp the data characteristics and data connotation, Lay the foundation for subsequent model training;
步骤2，通过校正后的测井数据中的测井深度和样品数据中的岩心样品深度，将测井数据(特征集)和岩心分析测试孔隙度数据(目标集)进行匹配关联；测井数据点间隔为0.125m，因此，深度匹配差不能大于0.0625m；Step 2: Match and associate the logging data (feature set) with the core analysis test porosity data (target set) through the logging depth in the corrected logging data and the core sample depth in the sample data; the logging data The point interval is 0.125m, therefore, the depth matching difference cannot be greater than 0.0625m;
步骤3，对特征集中的自然伽马、自然电位、声波时差、中子孔隙度、密度、深侧向电阻率和埋藏深度这些特征数据进行归一化处理。归一化方法采用：Step 3, normalize the characteristic data of natural gamma, natural potential, acoustic transit time, neutron porosity, density, deep lateral resistivity and burial depth in the feature set. The normalization method uses:
其中xnormal为一特征数据归一化后的数据，xmin代表这一特征数据中的最小值，xmax代表这一特征数据中最大值，x；where xnormal is the normalized data of a feature data, xmin represents the minimum value in this feature data, xmax represents the maximum value in this feature data, x;
步骤4，对归一化后的特征集进行降维处理。通过对各特征值之间的相关性进行分析，结合各测井数据的实际物理意义对岩石孔隙度的响应机理，通过分析特征数据的相关性及主成分分析，对特征数据集进行降维判断和处理；Step 4: Perform dimensionality reduction processing on the normalized feature set. By analyzing the correlation between each feature value, combined with the actual physical meaning of each logging data to the response mechanism of rock porosity, by analyzing the correlation and principal component analysis of the feature data, the feature data set is dimensionally reduced and judged and processing;
步骤5，将降维处理后的特征集平均分为5份，将对应的目标集也分为相应的5份；Step 5, the feature set after dimensionality reduction processing is divided into 5 parts on average, and the corresponding target set is also divided into corresponding 5 parts;
步骤6，依次选择第五步中的一份数据i作为测试集的特征集F_test(i)，对应的目标集为测试集的目标集T_test(i)，其余4份数据组成训练集合的特征集F_train(i)和目标集T_train(i)；通过多次训练，选择最优的训练结果；选择不同的机器学习算法，实现多个训练模型和交叉验证结果；Step 6: Select a piece of data i in the fifth step as the feature set F_test(i) of the test set, the corresponding target set is the target set T_test(i) of the test set, and the remaining 4 pieces of data form the feature set of the training set. F_train(i) and target set T_train(i); select the optimal training result through multiple trainings; select different machine learning algorithms to achieve multiple training models and cross-validation results;
步骤7，根据每个已经训练模型的交叉验证结果，对每个训练模型进行评价。主要的评价指标包括均方误差(MSE)、均方根误差(RMSE)、平均绝对误差(MAE)和R2。其中MSE的计算方法如下：Step 7: Evaluate each trained model according to the cross-validation result of each trained model. The main evaluation indicators include mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE) and R2 . The calculation method of MSE is as follows:
其中RMSE的计算方法如下：The calculation method of RMSE is as follows:
其中MAE的计算方法如下：The calculation method of MAE is as follows:
其中R2的计算方法如下：where R2 is calculated as follows:
其中，yi为测试集中样品实际分析测试孔隙度；
步骤8，将得到的最优模型作为致密砂岩的孔隙度解释模型在研究区进行应用，解决非常规致密砂岩孔隙度较难预测的问题。In
步骤9，新数据的加入和模型的重新优化。
本实例中基于不同算法的训练结果模型的评价指标如下表1：The evaluation indicators of the training result models based on different algorithms in this example are shown in Table 1:
表1基于不同算法训练模型的评价指标Table 1 Evaluation indicators of training models based on different algorithms
如图2所示，左侧为基于随机森林算法的预测结果，右侧为基于K-邻近法算法的预测结果。结果表明基于K-邻近法和随机森林算法的训练结果模型表现出较好的预测效果。As shown in Figure 2, the left side is the prediction result based on the random forest algorithm, and the right side is the prediction result based on the K-proximity method. The results show that the training results model based on K-proximity method and random forest algorithm shows better prediction effect.
对于本领域技术人员而言，显然本发明不限于上述示范性实施例的细节，而且在不背离本发明的精神或基本特征的情况下，能够以其他的具体形式实现本发明。因此，无论从哪一点来看，均应将实施例看作是示范性的，而且是非限制性的，本发明的范围由所附权利要求而不是上述说明限定，因此旨在将落在权利要求的等同要件的含义和范围内的所有变化囊括在本发明内。不应将权利要求中的任何附图标记视为限制所涉及的权利要求。It will be apparent to those skilled in the art that the present invention is not limited to the details of the above-described exemplary embodiments, but that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments are to be regarded in all respects as illustrative and not restrictive, and the scope of the invention is to be defined by the appended claims rather than the foregoing description, which are therefore intended to fall within the scope of the claims. All changes within the meaning and scope of the equivalents of , are included in the present invention. Any reference signs in the claims shall not be construed as limiting the involved claim.
此外，应当理解，虽然本说明书按照实施方式加以描述，但并非每个实施方式仅包含一个独立的技术方案，说明书的这种叙述方式仅仅是为清楚起见，本领域技术人员应当将说明书作为一个整体，各实施例中的技术方案也可以经适当组合，形成本领域技术人员可以理解的其他实施方式。In addition, it should be understood that although this specification is described in terms of embodiments, not each embodiment only includes an independent technical solution, and this description in the specification is only for the sake of clarity, and those skilled in the art should take the specification as a whole , the technical solutions in each embodiment can also be appropriately combined to form other implementations that can be understood by those skilled in the art.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111442082.1ACN114397711A (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 |
|---|---|---|---|
| CN202111442082.1ACN114397711A (en) | 2021-11-30 | 2021-11-30 | Unconventional tight sandstone reservoir porosity prediction method based on machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114397711Atrue CN114397711A (en) | 2022-04-26 |
Family
ID=81225580
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111442082.1APendingCN114397711A (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 | A 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 | A Reservoir Physical Parameter Prediction Method Combined with 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
- 2021-11-30CNCN202111442082.1Apatent/CN114397711A/enactivePending
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 | A Reservoir Physical Parameter Prediction Method Combined with 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 | A rock porosity prediction method based on small sample while-drilling data inversion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10324229B2 (en) | System and method of pore type classification for petrophysical rock typing | |
| CN109800954B (en) | Reservoir evaluation method based on logging data | |
| CN113792936A (en) | A method, system, equipment and storage medium for intelligent identification of lithology while drilling | |
| Zhu et al. | Rapid identification of high-quality marine shale gas reservoirs based on the oversampling method and random forest algorithm | |
| CN111487691B (en) | Method for quantitatively identifying lithology and sand body structure of tight sandstone reservoir | |
| CN110619353A (en) | Multi-scale logging curve automatic identification method based on deep learning | |
| CN104047598A (en) | Heterogeneous paleo-karst carbonate reservoir productivity prediction method | |
| CN114723095A (en) | Missing logging curve prediction method and device | |
| CN114638300B (en) | A method, device and storage medium for identifying "sweet spots" in shale oil and gas reservoirs | |
| Yu et al. | Combining K‐Means Clustering and Random Forest to Evaluate the Gas Content of Coalbed Bed Methane Reservoirs | |
| CN114818076A (en) | Machine learning-based fault closed hydrocarbon column height evaluation method | |
| CN115629414A (en) | Source rock TOC prediction method, system, electronic equipment and medium in sparse well area | |
| CN116821786A (en) | Hypotonic reservoir classification method, device and medium | |
| CN119538763B (en) | Machine learning-based tight sandstone hydraulic fracture layer penetration prediction method | |
| CN119004289B (en) | A diagenetic facies identification method based on geological constraints and well logging parameter fusion clustering | |
| US20230142227A1 (en) | System and method for radioactivity prediction to evaluate formation productivity | |
| CN114397711A (en) | Unconventional tight sandstone reservoir porosity prediction method based on machine learning | |
| Sarkheil et al. | The fracture network modeling in naturally fractured reservoirs using artificial neural network based on image loges and core measurements | |
| CN111236934B (en) | Method and device for determining flooding level | |
| CN118966003A (en) | A reservoir permeability prediction method based on flow unit index classification | |
| CN118958961A (en) | Method, device, medium and equipment for evaluating geological engineering sweet spots in low-permeability sandstone reservoirs | |
| Carrasquilla et al. | Using facies, data mining and artificial intelligence concepts in the evaluation of a carbonate reservoir in Campos basin, Southeastern Brazil | |
| CN114429165A (en) | A method and device for classification of well logging fractal dimension pore structure | |
| CN117056673A (en) | Artificial intelligent identification method for logging lithofacies | |
| Damasceno et al. | Source rock evaluation from rock to seismic: Integrated machine learning based workflow |
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 | ||
| RJ01 | Rejection of invention patent application after publication | Application publication date:20220426 |