Method, device and equipment for determining reservoir hydrocarbon production

Abstract

The application discloses a method, device and equipment for determining reservoir oil and gas productivity, wherein the method comprises the following steps: obtaining reservoir physical property data of a target oil and gas well section; determining target reservoir distribution characteristics of the target oil and gas well section based on the reservoir physical property data and a relationship between physical property parameters and oil and gas accumulation dynamic mechanism; wherein the target reservoir distribution characteristics are used for quantifying distribution proportions of different reservoir types of the target oil and gas well section; inputting the target logging data and the target reservoir distribution characteristics into a first productivity model constructed in advance, and outputting target productivity data of the target oil and gas well section; wherein the first productivity model is constructed by analyzing an association relationship between historical reservoir distribution characteristics and historical logging data and historical productivity data of a plurality of historical oil and gas well sections. Through the above method, systematic, quantitative and accurate productivity prediction of a volcanic reservoir can be realized.

Description

Technical Field

[0001] This application relates to the field of oil and gas exploration and development technology, and in particular to a method, apparatus and equipment for determining reservoir oil and gas production capacity. Background Technology

[0002] Volcanic reservoirs are an important area in oil and gas exploration and development, but the high complexity of their lithology, pore structure, and accumulation mechanisms has made production capacity prediction a long-term and significant challenge. Unlike conventional clastic reservoirs, volcanic reservoirs have diverse spatial types, strong nonlinear porosity-permeability relationships, and multiple accumulation dynamic mechanisms, resulting in discontinuous distribution of economically valuable "sweet spots" that are difficult to accurately identify.

[0003] Current production capacity prediction methods are mainly based on the understanding of conventional reservoirs, which has significant limitations when applied to volcanic reservoirs. These methods primarily include prediction methods based on static geological parameters, numerical simulation or analysis methods based on dynamic production data, and prediction methods based on geophysical or logging responses. However, these methods are ill-suited to the extremely heterogeneous pore-throat structure of volcanic rocks, and fail to fully consider the controlling effect of differences in hydrocarbon accumulation mechanisms on production capacity, easily leading to misjudgments such as "high pore size, low production" or "low pore size, high production." Furthermore, current logging and seismic data are insufficient to accurately characterize the internal structure of volcanic reservoirs; and gas logging responses are influenced by multiple factors such as lithology, physical properties, and drilling techniques, resulting in insufficient geological interpretability and extrapolation capabilities of existing methods. Therefore, current methods are ill-suited to the extremely heterogeneous pore-throat structure of volcanic rocks, fail to fully consider the controlling effect of differences in hydrocarbon accumulation mechanisms on production capacity, and cannot achieve systematic, quantitative, and accurate production capacity prediction for volcanic reservoirs.

[0004] No effective solution has yet been proposed to address the above issues. Summary of the Invention

[0005] The purpose of this application is to provide a method, apparatus, and equipment for determining reservoir oil and gas production capacity, so as to solve the problem that it is impossible to achieve systematic, quantitative, and accurate production capacity prediction for volcanic rock reservoirs.

[0006] To address the aforementioned technical problems, the first aspect of this specification provides a method for determining reservoir oil and gas production capacity, comprising: Obtain reservoir physical property data for the target oil and gas well section; Based on the reservoir physical property data and the relationship between physical property parameters and hydrocarbon accumulation dynamics, the target reservoir distribution characteristics of the target oil and gas well interval are determined; wherein, the target reservoir distribution characteristics are used to quantify the distribution proportion of different reservoir types in the target oil and gas well interval. The target reservoir distribution characteristics are input into a pre-constructed first production capacity model, and the target production capacity data of the target oil and gas well section are output; wherein, the first production capacity model is constructed by analyzing the correlation between the historical reservoir distribution characteristics and historical production capacity data of multiple historical oil and gas well sections.

[0007] In some embodiments of this specification, the relationship between the physical properties and the hydrocarbon accumulation dynamics is determined in the following ways: Acquire historical physical property data of multiple historical oil and gas well sections, wherein the historical physical property data carries labels characterizing the reservoir type of oil and gas; Based on historical physical property data of multiple historical oil and gas well sections, the critical physical property thresholds of each dimension of physical property parameters corresponding to the historical physical property data are determined. The critical physical property thresholds are used to characterize the critical thresholds of the corresponding physical property parameters in different reservoir oil and gas types. Based on the critical physical property thresholds of multiple dimensions of physical property parameters, the reservoir types corresponding to multiple historical oil and gas well sections and the reservoir physical property ranges corresponding to each reservoir type are determined as the relationship between the physical property parameters and the oil and gas accumulation dynamic mechanism.

[0008] In some embodiments of this specification, based on historical physical property data from multiple historical oil and gas well sections, critical physical property thresholds for each dimension of physical property parameters corresponding to the historical physical property data are determined, including: Based on the aforementioned historical physical property data, for any dimension of physical property parameter: Determine the data range of the physical property data corresponding to the physical property parameters, divide the data range into multiple continuous sub-ranges, and count the number of reservoir segments of different reservoir oil and gas reservoir types in each sub-range. Based on the number of reservoir segments of different oil and gas reservoir types in each sub-interval, the frequency of reservoirs of different oil and gas reservoir types in each sub-interval is determined. Based on the frequency of reservoirs of different oil and gas reservoir types within multiple sub-intervals, the critical physical property thresholds corresponding to the physical property parameters are determined.

[0009] In some embodiments of this specification, the reservoir types include Class I reservoirs, Class II reservoirs, Class III reservoirs, and Class IV reservoirs; the critical physical property thresholds for each dimension of physical property parameters include critical thresholds for porosity and critical thresholds for permeability; The reservoir property ranges corresponding to each reservoir type include: The porosity of the first type of reservoir is greater than the critical porosity threshold, and the permeability of the first type of reservoir is greater than the critical permeability threshold. The porosity of the second type of reservoir is less than or equal to the critical porosity threshold, and the permeability of the second type of reservoir is less than or equal to the critical permeability threshold. The porosity of the third type of reservoir is greater than the critical porosity threshold, and the permeability of the third type of reservoir is less than or equal to the critical permeability threshold. The porosity of the fourth type of reservoir is less than or equal to the critical porosity threshold, and the permeability of the fourth type of reservoir is greater than the critical permeability threshold.

[0010] In some embodiments of this specification, based on the reservoir physical property data and the relationship between physical property parameters and hydrocarbon accumulation dynamics, the target reservoir distribution characteristics of the target oil and gas well interval are determined, including: Based on the reservoir physical property data and the relationship between the physical property parameters and the hydrocarbon accumulation dynamic mechanism, the proportion of each reservoir type in the target oil and gas well interval is determined as the distribution characteristic of the target reservoir.

[0011] In some embodiments of this specification, the method further includes: The target reservoir distribution characteristics are input into a pre-constructed gas logging anomaly model, and the gas logging anomaly degree of the target oil and gas well section is output; wherein, the gas logging anomaly model is constructed by analyzing the correlation between historical reservoir distribution characteristics and data characterizing hydrocarbon gas anomalies in historical logging data; The gas logging anomaly value is input into a pre-constructed second production capacity model, and the target oil and gas production capacity of the target oil and gas well section is output; wherein, the second production capacity model is constructed by analyzing the correlation between data characterizing hydrocarbon gas anomalies and historical production capacity data of multiple historical oil and gas well sections.

[0012] In some embodiments of this specification, the gas measurement anomaly model is trained in the following manner: Hydrocarbon gas concentration data of the multiple historical oil and gas well sections are analyzed from the historical logging data; Obtain the baseline hydrocarbon gas concentration for each historical oil and gas well section; Based on the hydrocarbon gas concentration data and baseline of each historical oil and gas well section, the degree of hydrocarbon gas anomaly in each historical oil and gas well section is determined. Using hydrocarbon gas anomaly as the dependent variable and reservoir distribution characteristics as the independent variable, the historical reservoir distribution characteristics and hydrocarbon gas anomaly of the multiple historical oil and gas well sections are analyzed to construct the gas logging anomaly model.

[0013] In some embodiments of this specification, the historical production capacity data or target production capacity data includes the daily oil equivalent of the corresponding oil and gas well section; The first production capacity model is constructed by analyzing the historical reservoir distribution characteristics of multiple historical oil and gas well sections and the correlation between historical logging data and historical daily oil production equivalent; or, the second production capacity model is constructed by analyzing the correlation between data characterizing hydrocarbon gas anomalies of multiple historical oil and gas well sections and historical daily oil production equivalent. The historical daily oil equivalent production of each historical oil and gas well section is calculated using the following formula: ; Among them, Q eq Q represents historical daily oil production equivalent. o Q represents daily oil production. g denoted by , where 'a' represents the daily gas production and 'a' represents the conversion coefficient from the gas phase to the oil phase.

[0014] The second aspect of this specification provides an apparatus for determining reservoir oil and gas production capacity, comprising: The acquisition module is used to acquire reservoir property data of the target oil and gas well section; The processing module is used to determine the target reservoir distribution characteristics of the target oil and gas well section based on the reservoir physical property data and the relationship between the physical property parameters and the hydrocarbon accumulation dynamic mechanism; wherein, the target reservoir distribution characteristics are used to quantify the distribution proportion of different reservoir types in the target oil and gas well section. The determination module is used to input the target reservoir distribution characteristics into a pre-constructed first production capacity model and output the target production capacity data of the target oil and gas well section; wherein, the first production capacity model is constructed by analyzing the correlation between the historical reservoir distribution characteristics and historical production capacity data of multiple historical oil and gas well sections.

[0015] A third aspect of this specification provides an electronic device, comprising: a memory and a processor, wherein the processor and the memory are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to implement the steps of the method described in any of the first aspects.

[0016] Based on the method, apparatus, and equipment for determining reservoir oil and gas production capacity provided in the embodiments of this specification, the reservoir physical property data of the target oil and gas well section are acquired; based on the reservoir physical property data and the relationship between physical property parameters and oil and gas accumulation dynamic mechanisms, the target reservoir distribution characteristics of the target oil and gas well section are determined; wherein, the target reservoir distribution characteristics are used to quantify the distribution proportion of different reservoir types in the target oil and gas well section; the target logging data and the target reservoir distribution characteristics are input into a pre-constructed first production capacity model, and the target production capacity data of the target oil and gas well section is output; wherein, the first production capacity model is constructed by analyzing the historical reservoir distribution characteristics of multiple historical oil and gas well sections and the correlation between historical logging data and historical production capacity data. By linking reservoir physical parameters with hydrocarbon accumulation dynamics using the methods described above, and thereby quantifying the distribution characteristics of target reservoirs, the key geological factors controlling hydrocarbon enrichment and seepage can be more accurately reflected, and the complex structure of the reservoirs can be comprehensively reflected, providing a foundation for subsequent accurate production capacity prediction. The target production capacity data is determined by constructing a first production capacity model that characterizes the relationship between reservoir distribution characteristics and logging parameters and production capacity parameters. This model has strong interpretability and high prediction accuracy, providing a direct and reliable basis for the selection of rolling exploration targets. Furthermore, by quantifying reservoir distribution characteristics, the first production capacity model can be adapted to extremely heterogeneous pore-throat structures such as volcanic rocks, fully considering the controlling effect of differences in hydrocarbon accumulation dynamics on production capacity, enabling systematic, quantitative, and accurate production capacity prediction for volcanic reservoirs. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application 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 recorded in this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 The diagram shown is a schematic representation of a method for determining reservoir oil and gas production capacity provided in an embodiment of this specification. Figure 2 The diagram shown is a schematic representation of a method for determining the relationship between physical property parameters and hydrocarbon accumulation dynamics provided in the embodiments of this specification. Figure 3 The diagram shown is a schematic representation of a method for constructing a gas measurement anomaly model provided in an embodiment of this specification. Figure 4 The diagram shown is a schematic representation of a quantitative prediction method for volcanic rock productivity provided in an embodiment of this specification. Figure 5A The diagram shown is a schematic representation of a method for determining the lower limit of volcanic rock buoyancy accumulation provided in an embodiment of this specification. Figure 5B The diagram shown is a schematic representation of a method for determining the lower limit of volcanic rock buoyancy accumulation provided in an embodiment of this specification. Figure 6A The diagram shown is a schematic diagram of the pore-permeability cross-section of the 212 fault blocks into four types of reservoirs provided in the embodiments of this specification; Figure 6B The diagram shown is a schematic diagram of the pore-permeability cross-section of the 214 fault blocks used to divide the reservoirs into four types, as provided in the embodiments of this specification. Figure 6C The diagram shown is a schematic diagram of the pore-permeability cross-section of the 201 fault block into four types of reservoirs provided in the embodiments of this specification; Figure 6D The diagram shown is a schematic diagram of the pore-permeability cross-section of the 202 fault block into four types of reservoirs provided in the embodiments of this specification; Figure 7 The figure shown is the gas measurement anomaly amplitude value (A) provided in the embodiments of this specification. tc A schematic diagram of a prediction model validation method; Figure 8 The diagram shown is a schematic of a verification method for the capacity prediction model provided in the embodiments of this specification. Figure 9 The diagram shown is a schematic of a reservoir oil and gas production capacity determination device provided in an embodiment of this specification. Figure 10 The diagram shown is a schematic of an electronic device provided in an embodiment of this specification. Detailed Implementation

[0019] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0020] It should be noted that the information and data related to users involved in the embodiments of this specification are all information and data authorized by the user or fully authorized by the relevant parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of the relevant data all comply with relevant laws, regulations, and standards, and necessary confidentiality measures have been taken. They do not violate public order and good morals, and corresponding operation entry points are provided for users or relevant parties to choose to authorize or refuse.

[0021] It should also be noted that in the embodiments of this specification, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0022] As mentioned earlier, volcanic reservoirs, due to their complex lithology, highly heterogeneous porosity and permeability structures, and diverse accumulation mechanisms, have always presented a technical challenge in oil and gas exploration and development. Traditional production prediction methods are mostly designed for clastic or tight sandstone reservoirs, relying on static physical parameters or dynamic production data to establish empirical or theoretical models, which are difficult to directly apply to complex reservoirs like volcanic rocks. In volcanic reservoirs, the buoyancy lower limit (BHAD) is a key geological threshold controlling whether oil and gas can effectively accumulate and form reservoirs. However, current technologies lack a systematic method to couple BHAD with reservoir classification, gas logging response, and quantitative production capacity, resulting in low reliability and poor applicability of prediction results, failing to meet the needs of refined exploration and target selection in volcanic oil and gas reservoirs.

[0023] Geological uniqueness of volcanic reservoirs and challenges in productivity prediction: (1) Extremely complex lithology and pore throat structure: Volcanic rocks have diverse reservoir space types, including primary pores (such as vesicles and intergranular pores), secondary pores (such as dissolution pores and cavities), and fractures (tectonic fractures and diagenetic fractures). These pore types vary in size, shape, and connectivity, resulting in complex relationships between reservoir physical parameters (porosity and permeability), often exhibiting strong nonlinear characteristics, which are difficult to describe using empirical formulas applicable to clastic rocks.

[0024] (2) Diverse hydrocarbon accumulation mechanisms: Unlike the buoyancy-dominated hydrocarbon accumulation mechanism in conventional sandstone reservoirs, hydrocarbon charging and accumulation in volcanic reservoirs are controlled by multiple dynamics. In addition to buoyancy, non-buoyancy mechanisms such as source-reservoir pressure difference, diffusion, capillary forces, and fluid activity driven by tectonic stress may play a key or even dominant role in tight sections, fracture zones, or dissolution-cavity zones. Hydrocarbon reservoirs formed by different dynamic mechanisms have significantly different production capacity characteristics, production dynamics, and development methods.

[0025] (3) Difficulty in identifying “sweet spots”: In a highly heterogeneous environment, economically valuable “sweet spots” (i.e., high-yield enrichment areas) are often limited in scale and spatially discontinuous. Traditional prediction methods based on single physical property parameters (such as porosity > a certain empirical lower limit) or seismic attributes are difficult to effectively distinguish reservoirs of different origins and different productivity levels, resulting in low exploration hit rate and weak targeting of development plans.

[0026] Currently, production capacity prediction methods mainly stem from the understanding of clastic or carbonate reservoirs, and their technical approaches can be summarized into the following categories: (1) "Sweet Spot" Prediction Method Based on Static Geological Parameters: Method Overview: This method mainly utilizes static parameters such as porosity, permeability, and gas saturation obtained from well logging and core analysis. Predictions are made by establishing statistical relationships (such as cross plots and empirical formulas) between these parameters and oil production capacity. Limitations in Volcanic Rocks: The porosity-permeability relationship in volcanic rocks is discrete, and single physical property parameters cannot fully reflect the complex reservoir space and seepage capacity. For example, high-porosity reservoirs may be ineffective due to extremely low permeability, while fractured zones may have high production but low porosity. Static parameter models cannot capture dynamic hydrocarbon accumulation processes and fluid flow mechanisms, often resulting in misjudgments such as "high porosity, low production" or "low porosity, high production."

[0027] (2) Numerical simulation / decline analysis based on production dynamic data: Method overview: For wells already in production, numerical simulation or production decline analysis (such as Arps decline) is performed using historical production data (pressure, production rate) to infer reservoir parameters and predict future production capacity. Limitations in volcanic rocks: This method heavily relies on existing production data and is a "post-hoc" analysis, which cannot be used for early-stage prediction in un-drilled areas or new strata. In addition, the complex seepage mechanism of volcanic reservoirs (such as multi-medium flow) makes it difficult to accurately characterize traditional homogeneous or dual-medium models, resulting in difficulties in historical fitting and large uncertainty in prediction extrapolation.

[0028] (3) Prediction methods based on geophysical response (including gas logging): Method overview: Prediction models are established by utilizing the correlation between seismic attributes (such as amplitude, impedance, AVO) or logging parameters (such as total hydrocarbons in gas logging, resistivity) and production capacity. In recent years, machine learning algorithms have also been frequently combined. Limitations in volcanic rocks: Seismic methods are limited by resolution and cannot accurately depict small-scale reservoir changes within volcanic rocks. Although gas logging information can directly reflect the hydrocarbon content of the formation, its response intensity is affected by the coupling of multiple factors such as drilling technology, lithology, and reservoir properties. Existing methods mostly remain at the stage of qualitative or semi-quantitative interpretation, or although they attempt to quantify, they often lack a theoretical framework that links geochemical response with reservoir geological genesis (hydrogenation dynamics), resulting in insufficient interpretability and geological extrapolation ability of the models.

[0029] Furthermore, in some implementation scenarios, a production capacity prediction method based on dynamic-static parameter coupling is provided. This method obtains static parameters such as porosity, permeability, and gas saturation from well logging data, combines them with dynamic data such as production pressure differential, constructs a single-well daily gas production calculation model, and optimizes the gas production factor using the least squares method to achieve quantitative prediction of single-well production capacity in tight sandstone gas reservoirs. This prediction model is highly dependent on physical properties such as porosity and permeability, and is suitable for tight sandstone reservoirs with relatively stable porosity-permeability relationships. Volcanic reservoirs have complex porosity-permeability structures, often developing various reservoir spaces such as dissolution pores and fractures. The relationship between physical properties and production capacity is highly nonlinear, and directly applying this model will lead to large prediction errors. In addition, this method does not consider the differences in reservoir formation dynamic mechanisms and cannot distinguish between buoyancy-dominated and non-buoyancy-dominated reservoir types, thus limiting its applicability in reservoirs with diverse formation mechanisms, such as volcanic rocks.

[0030] In other implementation scenarios, a method for production capacity prediction using gas logging data combined with neural networks has been proposed. This method extracts the ratio of light to heavy components from gas logging data, constructs a spider diagram to calculate the area ratio, establishes its relationship with the production gas-oil ratio, and combines inflow dynamic equations and neural networks to achieve quantitative prediction of oil and gas production capacity. Although this method makes full use of gas logging information, its core still relies on a data-driven neural network model and lacks clear geological theoretical support. For volcanic reservoirs, gas logging responses are affected by multiple factors such as lithology, diagenesis, and fracture development, making it difficult to establish robust predictive relationships based solely on data fitting. Furthermore, this method does not introduce a reservoir classification mechanism, making it unable to distinguish the contribution of different hydrocarbon generation types to production capacity, resulting in poor interpretability and weak extrapolation ability in complex volcanic reservoirs.

[0031] To address the challenge of existing technologies failing to provide systematic, quantitative, and accurate production capacity prediction for volcanic reservoirs, this specification provides a method for determining reservoir oil and gas production capacity. This method can objectively and quantitatively determine the BHAD threshold of volcanic rocks. Furthermore, the BHAD theory can be coupled with reservoir fine classification and gas response systems to establish a quantitative prediction model from geological parameters to production capacity, providing a direct and reliable basis for the optimal selection of rolling exploration targets.

[0032] The method for determining reservoir oil and gas production capacity provided in the embodiments of this specification will be described below with reference to the accompanying drawings.

[0033] Figure 1The diagram illustrates a method for determining reservoir oil and gas production capacity provided in an embodiment of this specification. While this specification provides method operation steps or apparatus structures as shown in the following embodiments or figures, the method or apparatus may include more or fewer operation steps or module units, either combined or integrated, based on conventional or non-inventive methods. In steps or structures where there is no logically necessary causal relationship, the execution order of these steps or the module structure of the apparatus is not limited to the execution order or module structure shown in the embodiments or figures of this specification. When the method or module structure is applied in actual devices, servers, or terminal products, it can be executed sequentially or in parallel according to the method or module structure shown in the embodiments or figures (e.g., in a parallel processor or multi-threaded processing environment, or even in a distributed processing or server cluster implementation environment). Figure 1 As shown, it may include: S101: Obtain reservoir physical property data for the target oil and gas well section.

[0034] It is understandable that reservoir physical property data can be obtained by analyzing and testing the target oil and gas well section, or by further processing the target logging data of the target oil and gas well section.

[0035] One method for analyzing and testing the target oil and gas well section is, for example, core testing. By analyzing and testing the core samples of the target oil and gas well section, the corresponding reservoir physical property data can be obtained as the reservoir physical property data of the target oil and gas well section.

[0036] The target logging data can be the original logging data corresponding to the target oil and gas well section, such as electrical measurement data (resistivity, spontaneous potential, etc.), physical measurement data (natural gamma, supplementary neutrons, bulk density, photoelectric absorption cross-section index, etc.), acoustic measurement data (acoustic transit time, etc.), formation pressure data, etc. Then, by interpreting and analyzing the original logging data, reservoir physical property data used to quantify the distribution characteristics of the target reservoir can be obtained. The target logging data can also be data obtained after interpreting and analyzing the original logging data, such as reservoir physical property data used to quantify the distribution characteristics of the target reservoir. Reservoir physical property data can include, for example, porosity (…). ), permeability (K) and maximum pore throat radius (R) max The target oil and gas well section may include one or more reservoir sections, and therefore the reservoir property data may include reservoir property data of one or more reservoir sections.

[0037] In specific implementation, porosity data for the target oil and gas well section can be obtained by utilizing one or more of the acoustic transit time (AC), density (DEN), and neutron porosity (CNL) from the original logging data, through the Willy formula or empirical equations, and after core calibration. Permeability data for the target oil and gas well section can be obtained by establishing an empirical relationship between porosity and permeability (such as the porosity-permeability relationship) or by using methods such as the T2 distribution from nuclear magnetic resonance logging. Furthermore, the relationship between nuclear magnetic resonance T2 relaxation time and pore throat radius can be established by interpreting the nuclear magnetic resonance logging data, and the pore throat radius distribution can be obtained based on this relationship. The maximum pore throat radius at each depth point can then be determined from the pore throat radius distribution. In other embodiments, other methods can be used to analyze the original logging data to obtain reservoir property data; this specification does not impose limitations on these methods.

[0038] S102: Based on the reservoir physical property data and the relationship between physical property parameters and hydrocarbon accumulation dynamics, determine the target reservoir distribution characteristics of the target oil and gas well section; wherein, the target reservoir distribution characteristics are used to quantify the distribution proportion of different reservoir types in the target oil and gas well section.

[0039] It is understandable that the relationship between physical properties and the dynamic mechanism of hydrocarbon accumulation can be a quantified correlation between physical properties and dynamic field types. This can include the correlation between various dimensions of physical properties (such as porosity, permeability, maximum pore throat radius, etc.) and dynamic field types. Based on this correlation and reservoir physical property data, reservoir types can be classified. Furthermore, based on the classified reservoir types, the target reservoir distribution characteristics of target oil and gas well intervals can be determined. It is also understood that different reservoir types correspond to different reservoir geological genesis; for example, oil and gas reservoirs are mainly driven by buoyancy, mainly by non-buoyancy, mainly by geological fluid activity, and mainly by tectonic stress.

[0040] In some embodiments of this specification, the target reservoir distribution characteristics may include the proportion of each reservoir type in the target oil and gas well section. By characterizing the reservoir distribution characteristics as the proportion of each reservoir type, geological factors can be correlated with oil and gas well productivity, thus quantifying oil and gas well productivity more accurately. Furthermore, the target reservoir distribution characteristics may include the spatial proportion of reservoir types. By characterizing the spatial proportion of reservoir types, the reservoir distribution characteristics, which characterize the spatial geological structure of the reservoir, can be correlated with oil and gas well productivity, thus more accurately representing the relationship between the spatial distribution of reservoir types and oil and gas well productivity.

[0041] S103: Input the target reservoir distribution characteristics into a pre-constructed first production capacity model and output the target production capacity data of the target oil and gas well section; wherein, the first production capacity model is constructed by analyzing the correlation between the historical reservoir distribution characteristics and historical production capacity data of multiple historical oil and gas well sections.

[0042] It is understood that the first production capacity model can be used to characterize the relationship between reservoir distribution and production capacity parameters. The first production capacity model can be a mathematical model, such as a linear model or a logarithmic model, or an artificial intelligence model, such as a machine learning model (e.g., support vector machine, gradient boosting decision tree, etc.) or a deep learning model (e.g., convolutional neural network, recurrent neural network, etc.). This specification does not impose any restrictions on this.

[0043] In practice, a suitable mathematical model or artificial intelligence model can be selected by analyzing the statistical characteristics and correlations between historical reservoir distribution characteristics and historical production capacity data.

[0044] For example, historical reservoir distribution characteristics can be matched with historical production capacity data to determine the correspondence between the two, and a scatter plot of historical reservoir distribution characteristics and historical production capacity data can be drawn. Based on this scatter plot, the statistical trend and correlation between reservoir distribution characteristics and production capacity parameters can be observed, providing a basis for the selection of subsequent mathematical models. Furthermore, after determining the model form, regression fitting can be performed based on historical reservoir distribution characteristics and historical production capacity data to determine model parameters and construct a first production capacity model. In other embodiments, based on historical reservoir distribution characteristics and historical production capacity data, corresponding candidate models can be fitted for different model forms, and then indicators such as the coefficient of determination and the sum of squared residuals of each candidate model, which characterize the model fitting accuracy, can be calculated. Based on these indicators, a first production capacity model can be selected from multiple candidate models.

[0045] For example, historical reservoir distribution characteristics can be matched with historical production data to determine the correspondence between the two, and feature vectors can be extracted, which may include statistical features, spatial features, etc., to select a suitable artificial intelligence model structure. After determining the target model structure, historical reservoir distribution characteristics can be used as input for model training, and historical production data can be used as the expected output for model training. The model can be trained until a preset iteration condition or other termination condition is met to obtain the first production model.

[0046] In the embodiments of this specification, the reservoir's physical properties are correlated with the hydrocarbon accumulation dynamic mechanism, thereby quantifying the target reservoir distribution characteristics. This more accurately reflects the key geological factors controlling hydrocarbon enrichment and seepage, and comprehensively reflects the complex structure of the reservoir, providing a foundation for subsequent accurate production capacity prediction. The target production capacity data is determined by constructing a first production capacity model that characterizes the relationship between reservoir distribution characteristics and logging parameters and production capacity parameters. This model has strong interpretability and high prediction accuracy, providing a direct and reliable basis for the selection of rolling exploration targets. Furthermore, by quantifying the reservoir distribution characteristics, the first production capacity model can be adapted to extremely heterogeneous pore-throat structures such as volcanic rocks, fully considering the controlling effect of differences in hydrocarbon accumulation dynamic mechanisms on production capacity, enabling systematic, quantitative, and accurate production capacity prediction for volcanic rock reservoirs.

[0047] refer to Figure 2 As shown in some embodiments of this specification, the relationship between the physical properties and the hydrocarbon accumulation dynamics can be determined in the following ways: S201: Obtain historical physical property data of multiple historical oil and gas well sections, wherein the historical physical property data carries labels characterizing the reservoir type of oil and gas reservoir.

[0048] It is understandable that multiple historical oil and gas well intervals can be considered proven oil and gas well intervals, and each interval can include at least one reservoir type. Reservoir types can include conventional and tight reservoirs. Conventional reservoirs can be free-dynamic fields, such as reservoirs with industrial oil and gas flow and buoyancy as the dominant dynamic force for reservoir formation. Tight reservoirs can be confined dynamic fields, such as reservoirs with low production or requiring fracturing for production, and non-buoyancy (e.g., pressure differential, diffusion) as the dominant dynamic force for reservoir formation, or clearly defined dry or water-bearing layers. Reservoir types can serve as a preliminary classification of reservoir intervals, and different labels can be assigned to different reservoir types. A set of historical logging data corresponding to the same location within the same reservoir interval can be considered a data sample. The reservoir type can then be pre-labeled for each data sample, and the labeled reservoir type can serve as a label for that data sample (or that set of historical physical property data).

[0049] In practice, measured data on the physical properties of volcanic reservoirs in the target formation from all wells within the study area can be collected, including porosity ( ), permeability (K) and maximum pore throat radius (R) maxEach well can include at least one sampling well section as a historical oil and gas well section, and each historical oil and gas well section can be a sample, with a total sample size N > 30 to ensure statistical significance. Furthermore, the reservoir type attributes of the samples can be identified. Based on oil testing results, production dynamics, and geological analysis, each sample point can be clearly classified into two types of oil and gas reservoirs: conventional oil and gas reservoirs (free dynamic field) samples, derived from proven oil and gas reservoirs with industrial oil and gas flow and buoyancy as the dominant dynamic force; and tight oil and gas reservoirs (confined dynamic field) samples, derived from proven oil and gas reservoirs with low production or requiring fracturing for production and non-buoyancy (such as pressure difference, diffusion, etc.) as the dominant dynamic force, or clearly defined dry or water-bearing layers.

[0050] S202: Based on historical physical property data of multiple historical oil and gas well sections, determine the critical physical property thresholds of each dimension of physical property parameters corresponding to the historical physical property data. The critical physical property thresholds are used to characterize the critical thresholds of the corresponding physical property parameters in different reservoir oil and gas types.

[0051] The critical physical property threshold can be understood as the buoyancy-driven hydrocarbon accumulation limit (BHAD), referring to the critical physical property conditions (such as porosity threshold and permeability threshold) at which the hydrocarbon migration and accumulation dynamics shift from buoyancy-dominated to non-buoyancy-dominated under a specific geological context. This threshold is a core geological parameter for classifying reservoir accumulation dynamics and predicting their production potential. Porosity, permeability, and maximum pore throat radius gradually decrease with increasing burial depth. When the values ​​of these physical property parameters reach the BHAD value, the corresponding depth is the critical depth of the BHAD. Above this depth, hydrocarbon migration is dominated by buoyancy, and the entire process occurs within a free dynamic field. Below this depth, hydrocarbon migration is dominated by non-buoyancy, and the entire process occurs within a confined dynamic field. Therefore, the critical physical property threshold for each dimension can be determined by analyzing the data corresponding to the physical property parameters in historical physical property data.

[0052] In some embodiments of this specification, determining the critical physical property thresholds for each dimension of physical property parameters corresponding to the historical physical property data based on historical physical property data from multiple historical oil and gas well sections may include: based on the historical physical property data, for any dimension of physical property parameter: The data range of the physical property data corresponding to the physical property parameter is determined, the data range is divided into multiple continuous sub-ranges, and the number of reservoir segments of different oil and gas reservoir types in each sub-range is counted; based on the number of reservoir segments of different oil and gas reservoir types in each sub-range, the frequency of reservoirs of different oil and gas reservoir types in each sub-range is determined; based on the frequency of reservoirs of different oil and gas reservoir types in multiple sub-ranges, the critical physical property threshold corresponding to the physical property parameter is determined.

[0053] Furthermore, based on the historical physical property data, frequency distribution curves for different reservoir oil and gas reservoir types are plotted for any dimension of physical property parameters, and the values ​​of physical property parameters corresponding to the intersection points of the frequency distribution curves for different reservoir oil and gas reservoir types are used as the critical physical property thresholds of the physical property parameters.

[0054] It is understandable that determining the critical physical property threshold can be achieved by statistically analyzing the differences in the distribution of physical property parameters across multiple samples. Specifically, when determining the critical physical property threshold, the data intervals of physical property data corresponding to multiple samples can be divided into a series of continuous sub-intervals. The number of samples of different reservoir types (i.e., the number of reservoir segments) within each sub-interval can be counted, and the frequency of occurrence of samples of the corresponding types can be determined. Then, in the same coordinate system, corresponding frequency distribution curves can be plotted based on the frequencies corresponding to each reservoir type within each sub-interval. The physical property value corresponding to the intersection of the two curves is taken as the critical physical property threshold. Below this value, the frequency of tight reservoir samples will be higher than that of conventional reservoirs; above this value, the frequency of conventional reservoir samples will be higher than that of tight reservoirs.

[0055] In specific implementation, porosity ( Permeability (K), Maximum pore throat radius (R) max Three parameters are used to determine the full data range and divide it into several continuous physical property intervals (groups). The number of samples falling within each physical property interval is counted in both the "conventional oil and gas reservoir sample set" and the "tight oil and gas reservoir sample set". The frequency of each interval in each sample set is calculated (number of samples in that interval / total number of samples in that sample set). A frequency distribution curve is plotted: using the physical property parameter values ​​( K, R max Using the x-axis as the horizontal axis and the frequency of occurrence as the vertical axis, plot the physical property frequency distribution curves for "conventional oil and gas reservoirs" and "tight oil and gas reservoirs" on the same coordinate system (usually using a line graph or smooth curve connecting the midpoint frequencies of each interval). Identify the intersection point and determine the BHAD threshold: observe the intersection of the two frequency distribution curves. Theoretically, below a certain physical property value, the frequency of tight reservoir samples will be higher than that of conventional reservoirs; above this value, the frequency of conventional reservoir samples will be higher than that of tight reservoirs. The physical property parameter value corresponding to the intersection point (or the midpoint of the intersection interval) of the two frequency distribution curves on the horizontal axis is the desired lower limit of buoyancy accumulation (BHAD) threshold. [Further details on the BHAD threshold would follow here.] K, R max By repeating the above process, the corresponding result can be obtained. BHAD K BHAD R max-BHAD .

[0056] S203: Based on the critical physical property thresholds of multiple dimensions of physical property parameters, determine the reservoir types corresponding to multiple historical oil and gas well sections and the reservoir physical property intervals corresponding to each reservoir type as the relationship between the physical property parameters and the oil and gas accumulation dynamic mechanism.

[0057] It is understandable that different reservoir property intervals can be obtained by combining multiple critical property thresholds. Each reservoir property interval can include a property interval for each property parameter, and each reservoir property interval can correspond to a reservoir type. Furthermore, each reservoir type and its corresponding reservoir property interval can serve as a representation of the relationship between property parameters and hydrocarbon accumulation dynamics. By using different reservoir types and their corresponding reservoir property intervals, the hydrocarbon accumulation dynamics can be reflected more accurately and reliably, providing a foundation for subsequent quantitative and precise production capacity prediction.

[0058] In some embodiments of this specification, the reservoir type may include a first type of reservoir, a second type of reservoir, a third type of reservoir, and a fourth type of reservoir; the critical physical property thresholds for each dimension of physical property parameters may include a critical porosity threshold and a critical permeability threshold. Further, the reservoir property ranges corresponding to each reservoir type may include: the porosity of the first type of reservoir is greater than the critical porosity threshold, and the permeability of the first type of reservoir is greater than the critical permeability threshold; the porosity of the second type of reservoir is less than or equal to the critical porosity threshold, and the permeability of the second type of reservoir is less than or equal to the critical permeability threshold; the porosity of the third type of reservoir is greater than the critical porosity threshold, and the permeability of the third type of reservoir is less than or equal to the critical permeability threshold; the porosity of the fourth type of reservoir is less than or equal to the critical porosity threshold, and the permeability of the fourth type of reservoir is greater than the critical permeability threshold.

[0059] It is understandable that the maximum pore throat radius is highly applicable to the dynamic field classification of conventional reservoirs. However, due to the complex lithology, strong heterogeneity of pore-permeability structure, and diverse accumulation mechanisms of volcanic rocks, its applicability to the dynamic field classification of volcanic rocks is poor. Therefore, in the embodiments of this specification, reservoir classification is considered based on critical thresholds for porosity and permeability. In other embodiments or other application scenarios, more or fewer critical thresholds for physical properties can be used for reservoir classification, thereby identifying more or fewer reservoir types. This specification does not impose any limitations on this.

[0060] In practice, a porosity-permeability distribution map can be drawn for each historical oil and gas well section. Then, based on the critical conditions of the physical properties (porosity and permeability) corresponding to the buoyancy-driven hydrocarbon accumulation depth (BHAD) of the volcanic rock reservoir, each historical oil and gas well section can be divided into four types of reservoirs, corresponding to four types of hydrocarbon accumulation driving forces: X1 type (i.e., the first reservoir, which is a high-porosity and high-permeability reservoir): > BHAD and > BHAD → Primarily driven by buoyancy, corresponding to conventional oil and gas reservoirs. X2 type (i.e., the second reservoir, a low-porosity, low-permeability reservoir): ≤ BHAD and ≤ BHAD → Primarily driven by non-buoyancy, corresponding to tight oil and gas reservoirs. X3 type (i.e., the third reservoir, which is a high-porosity, low-permeability reservoir): > BHAD and ≤ BHAD → Primarily driven by geofluid activity, corresponding to dissolution-cavity type oil and gas reservoirs. X4 type (i.e., the fourth reservoir, a low-porosity, high-permeability reservoir): ≤ BHAD and > BHAD → Primarily driven by tectonic stress, corresponding to fractured oil and gas reservoirs. The dynamic field is determined based on the BHAD (Boundary High Depth). Oil and gas reservoirs above the depth corresponding to the BHAD are located in a free dynamic field, dominated by buoyancy (X1 type > 50%). Oil and gas reservoirs below this depth are mainly located in a confined dynamic field, dominated by non-buoyancy (X2 type > 50%). The other two types of oil and gas reservoirs are represented by data on stress or dissolution (X3, X4).

[0061] In some embodiments of this specification, determining the target reservoir distribution characteristics of the target oil and gas well interval based on the reservoir physical property data and the relationship between physical property parameters and hydrocarbon accumulation dynamics may include: Based on the reservoir physical property data and the relationship between the physical property parameters and the hydrocarbon accumulation dynamic mechanism, the proportion of each reservoir type in the target oil and gas well interval is determined as the distribution characteristic of the target reservoir.

[0062] It is understandable that when determining the distribution characteristics of the target reservoir, the reservoir type of each sampling point in the target oil and gas well section can be determined based on the pre-determined reservoir type and the reservoir property range corresponding to each reservoir type. Then, the thickness or volume ratio of the sampling point corresponding to each reservoir type can be calculated as the distribution characteristics of the target reservoir.

[0063] In practice, for each target volcanic rock segment at each sampling point: determine its category (X1–X4) point by point or segment by segment; and statistically analyze the thickness or volume percentage of each category: where H XiH represents the thickness of the i-th type of reservoir. total The total thickness of the sampling points is given; furthermore, the "four types of reservoir proportion vector" for each well can be output: [X1%, X2%, X3%, X4%], as the target reservoir distribution characteristics for subsequent quantitative evaluation of driving force contribution. The proportion of the i-th type of reservoir can be expressed by the following formula: X i %=H Xi / H total ×100% formula (1) In some embodiments of this specification, considering the relatively poor relationship between the proportion vectors of the four types of reservoirs and their production capacity, and the interaction between the data of the four types of reservoirs, a gas anomaly model and a second production capacity model can be combined to separate geological and engineering factors to achieve production capacity prediction. The gas anomaly model can predict the gas anomaly degree of the corresponding well section based on the input reservoir distribution characteristics. This gas anomaly degree can characterize the relative intensity of hydrocarbon anomalies at the corresponding sampling point. The second production capacity model can predict the production capacity of the corresponding well section based on the gas anomaly degree output by the gas anomaly degree model. That is, the gas anomaly model can reflect geological enrichment, while the second production capacity model can incorporate engineering recoverability. This improves the accuracy of production capacity prediction while enhancing model interpretability and reducing model complexity. Introducing the gas anomaly model can better constrain the relationship between dynamic parameters and hydrocarbon enrichment.

[0064] Specifically, the method for determining the reservoir oil and gas production capacity may further include: inputting the target reservoir distribution characteristics into a pre-constructed gas logging anomaly model and outputting the gas logging anomaly degree of the target oil and gas well section; wherein, the gas logging anomaly model is constructed by analyzing the correlation between historical reservoir distribution characteristics and data characterizing hydrocarbon gas anomalies in historical logging data; inputting the gas logging anomaly value into a pre-constructed second production capacity model and outputting the target oil and gas production capacity of the target oil and gas well section; wherein, the second production capacity model is constructed by analyzing the correlation between data characterizing hydrocarbon gas anomalies in multiple historical oil and gas well sections and historical production capacity data.

[0065] refer to Figure 3 As shown, in some embodiments of this specification, the gas measurement anomaly model can be trained in the following ways: S301: Extract hydrocarbon gas concentration data from the historical logging data of the multiple historical oil and gas well sections.

[0066] Among them, the hydrocarbon gas concentration data of each historical oil and gas well section is the total hydrocarbon (TC) value. The TC value can be the total concentration of hydrocarbon gas detected in the gas logging (usually the sum of C1 to C5 hydrocarbon components).

[0067] S302: Obtain the baseline hydrocarbon gas concentration for each historical oil and gas well section.

[0068] In practice, within the study well section, a geologically recognized tight layer section (such as thick tight volcanic rock or mudstone) without oil and gas can be selected, and the average value of its TC curve can be calculated as the background value of the gas measurement response of the corresponding well section. This background value is the hydrocarbon gas concentration baseline, which is used to normalize the hydrocarbon gas concentration data to obtain the corresponding hydrocarbon gas anomaly degree.

[0069] S303: Based on the hydrocarbon gas concentration data and baseline of each historical oil and gas well section, determine the hydrocarbon gas anomaly degree of each historical oil and gas well section.

[0070] Among them, the anomaly degree of hydrocarbon gases is A. tc (Normalized gas anomaly amplitude value) can be a dimensionless parameter characterizing the relative intensity of hydrocarbon anomalies in a reservoir section. In practice, the reservoir point TC value and the background baseline (TC) can be calculated first. baseline The difference (TC) amp Then divide the difference by the TC in the well section. amp The maximum value is normalized to a percentage. A tc The value can range from 0% to 100%, with a higher value indicating a stronger gas measurement anomaly.

[0071] S304: Using hydrocarbon gas anomaly as the dependent variable and reservoir distribution characteristics as the independent variable, analyze the historical reservoir distribution characteristics and hydrocarbon gas anomaly of the multiple historical oil and gas well sections to construct the gas logging anomaly model.

[0072] In practice, a model framework for the gas logging anomaly model can be constructed using a stepwise regression model. Then, the same calculation method as the target reservoir distribution characteristics of the aforementioned target oil and gas well sections can be used to calculate the historical reservoir distribution characteristics of each historical oil and gas well section. Based on the hydrocarbon gas anomaly values ​​and historical reservoir distribution characteristics obtained from the aforementioned calculations, regression analysis can be performed on the constructed model framework to obtain the gas logging anomaly model.

[0073] In practice, the gas measurement anomaly model can be constructed in the following ways: S1. Data Matching and TC Anomaly Calculation. Extract the total hydrocarbon (TC) logging curve values ​​from historical oil and gas well sections, strictly corresponding to the depths of porosity and permeability sampling points. TC values ​​are the total hydrocarbon gas concentration (C1 + C2 + C3 + …). This ensures a one-to-one correspondence between the "reservoir type percentage - TC anomaly value" samples at depth. Within the study section, select a recognized tight reservoir section (such as a tight volcanic rock or mudstone section), and define its average TC value as TC. baselineFor each sampling point corresponding to the pore seepage data, calculate the anomalous magnitude of its TC value relative to the baseline: TC amp =TC sample -TC baseline To eliminate dimensional differences between wells, the abnormal amplitude value is normalized to the ratio of the maximum TC abnormal amplitude within the well section, thus obtaining the final TC gas logging abnormal amplitude value (A). tc (i.e., hydrocarbon gas anomaly) Formula (2) in, It is a dimensionless value between 0% and 100%, representing the relative intensity of the gas measurement anomaly at the current sampling point.

[0074] Ultimately, a vector can be formed with the proportions of four reservoir types [X1%, X2%, X3%, X4%] as independent variables, and the corresponding A... tc The sample dataset is the dependent variable.

[0075] S2. Model framework construction based on stepwise regression: using A tc Let A be the dependent variable (Y), and let X1%, X2%, X3%, and X4% of the four reservoir types be the independent variables. Stepwise regression analysis was used to control model complexity and select the factors that affect A. tc Reservoir types with significant impact. Modeling and variable selection: Independent variables are allowed to enter the model as linear, quadratic, or interaction terms, but the following principles must be followed to ensure model simplicity and generalization ability: the total number of terms in the model (including the constant term) does not exceed 6, and the highest order of a single independent variable does not exceed third order. The selection criteria for stepwise regression are set as follows: the significance level (p-value) of the F-statistic is ≤0.05 at the entry threshold and ≥0.10 at the exit threshold. The final quantitative prediction model can be in the form of multiple linear or finite nonlinear, with the following general formula: Formula (3) in, 0 is a constant term. For regression coefficients, For the selected independent variables (such as X1, X2², X1... X3, etc.

[0076] S3. Model Validation and Accuracy Requirement Validation Methods. A hold-out method can be used, randomly dividing the total dataset into a training set (typically 70%-80%) and a test set (20%-30%). The model is built using the training set, and its prediction accuracy is validated on the test set. The model must simultaneously meet the following two accuracy requirements to pass validation: the coefficient of determination is greater than a preset threshold, for example, the coefficient of determination... 2 A value ≥0.7 indicates that the model can explain A.tc More than 85% of the information is changing; the average relative error is less than a preset error threshold. The average relative error can be expressed as: ,in N To validate the sample size, for example, a preset error threshold of 15% can be used to ensure that the average deviation between the model's predicted values ​​and the actual values ​​is less than 15%.

[0077] In some embodiments of this specification, the historical production capacity data or target production capacity data may include the daily oil equivalent of the corresponding oil and gas well section; furthermore, the first production capacity model can be constructed by analyzing the historical reservoir distribution characteristics of multiple historical oil and gas well sections and the correlation between historical logging data and historical daily oil equivalent; or, the second production capacity model can be constructed by analyzing the correlation between data characterizing hydrocarbon gas anomalies of multiple historical oil and gas well sections and historical daily oil equivalent.

[0078] The historical daily oil equivalent production of each historical oil and gas well section can be calculated using the following formula: Formula (4) Among them, Q eq Q represents historical daily oil production equivalent. o Q represents daily oil production. g This represents the daily gas production, and 'a' represents the conversion coefficient from the gas phase to the oil phase. For example, 'a' can be 1500.

[0079] In practice, the second capacity model can be constructed in the following ways: S1. Production Data Preparation and Standardized Production Data Collection. Specifically, this involves collecting the corresponding daily oil production (Q) from the tested well sections within the study area. o (Unit: t / d), Daily gas production (Q) g (Unit: m³ / d) and daily water production (Q) w (Unit: m³ / d) Data. Natural gas production can then be converted to oil equivalent based on energy equivalent. According to industry standards, a conversion factor is used where 1500 m³ of natural gas is equivalent to 1 ton of crude oil. Calculate the daily oil equivalent (Q). eq ( ) as a unified production capacity indicator.

[0080] S2, TC—Capacity Relationship Modeling. The calculated TC anomaly magnitude value (A) tc ) and the daily oil equivalent of the corresponding well section (Q) eq Match the data. Draw A. tc With Q eq A scatter plot was generated to observe the statistical trends and correlations between the two, providing a basis for model selection. Based on the trends presented in the scatter plot, model A was selected and established. tc Predict Qeq The regression model. Candidate model forms include, but are not limited to, the following types: Linear model: Logarithmic model: .

[0081] Specifically, the model with the highest coefficient of determination (R²) and the smallest sum of squared residuals can be selected, resulting in a high goodness of fit. This ensures that the model's form aligns with our understanding of geological and seepage mechanisms. Furthermore, the model should not exhibit drastic, non-physical oscillations or outliers at the edges of the data range, demonstrating good extrapolation stability.

[0082] S3. Validation and Reliability Evaluation of Prediction Results. The optimized production capacity prediction model can be applied to newly drilled wells or untested sections. First, based on the reservoir type determined in the aforementioned examples and the reservoir property data of the section to be predicted, the reservoir proportion vector (X1, X2, X3, X4) of the section to be predicted is determined. Second, the reservoir proportion vector is input into the quantitative prediction model for total hydrocarbon anomaly amplitude to obtain the TC anomaly amplitude value A of the section to be predicted. tc Finally, the TC anomaly amplitude values ​​A of these segments were determined. tc The data is input into the production capacity forecasting model to predict the corresponding daily oil equivalent (Q). eq The predicted production capacity is used as the production capacity prediction result. After the actual oil testing results are obtained for the predicted layer, the model prediction value is compared with the actual oil testing results. The "prediction consistency rate" is defined as follows: For continuous values, the relative error between the predicted value and the actual value can be calculated. To facilitate engineering applications, production capacity levels can be set, and the proportion of samples whose predicted production capacity level matches the actual production capacity level can be used as the consistency rate. Alternatively, indicators such as root mean square error (RMSE) and mean absolute percentage error (MAPE) can be used for comprehensive evaluation. If the prediction consistency rate is greater than the corresponding preset threshold, such as 70% (or the MAPE is less than the corresponding preset threshold, such as 30%, depending on the specific data distribution), then the established TC-production capacity prediction model is considered reliable and can be used for rapid prediction of reservoir production capacity and selection of favorable targets in the study area. If the consistency rate does not meet the standard, it is necessary to return to check the data quality, model form, or consider introducing other control factors (such as reservoir thickness, pressure coefficient, etc.) for multivariate modeling.

[0083] Reference Figure 4 As shown in the embodiments of this specification, a method for quantitative prediction of volcanic rock productivity is also provided. This method uses a volcanic oil and gas reservoir in well A as an example, but the application of these embodiments is not limited to this specific region or lithology. The method may include: S1. Data collection and determination of the lower limit of volcanic rock buoyancy for hydrocarbon accumulation (BHAD).

[0084] S1.1 Data Collection and Sample Dynamic Field Property Calibration. First, the system collected measured data from all exploration, appraisal, and development wells that encountered volcanic rock formations within the A well area. The collected data mainly included two categories: reservoir physical property data, derived from core experimental analysis and reliable well logging interpretation results. Key parameters included porosity (…). (Unit: %), permeability (K, unit: mD), and the maximum pore throat radius (R) of the reservoir obtained by mercury intrusion porosimetry. max (Unit: μm). To ensure statistical significance, a total of 6404 valid sample points were collected (N > 30). Production dynamics and oil testing data: Oil testing conclusions, daily oil production, daily gas production, and production test data for each well's corresponding stratigraphic interval were collected. Based on the above data, the "dynamic field attribute" of each reservoir physical property sample point was calibrated, and they were classified into two mutually exclusive sample sets: Conventional oil and gas reservoir sample set (free dynamic field): Sample points are from intervals where the oil testing conclusion is "industrial oil flow" or "industrial gas flow," and the production dynamics indicate high production capacity and strong natural production capacity. These oil and gas reservoirs are considered to have buoyancy as the main driving force for oil and gas accumulation during their formation and development. Tight oil and gas reservoir sample set (confined dynamic field): Sample points are from intervals where the oil testing conclusion is "low-yield oil flow," "low-yield gas flow," "dry layer," or "water layer," or where large-scale fracturing is required to obtain economic production. Oil and gas accumulation in these reservoirs is mainly driven by non-buoyancy forces (such as source-reservoir pressure difference, diffusion, etc.).

[0085] S1.2 Quantitative Identification of BHAD Threshold—Based on Frequency Distribution Curve Cross-Method for Dynamic Field Classification. This step aims to determine the critical physical property value that distinguishes the two types of dynamic fields, namely the lower limit of buoyancy accumulation (BHAD), through objective statistical methods. This is to determine the porosity threshold (…). BHAD Taking ) as an example, the specific operation process includes (this method is also applicable to penetration rate (K) BHAD ) and maximum throat radius (R) max-BHAD (determination of) (1) Data grouping: The porosity data range of all 6404 sample points (e.g., 0% to 25%) is divided into continuous property intervals with a fixed group interval (e.g., 0.5%).

[0086] (2) Frequency statistics: The number of samples whose porosity values ​​fall within each interval in the “conventional oil and gas reservoir sample set” and the “tight oil and gas reservoir sample set” are counted respectively.

[0087] (3) Calculate the frequency: Divide the number of samples in each interval by the total number of samples in its sample set to obtain the "frequency" of the interval in each sample set.

[0088] (4) Plot the frequency distribution curves: Using "porosity value" as the abscissa and "frequency" as the ordinate, plot the frequency distribution curves of the two sample sets on the same graph (a histogram or a smooth curve can be used to connect the midpoints of each interval). Figure 5A As shown, the frequency distribution curves of the conventional oil and gas reservoir sample set have peak values ​​that are biased towards the high porosity region, while the frequency distribution curves of the tight oil and gas reservoir sample set have peak values ​​that are biased towards the low porosity region. Figure 5B The graph shows the frequency distribution curves of two sample sets plotted on the same graph, with "permeability value" as the x-axis and "frequency" as the y-axis (a histogram or a smooth curve can be used to connect the midpoints of each interval).

[0089] (5) Identify the intersection point and determine the threshold: Observe the intersection of the two frequency distribution curves. Near a theoretically reasonable intersection point, the frequency advantage of tight reservoir samples will be converted into the frequency advantage of conventional reservoir samples. The value corresponding to the intersection point (or the midpoint of the intersection area) of the two curves on the horizontal axis (porosity axis) is the porosity threshold determined as the lower limit of buoyancy accumulation. BHAD In this embodiment, the porosity value corresponding to the intersection point is 9% (see [reference]). Figure 5A ).

[0090] (6) Repeat the process to determine other parameter thresholds: Apply the exact same procedure to the penetration rate data to obtain the penetration rate threshold K. BHAD = 1 mD. Applying the maximum throat radius data, we obtain R. max-BHAD = 0.8 μm.

[0091] S2. Divide the reservoirs into four categories (X1, X2, X3, X4) and calculate their proportions based on the BHAD threshold determined in the previous step. BHAD =9%, K BHAD =1 mD) is used as the classification standard to classify the reservoir type at each depth sampling point (or logging interpretation layer) within the target well section. The classification rules are based on the comparison of two parameters, porosity and permeability, with their respective thresholds, defining four types of reservoirs and their corresponding dominant hydrocarbon accumulation dynamics as shown in Table 1: Table 1

[0092] For each well in the study area that needs to be evaluated, the following operations are performed on the target volcanic rock formations encountered during drilling: (1) Point-by-point classification: Based on the well logging interpretation porosity and permeability curves of the well, and in conjunction with the above classification rules, all sampling points in the layer are classified.

[0093] (2) Statistical thickness percentage: The total thickness (H) of each type of reservoir (X1, X2, X3, X4) within this segment is calculated cumulatively.X1 H X2 H X3 H X4 ).

[0094] (3) Calculate the percentage vector: Calculate the percentage of each type of reservoir thickness in the total interpreted thickness to form the "four types of reservoir percentage vector" for the well (or the interval): [X1% = H X1 / H total [100%, X2%, X3%, X4%]. This vector quantitatively characterizes the relative magnitudes of the four hydrocarbon accumulation dynamics contributions within the evaluation unit.

[0095] The pore-permeability cross-connection of some fault blocks, based on the BHAD classification of four types of reservoirs, can be seen as follows: Figure 6A , Figure 6B , Figure 6C and Figure 6D As shown in the figures. In each figure, 'a' represents the sample quantity distribution of each type of reservoir, and 'b' represents the thickness percentage of each type of reservoir.

[0096] S3. Establish a quantitative prediction model for the abnormal amplitude of total hydrocarbon (TC) values.

[0097] S3.1 To establish the relationship between reservoir type and hydrocarbon-bearing response, it is necessary to extract geochemical logging information—total hydrocarbon (TC) values—that strictly correspond to the depth of physical property data. Specifically, this includes: (1) Data extraction and alignment: Extract the total hydrocarbon (TC, i.e., the total concentration of C1 to C5 hydrocarbon gases) curve from the well logging data. Ensure that each reservoir property sampling point has a TC value that matches its depth.

[0098] (2) Definition and calculation of TC abnormal amplitude value (A tc Within the study section, geologically recognized tight layers (such as thick-layered tight volcanic rocks or mudstone) free of oil and gas are selected, and the average value of the TC curve for this section is calculated as the background TC value for this well. baseline .

[0099] (3) Calculate the original anomaly magnitude: For each sampling point, calculate the difference between its TC value and the baseline: TC amp-raw =TC sample - TC baseline .

[0100] (4) In-well normalization: To eliminate the influence of absolute dimensions caused by differences in gas logging instruments, drilling fluids, etc., between different wells, in-well normalization is performed. Calculate the TC within the target formation of the well. amp-raw The maximum value (TC) amp-max The normalized TC outlier magnitude value (A) tc The calculation formula is: Atc = (TC amp-raw / TC amp-max ) 100%. Among them, A tc It is a dimensionless value between 0% and 100%, where 100% represents the strongest gas logging anomaly in the well section and 0% represents no anomaly (consistent with the baseline).

[0101] (5) Constructing a modeling dataset: A dataset was constructed for 13 wells and 24 sections with oil testing results in the study area. Each data sample contains a vector of the proportion of four types of reservoirs (independent variables) and the average "TC anomaly amplitude value A" calculated for that section. tc (dependent variable).

[0102] S3.2, Model construction based on stepwise regression, with A tc Using X1%, X2%, X3%, and X4% as independent variables, a quantitative prediction model is constructed using stepwise regression analysis. The modeling process follows these principles to ensure the robustness and practicality of the model: Variable selection: Independent variables are allowed to enter the model as linear terms (e.g., X1), quadratic terms (e.g., X2²), or interaction terms (e.g., X1·X3). Complexity control: The total number of terms in the model (including the constant term) is set to no more than 6, and the highest order of a single independent variable is no more than third. Statistical significance criteria: The entry significance level (p-value) for the F-test in stepwise regression is set to ≤0.05, and the exit significance level is set to ≥0.10. After the above stepwise regression analysis, the software automatically selects variables that are effective against A. tc The combination of variables with significant influence. The optimal prediction model established in this embodiment is: TC=46.2361+0.0555X1·X3-0.8443X2+0.0050X2 2 -0.0040X4 2 +0.0352X3·X4-0.9719X3 Formula (5) S3.3 Model Validation. To evaluate the prediction accuracy and generalization ability of the above predictions, the following validation is performed. Goodness-of-fit test: The model predictions A... tc The value of A in 24 actual segments tc The values ​​were compared and calculated, yielding a coefficient of determination R² = 0.9031. This indicates that the model can explain A. tc The value changed by approximately 90.31%, indicating an excellent fit (see [reference]). Figure 7Residual analysis: The predicted residual (predicted value - actual value) was calculated for each sample. Of the 24 samples, 21 had residuals with an absolute value less than 10, accounting for 87.5% of the total samples. The largest residual was -11.94, which is within acceptable geological anomaly deviation. The model's predicted values ​​are highly consistent with the actual values. Error statistics: The mean relative error (MRE) for all samples was calculated to be 12.5%, meeting the preset accuracy requirement of less than 15%.

[0103] S4. Capacity forecasting and model validation.

[0104] S4.1 Standardized collection of production capacity data: The oil testing results for the 24 layers are collected, including daily oil production (Q). o , t / d), daily gas production (Q g (m³ / d). For a unified comparison, natural gas production was converted to oil equivalent according to industry-standard (1500 cubic meters of natural gas is approximately equivalent to the calorific value of 1 ton of crude oil), and the daily oil equivalent (Q) was calculated. eq As the final capacity indicator: Q eq = Q o + Q g / 1500 (unit: t / d).

[0105] S4.2, TC-Production Capacity Relationship Modeling: The A predicted by formula (5) for each segment. tc Value (or directly use the measured A) tc (value) and its actual Q eq Pair values ​​and draw A tc With Q eq Scatter plot (e.g.) Figure 8 As shown). By Figure 8 It can be seen that there is a clear positive correlation between the two, and they conform to a logarithmic growth relationship. Using regression analysis, the capacity prediction model is established as follows (6): Q eq =1.1038 A tc -8.3338. The determination coefficient R² of this model is 0.7437, indicating that A tc It can effectively predict trends in production capacity changes.

[0106] S4.3, Validation of Prediction Results and Application of Reliability Evaluation Model: For new untested wells or sections in the study area (such as a section of Jinlong 54 well), first perform the steps S1 to S3 above to obtain the proportion vector of its four types of reservoirs, and substitute it into formula (5) to predict its A tc Value. Capacity forecast: The forecast of A tc Substituting the value into the capacity prediction model, i.e., formula (6), the predicted daily oil equivalent Q is calculated. eq-predEvaluation criteria: In this embodiment, a model is considered reliable if the relative prediction error is less than 20% or the proportion of samples correctly predicting the production capacity level exceeds 80%. Practical application results show that the model's prediction accuracy exceeds 85%, meeting engineering decision-making requirements. It can be used to guide the selection of rolling exploration targets and the review of old wells in the study area and areas with similar geological conditions.

[0107] Based on the method for determining reservoir oil and gas production capacity described above, one or more embodiments of this specification also provide an apparatus for determining reservoir oil and gas production capacity. The apparatus may include devices (including distributed systems), software (applications), modules, plug-ins, servers, clients, etc., using the methods described in the embodiments of this specification, combined with necessary implementation hardware. Based on the same innovative concept, the apparatuses in one or more embodiments provided in this specification are as described in the following embodiments. Since the implementation schemes and methods for solving the problem by the apparatus are similar, the implementation of the specific apparatus in the embodiments of this specification can refer to the implementation of the foregoing method, and repeated details will not be elaborated further. As used below, the terms "unit" or "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated. Figure 9 The diagram shown is a schematic representation of a reservoir oil and gas production capacity determination device provided in an embodiment of this specification. Figure 9 As shown, the apparatus 900 for determining the reservoir's oil and gas production capacity may include: The acquisition module 901 is used to acquire target logging data for the target oil and gas well section; The processing module 902 is used to determine the target reservoir distribution characteristics of the target oil and gas well section based on the reservoir physical property data in the target logging data and the relationship between the physical property parameters and the hydrocarbon accumulation dynamic mechanism; wherein, the target reservoir distribution characteristics are used to quantify the distribution proportion of different reservoir types in the target oil and gas well section. The determination module 903 is used to input the target reservoir distribution characteristics into a pre-constructed first production capacity model and output the target production capacity data of the target oil and gas well section; wherein, the first production capacity model is constructed by analyzing the correlation between the historical reservoir distribution characteristics and historical production capacity data of multiple historical oil and gas well sections.

[0108] In some embodiments of this specification, the relationship between the physical property parameters and the hydrocarbon accumulation dynamic mechanism is determined in the following manner: acquiring historical logging data of multiple historical oil and gas well sections, the historical logging data including historical physical property data, the historical physical property data carrying labels characterizing reservoir oil and gas types; based on the historical physical property data of multiple historical oil and gas well sections, determining the critical physical property thresholds of each dimension of physical property parameters corresponding to the historical physical property data, the critical physical property thresholds being used to characterize the critical thresholds of the corresponding physical property parameters in different reservoir oil and gas types; based on the critical physical property thresholds of multiple dimensions of physical property parameters, determining the reservoir types corresponding to multiple historical oil and gas well sections and the reservoir physical property intervals corresponding to each reservoir type as the relationship between the physical property parameters and the hydrocarbon accumulation dynamic mechanism.

[0109] In some embodiments of this specification, determining the critical physical property thresholds for each dimension of physical property parameters corresponding to historical physical property data based on historical physical property data of multiple historical oil and gas well sections may include: based on the historical physical property data, for any dimension of physical property parameter: determining the data interval of the physical property data corresponding to the physical property parameter, dividing the data interval into multiple consecutive sub-intervals, and counting the number of reservoir segments of different reservoir types in each sub-interval; determining the frequency of reservoirs of different reservoir types in each sub-interval based on the number of reservoir segments of different reservoir types in each sub-interval; and determining the critical physical property thresholds corresponding to the physical property parameter based on the frequency of reservoirs of different reservoir types in multiple sub-intervals.

[0110] In some embodiments of this specification, the reservoir types include Class I reservoirs, Class II reservoirs, Class III reservoirs, and Class IV reservoirs; the critical physical property thresholds for each dimension of physical property parameters include critical thresholds for porosity and permeability; the reservoir property ranges corresponding to each reservoir type include: Class I reservoirs have porosity greater than the critical threshold for porosity and permeability greater than the critical threshold for permeability; Class II reservoirs have porosity less than or equal to the critical threshold for porosity and permeability less than or equal to the critical threshold for permeability; Class III reservoirs have porosity greater than the critical threshold for porosity and permeability less than or equal to the critical threshold for permeability; and Class IV reservoirs have porosity less than or equal to the critical threshold for porosity and permeability greater than the critical threshold for permeability.

[0111] In some embodiments of this specification, the processing module 902 is specifically used to: determine the proportion of each reservoir type in the target oil and gas well section as the target reservoir distribution characteristics based on the reservoir physical property data and the relationship between the physical property parameters and the oil and gas accumulation dynamic mechanism.

[0112] In some embodiments of this specification, the above-described apparatus can also be used to: input the target reservoir distribution characteristics into a pre-constructed gas logging anomaly model and output the gas logging anomaly degree of the target oil and gas well section; wherein the gas logging anomaly model is constructed by analyzing the correlation between historical reservoir distribution characteristics and data characterizing hydrocarbon gas anomalies in historical logging data; input the gas logging anomaly value into a pre-constructed second production capacity model and output the target oil and gas production capacity of the target oil and gas well section; wherein the second production capacity model is constructed by analyzing the correlation between data characterizing hydrocarbon gas anomalies and historical production capacity data of multiple historical oil and gas well sections.

[0113] In some embodiments of this specification, the gas logging anomaly model is trained in the following manner: hydrocarbon gas concentration data of the multiple historical oil and gas well sections are parsed from the historical logging data; the hydrocarbon gas concentration baseline corresponding to each historical oil and gas well section is obtained; based on the hydrocarbon gas concentration data and the hydrocarbon gas concentration baseline of each historical oil and gas well section, the hydrocarbon gas anomaly degree of each historical oil and gas well section is determined; with the hydrocarbon gas anomaly degree as the dependent variable and the reservoir distribution characteristics as the independent variable, the historical reservoir distribution characteristics and hydrocarbon gas anomaly degree of the multiple historical oil and gas well sections are analyzed to construct the gas logging anomaly model.

[0114] In some embodiments of this specification, the historical production capacity data or target production capacity data includes the daily oil equivalent of the corresponding oil and gas well section; the first production capacity model is constructed by analyzing the historical reservoir distribution characteristics and the correlation between historical logging data and historical daily oil equivalent of multiple historical oil and gas well sections; or, the second production capacity model is constructed by analyzing the correlation between data characterizing hydrocarbon gas anomalies and historical daily oil equivalent of multiple historical oil and gas well sections; the historical daily oil equivalent of each historical oil and gas well section is calculated using the following formula: ; Among them, Q eq Q represents historical daily oil production equivalent. o Q represents daily oil production. g denoted by , where 'a' represents the daily gas production and 'a' represents the conversion coefficient from the gas phase to the oil phase.

[0115] The descriptions and functions of the above modules can be found in the section on methods for determining reservoir oil and gas production capacity, and will not be repeated here.

[0116] This application also provides an electronic device, such as... Figure 10 As shown, the electronic device may include a processor 1001 and a memory 1002, wherein the processor 1001 and the memory 1002 may be connected via a bus or other means. Figure 10 Taking the example of a connection between China and Israel via a bus.

[0117] Processor 1001 may be a central processing unit (CPU). Processor 1001 may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations thereof.

[0118] The memory 1002, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the method for determining reservoir oil and gas production capacity in the embodiments of the present invention. The processor 1001 executes various functional applications and data processing of the processor by running the non-transitory software programs, instructions, and modules stored in the memory 1002, thereby realizing the method for determining reservoir oil and gas production capacity in the above-described method embodiments.

[0119] The memory 1002 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created by the processor 1001, etc. Furthermore, the memory 1002 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 1002 may optionally include memory remotely located relative to the processor 1001, and these remote memories may be connected to the processor 1001 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0120] The one or more modules are stored in the memory 1002, and when executed by the processor 1001, they perform the following method for determining reservoir oil and gas production capacity: Acquire target logging data for the target oil and gas well section; based on the reservoir property data in the target logging data, and the relationship between the property parameters and the hydrocarbon accumulation dynamic mechanism, determine the target reservoir distribution characteristics of the target oil and gas well section; wherein, the target reservoir distribution characteristics are used to quantify the distribution proportion of different reservoir types in the target oil and gas well section; input the target reservoir distribution characteristics into a pre-constructed first production capacity model, and output the target production capacity data of the target oil and gas well section; wherein, the first production capacity model is constructed by analyzing the correlation between historical reservoir distribution characteristics and historical production capacity data of multiple historical oil and gas well sections.

[0121] The specific details of the aforementioned electronic device can be understood by referring to the relevant descriptions and effects in the above method embodiments, and will not be repeated here.

[0122] This specification also provides a computer storage medium storing computer program instructions, which, when executed, implement the steps of the method for determining reservoir oil and gas production capacity described above.

[0123] This specification also provides a computer program product, which includes a computer program that, when executed, implements the steps of the method for determining reservoir oil and gas production capacity described above.

[0124] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium can also include combinations of the above types of memory.

[0125] The various embodiments in this specification are described in a progressive manner. For the same or similar parts between the various embodiments, please refer to each other. The focus of each embodiment is to describe the differences from other embodiments.

[0126] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions.

[0127] For ease of description, the above devices are described separately by function as various units. Of course, in implementing this application, the functions of each unit can be implemented in one or more software and / or hardware.

[0128] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute certain parts of the methods of various embodiments of this application.

[0129] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc.

[0130] This application can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0131] Although this application has been described through embodiments, those skilled in the art will know that this application has many modifications and variations without departing from the spirit of this application, and it is intended that the appended claims cover such modifications and variations without departing from the spirit of this application.

Claims

1. A method for determining reservoir oil and gas production capacity, characterized in that, include: Obtain reservoir physical property data for the target oil and gas well section; Based on the reservoir physical property data and the relationship between physical property parameters and hydrocarbon accumulation dynamics, the target reservoir distribution characteristics of the target oil and gas well interval are determined; wherein, the target reservoir distribution characteristics are used to quantify the distribution proportion of different reservoir types in the target oil and gas well interval. The target reservoir distribution characteristics are input into a pre-constructed first production capacity model, and the target production capacity data of the target oil and gas well section are output; wherein, the first production capacity model is constructed by analyzing the correlation between the historical reservoir distribution characteristics and historical production capacity data of multiple historical oil and gas well sections.

2. The method for determining reservoir oil and gas production capacity according to claim 1, characterized in that, The relationship between the physical properties and the hydrocarbon accumulation dynamics was determined in the following way: Acquire multiple historical oil and gas well sections and historical physical property data, wherein the historical physical property data carries tags characterizing the reservoir type; Based on historical physical property data of multiple historical oil and gas well sections, the critical physical property thresholds of each dimension of physical property parameters corresponding to the historical physical property data are determined. The critical physical property thresholds are used to characterize the critical thresholds of the corresponding physical property parameters in different reservoir oil and gas types. Based on the critical physical property thresholds of multiple dimensions of physical property parameters, the reservoir types corresponding to multiple historical oil and gas well sections and the reservoir physical property ranges corresponding to each reservoir type are determined as the relationship between the physical property parameters and the oil and gas accumulation dynamic mechanism.

3. The method for determining reservoir oil and gas production capacity according to claim 2, characterized in that, Based on historical physical property data from multiple historical oil and gas well sections, the critical physical property thresholds for each dimension of physical property parameters corresponding to the historical physical property data are determined, including: Based on the aforementioned historical physical property data, for any dimension of physical property parameter: Determine the data range of the physical property data corresponding to the physical property parameters, divide the data range into multiple continuous sub-ranges, and count the number of reservoir segments of different reservoir oil and gas reservoir types in each sub-range. Based on the number of reservoir segments of different oil and gas reservoir types in each sub-interval, the frequency of reservoirs of different oil and gas reservoir types in each sub-interval is determined. Based on the frequency of reservoirs of different oil and gas reservoir types within multiple sub-intervals, the critical physical property thresholds corresponding to the physical property parameters are determined.

4. The method for determining reservoir oil and gas production capacity according to claim 2, characterized in that, The reservoir types include Class I reservoirs, Class II reservoirs, Class III reservoirs, and Class IV reservoirs; the critical physical property thresholds for each dimension of physical property parameters include the critical threshold for porosity and the critical threshold for permeability; The reservoir property ranges corresponding to each reservoir type include: The porosity of the first type of reservoir is greater than the critical porosity threshold, and the permeability of the first type of reservoir is greater than the critical permeability threshold. The porosity of the second type of reservoir is less than or equal to the critical porosity threshold, and the permeability of the second type of reservoir is less than or equal to the critical permeability threshold. The porosity of the third type of reservoir is greater than the critical porosity threshold, and the permeability of the third type of reservoir is less than or equal to the critical permeability threshold. The porosity of the fourth type of reservoir is less than or equal to the critical porosity threshold, and the permeability of the fourth type of reservoir is greater than the critical permeability threshold.

5. The method for determining reservoir oil and gas production capacity according to claim 1, characterized in that, Based on the reservoir physical property data and the relationship between physical property parameters and hydrocarbon accumulation dynamics, the target reservoir distribution characteristics of the target oil and gas well intervals are determined, including: Based on the reservoir physical property data and the relationship between the physical property parameters and the hydrocarbon accumulation dynamic mechanism, the proportion of each reservoir type in the target oil and gas well interval is determined as the distribution characteristic of the target reservoir.

6. The method for determining reservoir oil and gas production capacity according to claim 1, characterized in that, Also includes: The target reservoir distribution characteristics are input into a pre-constructed gas logging anomaly model, and the gas logging anomaly degree of the target oil and gas well section is output; wherein, the gas logging anomaly model is constructed by analyzing the correlation between historical reservoir distribution characteristics and data characterizing hydrocarbon gas anomalies in historical logging data; The gas logging anomaly value is input into a pre-constructed second production capacity model, and the target oil and gas production capacity of the target oil and gas well section is output; wherein, the second production capacity model is constructed by analyzing the correlation between data characterizing hydrocarbon gas anomalies and historical production capacity data of multiple historical oil and gas well sections.

7. The method for determining reservoir oil and gas production capacity according to claim 6, characterized in that, The gas anomaly model was trained in the following manner: Hydrocarbon gas concentration data of the multiple historical oil and gas well sections are analyzed from the historical logging data; Obtain the baseline hydrocarbon gas concentration for each historical oil and gas well section; Based on the hydrocarbon gas concentration data and baseline of each historical oil and gas well section, the degree of hydrocarbon gas anomaly in each historical oil and gas well section is determined. Using hydrocarbon gas anomaly as the dependent variable and reservoir distribution characteristics as the independent variable, the historical reservoir distribution characteristics and hydrocarbon gas anomaly of the multiple historical oil and gas well sections are analyzed to construct the gas logging anomaly model.

8. The method for determining reservoir oil and gas production capacity according to claim 6, characterized in that, The historical production capacity data or target production capacity data includes the daily oil equivalent of the corresponding oil and gas well section; The first production capacity model is constructed by analyzing the historical reservoir distribution characteristics of multiple historical oil and gas well sections and the correlation between historical logging data and historical daily oil production equivalent; or, the second production capacity model is constructed by analyzing the correlation between data characterizing hydrocarbon gas anomalies of multiple historical oil and gas well sections and historical daily oil production equivalent. The historical daily oil equivalent production of each historical oil and gas well section is calculated using the following formula: ； Among them, Q eq Q represents historical daily oil production equivalent. o Q represents daily oil production. g denoted by , where 'a' represents the daily gas production and 'a' represents the conversion coefficient from the gas phase to the oil phase.

9. A device for determining reservoir oil and gas production capacity, characterized in that, include: The acquisition module is used to acquire reservoir property data of the target oil and gas well section; The processing module is used to determine the target reservoir distribution characteristics of the target oil and gas well section based on the reservoir physical property data and the relationship between the physical property parameters and the hydrocarbon accumulation dynamic mechanism; wherein, the target reservoir distribution characteristics are used to quantify the distribution proportion of different reservoir types in the target oil and gas well section. The determination module is used to input the target reservoir distribution characteristics into a pre-constructed first production capacity model and output the target production capacity data of the target oil and gas well section; wherein, the first production capacity model is constructed by analyzing the correlation between the historical reservoir distribution characteristics and historical production capacity data of multiple historical oil and gas well sections.

10. An electronic device, characterized in that, include: A memory and a processor, the processor and the memory being communicatively connected to each other, the memory storing computer instructions, the processor executing the computer instructions to implement the steps of the method according to any one of claims 1 to 8.

Images