Methods, devices, equipment, media, and products for geothermal prediction
By acquiring and analyzing the geothermal influence parameters of the target well logging, and using the geothermal prediction model for multi-dimensional prediction, the problem of limited drilling temperature measurement depth was solved, and accurate prediction of geothermal temperature throughout the entire well section was achieved.
Patent Information
- Application Number
- CN202510599933.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-09
- Publication Date
- 2026-11-10
AI Technical Summary
In existing technologies, well temperature measurement can only obtain formation temperature at a limited depth, and fails to consider the influence of formation physical parameters on geothermal temperature, resulting in insufficient accuracy of geothermal prediction.
By acquiring multiple geothermal influence parameters from the target well logging, and using a geothermal prediction model for analysis and processing, the mapping relationship of geothermal temperature throughout the well section is determined. Considering multiple geothermal influence sample parameters and sample data, the geothermal prediction model is trained to achieve multi-dimensional prediction of deep formation temperature.
It improves the accuracy of geothermal prediction and enables more precise determination of formation temperature throughout the well.
Smart Images

Figure CN123068809A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of geothermal resource exploration technology, and in particular to a method, apparatus, equipment, medium and product for geothermal temperature prediction. Background Technology
[0002] Geothermal temperature, or formation temperature, is an important geophysical parameter reflecting the heat transfer and distribution within the Earth, and is of great significance for the exploration, assessment, and development of geothermal resources. Well drilling is the most direct and effective way to obtain formation temperature; however, the drilling depth is limited, making it difficult to obtain temperatures from deep formations.
[0003] Generally, geothermal gradients can be determined using drilling temperature data, from which the formation temperature at depth can be inferred. However, this method only considers the linear relationship between geothermal temperature and depth, neglecting the influence of other formation properties on geothermal temperature. Therefore, it reduces the accuracy of geothermal prediction. Summary of the Invention
[0004] This disclosure provides a method, apparatus, equipment, medium, and product for geothermal prediction, which can improve the accuracy of geothermal prediction.
[0005] In a first aspect, this disclosure provides a method for predicting geothermal temperature, including:
[0006] Obtain multiple geothermal influence parameters from the target well logging;
[0007] Based on the geothermal prediction model, the multiple geothermal influencing parameters are analyzed and processed to determine the geothermal prediction result of the target well. The geothermal prediction result is a mapping relationship of geothermal temperature throughout the well section. The geothermal prediction model is trained using multiple geothermal influencing sample parameters that affect the geothermal prediction result and the geothermal sample data corresponding to the multiple geothermal influencing sample parameters.
[0008] Optionally, the step of analyzing and processing the multiple geothermal influence parameters based on the geothermal prediction model to determine the geothermal prediction result of the target well includes:
[0009] Feature extraction is performed on the multiple geothermal influencing parameters to obtain the influencing feature vector;
[0010] The weight values are adjusted based on the influence feature vector to determine the geothermal prediction result, wherein the weight values are the connection weights between neurons in each layer of the geothermal prediction model.
[0011] Optionally, obtaining multiple geothermal influence parameters from the target well logging includes:
[0012] Acquire the well depth data and multiple logging physical parameters of the target well;
[0013] Based on the Pearson correlation coefficient, each of the well logging physical property parameters is analyzed to determine the influence coefficient of each of the well logging physical property parameters on geothermal temperature;
[0014] The absolute values of the influence coefficients of each logging property parameter on geothermal temperature are sorted from largest to smallest to determine the target logging property parameter, wherein the target logging property parameter includes at least one of the logging property parameters.
[0015] The target logging physical property parameters and the well depth data are used as the multiple geothermal influence parameters.
[0016] Optionally, before analyzing and processing the multiple geothermal influence parameters based on the geothermal prediction model to determine the geothermal prediction result of the target well, the method further includes:
[0017] Obtain geothermal influence sample parameters and geothermal sample data for the target well logging;
[0018] The geothermal influence sample parameters and the geothermal sample data are divided into a training sample set and a test sample set;
[0019] The training sample set is used to train the ground temperature prediction model to be trained, and the ground temperature prediction model to be tested is determined.
[0020] The ground temperature prediction model to be tested is tested based on the test sample set to determine the ground temperature prediction model.
[0021] Optionally, the step of testing the ground temperature prediction model based on the test sample set to determine the ground temperature prediction model includes:
[0022] Based on the ground temperature prediction results generated by the ground temperature prediction model to be tested and the ground temperature sample data in the test sample set, the error of the ground temperature prediction model to be tested is evaluated, and the first error parameter is determined.
[0023] If the first error parameter meets the first error range, the ground temperature prediction model to be tested is used as the ground temperature prediction model.
[0024] Optionally, after analyzing and processing the multiple geothermal influence parameters based on the geothermal prediction model to determine the geothermal prediction result of the target well, the method further includes:
[0025] Obtain the geothermal measurement value of the target well;
[0026] Based on the measured ground temperature value and the predicted ground temperature result, an error verification is performed to obtain a second error parameter;
[0027] If the second error parameter meets the second error range, the geothermal prediction result is determined to be correct.
[0028] Secondly, this disclosure provides a device for predicting ground temperature, comprising:
[0029] The acquisition module is used to acquire multiple geothermal influence parameters of the target well logging.
[0030] The determination module is used to analyze and process the multiple geothermal influence parameters based on the geothermal prediction model to determine the geothermal prediction result of the target well. The geothermal prediction result is a mapping relationship of geothermal temperature for the entire well section. The geothermal prediction model is trained using multiple geothermal influence sample parameters that affect the geothermal prediction result and geothermal sample data corresponding to the multiple geothermal influence sample parameters.
[0031] Thirdly, this disclosure provides a computer device including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the geothermal prediction method described above.
[0032] Fourthly, this disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the geothermal prediction method described above.
[0033] Fifthly, this disclosure provides a computer program product, including a computer program / instructions, which, when executed by a processor, implements the steps of the geothermal prediction method described above.
[0034] This disclosure acquires multiple geothermal influence parameters from a target well logging operation. Based on a geothermal prediction model, these parameters are analyzed and processed to determine the geothermal prediction results for the target well logging operation. The geothermal prediction results represent a mapping relationship of geothermal temperature across the entire well section. The geothermal prediction model is trained using multiple geothermal influence sample parameters and corresponding geothermal sample data. By learning the quantitative relationship between multiple parameters influencing geothermal temperature and geothermal temperature, multi-dimensional prediction of deep formation temperature in the target well logging operation is achieved, thereby determining the formation temperature across the entire well section. Therefore, the accuracy of geothermal prediction can be improved. Attached Figure Description
[0035] The present disclosure will be described in more detail below based on embodiments and with reference to the accompanying drawings:
[0036] Figure 1 This is a flowchart of a method for predicting ground temperature provided in this disclosure.
[0037] Figure 2 A schematic diagram of the structure for making predictions using the geothermal prediction model provided in this disclosure.
[0038] Figure 3 The flowchart for obtaining geothermal influence parameters provided in this disclosure
[0039] Figure 4 The diagram shows the correlation analysis results of the logging physical property parameters provided in this disclosure.
[0040] Figure 5 This is a comparison chart of the errors between the measured and predicted ground temperature values provided in this disclosure.
[0041] Figure 6 Another flowchart for a method of geothermal prediction provided in this disclosure.
[0042] Figure 7 This is a schematic diagram of the geothermal curve for the entire well section provided in this disclosure.
[0043] Figure 8 This is a schematic diagram of the structure of a geothermal prediction device provided in this disclosure. Detailed Implementation
[0044] To enable those skilled in the art to better understand the technical solution of this application, the application scenario of this application will be described first below.
[0045] Geothermal resources possess advantages such as large reserves, renewability, and low carbon emissions, making them an ideal form of energy. They can be used for indoor heating, industrial and agricultural applications, and power generation, playing a significant role in alleviating energy shortages. Deep geothermal resources, especially hot dry rock geothermal resources, are extremely abundant on Earth, with safe development, low carbon emissions, and very broad application prospects, making them an ideal supplement to the existing energy system. Earth's temperature, or formation temperature, is an important geophysical parameter reflecting the heat transfer and distribution within the Earth, and is crucial for the exploration, assessment, and development of geothermal resources. Drilling for temperature measurement is the most direct and effective way to obtain formation temperature; however, the depth of drilling for temperature measurement is limited, making it difficult to obtain deep formation temperatures.
[0046] Currently, geothermal gradients can be determined using wellbore temperature data, from which the formation temperature at depth can be inferred. However, this method is not easy to obtain deep formation temperatures and only considers the linear relationship between geothermal temperature and depth, without taking into account the influence of other formation properties on geothermal temperature. Therefore, it reduces the accuracy of geothermal prediction.
[0047] To address the aforementioned technical problems, this disclosure provides a method, apparatus, equipment, medium, and product for geothermal prediction. In this disclosure, multiple geothermal influence parameters of a target well are acquired; these parameters are analyzed and processed based on a geothermal prediction model to determine the geothermal prediction result for the target well. The geothermal prediction result represents a mapping relationship of geothermal temperature across the entire well section. The geothermal prediction model is trained using multiple geothermal influence sample parameters affecting the prediction result and corresponding geothermal sample data. By learning the quantitative relationship between multiple parameters influencing geothermal temperature and geothermal temperature, multi-dimensional prediction of the deep formation temperature of the target well is achieved, thereby determining the formation temperature across the entire well section. Therefore, the accuracy of geothermal prediction can be improved.
[0048] To enable those skilled in the art to better understand the technical solutions of this disclosure, and to fully understand and implement the process of how this disclosure applies technical means to solve technical problems and achieve corresponding technical effects, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, not all embodiments. The embodiments of this disclosure and the various features within them can be combined with each other without conflict, and the resulting technical solutions are all within the protection scope of this disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort should fall within the protection scope of this disclosure.
[0049] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0050] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.
[0051] Example 1
[0052] Figure 1 This is a flowchart illustrating a method for predicting ground temperature provided in this disclosure. Figure 1 As shown, the method includes:
[0053] S101: Obtain multiple geothermal influence parameters of the target well logging.
[0054] Specifically, drilling into a target well allows for the collection of logging data. Analyzing the physical properties of this logging data identifies geothermal parameters that influence geothermal temperature. In this embodiment, geothermal parameters may include well depth data and multiple logging physical properties, such as sonic transit time, porosity, natural gamma ray, and resistivity. The target well may be a geothermal well.
[0055] S102: Based on the geothermal prediction model, multiple geothermal influencing parameters are analyzed and processed to determine the geothermal prediction results of the target well.
[0056] Specifically, the geothermal prediction model is trained using multiple geothermal influence sample parameters that affect the geothermal prediction results and the corresponding geothermal sample data. In this embodiment, features can be extracted from multiple geothermal influence parameters, and the influence feature vectors can be analyzed and their weights adjusted to generate geothermal prediction results under the influence of the current geothermal influence parameters. The geothermal prediction results represent the mapping relationship of geothermal temperature across the entire well section.
[0057] This disclosure acquires multiple geothermal influence parameters from a target well logging operation. Based on a geothermal prediction model, these parameters are analyzed and processed to determine the geothermal prediction results for the target well logging operation. The geothermal prediction results represent a mapping relationship of geothermal temperature across the entire well section. The geothermal prediction model is trained using multiple geothermal influence sample parameters and corresponding geothermal sample data. By learning the quantitative relationship between multiple parameters influencing geothermal temperature and geothermal temperature, multi-dimensional prediction of deep formation temperature in the target well logging operation is achieved, thereby determining the formation temperature across the entire well section. Therefore, the accuracy of geothermal prediction can be improved.
[0058] Example 2
[0059] Based on the above embodiments, an exemplary method for determining the geothermal prediction results of a target well by analyzing and processing multiple geothermal influence parameters based on a geothermal prediction model includes:
[0060] Feature extraction is performed on multiple geothermal influencing parameters to obtain influence feature vectors; the weight values are adjusted based on the influence feature vectors to determine the geothermal prediction results.
[0061] Specifically, multiple geothermal influencing parameters are input into the geothermal prediction model. The input layer extracts features to obtain an influencing feature vector. The hidden layer abstracts the influencing feature vector and adjusts its weights. Then, the weights between the hidden layer and the output layer are adjusted, and finally, the geothermal prediction result is output in the output layer. Figure 2 A schematic diagram of the structure for making predictions using the geothermal prediction model provided in this disclosure is shown below. Figure 2 As shown. In this embodiment, the geothermal prediction model can be a BP (BackPropagation) neural network model. The weights are the connection weights between neurons in each layer of the geothermal prediction model, such as the weights connecting the input layer to the hidden layer and the weights connecting the hidden layer to the output layer.
[0062] Example 3
[0063] Based on the above embodiments, Figure 3 This is a flowchart for obtaining parameters affecting geothermal temperature, as provided in this disclosure.
[0064] Exemplary methods for obtaining multiple geothermal influence parameters of a target well logging operation include:
[0065] S301: Obtain the target well depth data and multiple well logging physical parameters.
[0066] Specifically, drilling is performed on the target well to obtain logging data. This logging data includes well depth data and multiple logging physical parameters. In this embodiment, the logging physical parameters include sonic transit time, porosity, natural gamma ray, resistivity, permeability, and water saturation.
[0067] S302: Based on the Pearson correlation coefficient, analyze each logging property parameter to determine the influence coefficient of each logging property parameter on geothermal temperature.
[0068] Specifically, the Pearson correlation coefficient between each logging physical property parameter is calculated to measure the linear correlation between two variables and characterize the degree of mutual influence between different parameters. The influence coefficient ranges from [-1, 1], and the larger the absolute value of the influence coefficient, the stronger the correlation.
[0069] Figure 4 The following is a graph showing the correlation analysis results of the logging physical property parameters provided in this disclosure, such as... Figure 4 As shown, the influence coefficients of geothermal temperature and sonic transit time are -0.75 and -0.5, respectively, showing a negative correlation; while the influence coefficients of natural gamma ray and resistivity are 0.36 and 0.13, respectively, showing a positive correlation. The target logging physical property parameters include at least one logging physical property parameter.
[0070] S303: Sort the absolute values of the influence coefficients of each logging property parameter on geothermal temperature from largest to smallest to determine the target logging property parameter.
[0071] Specifically, after analyzing the Pearson correlation coefficient, the absolute values of the influence coefficients of each logging property parameter on geothermal temperature are sorted from largest to smallest. In this embodiment, the target logging property parameters include sonic transit time, porosity, natural gamma, and resistivity.
[0072] S304: Use the target logging physical property parameters and well depth data as multiple geothermal influence parameters.
[0073] Specifically, for geothermal temperature, well depth data is one of the important factors affecting geothermal temperature. Therefore, the determined target logging physical property parameters and well depth data are used as multiple geothermal influencing parameters.
[0074] Example 4
[0075] Based on the above embodiments, before analyzing and processing multiple geothermal influence parameters based on the geothermal prediction model to determine the geothermal prediction result of the target well, the method further includes:
[0076] Obtain geothermal influence sample parameters and geothermal sample data for the target well logging.
[0077] Specifically, in this embodiment, multiple sets of historical geothermal influence sample parameters and geothermal sample data are required. The geothermal influence sample parameters are used as input samples, and the geothermal sample data are used as output samples to train the geothermal prediction model to be trained.
[0078] The parameters and data of the ground temperature influence samples are divided into training sample set and test sample set; the ground temperature prediction model to be trained is trained based on the training sample set, and the ground temperature prediction model to be tested is determined.
[0079] Specifically, the sample parameters and data can be randomly shuffled, and 70% of the geothermal influence sample parameters and geothermal sample data can be selected as the training sample set, while 30% can be used as the test sample set. The geothermal prediction model to be trained learns the feature relationships in the training sample set and is then trained to obtain the geothermal prediction model to be tested. In this embodiment, the constructed geothermal prediction model to be trained is based on a neural network architecture, and the number of hidden layer nodes in the model can be up to 9. A direct mapping relationship between geothermal influence parameters and geothermal temperature is established, which can more accurately predict the deep geothermal temperature of the target well compared to a simple linear relationship.
[0080] The ground temperature prediction model under test is tested based on the test sample set to determine the ground temperature prediction model.
[0081] Example:
[0082] Based on the ground temperature prediction results generated by the ground temperature prediction model to be tested and the ground temperature sample data in the test sample set, the error of the ground temperature prediction model to be tested is evaluated to determine the first error parameter; if the first error parameter meets the first error range, the ground temperature prediction model to be tested is used as the ground temperature prediction model.
[0083] Specifically, testing the ground temperature prediction model can determine its reliability, which is assessed through absolute error evaluation. The first error parameter can be determined using the following formula:
[0084]
[0085] Where MAE is the first error parameter, L is the number of test sample sets, and test i pre The test result is the geothermal prediction result generated by the geothermal prediction model based on the geothermal influence sample parameters in the i-th test sample. i obs This is the data for the i-th geothermal sample in the test sample set.
[0086] By determining whether the magnitude of the first error parameter falls within the first error range, it is determined whether the current ground temperature prediction model to be tested meets the training requirements. If it meets the first error range, the ground temperature prediction model to be tested is adopted as the ground temperature prediction model; if it does not meet the first error range, model training continues.
[0087] Example 5
[0088] Based on the above embodiments, after analyzing and processing multiple geothermal influence parameters based on the geothermal prediction model to determine the geothermal prediction results of the target well, the method further includes:
[0089] Obtain the geothermal measurement value of the target well; verify the error based on the geothermal measurement value and the geothermal prediction result to obtain the second error parameter; if the second error parameter meets the second error range, determine that the geothermal prediction result is correct.
[0090] Specifically, after obtaining the predicted geothermal temperature results from the target well logging, the prediction results can be verified. By acquiring the logging data from the target well, the geothermal measurement value is determined, and the relative error is judged based on the geothermal measurement value and the prediction result. The second error parameter can be determined according to the following formula:
[0091] Err=|T pre -T obs | / T obs
[0092] Where Err is the second error parameter, T pre For the ground temperature prediction results, T obs This is the measured ground temperature value.
[0093] The accuracy of the current ground temperature prediction result is determined by judging whether the magnitude of the second error parameter is within the second error range. If it meets the second error range, the ground temperature prediction result is determined to be correct. Figure 5 This is a comparison chart of the errors between the measured and predicted ground temperature values provided in this disclosure, such as... Figure 5 As shown, 85 sets of sample data were selected within the target well depth range of 100m to 4500m, and the prediction error was less than 2%, achieving the expected results.
[0094] Example 6
[0095] Based on the above embodiments, this embodiment provides an application example. Figure 6 Another flowchart is provided for a method of geothermal prediction according to this disclosure. Figure 6 As shown, the method includes:
[0096] S601: Obtain logging data from geothermal wells, analyze the influence relationship of physical property parameters in the logging data, and determine the factors affecting geothermal temperature.
[0097] Specifically, the physical properties in well logging data include geothermal temperature, resistivity, porosity, sonic transit time, and natural gamma. Analyzing the influence relationship between two physical properties identifies those with a significant impact on geothermal temperature, which are then considered influencing factors. For geothermal temperature, well depth is also a crucial factor. These influencing factors can be multiple physical properties.
[0098] S602: Using the influencing factors and ground temperature data as the input and output sets respectively, the ground temperature prediction model is trained to obtain the ground temperature prediction model.
[0099] Specifically, by using influencing factors as the training input set and geothermal data as the training output set, the neural network model can learn the correlation between features and adjust the model parameters so that the model's output meets expectations, thus obtaining a well-trained geothermal prediction model.
[0100] S603: Input the well depth data and well logging physical property parameters from the well logging data into the geothermal prediction model to obtain the geothermal well full section geothermal curve.
[0101] Specifically, well depth data and logging physical property parameters are factors affecting geothermal temperature. These are input into a trained geothermal prediction model, which can then predict the deep geothermal temperature value of the geothermal well in order to obtain a geothermal temperature curve for the entire well section. Figure 7 This is a schematic diagram of the geothermal curve for the entire well section provided in this disclosure, such as... Figure 7 As shown, a geothermal prediction model is obtained by training a neural network based on well logging temperature data at depths shallower than 4500m; then, well logging physical property parameters from 4500m to 5100m are used as input to obtain temperature data from 4500m to 5100m based on the geothermal prediction model; finally, the geothermal curve of the entire well section is obtained by integrating the existing temperature data and the predicted temperature.
[0102] Example 7
[0103] Figure 8 This is a schematic diagram of the structure of a geothermal prediction device provided in this disclosure. Figure 8 As shown, the device 800 includes an acquisition module 810 and a determination module 820.
[0104] The acquisition module 810 is used to acquire multiple geothermal influence parameters of the target well logging;
[0105] The determination module 820 is used to analyze and process the multiple geothermal influence parameters based on the geothermal prediction model to determine the geothermal prediction result of the target well. The geothermal prediction result is a mapping relationship of geothermal temperature for the entire well section. The geothermal prediction model is trained using multiple geothermal influence sample parameters that affect the geothermal prediction result and geothermal sample data corresponding to the multiple geothermal influence sample parameters.
[0106] Optionally, the acquisition module is used for:
[0107] Feature extraction is performed on the multiple geothermal influencing parameters to obtain the influencing feature vector;
[0108] The weight values are adjusted based on the influence feature vector to determine the geothermal prediction result, wherein the weight values are the connection weights between neurons in each layer of the geothermal prediction model.
[0109] Optionally, the acquisition module is used for:
[0110] Acquire the well depth data and multiple logging physical parameters of the target well;
[0111] Based on the Pearson correlation coefficient, each of the well logging physical property parameters is analyzed to determine the influence coefficient of each of the well logging physical property parameters on geothermal temperature;
[0112] The absolute values of the influence coefficients of each logging property parameter on geothermal temperature are sorted from largest to smallest to determine the target logging property parameter, wherein the target logging property parameter includes at least one of the logging property parameters.
[0113] The target logging physical property parameters and the well depth data are used as the multiple geothermal influence parameters.
[0114] Optionally, the device further includes:
[0115] Before analyzing and processing the multiple geothermal influence parameters based on the geothermal prediction model to determine the geothermal prediction result of the target well, the geothermal influence sample parameters and geothermal sample data of the target well are obtained.
[0116] The geothermal influence sample parameters and the geothermal sample data are divided into a training sample set and a test sample set;
[0117] The training sample set is used to train the ground temperature prediction model to be trained, and the ground temperature prediction model to be tested is determined.
[0118] The ground temperature prediction model to be tested is tested based on the test sample set to determine the ground temperature prediction model.
[0119] Optionally, the determining module is used to:
[0120] Based on the ground temperature prediction results generated by the ground temperature prediction model to be tested and the ground temperature sample data in the test sample set, the error of the ground temperature prediction model to be tested is evaluated, and the first error parameter is determined.
[0121] If the first error parameter meets the first error range, the ground temperature prediction model to be tested is used as the ground temperature prediction model.
[0122] Optionally, the device further includes:
[0123] After analyzing and processing the multiple geothermal influence parameters based on the geothermal prediction model to determine the geothermal prediction result of the target well, the geothermal measurement value of the target well is obtained.
[0124] Based on the measured ground temperature value and the predicted ground temperature result, an error verification is performed to obtain a second error parameter;
[0125] If the second error parameter meets the second error range, the geothermal prediction result is determined to be correct.
[0126] Based on the above embodiments, this embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory. The processor executes the computer program to implement the steps of the ground temperature prediction method described in the above embodiments.
[0127] In some embodiments of this example, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the geothermal prediction method described in the above embodiments.
[0128] In some embodiments of this example, a computer program product is provided, including a computer program / instructions, which, when executed by a processor, implements the steps of the geothermal prediction method described in the above embodiments.
[0129] The processor may include, but is not limited to, one or more processors or microprocessors. Each processor may be implemented as an Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), controller, microcontroller, microprocessor, or other electronic component, for executing the methods in the above embodiments.
[0130] Computer-readable storage media can be implemented by any type of volatile or non-volatile storage device or a combination thereof. Computer-readable storage media may include, but are not limited to, random access memory (RAM), read-only memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, and computer storage media (e.g., hard disks, floppy disks, solid-state drives, removable disks, CD-ROMs, DVD-ROMs, Blu-ray discs, etc.).
[0131] Computer-readable storage media may also store at least one computer-executable program / instruction, such as computer-readable instructions. Computer-readable storage media include, but are not limited to, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Computer-readable storage media may include, for example, read-only memory (ROM), hard disk, flash memory, etc. For example, a non-transitory computer-readable storage medium may be connected to a computing device such as a computer, and then, when the computing device executes the computer-readable instructions stored on the computer-readable storage medium, the various methods described above can be performed.
[0132] In addition, the computer device may include (but is not limited to) a data bus, an input / output (I / O) bus, a display, and input / output devices (e.g., keyboard, mouse, speakers, etc.).
[0133] The processor can communicate with external devices via the I / O bus through wired or wireless networks.
[0134] In one embodiment, the at least one computer-executable instruction may also be compiled into or comprise a software product / computer program product, wherein one or more computer-executable instructions are executed by a processor to perform the steps of the various functions and / or methods in the embodiments described herein.
[0135] In the embodiments provided in this disclosure, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.
[0136] It should be noted that, in this disclosure, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element limited by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.
[0137] While the embodiments disclosed herein are as described above, the foregoing content is merely for the purpose of facilitating understanding of this disclosure and is not intended to limit this disclosure. Any person skilled in the art to which this disclosure pertains may make any modifications and changes in form and detail of the implementation without departing from the spirit and scope of this disclosure; however, the scope of patent protection of this disclosure shall still be determined by the scope defined in the appended claims.
Claims
1. A method for predicting ground temperature, characterized in that, include: Obtain multiple geothermal influence parameters from the target well logging; Based on the geothermal prediction model, the multiple geothermal influencing parameters are analyzed and processed to determine the geothermal prediction result of the target well. The geothermal prediction result is a mapping relationship of geothermal temperature throughout the well section. The geothermal prediction model is trained using multiple geothermal influencing sample parameters that affect the geothermal prediction result and the geothermal sample data corresponding to the multiple geothermal influencing sample parameters.
2. The method according to claim 1, characterized in that, The analysis and processing of the multiple geothermal influence parameters based on the geothermal prediction model to determine the geothermal prediction results of the target well logging includes: Feature extraction is performed on the multiple geothermal influencing parameters to obtain the influencing feature vector; The weight values are adjusted based on the influence feature vector to determine the geothermal prediction result, wherein the weight values are the connection weights between neurons in each layer of the geothermal prediction model.
3. The method according to claim 1, characterized in that, The acquisition of multiple geothermal influence parameters from the target well logging includes: Acquire the well depth data and multiple logging physical parameters of the target well; Based on the Pearson correlation coefficient, each of the well logging physical property parameters is analyzed to determine the influence coefficient of each of the well logging physical property parameters on geothermal temperature; The absolute values of the influence coefficients of each logging property parameter on geothermal temperature are sorted from largest to smallest to determine the target logging property parameter, wherein the target logging property parameter includes at least one of the logging property parameters. The target logging physical property parameters and the well depth data are used as the multiple geothermal influence parameters.
4. The method according to claim 1, characterized in that, Before analyzing and processing the multiple geothermal influence parameters based on the geothermal prediction model to determine the geothermal prediction result of the target well, the method further includes: Obtain geothermal influence sample parameters and geothermal sample data for the target well logging; The geothermal influence sample parameters and the geothermal sample data are divided into a training sample set and a test sample set; The training sample set is used to train the ground temperature prediction model to be trained, and the ground temperature prediction model to be tested is determined. The ground temperature prediction model to be tested is tested based on the test sample set to determine the ground temperature prediction model.
5. The method according to claim 4, characterized in that, The step of testing the ground temperature prediction model based on the test sample set to determine the ground temperature prediction model includes: Based on the ground temperature prediction results generated by the ground temperature prediction model to be tested and the ground temperature sample data in the test sample set, the error of the ground temperature prediction model to be tested is evaluated, and the first error parameter is determined. If the first error parameter meets the first error range, the ground temperature prediction model to be tested is used as the ground temperature prediction model.
6. The method according to claim 1, characterized in that, After analyzing and processing the multiple geothermal influence parameters based on the geothermal prediction model to determine the geothermal prediction result of the target well, the method further includes: Obtain the geothermal measurement value of the target well; Based on the measured ground temperature value and the predicted ground temperature result, an error verification is performed to obtain a second error parameter; If the second error parameter meets the second error range, the geothermal prediction result is determined to be correct.
7. A device for predicting ground temperature, characterized in that, include: The acquisition module is used to acquire multiple geothermal influence parameters of the target well logging. The determination module is used to analyze and process the multiple geothermal influence parameters based on the geothermal prediction model to determine the geothermal prediction result of the target well. The geothermal prediction result is a mapping relationship of geothermal temperature for the entire well section. The geothermal prediction model is trained using multiple geothermal influence sample parameters that affect the geothermal prediction result and geothermal sample data corresponding to the multiple geothermal influence sample parameters.
8. A computer device, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the method according to any one of claims 1 to 6.
10. A computer program product comprising a computer program / instructions, characterized in that, When executed by a processor, the computer program implements the steps of the method according to any one of claims 1 to 6.
