Method and device for predicting success rate of oil and gas exploration

Abstract

This invention provides a method and apparatus for predicting the success rate of oil and gas exploration. The method includes: quantitatively evaluating multiple oil and gas accumulation geological conditions in a study area to obtain multiple single-factor geological evaluation value maps; extracting the single-factor geological evaluation value of each well from each single-factor geological evaluation value map based on the location of multiple exploration wells in the study area; combining the single-factor geological evaluation value of each well and the type of each well into training set data; calculating the logarithmic Mahalanobis distance from each well to each well type in the training set data; drawing a two-dimensional Mahalanobis distance grid map based on the calculated logarithmic Mahalanobis distance; and calculating the oil and gas exploration success rate of each grid in the two-dimensional Mahalanobis distance grid map. This invention can accurately predict the success rate of oil and gas exploration.

Description

Technical Field

[0001] This invention relates to the field of geological exploration technology, and in particular to a method and apparatus for predicting the success rate of oil and gas exploration. Background Technology

[0002] Evaluate and predict the success rate of exploration targets, select favorable areas, avoid drilling risks, and provide a basis for decision-making in oil and gas drilling deployment.

[0003] Exploration risk prediction and assessment methods can be summarized into three main categories.

[0004] The first type, the genetic method, overlays geological factors controlling hydrocarbon accumulation, such as hydrocarbon source, reservoir, caprock, migration, trap, and preservation conditions, onto a single geological map. This describes the favorable areas and geological risks of the spatial distribution of hydrocarbon resources. This is a conventional method for geological risk assessment. This type of method, based on the genetic mechanism-driven overlay mapping, is a qualitative or semi-quantitative assessment. Its drawback is the lack of quantitative models or the relatively simple models.

[0005] The second category is multivariate statistical methods. These methods use statistical models to predict the spatial distribution of oil and gas resources based on information about the spatial distribution characteristics of oil and gas wells and non-oil and gas wells revealed by exploration wells. This method emphasizes information from individual wells but ignores other geological information. This second type of method only considers the distance from exploration wells to "oil and gas wells," neglecting the distance to "non-oil and gas wells," and has no advantage when the sample size is large.

[0006] The third category comprises comprehensive methods, such as object-oriented stochastic simulation and geological model-based stochastic simulation. For example, information integration methods combine geological, geophysical, and exploration engineering information to reflect the spatial distribution characteristics of oil and gas resources, and represent the distribution using maps to make the prediction results more intuitive. Another method uses multivariate statistics and information processing techniques to predict the spatial distribution of oil and gas resources. This involves integrating information using Mahalanobis distance discrimination, calculating the probability of oil and gas content in known samples using Bayes' theorem, and establishing a template for the probability of oil and gas content under different Mahalanobis distance values. This template is then used to predict the spatial distribution of oil and gas resources. A data-driven model using logistic regression integrates existing geoscience information and current exploration results to obtain a quantitative logistic regression relationship between oil and gas occurrence and key geological factors, which is then used to predict the probability of oil and gas occurrence. This third category of methods is a statistical method that combines geological understanding. It has mature statistical algorithms and a wide range of applications, but it lacks statistical experience data and models specific to regional geological conditions and drilling results, resulting in poor targeting.

[0007] In summary, the accuracy of existing methods for predicting the success rate of oil and gas exploration is relatively low. Summary of the Invention

[0008] This invention proposes a method for predicting the success rate of oil and gas exploration, which is used to accurately predict the success rate of oil and gas exploration. The method includes:

[0009] Quantitatively evaluate multiple hydrocarbon accumulation geological conditions in the study area and obtain multiple single-factor geological evaluation value maps;

[0010] Based on the location of multiple exploration wells in the study area, the single-factor geological evaluation value of each exploration well is extracted from each single-factor geological evaluation value map. The single-factor geological evaluation value of each exploration well and the type of each exploration well are combined into training set data.

[0011] Calculate the log-Madovish distance from each well to each well type in the training set data;

[0012] Draw a two-dimensional Mahalanobis distance grid based on the calculated log Mahalanobis distance;

[0013] Calculate the success rate of oil and gas exploration for each grid in a two-dimensional Mahalanobis distance grid map.

[0014] This invention provides an oil and gas detection success rate prediction device for accurately predicting the success rate of oil and gas detection. The device includes:

[0015] The module for obtaining single-factor geological evaluation value maps is used to quantitatively evaluate multiple hydrocarbon accumulation geological conditions in the study area and obtain multiple single-factor geological evaluation value maps.

[0016] The training set data acquisition module is used to extract the single-factor geological evaluation value of each well from each single-factor geological evaluation value map based on the location of multiple wells in the study area, and combine the single-factor geological evaluation value of each well and the type of each well into training set data.

[0017] The log-Mahland distance calculation module is used to calculate the log-Mahland distance from each well to each well type in the training set data.

[0018] The 2D Mahalanobis distance grid plotting module is used to plot a 2D Mahalanobis distance grid plot based on the calculated logarithmic Mahalanobis distance.

[0019] The oil and gas exploration success rate calculation module is used to calculate the oil and gas exploration success rate of each grid in a two-dimensional Mahalanobis distance grid map.

[0020] This invention also proposes a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-mentioned oil and gas detection success rate prediction method.

[0021] This invention also proposes a computer-readable storage medium storing a computer program that executes the above-described oil and gas exploration success rate prediction method.

[0022] In this embodiment of the invention, multiple hydrocarbon accumulation geological conditions in the study area are quantitatively evaluated to obtain multiple single-factor geological evaluation value maps. Based on the location of multiple exploration wells within the study area, the single-factor geological evaluation value of each well is extracted from each single-factor geological evaluation value map. The single-factor geological evaluation value of each well and the type of each well are combined to form training set data. The logarithmic Mahalanobis distance from each well to each well type in the training set data is calculated. A two-dimensional Mahalanobis distance grid map is drawn based on the calculated logarithmic Mahalanobis distance. The success rate of hydrocarbon exploration for each grid in the two-dimensional Mahalanobis distance grid map is calculated. In the above process, by calculating the logarithmic Mahalanobis distance from each well to each well type and drawing a two-dimensional Mahalanobis distance grid map, the success rate of hydrocarbon exploration for each grid in the two-dimensional Mahalanobis distance grid map can be obtained, resulting in high computational efficiency and high accuracy. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0024] Figure 1 This is a flowchart of the oil and gas detection success rate prediction method in an embodiment of the present invention;

[0025] Figure 2 This is a geological evaluation value diagram of the Sangonghe Formation reservoir conditions in the implementation of this invention;

[0026] Figure 3 This is a geological evaluation value map of the trap conditions of the Sangonghe Formation in the implementation of this invention;

[0027] Figure 4 This is a geological evaluation value map of hydrocarbon supply conditions in the Sangonghe Formation during the implementation of this invention;

[0028] Figure 5 This is a geological evaluation value diagram of the caprock and preservation conditions of the Sangonghe Formation in the implementation of this invention;

[0029] Figure 6 Two-dimensional Mahalanobis distance grid diagram of logarithmic Mahalanobis distance from all exploration wells to oil and gas well types in this embodiment of the invention;

[0030] Figure 7 This is a two-dimensional Mahalanobis distance grid diagram of the logarithmic Mahalanobis distances from all exploration wells to non-oil and gas well types in this embodiment of the invention;

[0031] Figure 8 This is an initial exploration success rate prediction map in an embodiment of the present invention;

[0032] Figure 9 This is a prediction chart of exploration success rate after multiple smoothing processes in an embodiment of the present invention.

[0033] Figure 10 This is a diagram showing the exploration success rate in an embodiment of the present invention;

[0034] Figure 11 This is a schematic diagram of the oil and gas detection success rate prediction device in an embodiment of the present invention;

[0035] Figure 12 This is a schematic diagram of a computer device in an embodiment of the present invention. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0037] In the description of this specification, the terms "comprising," "including," "having," and "containing" are open-ended terms, meaning that they include but are not limited to. The terms "an embodiment," "a specific embodiment," "some embodiments," and "for example," etc., refer to specific features, structures, or characteristics described in connection with that embodiment or example that are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, or characteristics described can be combined in any suitable manner in one or more embodiments or examples. The order of steps involved in the various embodiments is used to illustrate the implementation of this application, and the order of steps is not limited and can be adjusted appropriately as needed.

[0038] Figure 1 This is a flowchart of the oil and gas detection success rate prediction method in an embodiment of the present invention, as shown below. Figure 1 As shown, the method includes:

[0039] Step 101: Quantitatively evaluate multiple hydrocarbon accumulation geological conditions in the study area and obtain multiple single-factor geological evaluation value maps;

[0040] Step 102: Based on the location of multiple exploration wells in the study area, extract the single-factor geological evaluation value of each exploration well from each single-factor geological evaluation value map, and combine the single-factor geological evaluation value of each exploration well and the type of each exploration well into training set data;

[0041] Step 103: Calculate the log-Madaras distance from each well to each well type in the training set data;

[0042] Step 104: Draw a two-dimensional Mahalanobis distance grid based on the calculated log-Mahalanobis distance;

[0043] Step 105: Calculate the oil and gas exploration success rate for each grid in the two-dimensional Mahalanobis distance grid map.

[0044] In this embodiment of the invention, by calculating the logarithmic Mahalanobis distance from each exploration well to each type of exploration well and drawing a two-dimensional Mahalanobis distance grid, the success rate of oil and gas exploration for each grid in the two-dimensional Mahalanobis distance grid can be obtained, which has high calculation efficiency and high accuracy.

[0045] In one embodiment, the geological conditions for hydrocarbon accumulation include one or any combination of hydrocarbon generation or supply conditions, reservoir conditions, trap conditions, caprock conditions, and preservation conditions.

[0046] In step 101, multiple hydrocarbon accumulation geological conditions in the study area are quantitatively evaluated to obtain multiple single-factor geological evaluation value maps. The highest evaluation value is set to 1, and the lowest evaluation value to 0. Each hydrocarbon accumulation geological condition is quantitatively evaluated to obtain single-factor geological evaluation values, such as hydrocarbon generation or supply conditions, reservoir conditions, trap conditions, caprock conditions, and preservation conditions. These can be represented by single-factor geological evaluation values: R1, R2, R3, R4, and R5. Single-factor geological evaluation value maps for multiple points in the study area are then plotted, abbreviated as R1-Map, R2-Map, R3-Map, R4-Map, and R5-Map. The values ​​of R1, R2, R3, R4, and R5 are between 0 and 1.

[0047] In step 102, based on the locations of multiple exploration wells within the study area, the single-factor geological evaluation value of each exploration well is extracted from each single-factor geological evaluation value map. The single-factor geological evaluation value of each exploration well and the type of each exploration well are combined to form training set data. Specifically, the single-factor geological evaluation values ​​of all exploration wells are extracted from R1-Map, R2-Map, R3-Map, R4-Map, and R5-Map, namely R1(k), R2(k), R3(k), R4(k), and R5(k). Here, k is the sequence number of the exploration well. In one embodiment, the types of exploration wells include oil and gas wells and non-oil and gas wells. The single-factor geological evaluation values ​​(R1, R2, R3, R4, R5) of all exploration wells and the type of the exploration well are combined to form training set data A. MD The number of single-factor geological evaluation values ​​is determined by the geological conditions of the study area, and is generally 3 to 5. If there are 3, they are represented by R1, R2, and R3; if there are 4, they are represented by R1, R2, R3, and R4; and so on for other numbers.

[0048] In one embodiment, calculating the log-Madaras distance from each well to each well type in the training set data includes:

[0049] Calculate the Mahalanobis distance from each well to each well type in the training set data;

[0050] Calculate the logarithmic Mahalanobis distance based on the Mahalanobis distance.

[0051] Mahalanobis distance values ​​exhibit logarithmic variation, making statistical analysis difficult. Therefore, it is necessary to convert the geological evaluation values ​​into linearly varying values. Simultaneously, to avoid negative logarithmic Mahalanobis distances, a bias value needs to be added. Therefore, in one embodiment, the following formula is used to calculate the logarithmic Mahalanobis distance based on the stated Mahalanobis distance:

[0052] D oil =ln(d oil +a)

[0053] D dry =ln(d dry +a)

[0054] Among them, D oil D dry , , are the logarithmic values ​​of the Mahalanobis distances from each exploration well to oil / gas well type and non-oil / gas well type, respectively; a is the deviation value; d oil d dry These represent the distances from each exploration well to oil and gas well types and to non-oil and gas well types, respectively.

[0055] In one embodiment, drawing a two-dimensional Mahalanobis distance grid based on the calculated log-Mahalanobis distance includes:

[0056] Based on the minimum and maximum distribution of the logarithmic Mahalanobis distance from all exploration wells to oil and gas well types, the logarithmic Mahalanobis distance from all exploration wells to oil and gas well types is divided into a first number of intervals.

[0057] Based on the minimum and maximum distribution of the logarithmic Mahalanobis distance from all exploration wells to non-oil and gas well types, the logarithmic Mahalanobis distance from all exploration wells to non-oil and gas well types is divided into a second number of intervals.

[0058] A two-dimensional Mahalanobis distance grid is plotted with the logarithmic Mahalanobis distance from all exploration wells to oil and gas well types as the x-axis and the logarithmic Mahalanobis distance from all exploration wells to non-oil and gas well types as the y-axis.

[0059] Generally, both the first and second quantities are not less than 3. The number of grids in a two-dimensional Mahalanobis distance grid is the first quantity multiplied by the second quantity.

[0060] In one embodiment, the oil and gas exploration success rate of each grid in a two-dimensional Mahalanobis distance grid map is calculated using the following formula:

[0061] P(i,j)=100×S(i,j) / [S(i,j)+F(i,j)]

[0062] Where P(i,j) is the success rate of oil and gas exploration in grid (i,j), i = 0, 1, 2, ..., n-1, n is the first quantity, j = 0, 1, 2, ..., m-1, m is the second quantity; S(i,j) is the number of exploration wells in grid (i,j) that belong to the oil and gas well type; F(i,j) is the number of exploration wells in grid (i,j) that belong to the non-oil and gas well type.

[0063] This gives us an accurate value for the success rate of oil and gas exploration for each grid.

[0064] In one embodiment, the method further includes:

[0065] The success rate of oil and gas exploration in grids without exploration wells in a two-dimensional Marshall distance grid is smoothed.

[0066] This is because when there are no exploration wells in some grids, i.e. S(i,j)+F(i,j)=0, in order to improve the data continuity between grids, this invention proposes a smoothing processing method.

[0067] In one embodiment, the oil and gas exploration success rate of grids without exploration wells in a two-dimensional Marshall distance grid is smoothed, including:

[0068] When grid number i = 0 and j = 0, the following formula is used for smoothing:

[0069]

[0070] When grid number i = n-1 and j = 0, the following formula is used for smoothing:

[0071]

[0072] When grid number i = n-1 and j = m-1, the following formula is used for smoothing:

[0073]

[0074] When grid number i = 0 and j = m-1, the following formula is used for smoothing:

[0075]

[0076] When the grid consists of the four corner grids of a non-two-dimensional Mahalanobis distance grid, and i = 0 or i = n-1, the following formula is used for smoothing:

[0077]

[0078] When the grid consists of the four corner grids of a non-two-dimensional Mahalanobis distance grid, and j = 0 or j = m-1, the following formula is used for smoothing:

[0079]

[0080] In other cases, the following formula is used for smoothing:

[0081]

[0082] in, P(i,j) represents the oil and gas exploration success rate after grid (i,j) smoothing; P(i,j) represents the oil and gas exploration success rate before grid (i,j) smoothing.

[0083] After calculating the oil and gas exploration success rate for each grid, the two-dimensional Mahalanobis distance grid map can be transformed into an exploration success rate map, i.e., a risk visualization map, which is convenient for application and query.

[0084] The following is a specific embodiment to illustrate the specific application of the method proposed in this invention.

[0085] This embodiment comes from the Sangonghe Formation in the interior of the Junggar Basin.

[0086] The study area is located in the heart of the Junggar Basin, spanning 160 km east to west and 170 km north to south, with an area of ​​approximately 2.7 × 10⁴ km². 2 The study area includes the West Depression of Well 1, the Mosuowan Uplift, and the Luxi Uplift. The target stratum is the Jurassic Sangonghe Formation (J1s), the source rock is the Lower Permian Wuerhe Formation (P2w), and the caprock is Jurassic shale. The study area slopes from south to north, with finer facies in the south and coarser facies in the north. Oil and gas migrate from bottom to top and from south to north, forming fault-nose, fault-block, and lithological stratigraphic reservoirs. By the end of 2019, more than 203 exploration and appraisal wells had encountered the Sangonghe Formation and completed oil testing. Some oil and gas fields have been discovered in the Mosuowan Uplift, Mobei, Shixi, Shinan, and Xiayan areas.

[0087] This example uses four hydrocarbon accumulation geological conditions: reservoir conditions, trap conditions, hydrocarbon supply conditions, and caprock and preservation conditions. Among them, the caprock and preservation conditions are a combination of the caprock conditions and preservation conditions, mainly considering the geological conditions of this example.

[0088] (1) Reservoir conditions

[0089] Based on sedimentary microfacies, reservoir conditions were quantitatively evaluated, ranked in descending order of quality as follows: underwater distributary channels, sheet sands, beaches and sandy debris flows, interdistributary bays, and littoral lacustrines. The corresponding evaluation values ​​are shown in Table 1. Within the same sedimentary microfacies, the evaluation value for each point was a random sample from the minimum to the maximum value of that microfacies. Taking underwater distributary channels as an example, the sampling range was from 0.7 to 0.9, and the random sampled value was any real number between 0.7 and 0.9, inclusive. Using the above method, the sedimentary microfacies map was converted into a geological evaluation value map of reservoir conditions. Figure 2 This is a geological evaluation value diagram of the Sangonghe Formation reservoir conditions in the implementation of this invention.

[0090] Table 1

[0091]

[0092]

[0093] (2) Trap conditions

[0094] Based on the structural map of the top boundary of the Sangonghe Formation and the results of trap interpretation, structural traps are divided into two levels: confirmed traps and unconfirmed traps (see Table 2). Based on sedimentary microfacies maps, lithological traps are divided into two levels: lithological lenses (shoals, bars, etc.) and lithological barriers (bays, etc.). Furthermore, discovered oil and gas reservoirs are confirmed traps. Similarly, a geological evaluation value map of trap conditions was drawn using a random sampling method. Figure 3 This is a geological evaluation value diagram of the trap conditions of the Sangonghe Formation in the implementation of this invention.

[0095] Table 2

[0096] Classification Enclosed Minimum value (dimensionless) Maximum value (dimensionless) I Oil and gas reservoirs have been discovered. 1.0 1.0 II Implementing a trap (structural type) 0.7 0.8 III Pending confirmation of trap (structural type) 0.6 0.7 IV Lithological lenses (shoals, dams, etc.) 0.5 0.6 V Lithological barriers (intervals, etc.) 0.3 0.5

[0097] (3) Hydrocarbon supply conditions

[0098] The hydrocarbons in the Sangonghe Formation mainly originate from the underlying Permian Lower Wuerhe Formation source rocks. Vertically, they are primarily connected via source rock faults, while lateral migration is mainly controlled by sand bodies and tectonic ridges. The southern part, closer to the source rock, benefits from faults playing a crucial role in communication, making it relatively favorable overall. The northern part, much farther from the source rock (up to hundreds of kilometers), lacks fault connections and relies mainly on long-distance lateral migration for hydrocarbon supply, making it relatively unfavorable overall. Based on this understanding, and after completing the study of fault distribution and simulation of hydrocarbon migration channels, hydrocarbon supply conditions are divided into four levels: source rock-connecting faults + main path, main path, secondary path, southern near-source area, and northern far-source area (see Table 3). Similarly, a geological evaluation map of hydrocarbon supply conditions was drawn using random sampling. Figure 4 This is a geological evaluation value diagram of hydrocarbon supply conditions in the Sangonghe Formation during the implementation of this invention.

[0099] Table 3

[0100]

[0101]

[0102] (4) Covering layer and preservation conditions

[0103] The caprock and preservation conditions are mainly determined by the development of faults in the overlying strata and the distribution of unconformity weathering zones. Areas with well-developed overlying faults have a destructive effect, resulting in lower evaluation values ​​(0.1–0.2). Unconformity weathered clay provides good protection, leading to higher evaluation values ​​(0.7–0.9). Other areas have relatively well-developed mudstone and shale, acting as local caprocks, with evaluation values ​​(0.4–0.6). Then, a geological evaluation map of caprock and preservation conditions is obtained using random sampling. Figure 5 This is a geological evaluation value diagram of the caprock and preservation conditions of the Sangonghe Formation in the implementation of this invention.

[0104] Then, based on the coordinates of port 203 (see Table 4), from... Figures 2-5 Data from geological evaluation maps of reservoir conditions, trap conditions, hydrocarbon supply conditions, and caprock and preservation conditions were extracted to form training set A. MD .

[0105] Table 4

[0106]

[0107]

[0108]

[0109] Next, the logarithmic Mahalanobis distance from each well to each well type in the training set data was calculated, and the results are shown in the last two columns of Table 4.

[0110] A two-dimensional Mahalanobis distance grid was constructed based on the calculated logarithmic Mahalanobis distance. The training set contained 203 wells, including 109 oil and gas wells and 94 non-oil and gas wells. The horizontal axis (X-direction) was divided into 10 segments (n=10), and the vertical axis (Y-direction) was divided into 4 segments (m=4), resulting in a two-dimensional Mahalanobis distance grid consisting of 40 grids. Figure 6 In this embodiment of the invention, a two-dimensional Mahalanobis distance grid diagram of the logarithmic Mahalanobis distance from all exploration wells to oil and gas well types is presented. Figure 7 This is a two-dimensional Mahalanobis distance grid diagram of the logarithmic Mahalanobis distances from all exploration wells to non-oil and gas well types in this embodiment of the invention.

[0111] Based on the D of each exploration well in the training set data oil D dry Determine the grid where the well is located. Figure 8This is an initial exploration success rate prediction map in this embodiment of the invention, where 1 / 4 represents the number of oil and gas wells / total number of wells. The number of oil and gas wells in each grid is counted. Figure 8 (middle molecule) and total number of wells ( Figure 8 The middle denominator), then calculate the exploration success rate in each grid (the percentage value in the figure), forming Figure 8 The initial exploration success rate prediction map. For grids without exploration wells, the initial value is set to 0.5.

[0112] To improve the continuity of data between grids, 10 smoothing processes were performed, resulting in a smoothed exploration success rate map. Figure 9 This is a prediction chart of exploration success rate after multiple smoothing processes in an embodiment of the present invention.

[0113] Alternatively, it can be used as Figure 9 The exploration success rate prediction chart is a two-dimensional scale. Figure 6 and Figure 7 This is converted into an exploration success rate map, i.e., a risk visualization map. Figure 10 ), Figure 10 This is a graph showing the exploration success rate in an embodiment of the present invention.

[0114] In summary, the method proposed in this invention quantitatively evaluates multiple hydrocarbon accumulation geological conditions in the study area, obtaining multiple single-factor geological evaluation value maps. Based on the locations of multiple exploration wells within the study area, the single-factor geological evaluation value of each well is extracted from each single-factor geological evaluation value map. The single-factor geological evaluation value of each well and the type of each well are combined to form training set data. The logarithmic Mahalanobis distance from each well to each well type in the training set data is calculated. A two-dimensional Mahalanobis distance grid map is drawn based on the calculated logarithmic Mahalanobis distance. The success rate of hydrocarbon exploration for each grid in the two-dimensional Mahalanobis distance grid map is calculated. In the above process, by calculating the logarithmic Mahalanobis distance from each well to each well type and drawing a two-dimensional Mahalanobis distance grid map, the success rate of hydrocarbon exploration for each grid in the two-dimensional Mahalanobis distance grid map can be obtained, resulting in high computational efficiency and high accuracy.

[0115] This invention also proposes an oil and gas detection success rate prediction device, the principle of which is similar to the oil and gas detection success rate prediction method, and will not be described in detail here.

[0116] Figure 11 This is a schematic diagram of the oil and gas detection success rate prediction device in an embodiment of the present invention, as shown below. Figure 11 As shown, it includes:

[0117] The module 1101 for obtaining single-factor geological evaluation value maps is used to quantitatively evaluate multiple hydrocarbon accumulation geological conditions in the study area and obtain multiple single-factor geological evaluation value maps.

[0118] The training set data acquisition module 1102 is used to extract the single-factor geological evaluation value of each well from each single-factor geological evaluation value map according to the location of multiple wells in the study area, and combine the single-factor geological evaluation value of each well and the type of each well into training set data.

[0119] Logarithmic Mahalanobis distance calculation module 1103 is used to calculate the logarithmic Mahalanobis distance from each well to each well type in the training set data;

[0120] The 2D Mahalanobis distance grid plotting module 1104 is used to plot a 2D Mahalanobis distance grid plot based on the calculated log Mahalanobis distance.

[0121] The oil and gas exploration success rate calculation module 1105 is used to calculate the oil and gas exploration success rate of each grid in a two-dimensional Mahalanobis distance grid map.

[0122] In one embodiment, the geological conditions for hydrocarbon accumulation include one or any combination of hydrocarbon generation or supply conditions, reservoir conditions, trap conditions, caprock conditions, and preservation conditions.

[0123] In one embodiment, the type of exploration well includes oil and gas well types and non-oil and gas well types.

[0124] In one embodiment, the logarithmic Mahalanobis distance calculation module is specifically used for:

[0125] Calculate the Mahalanobis distance from each well to each well type in the training set data;

[0126] Calculate the logarithmic Mahalanobis distance based on the Mahalanobis distance.

[0127] In one embodiment, the logarithmic Mahalanobis distance calculation module is specifically used for:

[0128] The logarithmic Mahalanobis distance is calculated using the following formula based on the Mahalanobis distance:

[0129] D oil =ln(d oil +a)

[0130] D dry =ln(d dry +a)

[0131] Among them, D oil D dry , , are the logarithmic values ​​of the Mahalanobis distances from each exploration well to oil / gas well type and non-oil / gas well type, respectively; a is the deviation value; d oil d dry These represent the distances from each exploration well to oil and gas well types and to non-oil and gas well types, respectively.

[0132] In one embodiment, the two-dimensional Mahalanobis distance grid plotting module is specifically used for:

[0133] Based on the minimum and maximum distribution of the logarithmic Mahalanobis distance from all exploration wells to oil and gas well types, the logarithmic Mahalanobis distance from all exploration wells to oil and gas well types is divided into a first number of intervals.

[0134] Based on the minimum and maximum distribution of the logarithmic Mahalanobis distance from all exploration wells to non-oil and gas well types, the logarithmic Mahalanobis distance from all exploration wells to non-oil and gas well types is divided into a second number of intervals.

[0135] A two-dimensional Mahalanobis distance grid is plotted with the logarithmic Mahalanobis distance from all exploration wells to oil and gas well types as the x-axis and the logarithmic Mahalanobis distance from all exploration wells to non-oil and gas well types as the y-axis.

[0136] In one embodiment, the oil and gas exploration success rate calculation module is specifically used for:

[0137] The following formula is used to calculate the oil and gas exploration success rate for each grid in a two-dimensional Mahalanobis distance grid map:

[0138] P(i,j)=100×S(i,j) / [S(i,j)+F(i,j)]

[0139] Where P(i,j) is the success rate of oil and gas exploration in grid (i,j), i = 0, 1, 2, ..., n-1, n is the first quantity, j = 0, 1, 2, ..., m-1, m is the second quantity; S(i,j) is the number of exploration wells in grid (i,j) that belong to the oil and gas well type; F(i,j) is the number of exploration wells in grid (i,j) that belong to the non-oil and gas well type.

[0140] In one embodiment, the device further includes a smoothing module 1106, for:

[0141] The success rate of oil and gas exploration in grids without exploration wells in a two-dimensional Marshall distance grid is smoothed.

[0142] In one embodiment, the smoothing module is specifically used for:

[0143] The oil and gas exploration success rate of grids without exploration wells in the two-dimensional Marshall distance grid map is smoothed, including:

[0144] When grid number i = 0 and j = 0, the following formula is used for smoothing:

[0145]

[0146] When grid number i = n-1 and j = 0, the following formula is used for smoothing:

[0147]

[0148] When grid number i = n-1 and j = m-1, the following formula is used for smoothing:

[0149]

[0150] When grid number i = 0 and j = m-1, the following formula is used for smoothing:

[0151]

[0152] When the grid consists of the four corner grids of a non-two-dimensional Mahalanobis distance grid, and i = 0 or i = n-1, the following formula is used for smoothing:

[0153]

[0154] When the grid consists of the four corner grids of a non-two-dimensional Mahalanobis distance grid, and j = 0 or j = m-1, the following formula is used for smoothing:

[0155]

[0156] In other cases, the following formula is used for smoothing:

[0157]

[0158] in, P(i,j) represents the oil and gas exploration success rate after grid (i,j) smoothing; P(i,j) represents the oil and gas exploration success rate before grid (i,j) smoothing.

[0159] In summary, the apparatus proposed in this invention quantitatively evaluates multiple hydrocarbon accumulation geological conditions in the study area, obtaining multiple single-factor geological evaluation value maps. Based on the locations of multiple exploration wells within the study area, the single-factor geological evaluation value of each well is extracted from each single-factor geological evaluation value map. The single-factor geological evaluation value of each well and the type of each well are combined to form training set data. The logarithmic Mahalanobis distance from each well to each well type in the training set data is calculated. A two-dimensional Mahalanobis distance grid map is drawn based on the calculated logarithmic Mahalanobis distance. The success rate of hydrocarbon exploration for each grid in the two-dimensional Mahalanobis distance grid map is calculated. In the above process, by calculating the logarithmic Mahalanobis distance from each well to each well type and drawing a two-dimensional Mahalanobis distance grid map, the success rate of hydrocarbon exploration for each grid in the two-dimensional Mahalanobis distance grid map can be obtained, resulting in high computational efficiency and high accuracy.

[0160] Embodiments of this application also provide a computer device. Figure 12This is a schematic diagram of a computer device in an embodiment of the present invention. This computer device is capable of implementing all steps in the oil and gas detection success rate prediction method described in the above embodiments. The computer device specifically includes the following components:

[0161] Processor 1201, memory 1202, communications interface 1203, and communication bus 1204;

[0162] The processor 1201, memory 1202, and communication interface 1203 communicate with each other through the communication bus 1204; the communication interface 1203 is used to realize information transmission between server-side devices, detection devices, and user-side devices and other related devices.

[0163] The processor 1201 is used to call the computer program in the memory 1202. When the processor executes the computer program, it implements all the steps in the oil and gas detection success rate prediction method in the above embodiments.

[0164] The embodiments of this application also provide a computer-readable storage medium capable of implementing all steps of the oil and gas detection success rate prediction method in the above embodiments. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements all steps of the oil and gas detection success rate prediction method in the above embodiments.

[0165] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0166] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0167] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0168] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0169] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for predicting the success rate of oil and gas exploration, characterized in that, include: Quantitatively evaluate multiple hydrocarbon accumulation geological conditions in the study area and obtain multiple single-factor geological evaluation value maps; Based on the location of multiple exploration wells in the study area, the single-factor geological evaluation value of each exploration well is extracted from each single-factor geological evaluation value map, and the single-factor geological evaluation value of each exploration well and the type of each exploration well are combined into training set data. Calculate the log-Madovish distance from each well to each well type in the training set data; Draw a two-dimensional Mahalanobis distance grid based on the calculated log Mahalanobis distance; Calculate the success rate of oil and gas exploration for each grid in a two-dimensional Mahalanobis distance grid map; Calculating the log-Madaras distance from each well to each well type in the training set data includes: calculating the Mahalanobis distance from each well to each well type in the training set data; and calculating the log-Madarabis distance based on the Mahalanobis distance. A two-dimensional Mahalanobis distance grid is drawn based on the calculated log-Madanobis distances, including: dividing the log-Madanobis distances from all exploration wells to oil and gas well types into a first number of intervals based on the minimum and maximum distribution of the log-Madanobis distances from all exploration wells to oil and gas well types; dividing the log-Madanobis distances from all exploration wells to non-oil and gas well types into a second number of intervals based on the minimum and maximum distribution of the log-Madanobis distances from all exploration wells to non-oil and gas well types; and drawing a two-dimensional Mahalanobis distance grid with the log-Madanobis distances from all exploration wells to oil and gas well types as the horizontal axis and the log-Madanobis distances from all exploration wells to non-oil and gas well types as the vertical axis.

2. The method for predicting the success rate of oil and gas exploration as described in claim 1, characterized in that, The geological conditions for hydrocarbon accumulation include one or any combination of hydrocarbon generation or supply conditions, reservoir conditions, trap conditions, caprock conditions, and preservation conditions.

3. The method for predicting the success rate of oil and gas exploration as described in claim 1, characterized in that, The types of exploration wells include oil and gas wells and non-oil and gas wells.

4. The method for predicting the success rate of oil and gas exploration as described in claim 1, characterized in that, The logarithmic Mahalanobis distance is calculated using the following formula based on the Mahalanobis distance: in, , These are the logarithmic values ​​of the Mahalanobis distances from each exploration well to oil and gas well types and non-oil and gas well types, respectively. This is the deviation value; , These represent the distances from each exploration well to oil and gas well types and to non-oil and gas well types, respectively.

5. The method for predicting the success rate of oil and gas exploration as described in claim 1, characterized in that, The following formula is used to calculate the oil and gas exploration success rate for each grid in a two-dimensional Mahalanobis distance grid map: in, For grid The success rate of oil and gas exploration , As the first quantity, , The second quantity; For grid The number of exploration wells that belong to the oil and gas well type; For grid The number of exploration wells that are not oil and gas wells.

6. The method for predicting the success rate of oil and gas exploration as described in claim 1, characterized in that, Also includes: The success rate of oil and gas exploration in grids without exploration wells in a two-dimensional Marshall distance grid is smoothed.

7. The method for predicting the success rate of oil and gas exploration as described in claim 6, characterized in that, The oil and gas exploration success rate of grids without exploration wells in the two-dimensional Marshall distance grid map is smoothed, including: When grid number =0, When = 0, the following formula is used for smoothing: When grid number = , When = 0, the following formula is used for smoothing: When grid number = , = When smoothing occurs, the following formula is used: When grid number =0, = When smoothing occurs, the following formula is used: When the grid is the grid at the four corners of a non-two-dimensional Mahalanobis distance grid, and =0 or = When smoothing occurs, the following formula is used: When the grid is the grid at the four corners of a non-two-dimensional Mahalanobis distance grid, and =0 or = When smoothing occurs, the following formula is used: In other cases, the following formula is used for smoothing: in, For grid Oil and gas exploration success rate after smoothing; For grid Success rate of oil and gas exploration before smoothing.

8. A device for predicting the success rate of oil and gas detection, characterized in that, include: The module for obtaining single-factor geological evaluation value maps is used to quantitatively evaluate multiple hydrocarbon accumulation geological conditions in the study area and obtain multiple single-factor geological evaluation value maps. The training set data acquisition module is used to extract the single-factor geological evaluation value of each well from each single-factor geological evaluation value map based on the location of multiple wells in the study area, and combine the single-factor geological evaluation value of each well and the type of each well into training set data. The log-Mahland distance calculation module is used to calculate the log-Mahland distance from each well to each well type in the training set data. The 2D Mahalanobis distance grid plotting module is used to plot a 2D Mahalanobis distance grid plot based on the calculated logarithmic Mahalanobis distance. The oil and gas exploration success rate calculation module is used to calculate the oil and gas exploration success rate of each grid in the two-dimensional Mahalanobis distance grid map. The logarithmic Mahalanobis distance calculation module is specifically used for: calculating the Mahalanobis distance from each well to each well type in the training set data; and calculating the logarithmic Mahalanobis distance based on the Mahalanobis distance. The 2D Mahalanobis distance grid plotting module is specifically used for: dividing the logarithmic Mahalanobis distances from all exploration wells to oil and gas well types into a first number of intervals based on the minimum and maximum distribution of the logarithmic Mahalanobis distances from all exploration wells to oil and gas well types; dividing the logarithmic Mahalanobis distances from all exploration wells to non-oil and gas well types into a second number of intervals based on the minimum and maximum distribution of the logarithmic Mahalanobis distances from all exploration wells to non-oil and gas well types; plotting a 2D Mahalanobis distance grid plot with the logarithmic Mahalanobis distances from all exploration wells to oil and gas well types as the horizontal axis and the logarithmic Mahalanobis distances from all exploration wells to non-oil and gas well types as the vertical axis.

9. The oil and gas detection success rate prediction device as described in claim 8, characterized in that, The geological conditions for hydrocarbon accumulation include one or any combination of hydrocarbon generation or supply conditions, reservoir conditions, trap conditions, caprock conditions, and preservation conditions.

10. The oil and gas detection success rate prediction device as described in claim 8, characterized in that, The types of exploration wells include oil and gas wells and non-oil and gas wells.

11. The oil and gas detection success rate prediction device as described in claim 8, characterized in that, The logarithmic Mahalanobis distance calculation module is specifically used for: The logarithmic Mahalanobis distance is calculated using the following formula based on the Mahalanobis distance: in, , These are the logarithmic values ​​of the Mahalanobis distances from each exploration well to oil and gas well types and non-oil and gas well types, respectively. This is the deviation value; , These represent the distances from each exploration well to oil and gas well types and to non-oil and gas well types, respectively.

12. The oil and gas detection success rate prediction device as described in claim 8, characterized in that, The oil and gas exploration success rate calculation module is specifically used for: The following formula is used to calculate the oil and gas exploration success rate for each grid in a two-dimensional Mahalanobis distance grid map: in, For grid The success rate of oil and gas exploration , As the first quantity, , The second quantity; For grid The number of exploration wells that belong to the oil and gas well type; For grid The number of exploration wells that are not oil and gas wells.

13. The oil and gas detection success rate prediction device as described in claim 8, characterized in that, It also includes a smoothing module for: The success rate of oil and gas exploration in grids without exploration wells in a two-dimensional Marshall distance grid is smoothed.

14. The oil and gas detection success rate prediction device as described in claim 13, characterized in that, The smoothing module is specifically used for: The oil and gas exploration success rate of grids without exploration wells in the two-dimensional Marshall distance grid map is smoothed, including: When grid number =0, When = 0, the following formula is used for smoothing: When grid number = , When = 0, the following formula is used for smoothing: When grid number = , = When smoothing occurs, the following formula is used: When grid number =0, = When smoothing occurs, the following formula is used: When the grid is the grid at the four corners of a non-two-dimensional Mahalanobis distance grid, and =0 or = When smoothing occurs, the following formula is used: When the grid is the grid at the four corners of a non-two-dimensional Mahalanobis distance grid, and =0 or = When smoothing occurs, the following formula is used: In other cases, the following formula is used for smoothing: in, For grid Oil and gas exploration success rate after smoothing; For grid Success rate of oil and gas exploration before smoothing.

15. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method according to any one of claims 1 to 8.

16. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that performs the method according to any one of claims 1 to 8.

Images