Methods, devices, storage media and electronic equipment for predicting permafrost temperature

Abstract

This application provides a method, apparatus, storage medium, and electronic device for predicting permafrost temperature, relating to the field of geology. The electronic device acquires sample environmental factors, permafrost type, and ground temperature from a sample area; generates a ground temperature prediction model based on these factors; acquires target environmental factors for a target area; and processes these factors using the ground temperature prediction model to obtain the target ground temperature for the target area. Because this ground temperature prediction model is generated based on a large amount of sample data, it can more accurately predict the ground temperature in discontinuous permafrost regions.

Description

Technical Field

[0001] This application relates to the field of geology, and more specifically, to a method, apparatus, storage medium, and electronic device for predicting permafrost temperature. Background Technology

[0002] Permafrost refers to soil and rock layers buried at a certain depth below the Earth's surface that have remained at sub-zero temperatures for two or more consecutive years. A product of cold climates, permafrost possesses unique physical properties and is closely related to hydrology, water resources, ecological environment, and geological hazards in cold regions. It also significantly impacts the stability of engineering infrastructure. The classification, distribution, thermal characteristics, hydrological characteristics, and mechanical properties of permafrost are all hot topics of interest for researchers and engineers in related fields.

[0003] The thermal condition of permafrost is the most important indicator for evaluating the development and evolution of permafrost. In a narrow sense, the thermal condition of permafrost usually refers to the ground temperature value at one or several depths in a single site; while in a broader sense, it reflects the spatial extension of permafrost temperature. For permafrost temperature mapping aimed at describing the spatial distribution of permafrost, the annual average ground temperature at the depth of annual temperature variation is often used as the indicator. Theoretically, the depth of annual temperature variation refers to the depth where the annual temperature change is zero, but in practice, the depth where the annual temperature change equals 0.1℃ is often used. The annual average ground temperature is the average of continuously observed ground temperatures throughout the year. In engineering, a depth of 10-15m is often used as the depth of annual temperature variation, because the annual temperature variation at this depth is very small, and the annual average ground temperature can be replaced by a single instantaneous temperature measurement or the average of multiple instantaneous temperature measurements, without necessarily requiring annual observations.

[0004] Studies have found that island-like or scattered permafrost areas in discontinuous permafrost zones often contain historical remnants of permafrost, preserved due to ecological protection or special hydrogeological conditions. This makes the permafrost temperature in these areas insensitive to modern climate conditions, making its estimation extremely difficult. Summary of the Invention

[0005] To overcome at least one deficiency in the prior art, this application provides a method, apparatus, storage medium, and electronic device for predicting permafrost temperature, specifically including:

[0006] In a first aspect, this application provides a method for predicting permafrost temperature, the method comprising:

[0007] Obtain environmental factors, permafrost type, and ground temperature of the sample area;

[0008] A ground temperature prediction model is generated based on the environmental factors of the sample, the permafrost type of the sample, and the ground temperature of the sample.

[0009] Obtain the target environmental factors for the target area;

[0010] The target environmental factors are processed by the geothermal prediction model to obtain the target geothermal temperature of the target area.

[0011] Secondly, this application provides a permafrost temperature prediction device, the device comprising:

[0012] The model building module is used to obtain the sample environmental factors, sample permafrost type, and sample ground temperature of the sample area; and to generate a ground temperature prediction model based on the sample environmental factors, sample permafrost type, and sample ground temperature.

[0013] The ground temperature prediction module is used to obtain target environmental factors of the target area; the target environmental factors are processed by the ground temperature prediction model to obtain the target ground temperature of the target area.

[0014] Thirdly, this application provides a storage medium storing a computer program, which, when executed by a processor, implements the permafrost temperature prediction method.

[0015] Fourthly, this application provides an electronic device, which includes a processor and a memory. The memory stores a computer program, and when the computer program is executed by the processor, it implements the permafrost temperature prediction method.

[0016] Compared with the prior art, this application has the following beneficial effects:

[0017] The permafrost temperature prediction method, apparatus, storage medium, and electronic equipment provided in this application involve the electronic equipment acquiring sample environmental factors, sample permafrost type, and sample ground temperature of a sample area; generating a ground temperature prediction model based on the sample environmental factors, sample permafrost type, and sample ground temperature; acquiring target environmental factors for the target area; and processing the target environmental factors through the ground temperature prediction model to obtain the target ground temperature for the target area. Since this ground temperature prediction model is based on a large amount of sample data, it can more accurately predict the ground temperature in discontinuous permafrost areas. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A flowchart illustrating the permafrost temperature prediction method provided in this application embodiment;

[0020] Figure 2 This is a schematic diagram of the geothermal distribution characteristics provided in an embodiment of this application;

[0021] Figure 3 This is a schematic diagram of the structure of the permafrost temperature prediction device provided in the embodiments of this application;

[0022] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0023] Icons: 101-Model building module; 102-Geotemperature prediction module; 201-Memory; 202-Processor; 203-Communication unit; 204-System bus. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0025] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0026] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0027] In the description of this application, it should be noted that the terms "first," "second," "third," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance. Furthermore, 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 limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0028] Currently, methods for obtaining the temperature distribution of permafrost mainly fall into two categories: observation and simulation. Observation primarily involves placing temperature probes on the soil and rock profiles through excavation or drilling to measure the temperature. This is the most direct and accurate method, but current technology only supports single-point mode. Simulation methods can be further divided into empirical statistical models, semi-physical models, or process models, depending on the differences in data and algorithms.

[0029] Using empirical statistical models requires establishing statistical mapping functions or probabilistic statistical relationships between a large amount of field-measured ground temperature data and geographical environmental elements to predict ground temperature at single points or on a surface. Examples include elevation models or equivalent models dominated by elevation, annual average ground temperature models based on regression methods, and statistical-machine learning models driven by multi-source data in recent years.

[0030] Semi-physical models are based on some basic laws summarized from the mechanisms of heat conduction or temperature diffusion. They use relatively easy-to-observe and obtainable air temperature or surface parameters and stratum thermophysical parameters to simulate ground temperature, such as temperature displacement models and permafrost roof temperature models.

[0031] Process models are based on rigorous energy transfer and conversion mechanisms and use numerical calculation methods to simulate thermal dynamics, such as the GIPL model. In addition, permafrost temperature calculation modules coupled to climate models, hydrological models, or land surface process models also mostly belong to this category.

[0032] Based on the continuity of permafrost distribution in a plane (defined as the proportion of permafrost area), permafrost can be divided into two main categories: continuous permafrost and discontinuous permafrost. Different scholars have further subdivided these categories based on various indicators; for example, discontinuous permafrost can be further subdivided into discontinuous permafrost, island permafrost, and scattered permafrost. Discontinuity is closely related to the ground temperature of permafrost, but due to the lack of observable, quantitative, and unified indicators for classifying continuity, comparisons between the two are difficult. However, the general consensus is that continuous permafrost zones generally have lower ground temperatures, while discontinuous permafrost zones have relatively higher ground temperatures. Due to the influence of unfrozen water content in permafrost, under the same water content, low-temperature permafrost often has higher thermal conductivity and thermal conductivity than high-temperature permafrost; moreover, under temperature-driven effects, even weak phase transitions can affect the deep ground temperature of permafrost.

[0033] Furthermore, island-like or scattered permafrost areas in discontinuous permafrost zones often contain historical remnants of permafrost, preserved due to ecological protection or special hydrogeological conditions. This makes the permafrost temperature in these areas insensitive to modern climate conditions, making permafrost temperature estimation extremely difficult. Borehole-based ground temperature observations are very sparse and extremely costly, especially in rugged, inaccessible, and remote high-altitude plateau regions.

[0034] Therefore, based on current technology, the temperature conditions of island-like or scattered permafrost areas are relatively limited. Due to limitations in data, models, and the inherent developmental characteristics of permafrost itself, large-scale, coarse-grid geothermal estimations are relatively easy to achieve, while small-scale, fine-scale geothermal distribution mapping is difficult to create. However, such fine-scale mapping is essential for regional hydrological research, ecological environmental protection, and guiding engineering construction.

[0035] It should be noted that the defects in the solutions in the prior art are all the results of the inventors’ practice and careful research. Therefore, the discovery process of the above problems and the solutions proposed by the embodiments of this application in the following text should be the inventors’ contributions to this application in the process of invention and creation, and should not be understood as technical content known to those skilled in the art.

[0036] Therefore, this embodiment provides a method for predicting permafrost temperature applied to electronic devices, used to predict the ground temperature in discontinuous permafrost regions. The electronic device may be, but is not limited to, a mobile terminal, tablet computer, laptop computer, server, etc.

[0037] When used as a server, the server can be a single server or a group of servers. A server group can be centralized or distributed (e.g., the servers can be a distributed system). In some embodiments, the server can be local or remote relative to a user terminal. In some embodiments, the server can be implemented on a cloud platform; by way of example only, a cloud platform can include private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, inter-cloud, multi-cloud, etc., or any combination thereof. In some embodiments, the server can be implemented on an electronic device having one or more components.

[0038] Based on the above introduction, the following will combine... Figure 1This embodiment provides a detailed description of the permafrost temperature prediction method. However, it should be understood that the operations in the flowchart may not be performed in sequence, and steps without logical contextual relationships may be reversed or performed simultaneously. Furthermore, those skilled in the art, guided by the content of this application, may add one or more other operations to the flowchart, or remove one or more operations from the flowchart. For example... Figure 1 As shown, the method includes:

[0039] S101, obtain the environmental factors of the sample area, the type of frozen soil, and the ground temperature of the sample area.

[0040] Among them, the environmental factors of the sample area can be extracted using the geographical location information of the measuring points through a GIS (Geographic Information System) platform. The environmental factors used in this embodiment include climate factors, topographic factors, vegetation factors, and soil factors.

[0041] Climate factors include average temperature, average precipitation, average surface temperature, thaw index, and freeze index.

[0042] Topographic factors include elevation, slope, aspect, surface curvature, and topographic humidity index.

[0043] Vegetation factors include vegetation indices.

[0044] Soil factors include sand content, clay content, soil organic carbon density, surface gravel content, and soil dry bulk density.

[0045] S102 generates a ground temperature prediction model based on the sample's environmental factors, frozen soil type, and ground temperature.

[0046] In an optional implementation, the geothermal prediction model includes a permafrost identification model and a geothermal calculation model. Specifically, an electronic device inputs sample environmental factors into a machine learning model to be trained; the machine learning model is updated based on the difference between its prediction results and the sample permafrost type; and the permafrost identification model is obtained when the machine learning model meets preset conditions.

[0047] Then, the electronic device inputs the environmental factors of the sample area into the permafrost identification model to obtain the classification probability of the sample area as a continuous permafrost area, and uses it as the sample probability; based on the sample probability, the non-continuous permafrost area is determined from the sample area; the sample probability of the non-continuous permafrost area is fitted with the sample ground temperature of the non-continuous permafrost area to obtain the ground temperature calculation model.

[0048] For example, the field survey area is determined. Temperature measurements are taken at depths of 10-15 meters using boreholes. These boreholes cover several types of vegetation, including marshy alpine meadows, typical alpine meadows, and alpine grasslands. If the temperature measurements preliminarily indicate that the area above 4600m in the mountainous region is continuous permafrost, while the area between 4600m and 4000m is a discontinuous permafrost zone, especially in large areas around lakes where island-like permafrost exists, and the morphology and geothermal characteristics of these island-like permafrost have never been addressed in previous studies, then ground-penetrating radar (GPR) is used to obtain information on the presence of permafrost within the survey area, and the geographical location information of each measuring point is recorded.

[0049] In this process, denser measurements are conducted near each borehole; and the ground-penetrating radar survey lines are distributed from high to low altitudes, traversing different terrains and vegetation types, with denser measurements conducted in the alpine meadows and grasslands surrounding the lake. For example... Figure 2 As shown, the relationship between ground temperature and altitude reveals that simple elevation models cannot capture the temperature information of island-like permafrost and edge permafrost. The form of a simple elevation model is:

[0050] T = a·H + b

[0051] In the formula, T represents the permafrost temperature, H represents the altitude, and a and b are the coefficients of the univariate linear regression.

[0052] Based on auxiliary data such as on-site drilling survey data, the ground-penetrating radar data is interpreted interactively by human-computer interaction using expert knowledge to determine the status of permafrost at each measuring point and assign different values, i.e., permafrost is assigned a value of 1 and non-permafrost is assigned a value of 0.

[0053] Using a GIS platform, corresponding environmental factors were extracted from the geographic location information of the measurement points, and these factors, along with the measured permafrost type and ground temperature, constituted a sample dataset. Using this constructed dataset, with the existence of permafrost as the dependent variable and the corresponding environmental indicators as independent variables, a support vector machine classification model was trained using five-fold cross-validation to obtain a permafrost identification model.

[0054] Using this permafrost identification model, the existence and occurrence probability of permafrost in the sample area are predicted separately, and the probability of permafrost occurrence in the area is obtained and recorded on the GIS platform. Finally, based on the geographical location information of the temperature boreholes, the corresponding permafrost occurrence probability is extracted using the GIS platform; the sample ground temperature and classification probability at this location are fitted with a function to obtain a Sigmoid-based ground temperature calculation model.

[0055]

[0056] This geothermal calculation model can be used to calculate the geothermal temperature of a target area based on the probability that the target area is a permafrost region, where T represents the target geothermal temperature and P represents the classification probability that the target area is a continuous permafrost region.

[0057] The above is an introduction to geothermal prediction models. Please refer to [link / reference needed]. Figure 1 The method also includes:

[0058] S103, Obtain the target environmental factors of the target area.

[0059] S104: The target environmental factors are processed by the geothermal prediction model to obtain the target geothermal temperature of the target area.

[0060] In a specific implementation, the target environmental factors are input into the permafrost identification model to obtain the classification probability that the target area is a continuous permafrost area; if the classification probability is less than the probability threshold, the classification probability is processed by the ground temperature calculation model to obtain the target ground temperature of the target area.

[0061] Studies have found that for areas with a probability of permafrost occurrence greater than 0.8, the ground temperature calculated using this model has a large error. Therefore, in this embodiment, the probability threshold can be set to 0.8. Additionally, the ground temperature prediction model also includes a simple elevation model. When the probability of the target area being a continuous permafrost region is greater than 0.8, the elevation model is used to predict the target ground temperature for that area.

[0062] By comparing the predicted ground temperature with the measured ground temperature, it was found that the correlation coefficient between the results obtained in this embodiment and the measured results is close to 0.95, the estimated standard error is 0.37, and the ground temperature information of the island permafrost is captured very well, making up for the shortcomings of the elevation model.

[0063] The above is an introduction to methods for predicting permafrost temperature. Under the same inventive concept, this embodiment also provides a permafrost temperature prediction device. This device includes at least one software functional module that can be stored in a memory or embedded in the operating system (OS) of an electronic device. The processor in the electronic device is used to execute the executable module stored in the memory. For example, the software functional modules and computer programs included in this permafrost temperature prediction device. Please refer to... Figure 3 Functionally, this permafrost temperature prediction device may include:

[0064] The model building module 101 is used to obtain the sample environmental factors, sample permafrost type and sample ground temperature of the sample area; and to generate a ground temperature prediction model based on the sample environmental factors, sample permafrost type and sample ground temperature.

[0065] In this embodiment, the model building module 101 is used to implement Figure 1 For a detailed description of steps S101 and S102 in the model building module 101, please refer to the detailed description of steps S101 and S102.

[0066] The ground temperature prediction module 102 is used to obtain the target environmental factors of the target area; the target environmental factors are processed by the ground temperature prediction model to obtain the target ground temperature of the target area.

[0067] In this embodiment, the ground temperature prediction module 102 is used to implement... Figure 1 For a detailed description of steps S103 and S104 in the process, and for the geothermal prediction module 102, please refer to the detailed description of steps S103 and S104.

[0068] It is worth noting that, since they share the same inventive concept as the permafrost temperature prediction method, the above model construction module 101 and ground temperature prediction module 102 can also be used to implement other steps or sub-steps of the method. This implementation does not specifically limit this.

[0069] In addition, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0070] It should also be understood that if the above embodiments are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.

[0071] Therefore, this embodiment also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the permafrost temperature prediction method provided in this embodiment. The computer-readable storage medium can be any medium capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0072] Please refer to Figure 4This embodiment also provides an electronic device, which may include a processor 202 and a memory 201. The processor 202 and the memory 201 can communicate via a system bus 204. Furthermore, the memory 201 stores a computer program, and the processor implements the permafrost temperature prediction method provided in this embodiment by reading and executing the computer program in the memory 201 corresponding to the above embodiments.

[0073] See also Figure 4 The electronic device may also include a communication unit 203. The memory 201, processor 202 and communication unit 203 are electrically connected to each other directly or indirectly through system bus 204 to realize data transmission or interaction.

[0074] The memory 201 can be an information recording device based on any electronic, magnetic, optical, or other physical principles, used to record execution instructions, data, etc. In some embodiments, the memory 201 can be, but is not limited to, volatile memory, non-volatile memory, memory drive, etc.

[0075] For example only, the volatile memory can be random access memory (RAM). The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable read-only memory (EPROM), electrically erasable read-only memory (EEPROM), flash memory, etc.; the storage drive can be a disk drive, solid-state drive, any type of storage disk (such as optical disc, DVD, etc.), or similar storage media, or a combination thereof.

[0076] The communication unit 203 is used to send and receive data over a network. In some embodiments, the network may include a wired network, a wireless network, a fiber optic network, a telecommunications network, an intranet, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), a metropolitan area network (MAN), a public switched telephone network (PSTN), a Bluetooth network, a ZigBee network, or a near field communication (NFC) network, or any combination thereof. In some embodiments, the network may include one or more network access points. For example, the network may include wired or wireless network access points, such as base stations and / or network switching nodes, through which one or more components of the service request processing system can connect to the network to exchange data and / or information.

[0077] The processor 202 may be an integrated circuit chip with signal processing capabilities, and the processor may include one or more processing cores (e.g., a single-core processor or a multi-core processor). By way of example only, the processor described above may include a Central Processing Unit (CPU), an Application-Specific Integrated Circuit (ASIC), an Application-Specific Instruction-set Processor (ASIP), a Graphics Processing Unit (GPU), a Physics Processing Unit (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), a controller, a microcontroller unit, a Reduced Instruction Set Computing (RISC) computer, or a microprocessor, or any combination thereof.

[0078] In summary, it should be understood that the apparatus and methods disclosed in the above embodiments 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 application. 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 the block diagrams and / or flowcharts, and combinations of blocks in the 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.

[0079] The above descriptions are merely various embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for predicting permafrost temperature, characterized in that, The method includes: Obtain environmental factors, permafrost type, and ground temperature of the sample area; Based on the sample environmental factors, sample permafrost type, and sample ground temperature, a ground temperature prediction model is generated. The ground temperature prediction model includes a permafrost identification model and a ground temperature calculation model. The ground temperature calculation model is obtained by fitting a function between the sample probability of a non-continuous permafrost region in the sample area and the sample ground temperature of the non-continuous permafrost region. The sample probability of the non-continuous permafrost region is the classification probability of the non-continuous permafrost region by the permafrost identification model. Obtain the target environmental factors for the target area; The target environmental factors are processed by the geothermal prediction model to obtain the target geothermal temperature of the target area, including: The target environmental factors are input into the permafrost identification model to obtain the classification probability that the target area is a continuous permafrost area. If the classification probability is less than the probability threshold, the classification probability is processed by the ground temperature calculation model to obtain the target ground temperature of the target area. If the classification probability is greater than or equal to the probability threshold, the elevation model is used to predict the target ground temperature of the target area.

2. The method for predicting permafrost temperature according to claim 1, characterized in that, The step of generating a ground temperature prediction model based on the sample environmental factors, sample permafrost type, and sample ground temperature includes: The sample environmental factors are input into the machine learning model to be trained; The machine learning model is updated based on the difference between the prediction results output by the machine learning model and the sample permafrost type; the permafrost identification model is obtained when the machine learning model meets the preset conditions.

3. The method for predicting permafrost temperature according to claim 2, characterized in that, The step of generating a ground temperature prediction model based on the sample environmental factors, sample permafrost type, and sample ground temperature further includes: The environmental factors of the sample area are input into the permafrost identification model to obtain the classification probability that the sample area is a continuous permafrost area, and this probability is used as the sample probability. Based on the sample probability, discontinuous permafrost regions are identified from the sample region; The ground temperature calculation model is obtained by fitting the sample probability of the discontinuous permafrost region with the sample ground temperature of the discontinuous permafrost region.

4. The method for predicting permafrost temperature according to claim 1, characterized in that, The expression for the geothermal calculation model is as follows: in, Indicates the target ground temperature. This represents the classification probability that the target area is a continuous permafrost region.

5. The method for predicting permafrost temperature according to claim 1, characterized in that, The environmental factors of the sample include climate factors, topographic factors, vegetation factors, and soil factors.

6. The method for predicting permafrost temperature according to claim 5, characterized in that, The climate factors include average air temperature, average precipitation, average surface temperature, thaw index, and freeze index; The topographic factors include altitude, slope, aspect, surface curvature, and topographic humidity index; The vegetation factors include vegetation indices; The soil factors include sand content, clay content, soil organic carbon density, surface gravel content, and soil dry bulk density.

7. A permafrost temperature prediction device, characterized in that, The device includes: The model building module is used to obtain sample environmental factors, sample permafrost type, and sample ground temperature of the sample area; based on the sample environmental factors, sample permafrost type, and sample ground temperature, a ground temperature prediction model is generated, wherein the ground temperature prediction model includes a permafrost identification model and a ground temperature calculation model, the ground temperature calculation model is obtained by fitting a function between the sample probability of discontinuous permafrost areas in the sample area and the sample ground temperature of the discontinuous permafrost areas, and the sample probability of the discontinuous permafrost areas is the classification probability of the discontinuous permafrost areas by the permafrost identification model. The ground temperature prediction module is used to acquire target environmental factors for a target area; the method of processing the target environmental factors through the ground temperature prediction model to obtain the target ground temperature for the target area includes: The target environmental factors are input into the permafrost identification model to obtain the classification probability that the target area is a continuous permafrost area. If the classification probability is less than the probability threshold, the classification probability is processed by the ground temperature calculation model to obtain the target ground temperature of the target area. If the classification probability is greater than or equal to the probability threshold, the elevation model is used to predict the target ground temperature of the target area.

8. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the permafrost temperature prediction method according to any one of claims 1-6.

9. An electronic device, characterized in that, The electronic device includes a processor and a memory, the memory storing a computer program, which, when executed by the processor, implements the permafrost temperature prediction method according to any one of claims 1-6.

Images