A method and system for evaluating natural gas hydrate resources

Abstract

The present application discloses a method and system for evaluating natural gas hydrate resources, wherein the natural gas hydrate model in the evaluation method is obtained by the following steps: obtaining sample exploration data, sample occurrence category labels and sample exploration values ​​of natural gas hydrate resources; inputting the sample exploration data into a sample occurrence classification network to obtain a sample occurrence classification result; according to the sample occurrence classification result, inputting the sample exploration data into a sample occurrence inversion network to obtain a sample occurrence inversion result; according to the sample occurrence category labels, sample occurrence classification results, sample occurrence inversion results and sample exploration values, updating the parameters of the initialized natural gas hydrate model to obtain a trained natural gas hydrate model. The evaluation method can effectively reduce the difficulty of resource evaluation in the early stage of natural gas hydrate resource exploration, and improve the evaluation efficiency and evaluation accuracy. The present application can be widely used in the field of marine technology.

Description

Technical Field

[0001] The present application relates to the field of marine technology, and in particular to a method and system for evaluating natural gas hydrate resources. Background Art

[0002] Traditional gas hydrate resource evaluation methods can be roughly divided into two categories. The first type of resource evaluation method is based on the volumetric method, which obtains relevant key parameters and then directly evaluates the gas hydrate resources in a certain sea area based on the relevant key parameters; the second type of resource evaluation method is based on the genetic method, which simulates the evolution process of gas hydrate resource accumulation to achieve the evaluation of gas hydrate resources. In the early stage of gas hydrate resource exploration, it was difficult to obtain resource evaluation results through these two types of resource evaluation methods, and the evaluation efficiency and accuracy were not satisfactory.

[0003] Therefore, the problems existing in the prior art still need to be solved and optimized. Summary of the invention

[0004] To solve at least one of the above technical problems, the present application provides a method and system for evaluating natural gas hydrate resources, wherein the evaluation method can effectively reduce the difficulty of resource evaluation in the early stage of natural gas hydrate resource exploration, and improve the evaluation efficiency and evaluation accuracy.

[0005] According to a first aspect of the present application, a method for evaluating natural gas hydrate resources is provided, the method comprising:

[0006] Obtain early exploration data for gas hydrate resources to be identified;

[0007] The early exploration data of natural gas hydrate resources are input into the trained natural gas hydrate model for evaluation and identification to obtain the evaluation results of natural gas hydrate resources.

[0008] The natural gas hydrate model includes a sample occurrence classification network and a sample occurrence inversion network, and the trained natural gas hydrate model is obtained by the following steps:

[0009] Obtaining sample exploration data, sample occurrence category labels and sample exploration values ​​of natural gas hydrate resources, wherein the sample occurrence category labels are used to indicate the hydrate occurrence area category corresponding to the sample exploration data, and each hydrate occurrence area category corresponds to one sample occurrence inversion network;

[0010] Inputting the sample exploration data into the sample occurrence classification network to obtain a sample occurrence classification result, wherein the sample occurrence classification result is used to indicate the sample prediction attribution relationship of the sample exploration data in all the hydrate occurrence area categories;

[0011] According to the sample occurrence classification result, the sample exploration data is input into the sample occurrence inversion network to obtain a sample occurrence inversion result, wherein the sample occurrence inversion result is used to characterize the sample prediction exploration value of the sample exploration data in the sample occurrence inversion network having a sample prediction attribution relationship;

[0012] According to the sample occurrence category label, the sample occurrence classification result, the sample occurrence inversion result and the sample exploration value, the parameters of the initialized natural gas hydrate model are updated to obtain the trained natural gas hydrate model.

[0013] Further, in an embodiment of the present application, the sample occurrence inversion network includes a pore filling inversion network, a fracture filling inversion network and a composite filling inversion network, and the sample exploration data is input into the corresponding sample occurrence inversion network according to the sample occurrence classification result, including:

[0014] If the sample occurrence classification result is that the sample exploration data belongs to the pore-filling hydrate occurrence area, the sample exploration data is input into the pore-filling inversion network;

[0015] or,

[0016] If the sample occurrence classification result is that the sample exploration data belongs to the fracture-filling hydrate occurrence area, the sample exploration data is input into the fracture-filling inversion network;

[0017] or,

[0018] If the sample occurrence classification result is that the sample exploration data belongs to the composite filling type hydrate occurrence area, the sample exploration data is input into the composite filling inversion network.

[0019] Further, in an embodiment of the present application, according to the sample occurrence category label, the sample occurrence classification result, the sample occurrence inversion result and the sample exploration value, the parameters of the initialized natural gas hydrate model are updated to obtain the trained natural gas hydrate model, including:

[0020] Comparing the sample storage category label with the sample storage classification result to obtain a classification comparison result;

[0021] Comparing the sample occurrence inversion result and the sample exploration value to obtain an inversion comparison result;

[0022] Based on the classification comparison result and the inversion comparison result, a target loss function is calculated, and according to the target loss function, the parameters of the initialized natural gas hydrate model are updated to obtain the trained natural gas hydrate model.

[0023] Further, in an embodiment of the present application, the sample occurrence inversion result is at least one of a pore filling inversion result, a fracture filling inversion result or a composite filling inversion result, and the sample occurrence inversion result is compared with the sample exploration value to obtain an inversion comparison result;

[0024] Comparing the pore filling inversion result with the sample exploration value to obtain a pore inversion comparison result; or, comparing the fracture filling inversion result with the sample exploration value to obtain a fracture inversion comparison result; or, comparing the composite filling inversion result with the sample exploration value to obtain a composite inversion comparison result;

[0025] At least one of the obtained pore inversion comparison result, the fracture inversion comparison result or the composite inversion comparison result is used as the inversion comparison result.

[0026] Furthermore, in the embodiment of the present application, the sample exploration value is obtained by the following steps:

[0027] Acquire an exploration occurrence area corresponding to the sample exploration data, wherein the exploration occurrence area is any one of a pore-filling hydrate occurrence area, a fracture-filling hydrate occurrence area, and a composite-filling hydrate occurrence area;

[0028] Based on the exploration occurrence area, resource analysis is performed on the sample exploration data to obtain the sample exploration value.

[0029] Further, in the embodiment of the present application, the resource analysis of the sample exploration data is performed based on the exploration occurrence area to obtain the sample exploration value, including:

[0030] Gridding the exploration occurrence area to obtain a plurality of ore body units and ore body volume data corresponding to each of the ore body units;

[0031] According to the ore body unit, performing data inversion on the corresponding sample exploration data to obtain ore body inversion data;

[0032] The ore body inversion data and the ore body volume data corresponding to the ore body unit are integrated to obtain the sample exploration value.

[0033] According to a second aspect of the present application, a natural gas hydrate resource evaluation system is provided, the system comprising:

[0034] An acquisition unit, used to acquire early exploration data of natural gas hydrate resources to be identified;

[0035] The evaluation unit is used to input the early exploration data of natural gas hydrate resources into the trained natural gas hydrate model for evaluation and identification, so as to obtain the evaluation result of natural gas hydrate resources.

[0036] The natural gas hydrate model includes a sample occurrence classification network and a sample occurrence inversion network, and the trained natural gas hydrate model is obtained by the following steps:

[0037] Obtaining sample exploration data, sample occurrence category labels and sample exploration values ​​of natural gas hydrate resources, wherein the sample occurrence category labels are used to indicate the hydrate occurrence area category corresponding to the sample exploration data, and each hydrate occurrence area category corresponds to one sample occurrence inversion network;

[0038] Inputting the sample exploration data into the sample occurrence classification network to obtain a sample occurrence classification result, wherein the sample occurrence classification result is used to indicate the sample prediction attribution relationship of the sample exploration data in all the hydrate occurrence area categories;

[0039] According to the sample occurrence classification result, the sample exploration data is input into the sample occurrence inversion network to obtain a sample occurrence inversion result, wherein the sample occurrence inversion result is used to characterize the sample prediction exploration value of the sample exploration data in the sample occurrence inversion network having a sample prediction attribution relationship;

[0040] According to the sample occurrence category label, the sample occurrence classification result, the sample occurrence inversion result and the sample exploration value, the parameters of the initialized natural gas hydrate model are updated to obtain the trained natural gas hydrate model.

[0041] Furthermore, in the embodiment of the present application, the sample exploration value is obtained by the following steps:

[0042] Acquire an exploration occurrence area corresponding to the sample exploration data, wherein the exploration occurrence area is any one of a pore-filling hydrate occurrence area, a fracture-filling hydrate occurrence area, and a composite-filling hydrate occurrence area;

[0043] Based on the exploration occurrence area, resource analysis is performed on the sample exploration data to obtain the sample exploration value.

[0044] According to a third aspect of the present application, a computer device is provided, comprising:

[0045] at least one processor;

[0046] at least one memory for storing at least one program;

[0047] When the at least one program is executed by the at least one processor, the at least one processor implements the method as described above.

[0048] According to a fourth aspect of the present application, a computer-readable storage medium is provided, in which a program executable by a processor is stored. When the program executable by the processor is executed by the processor, it is used to implement the method described in the above aspects.

[0049] The beneficial effects of the technical solution provided by the embodiment of the present application are:

[0050] The present application provides a method and system for evaluating natural gas hydrate resources, wherein the evaluation method obtains early exploration data of natural gas hydrate resources to be identified; inputs the early exploration data of natural gas hydrate resources into a trained natural gas hydrate model for evaluation and identification, and obtains a natural gas hydrate resource evaluation result. The natural gas hydrate model includes a sample occurrence classification network and a sample occurrence inversion network, and the trained natural gas hydrate model is obtained by the following steps: obtaining sample exploration data, sample occurrence category labels and sample exploration values ​​of natural gas hydrate resources, the sample occurrence category labels are used to indicate the hydrate occurrence area category corresponding to the sample exploration data, and each hydrate occurrence area category corresponds to one sample occurrence inversion network; inputs the sample exploration data into the sample occurrence classification network to obtain a sample occurrence classification result, and the sample occurrence classification result is used to indicate the sample exploration value. The sample prediction attribution relationship of the data in all the hydrate occurrence area categories; according to the sample occurrence classification result, the sample exploration data is input into the sample occurrence inversion network to obtain the sample occurrence inversion result, and the sample occurrence inversion result is used to characterize the sample prediction exploration value of the sample exploration data in the sample occurrence inversion network with the sample prediction attribution relationship; according to the sample occurrence category label, the sample occurrence classification result, the sample occurrence inversion result and the sample exploration value, the parameters of the initialized natural gas hydrate model are updated to obtain the trained natural gas hydrate model. This evaluation method classifies the hydrate occurrence areas described in the sample exploration data through a sample occurrence classification network, and selects a matching sample occurrence inversion network through the hydrate occurrence area category corresponding to the sample exploration data to realize resource prediction of the sample exploration data, so that the trained natural gas hydrate model has high analysis efficiency and analysis accuracy for the natural gas hydrate resource exploration data to be identified, and effectively reduces the impact of the lack of relevant key parameters and / or the large deviation between the accumulation evolution model and the actual evolution model process in the early stage of natural gas hydrate resource exploration, thereby reducing the difficulty of resource analysis in the early stage of natural gas hydrate resource exploration. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A schematic diagram of a flow chart of a method for evaluating natural gas hydrate resources provided in an embodiment of the present application;

[0052] Figure 2 A schematic diagram of a natural gas hydrate model provided in an embodiment of the present application;

[0053] Figure 3 A schematic diagram of the relationship between the natural gas hydrate model provided in the embodiments of the present application;

[0054] Figure 4 A detailed flow chart of step S105 provided in an embodiment of the present application;

[0055] Figure 5 A detailed flow chart of step S106 provided in an embodiment of the present application;

[0056] Figure 6 A detailed flow chart of step B2 provided in an embodiment of the present application;

[0057] Figure 7 A schematic diagram of a flow chart of sample exploration value provided in an embodiment of the present application;

[0058] Figure 8 A detailed flow chart of step S108 provided in an embodiment of the present application;

[0059] Fig. 9 A schematic diagram of a framework of a natural gas hydrate resource evaluation system provided in an embodiment of the present application;

[0060] Fig.10 A structural block diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0061] The present application is further described below in conjunction with the accompanying drawings and specific embodiments. The described embodiments should not be regarded as limiting the present application, and all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0062] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0063] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0064] The following is an introduction to several terms involved in this application:

[0065] Natural gas hydrate: Natural gas hydrate is a non-stoichiometric ice-like crystalline compound formed under high pressure and low temperature by water molecules connected by hydrogen bonds to form cage-type cavities, in which guest molecules (such as CH4, C2H6, CO2, N2, H2S, etc.) are filled. The two are bound together by van der Waals forces. The natural gas hydrates that exist in large quantities in nature are mainly methane hydrates, which are widely distributed in the deep water environment of continental permafrost, oceans and some inland lakes.

[0066] At present, traditional gas hydrate resource evaluation methods can be roughly divided into two categories. The first type of resource evaluation method is based on the volumetric method. By obtaining relevant key parameters, the gas hydrate resources in a certain sea area are evaluated directly based on the relevant key parameters. This type of resource evaluation method requires obtaining more reliable key parameters (such as the thickness and saturation of gas hydrates). These key parameters often need to be obtained through drilling and logging combined with high-resolution three-dimensional seismic inversion. In the early stages of gas hydrate resource exploration, there are often no drilling and high-resolution three-dimensional seismic areas. There is a lot of uncertainty in the values ​​of key parameters, and the data quality is often not high, which makes resource evaluation in the early stages of gas hydrate resource exploration difficult and the evaluation accuracy is unsatisfactory.

[0067] The second type of resource evaluation method is based on the genetic method, which simulates the evolution process of natural gas hydrate resource accumulation through basin simulation. It needs to assume the accumulation simulation model of the exploration and storage area. However, there is often a large deviation between the assumed accumulation simulation model and the actual accumulation evolution process of the exploration and storage area, and there is also a large uncertainty, which makes the data obtained through the assumed accumulation simulation model low in quality, the resource evaluation difficult, and the evaluation accuracy unsatisfactory. In addition, due to the need to simulate the accumulation evolution process of the exploration and storage area, the efficiency of resource evaluation is unsatisfactory.

[0068] In addition, in the early stages of natural gas hydrate resource exploration (i.e., evaluating areas with low exploration levels, no drilling, and no high-resolution three-dimensional seismic data), analog values ​​can be taken based on the similarity of reservoir conditions in scale areas with high exploration levels, and resource evaluation results can be obtained more quickly. However, this method cannot fully consider the types of exploration host areas and the reservoir details corresponding to the host area types, and the objective accuracy of the resource evaluation results obtained is not high.

[0069] In view of this, an embodiment of the present application provides a method and system for evaluating natural gas hydrate resources, wherein the evaluation method classifies the hydrate occurrence areas to which sample exploration data belong through a sample occurrence classification network, and selects a matching sample occurrence inversion network through the hydrate occurrence area category corresponding to the sample exploration data to realize resource prediction of the sample exploration data, so that the trained natural gas hydrate model has high analysis efficiency and analysis accuracy for the natural gas hydrate resource exploration data to be identified, and effectively reduces the impact of the lack of relevant key parameters and / or the large deviation between the accumulation evolution model and the actual evolution model process in the early stage of natural gas hydrate resource exploration, thereby reducing the difficulty of resource analysis in the early stage of natural gas hydrate resource exploration.

[0070] A method and system for evaluating natural gas hydrate resources provided in an embodiment of the present application can be specifically illustrated by the following embodiments. First, a method for evaluating natural gas hydrate resources in an embodiment of the present application is described.

[0071] The evaluation method for natural gas hydrate resources provided in the embodiment of the present application can be applied to an application scenario of early natural gas hydrate resource evaluation in a certain sea area in the ocean. In the application scenario of early natural gas hydrate resource evaluation in the sea area, a trained natural gas hydrate model can be obtained through the evaluation method provided in the embodiment of the present application, and then the natural gas hydrate resource exploration data to be identified can be predicted and identified based on the trained natural gas hydrate model, which can effectively improve the objective credibility of the resource evaluation results in the early stage of natural gas hydrate resource exploration, as well as improve the evaluation efficiency and evaluation accuracy.

[0072] The present application can be used in many general or special 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, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0073] Reference Figure 1 , Figure 1 is an optional flow chart of a method for evaluating natural gas hydrate resources provided in an embodiment of the present application. Figure 1 The method for evaluating natural gas hydrate resources may include but is not limited to steps S101 to S102.

[0074] Step S101, obtaining early exploration data of natural gas hydrate resources to be identified;

[0075] Step S102: inputting the early exploration data of natural gas hydrate resources into the trained natural gas hydrate model for evaluation and identification to obtain a natural gas hydrate resource evaluation result.

[0076] In an embodiment of the present application, for exploration host areas in the early stages of gas hydrate resource exploration, the gas hydrate resource exploration data (such as electrical logging data and seismic data) obtained in the early stages of exploration can be input into a trained gas hydrate model, and the gas hydrate model performs evaluation and identification based on the learned sample structure characteristics to obtain a gas hydrate resource identification result indicating the resource quantity and / or resource abundance of the early stages of gas hydrate resource exploration.

[0077] Reference Figure 2 and Figure 3 The natural gas hydrate model includes a sample occurrence classification network and a sample occurrence inversion network. The trained natural gas hydrate model is obtained by the following steps:

[0078] Step S103, obtaining sample exploration data, sample occurrence category labels and sample exploration values ​​of natural gas hydrate resources, wherein the sample occurrence category labels are used to indicate the hydrate occurrence area category corresponding to the sample exploration data, and each hydrate occurrence area category corresponds to one sample occurrence inversion network;

[0079] In the embodiment of the present application, pore-filling hydrate occurrence areas, fracture-filling hydrate occurrence areas and composite-filling hydrate occurrence areas with a high degree of exploration and being representative can be selected as exploration scale areas, and the exploration data of the exploration scale areas can be used as sample exploration data. For example, drilling data, electrical logging data (such as acoustic wave data, resistivity, neutron density, natural gamma (GR), etc.) and seismic data (such as instantaneous frequency, instantaneous phase and instantaneous amplitude, etc.) with a high relationship between hydrate product and storage phase are selected as sample exploration data in step S103; the exploration conclusions of the exploration scale area (such as resource volume and resource abundance, etc.) are used as sample exploration values; each sample exploration data has a sample occurrence category label, and the sample occurrence category label is used to indicate whether each sample exploration data belongs to a pore-filling hydrate occurrence area, a fracture-filling hydrate occurrence area or a composite-filling hydrate occurrence area (i.e., the hydrate occurrence area category).

[0080] Step S104, inputting the sample exploration data into the sample occurrence classification network to obtain a sample occurrence classification result, wherein the sample occurrence classification result is used to indicate the sample prediction attribution relationship of the sample exploration data in all the hydrate occurrence area categories;

[0081] In an embodiment of the present application, a sample occurrence classification network can be constructed based on a multi-class support vector machine (Multi-Class SVM, MSVM). By inputting the sample exploration data into the sample occurrence classification network, a sample occurrence classification result obtained by the sample occurrence classification network predicting the sample exploration data is obtained. The sample occurrence classification result indicates whether the input sample exploration data belongs to a pore-filling type hydrate occurrence area, a fracture-filling type hydrate occurrence area or a composite-filling type hydrate occurrence area (that is, it indicates the sample prediction attribution relationship of the sample exploration data in all the hydrate occurrence area categories).

[0082] Step S105: according to the sample occurrence classification result, the sample exploration data is input into the sample occurrence inversion network to obtain a sample occurrence inversion result, wherein the sample occurrence inversion result is used to characterize the sample prediction exploration value of the sample exploration data in the sample occurrence inversion network having a sample prediction attribution relationship;

[0083] Furthermore, the sample occurrence inversion network includes a pore filling inversion network, a fracture filling inversion network and a composite filling inversion network. Figure 4 The step S105, according to the sample occurrence classification result, inputting the sample exploration data into the corresponding sample occurrence inversion network, comprises:

[0084] A1. If the sample occurrence classification result is that the sample exploration data belongs to the pore-filling hydrate occurrence area, the sample exploration data is input into the pore-filling inversion network;

[0085] or,

[0086] A2. If the sample occurrence classification result is that the sample exploration data belongs to the fracture-filling hydrate occurrence area, the sample exploration data is input into the fracture-filling inversion network;

[0087] or,

[0088] A3. If the sample occurrence classification result is that the sample exploration data belongs to the composite filling type hydrate occurrence area, the sample exploration data is input into the composite filling inversion network.

[0089] In the embodiment of the present application, the hydrate occurrence area category may be a pore-filling hydrate occurrence area, a fracture-filling hydrate occurrence area, or a composite-filling hydrate occurrence area. Specifically, when the sample occurrence classification result is that the sample exploration data belongs to the category of a pore-filling hydrate occurrence area, the sample exploration data may be input into the corresponding pore-filling inversion network for inversion, and the pore-filling inversion result predicted and output by the pore-filling inversion network is obtained. The pore-filling inversion result is used to characterize the sample exploration data whose hydrate occurrence area category is a pore-filling hydrate occurrence area, and the sample predicted exploration value in the corresponding pore-filling inversion network is assigned.

[0090] It can be understood that, for step A2 and step A3, they are similar to the content of the aforementioned step A1 and can be simply deduced by analogy. In addition, for the pore filling inversion network, it can be constructed based on the deep feedforward network (Deep Feedforward Network), and the output of the pore filling inversion network can be the resource volume and resource abundance corresponding to the sample exploration data (i.e., the pore filling inversion result), and the fracture filling inversion network and the composite filling inversion network are similar, and this application will not be repeated here.

[0091] Step S106: updating the parameters of the initialized natural gas hydrate model according to the sample occurrence category label, the sample occurrence classification result, the sample occurrence inversion result and the sample exploration value to obtain the trained natural gas hydrate model.

[0092] Further, refer to Figure 5 The step S106, updating the parameters of the natural gas hydrate model according to the sample occurrence category label, the sample occurrence classification result, the sample occurrence inversion result and the sample exploration value to obtain a trained natural gas hydrate model, comprises:

[0093] B1. Compare the sample storage category label with the sample storage classification result to obtain a classification comparison result;

[0094] B2. comparing the sample occurrence inversion result and the sample exploration value to obtain an inversion comparison result;

[0095] Furthermore, the sample occurrence inversion result is at least one of a pore filling inversion result, a fracture filling inversion result or a composite filling inversion result, referring to Figure 6 , the step B2, comparing the sample occurrence inversion result and the sample exploration value to obtain an inversion comparison result;

[0096] B21, comparing the pore filling inversion result and the sample exploration value to obtain a pore inversion comparison result; or, comparing the fracture filling inversion result and the sample exploration value to obtain a fracture inversion comparison result; or, comparing the composite filling inversion result and the sample exploration value to obtain a composite inversion comparison result;

[0097] B22. Use at least one of the obtained pore inversion comparison result, the fracture inversion comparison result or the composite inversion comparison result as the inversion comparison result.

[0098] In the embodiment of the present application, step B1 may be to calculate the prediction error between each sample occurrence category label and the corresponding sample occurrence classification result, so as to obtain the classification comparison result corresponding to each sample occurrence classification result; and the pore inversion comparison result, fracture inversion comparison result and composite inversion comparison result in step B21 are similar to the content of the aforementioned step B1 and can be simply derived by analogy. It is understandable that step B22 may use at least one of the obtained pore inversion comparison result, fracture inversion comparison result or composite inversion comparison result as the inversion comparison result based on actual needs.

[0099] B3. Calculate a target loss function based on the classification comparison result and the inversion comparison result, and update the parameters of the initialized natural gas hydrate model according to the target loss function to obtain the trained natural gas hydrate model.

[0100] In an embodiment of the present application, based on types of loss functions such as 0-1 loss function, square loss function, absolute loss function, logarithmic loss function, cross entropy loss function, etc., a classification loss function corresponding to all classification comparison results and an inversion loss function corresponding to all inversion comparison results can be calculated, and the classification loss function and the inversion loss function can be integrated to obtain a target loss function; then, based on the target loss function, the parameters of the natural gas hydrate model are jointly trained, and a trained natural gas hydrate model can be obtained by iterating several rounds. The specific number of iterations can be set in advance, or the training is considered to be completed when the natural gas hydrate model meets the accuracy requirements.

[0101] It should be noted that the parameters of the natural gas hydrate model can also be updated by training a sample occurrence classification network based on a classification loss function; training a pore filling inversion network based on a pore filling loss function in an inversion loss function, training a fracture filling inversion network based on a fracture filling loss function in an inversion loss function, and training a composite filling inversion network based on a composite filling loss function in an inversion loss function, wherein the pore filling loss function is calculated based on a pore inversion comparison result, the fracture filling loss function is calculated based on a fracture inversion comparison result, and the composite filling loss function is calculated based on a composite inversion comparison result. Then, the trained sample occurrence classification network, pore filling inversion network, fracture filling inversion network, and composite filling inversion network are used as trained natural gas hydrate models.

[0102] It is worth mentioning that the embodiment of the present application first classifies the natural gas hydrate resources based on their resource types, and then identifies the sample exploration data based on the sample occurrence inversion network established based on the type. Since the occurrence laws of the same type of storage resources are relatively consistent, the sample occurrence inversion network (i.e., pore filling inversion network, fracture filling inversion network, and composite filling inversion network) is relatively simple, and the prediction accuracy is higher than that of the hybrid prediction accuracy.

[0103] In some embodiments, reference Figure 7 , the sample exploration value is obtained by the following steps:

[0104] Step S107, obtaining an exploration occurrence area corresponding to the sample exploration data, wherein the exploration occurrence area is any one of a pore-filling hydrate occurrence area, a fracture-filling hydrate occurrence area, and a composite-filling hydrate occurrence area;

[0105] Step S108: Based on the exploration occurrence area, perform resource analysis on the sample exploration data to obtain the sample exploration value.

[0106] Further, refer to Figure 8 The step S108, based on the exploration occurrence area, performs resource analysis on the sample exploration data to obtain the sample exploration value, includes:

[0107] C1. Gridding the exploration occurrence area to obtain a plurality of ore body units and ore body volume data corresponding to each ore body unit;

[0108] C2. According to the ore body unit, performing data inversion on the corresponding sample exploration data to obtain ore body inversion data;

[0109] C3. Integrate the ore body inversion data and the ore body volume data corresponding to the ore body unit to obtain the sample exploration value.

[0110] In the embodiment of the present application, the exploration occurrence area is used to indicate the category of the hydrate occurrence area to which the sample exploration data belongs (such as a pore-filling hydrate occurrence area, a fracture-filling hydrate occurrence area, or a composite-filling hydrate occurrence area). Step C1 may be to grid the resource ore body of natural gas hydrate in the exploration occurrence area to obtain a number of relatively small ore body units, and the ore body volume data corresponding to each ore body unit may be calculated based on the area and reservoir thickness of the ore body unit; step C2 may be based on the category of the hydrate occurrence area indicated by the exploration occurrence area, and use well-seismic joint inversion to calculate the ore body inversion data corresponding to each ore body unit, and the ore body inversion data includes porosity, saturation and gas production factor.

[0111] It can be understood that when the sample exploration value is only the resource amount, step C3 can be to calculate the product of the ore volume data of all ore body units and the ore body inversion data to obtain the sample exploration value representing the total resource amount of natural gas hydrate in the exploration area; or, when the sample exploration value includes resource amount and resource abundance, step C3 can be based on the resource amount obtained above, by obtaining the ratio between the resource amount and the area of ​​the exploration area, so as to obtain the resource abundance of natural gas hydrate in the exploration area.

[0112] For example, the total amount of natural gas hydrate resources in the exploration host area in step C3 may be expressed as:

[0113]

[0114] Where Q is the total natural gas hydrate resources in the exploration area; i is the ore body unit number; n is the total number of ore body units; V i is the ore body volume data of the ore body unit labeled i; is the porosity of the ore body unit labeled i; H i is the saturation of the ore body unit labeled i; E is the gas production factor of natural gas hydrate.

[0115] Fig. 9 A schematic diagram of a framework of a natural gas hydrate resource evaluation system provided in an embodiment of the present application, the system comprising:

[0116] An acquisition unit 810 is used to acquire early exploration data of natural gas hydrate resources to be identified;

[0117] The evaluation unit 820 is used to input the early exploration data of natural gas hydrate resources into the trained natural gas hydrate model for evaluation and identification, so as to obtain the evaluation result of natural gas hydrate resources.

[0118] The natural gas hydrate model includes a sample occurrence classification network and a sample occurrence inversion network, and the trained natural gas hydrate model is obtained by the following steps:

[0119] Obtaining sample exploration data, sample occurrence category labels and sample exploration values ​​of natural gas hydrate resources, wherein the sample occurrence category labels are used to indicate the hydrate occurrence area category corresponding to the sample exploration data, and each hydrate occurrence area category corresponds to one sample occurrence inversion network;

[0120] Inputting the sample exploration data into the sample occurrence classification network to obtain a sample occurrence classification result, wherein the sample occurrence classification result is used to indicate the sample prediction attribution relationship of the sample exploration data in all the hydrate occurrence area categories;

[0121] According to the sample occurrence classification result, the sample exploration data is input into the sample occurrence inversion network to obtain a sample occurrence inversion result, wherein the sample occurrence inversion result is used to characterize the sample prediction exploration value of the sample exploration data in the sample occurrence inversion network having a sample prediction attribution relationship;

[0122] According to the sample occurrence category label, the sample occurrence classification result, the sample occurrence inversion result and the sample exploration value, the parameters of the initialized natural gas hydrate model are updated to obtain the trained natural gas hydrate model.

[0123] In some embodiments, the sample exploration value is obtained by the following steps:

[0124] Acquire an exploration occurrence area corresponding to the sample exploration data, wherein the exploration occurrence area is any one of a pore-filling hydrate occurrence area, a fracture-filling hydrate occurrence area, and a composite-filling hydrate occurrence area;

[0125] Based on the exploration occurrence area, resource analysis is performed on the sample exploration data to obtain the sample exploration value.

[0126] It can be understood that the contents of the above method embodiments are all applicable to the present system embodiments, the functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0127] Fig.10 A schematic diagram of the structure of a computer device provided in an embodiment of the present application includes:

[0128] at least one processor 980;

[0129] At least one memory 920, used to store at least one program;

[0130] When the at least one program is executed by the at least one processor 980, the at least one processor 980 implements the methods described in the foregoing embodiments.

[0131] An embodiment of the present application also provides a computer-readable storage medium, which stores a program executable by a processor. When the program executable by the processor is executed by the processor 980, it is used to implement the methods described in the above embodiments.

[0132] Specifically, the computer device may be a user terminal or a server.

[0133] The present application embodiment takes the computer device as a user terminal as an example, and the details are as follows:

[0134] like Fig.10 As shown, the computer device 900 may include an RF (Radio Frequency) circuit 910, a memory 920 including one or more computer-readable storage media, an input unit 930, a display unit 940, a sensor 950, an audio circuit 960, a WiFi module 970, a processor 980 including one or more processing cores, and a power supply 990. Those skilled in the art will appreciate that Fig.10 The device structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0135] The RF circuit 910 can be used for receiving and sending signals during information transmission or calls. In particular, after receiving the downlink information of the base station, it is handed over to one or more processors 980 for processing; in addition, the data related to the uplink is sent to the base station. Generally, the RF circuit 910 includes but is not limited to an antenna, at least one amplifier, a tuner, one or more oscillators, a user identity module (SIM) card, a transceiver, a coupler, an LNA (Low Noise Amplifier), a duplexer, etc. In addition, the RF circuit 910 can also communicate with the network and other devices through wireless communication. Wireless communication can use any communication standard or protocol, including but not limited to GSM (Global System of Mobile communication), GPRS (General Packet Radio Service), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), LTE (Long Term Evolution), email, SMS (Short Messaging Service), etc.

[0136] The memory 920 can be used to store software programs and modules. The processor 980 executes various functional applications and data processing by running the software programs and modules stored in the memory 920. The memory 920 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the device 900 (such as audio data, a phone book, etc.), etc. In addition, the memory 920 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 920 may also include a memory controller to provide the processor 980 and the input unit 930 with access to the memory 920. Although Fig.10 The RF circuit 910 is shown, but it is understandable that it is not an essential component of the device 900 and can be omitted as required without changing the essence of the invention.

[0137] The input unit 930 can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control. Specifically, the input unit 930 may include a touch-sensitive surface 932 and other input devices 931. The touch-sensitive surface 932, also known as a touch display screen or a touch pad, can collect user touch operations on or near it (such as operations performed by users using fingers, styluses, or any other suitable objects or accessories on or near the touch-sensitive surface 932), and drive corresponding connection devices according to a pre-set program. Optionally, the touch-sensitive surface 932 may include a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into touch point coordinates, and then sends it to the processor 980, and can receive and execute commands sent by the processor 980. In addition, the touch-sensitive surface 932 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic waves. In addition to the touch-sensitive surface 932, the input unit 930 may also include other input devices 931. Specifically, the other input devices 931 may include but are not limited to one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, etc.

[0138] The display unit 940 can be used to display information input by the user or information provided to the user and various graphical user interfaces of the control 900, which can be composed of graphics, text, icons, videos and any combination thereof. The display unit 940 may include a display panel 941. Optionally, the display panel 941 may be configured in the form of LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), etc. Further, the touch-sensitive surface 932 may be covered on the display panel 941. When the touch-sensitive surface 932 detects a touch operation on or near it, it is transmitted to the processor 980 to determine the type of touch event. Subsequently, the processor 980 provides a corresponding visual output on the display panel 941 according to the type of touch event. Although in Fig.10 In the embodiment, the touch-sensitive surface 932 and the display panel 941 are implemented as two independent components to implement input and output functions, but in some embodiments, the touch-sensitive surface 932 and the display panel 941 can be integrated to implement input and output functions.

[0139] The computer device 900 may also include at least one sensor 950, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel 941 according to the brightness of the ambient light, and the proximity sensor may turn off the display panel 941 and / or the backlight when the device 900 is moved to the ear. As a type of motion sensor, the gravity acceleration sensor can detect the magnitude of acceleration in each direction (generally three axes), and can detect the magnitude and direction of gravity when stationary, which can be used for applications that identify the posture of the mobile phone (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc.; as for other sensors such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc. that can also be configured in the device 900, they will not be repeated here.

[0140] The audio circuit 960, the speaker 961, and the microphone 962 can provide an audio interface between the user and the device 900. The audio circuit 960 can transmit the electrical signal converted from the received audio data to the speaker 961, which is converted into a sound signal for output; on the other hand, the microphone 962 converts the collected sound signal into an electrical signal, which is received by the audio circuit 960 and converted into audio data, and then the audio data is processed by the output processor 980 and sent to another control device through the RF circuit 910, or the audio data is output to the memory 920 for further processing. The audio circuit 960 may also include an earplug jack to provide communication between an external headset and the device 900.

[0141] The device 900 can transmit information with the wireless transmission module set on the fighting device through the WiFi module 970.

[0142] The processor 980 is the control center of the device 900. It uses various interfaces and lines to connect various parts of the entire control device. It executes various functions of the device 900 and processes data by running or executing software programs and / or modules stored in the memory 920, and calling data stored in the memory 920, so as to monitor the control device as a whole. Optionally, the processor 980 may include one or more processing cores; optionally, the processor 980 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 950.

[0143] The device 900 also includes a power supply 990 (such as a battery) for supplying power to each component. Preferably, the power supply can be logically connected to the processor 980 through a power management system, so that the power management system can manage charging, discharging, and power consumption management. The power supply 990 can also include any components such as one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators.

[0144] Although not shown, the device 900 may also include a camera, a Bluetooth module, etc., which will not be described in detail here.

[0145] An embodiment of the present application further provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor executes the method described in the above embodiments.

[0146] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein, for example. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0147] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0148] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0149] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0150] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0151] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store program codes.

[0152] The step numbers in the above method embodiment are only provided for the convenience of explanation and description, and no limitation is imposed on the order of the steps. The execution order of each step in the embodiment can be adaptively adjusted according to the understanding of those skilled in the art.

[0153] The above is a specific description of the preferred implementation of the present application, but the present application is not limited to the described embodiments. Technical personnel familiar with the field may make various equivalent modifications or substitutions without violating the spirit of the present application. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present application.

Claims

1. A method for evaluating natural gas hydrate resources, characterized in that: The method comprises: Obtain early exploration data for gas hydrate resources to be identified; Inputting the early exploration data of natural gas hydrate resources into the trained natural gas hydrate model for evaluation and identification to obtain a natural gas hydrate resource evaluation result; The natural gas hydrate model includes a sample occurrence classification network and a sample occurrence inversion network, and the trained natural gas hydrate model is obtained by the following steps: Obtaining sample exploration data, sample occurrence category labels and sample exploration values ​​of natural gas hydrate resources, wherein the sample occurrence category labels are used to indicate the hydrate occurrence area category corresponding to the sample exploration data, and each hydrate occurrence area category corresponds to one sample occurrence inversion network; Inputting the sample exploration data into the sample occurrence classification network to obtain a sample occurrence classification result, wherein the sample occurrence classification result is used to indicate the sample prediction attribution relationship of the sample exploration data in all the hydrate occurrence area categories; According to the sample occurrence classification result, the sample exploration data is input into the sample occurrence inversion network to obtain a sample occurrence inversion result, wherein the sample occurrence inversion result is used to characterize the sample prediction exploration value of the sample exploration data in the sample occurrence inversion network having a sample prediction attribution relationship; According to the sample occurrence category label, the sample occurrence classification result, the sample occurrence inversion result and the sample exploration value, updating the parameters of the initialized natural gas hydrate model to obtain the trained natural gas hydrate model; According to the sample occurrence category label, the sample occurrence classification result, the sample occurrence inversion result and the sample exploration value, the parameters of the initialized natural gas hydrate model are updated to obtain the trained natural gas hydrate model, including: Comparing the sample storage category label with the sample storage classification result to obtain a classification comparison result; Comparing the sample occurrence inversion result and the sample exploration value to obtain an inversion comparison result; Based on the classification comparison result and the inversion comparison result, a target loss function is calculated, and according to the target loss function, the parameters of the initialized natural gas hydrate model are updated to obtain the trained natural gas hydrate model.

2. A method for evaluating natural gas hydrate resources according to claim 1, characterized in that: The sample occurrence inversion network includes a pore filling inversion network, a fracture filling inversion network and a composite filling inversion network. According to the sample occurrence classification result, the sample exploration data is input into the corresponding sample occurrence inversion network, including: If the sample occurrence classification result is that the sample exploration data belongs to the pore-filling hydrate occurrence area, the sample exploration data is input into the pore-filling inversion network; or, If the sample occurrence classification result is that the sample exploration data belongs to the fracture-filling hydrate occurrence area, the sample exploration data is input into the fracture-filling inversion network; or, If the sample occurrence classification result is that the sample exploration data belongs to the composite filling type hydrate occurrence area, the sample exploration data is input into the composite filling inversion network.

3. The method for evaluating natural gas hydrate resources according to claim 1, characterized in that: The sample occurrence inversion result is at least one of a pore filling inversion result, a fracture filling inversion result or a composite filling inversion result, and the sample occurrence inversion result is compared with the sample exploration value to obtain an inversion comparison result; Comparing the pore filling inversion result with the sample exploration value to obtain a pore inversion comparison result; or, comparing the fracture filling inversion result with the sample exploration value to obtain a fracture inversion comparison result; or, comparing the composite filling inversion result with the sample exploration value to obtain a composite inversion comparison result; At least one of the obtained pore inversion comparison result, the fracture inversion comparison result or the composite inversion comparison result is used as the inversion comparison result.

4. The method for evaluating natural gas hydrate resources according to claim 1, characterized in that: The sample exploration value is obtained by the following steps: Acquire an exploration occurrence area corresponding to the sample exploration data, wherein the exploration occurrence area is any one of a pore-filling hydrate occurrence area, a fracture-filling hydrate occurrence area, and a composite-filling hydrate occurrence area; Based on the exploration occurrence area, resource analysis is performed on the sample exploration data to obtain the sample exploration value.

5. A method for evaluating natural gas hydrate resources according to claim 4, characterized in that: The step of performing resource analysis on the sample exploration data based on the exploration occurrence area to obtain the sample exploration value includes: Gridding the exploration occurrence area to obtain a plurality of ore body units and ore body volume data corresponding to each of the ore body units; According to the ore body unit, performing data inversion on the corresponding sample exploration data to obtain ore body inversion data; The ore body inversion data and the ore body volume data corresponding to the ore body unit are integrated to obtain the sample exploration value.

6. A natural gas hydrate resource evaluation system, characterized in that: The system comprises: An acquisition unit, used to acquire early exploration data of natural gas hydrate resources to be identified; An evaluation unit, used for inputting the early exploration data of natural gas hydrate resources into a trained natural gas hydrate model for evaluation and identification, and obtaining a natural gas hydrate resource evaluation result; The natural gas hydrate model includes a sample occurrence classification network and a sample occurrence inversion network, and the trained natural gas hydrate model is obtained by the following steps: Obtaining sample exploration data, sample occurrence category labels and sample exploration values ​​of natural gas hydrate resources, wherein the sample occurrence category labels are used to indicate the hydrate occurrence area category corresponding to the sample exploration data, and each hydrate occurrence area category corresponds to one sample occurrence inversion network; Inputting the sample exploration data into the sample occurrence classification network to obtain a sample occurrence classification result, wherein the sample occurrence classification result is used to indicate the sample prediction attribution relationship of the sample exploration data in all the hydrate occurrence area categories; According to the sample occurrence classification result, the sample exploration data is input into the sample occurrence inversion network to obtain a sample occurrence inversion result, wherein the sample occurrence inversion result is used to characterize the sample prediction exploration value of the sample exploration data in the sample occurrence inversion network having a sample prediction attribution relationship; According to the sample occurrence category label, the sample occurrence classification result, the sample occurrence inversion result and the sample exploration value, updating the parameters of the initialized natural gas hydrate model to obtain the trained natural gas hydrate model; According to the sample occurrence category label, the sample occurrence classification result, the sample occurrence inversion result and the sample exploration value, the parameters of the initialized natural gas hydrate model are updated to obtain the trained natural gas hydrate model, including: Comparing the sample storage category label with the sample storage classification result to obtain a classification comparison result; Comparing the sample occurrence inversion result and the sample exploration value to obtain an inversion comparison result; Based on the classification comparison result and the inversion comparison result, a target loss function is calculated, and according to the target loss function, the parameters of the initialized natural gas hydrate model are updated to obtain the trained natural gas hydrate model.

7. A natural gas hydrate resource evaluation system according to claim 6, characterized in that: The sample exploration value is obtained by the following steps: Acquire an exploration occurrence area corresponding to the sample exploration data, wherein the exploration occurrence area is any one of a pore-filling hydrate occurrence area, a fracture-filling hydrate occurrence area, and a composite-filling hydrate occurrence area; Based on the exploration occurrence area, resource analysis is performed on the sample exploration data to obtain the sample exploration value.

8. A computer device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method according to any one of claims 1 to 5.

9. A computer-readable storage medium storing a program executable by a processor, characterized in that: The program executable by the processor is used to implement the method according to any one of claims 1 to 5 when executed by the processor.

Images