Estimation method and related device for ground thermal state distribution in regular grid-type frozen soil areas

Abstract

The present application provides a method for estimating the ground thermal state distribution in a regular grid-type frozen soil area and a related device. In this method, an electronic device obtains measured temperature information and predicted temperature information of a target frozen soil area, wherein the measured temperature information includes the measured ground temperature at multiple observation scales, and the predicted temperature information includes the predicted ground temperature at multiple observation scales; the predicted temperature information is corrected by a pre-built semivariogram model to obtain optimized predicted temperature information; the optimized predicted temperature information is fused with the measured temperature information to obtain the ground temperature information of the target frozen soil area; based on the ground temperature information of the target frozen soil area, a ground thermal state distribution map of the target frozen soil area is generated. In this way, the thermal state of the frozen soil can be obtained non-destructively, and a ground thermal state distribution map at a reasonably set monitoring spatial scale can be generated, thereby effectively guiding engineering construction practices and ecological environmental assessments in frozen soil areas.

Description

Technical Field

[0001] The present application relates to the technical field of physical geography and geographic information systems, and in particular to a method for estimating the distribution of ground thermal state in a regular grid-type permafrost region and related devices. Background Art

[0002] Frozen soil is a crucial component of the cryosphere, one of the five major spheres of the Earth system. Its changes are closely linked to the cryosphere, atmosphere, biosphere, and pedosphere. Permafrost, seasonally frozen ground, and temporary frozen ground cover approximately 50% of the land surface area, with permafrost accounting for approximately 22% of the Northern Hemisphere's land surface area. Permafrost stores more soil organic carbon than vegetation and atmospheric carbon combined, making it one of the most critical carbon reservoirs in terrestrial ecosystems. Even small changes in permafrost affect the atmosphere, significantly impacting sustainable economic and social development and the achievement of carbon peak and carbon neutrality policies. Ground temperature is a key indicator of energy and water exchange between the atmosphere and pedosphere. It is also an important driver of frozen soil simulation and mapping, and plays a decisive role in the stability and dynamics of cryosphere-related environmental factors, including climate change and ecohydrology.

[0003] Due to the lack of necessary basic data, traditional permafrost engineering and permafrost thermal status surveys have problems with ecological damage and scale effects of the monitoring system. Summary of the Invention

[0004] In order to overcome at least one of the shortcomings of the prior art, the present application provides a method for estimating the ground thermal state distribution in a regular grid-type permafrost region and a related device, comprising:

[0005] In a first aspect, the present application provides a method for estimating ground thermal state distribution in a regular grid-type permafrost region, the method comprising:

[0006] Acquiring measured temperature information and predicted temperature information of the target frozen ground area, wherein the measured temperature information includes measured ground temperatures at multiple observation scales, and the predicted temperature information includes predicted ground temperatures at the multiple observation scales;

[0007] Correcting the predicted temperature information using a pre-constructed semivariogram model to obtain optimized predicted temperature information, wherein the semivariogram model characterizes the spatial variability of ground temperature in the target frozen soil area;

[0008] fusing the optimized predicted temperature information with the measured temperature information to obtain ground temperature information of the target frozen soil area;

[0009] A ground thermal state distribution map of the target permafrost area is generated based on the ground temperature information of the target permafrost area.

[0010] In a second aspect, the present application provides a regular grid-type permafrost region ground thermal state distribution estimation device, the device comprising:

[0011] a temperature acquisition module, configured to acquire measured temperature information and predicted temperature information of a target permafrost zone, wherein the measured temperature information includes measured ground temperatures at multiple observation scales, and the predicted temperature information includes predicted ground temperatures at the multiple observation scales;

[0012] a temperature optimization module, configured to correct the predicted temperature information using a pre-constructed semivariogram model to obtain optimized predicted temperature information, wherein the semivariogram model characterizes the measurement error, spatial variability, and maximum distance of spatial autocorrelation of the ground temperature in the target permafrost area;

[0013] The temperature optimization module is further configured to fuse the optimized predicted temperature information with the measured temperature information to obtain ground temperature information of the target frozen soil area;

[0014] The image drawing module is used to generate a ground thermal state distribution map of the target permafrost area according to the ground temperature information of the target permafrost area.

[0015] In a third aspect, the present application provides a storage medium storing a computer program. When the computer program is executed by a processor, the method for estimating the ground thermal state distribution in a regular grid-type permafrost area is implemented.

[0016] In a fourth aspect, the present application provides an electronic device comprising a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the method for estimating the ground thermal state distribution in a regular grid-type permafrost area is implemented.

[0017] Compared with the prior art, this application has the following beneficial effects:

[0018] The present application provides a method and related device for estimating the ground thermal state distribution in a regular grid-type frozen soil area. In this method, an electronic device obtains measured temperature information and predicted temperature information of a target frozen soil area, wherein the measured temperature information includes measured ground temperatures at multiple observation scales, and the predicted temperature information includes predicted ground temperatures at multiple observation scales; the predicted temperature information is corrected by a pre-constructed semivariogram model to obtain optimized predicted temperature information; wherein the semivariogram model characterizes the measurement error, spatial variability, and spatial autocorrelation of the ground temperature in the target frozen soil area; the optimized predicted temperature information is fused with the measured temperature information to obtain the ground temperature information of the target frozen soil area; based on the ground temperature information of the target frozen soil area, a ground thermal state distribution map of the target frozen soil area is generated. In this way, using the predicted ground temperatures at different scales and the measured ground temperatures, the thermal state of the frozen soil can be non-destructively obtained, and a ground thermal state distribution map at a reasonably set monitoring spatial scale can be generated, thereby effectively guiding engineering construction practices and ecological environmental assessments in frozen soil areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 A schematic diagram of a flow chart of a method for estimating ground thermal state distribution in a regular grid-type permafrost region provided in an embodiment of the present application;

[0021] Figure 2 A schematic diagram of temperature distribution layers in a permafrost region provided in an embodiment of the present application;

[0022] Figure 3 A schematic diagram showing the relationship between the multi-stage temperature sensor arrays provided in an embodiment of the present application;

[0023] Figure 4 A schematic diagram of the structure of a regular grid-type permafrost region ground thermal state distribution estimation device provided in an embodiment of the present application;

[0024] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Generally, the components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations.

[0026] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for protection, but merely represents selected embodiments of the present application. All other embodiments obtained by persons of ordinary skill in the art based on the embodiments in the present application without creative work are within the scope of protection of the present application.

[0027] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0028] In the description of this application, it should be noted that, in addition, the terms "first", "second", "third", etc. are used only to distinguish descriptions and should not be understood as indicating or implying relative importance. In addition, the terms "comprise", "include" or any other variations are intended to cover non-exclusive inclusion, so that a process, method, article or device that includes a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device that includes the element.

[0029] Based on the above statement, as introduced in the background technology, traditional permafrost engineering and permafrost drilling temperature detection have problems of ecological damage and scale effect of the monitoring system.

[0030] In this regard, it should be understood that in related technologies, geological surveys mainly rely on borehole drilling and temperature chain temperature measurement to obtain the thermal state of permafrost. However, during the process of drilling rigs entering the site and drilling, it will cause great damage to the surrounding vegetation and soil, especially in the alpine permafrost areas with harsh climate environments, and these damages are difficult to recover. Permafrost drilling may even lead to ecological degradation and aggravate problems such as black soil flattening, land sandification and desertification in alpine grasslands. Therefore, how to non-destructively obtain the thermal state of permafrost to guide permafrost engineering construction practices and permafrost ecological environment assessments has become one of the major issues that urgently need to be solved in the fields of geoengineering and environmental science and technology.

[0031] Furthermore, when conducting ecological and environmental assessments, predicting freeze-thaw disasters, and designing and constructing frozen soil projects, whether using permafrost drilling or self-recording thermometers to monitor the thermal state of permafrost, the monitoring system faces the issue of scale effects. Specifically, how should the distances between adjacent monitoring points be set? If the distances between adjacent monitoring points are too far, insufficient data coverage will inevitably occur due to the spatial heterogeneity of geographic elements. Conversely, if the distances between adjacent monitoring points are too close, strong spatial autocorrelation will result, significantly increasing monitoring costs and consuming more manpower and financial resources. Therefore, how to appropriately determine the spatial scale for monitoring permafrost elements has become a critical issue in the fields of physical geography and geographic information systems.

[0032] Based on the discovery of the above technical problems, the inventors have proposed the following technical solutions after creative work to solve or improve the above problems. It should be noted that the defects existing in the solutions in the above prior art are the results obtained by the inventors after practice and careful research. Therefore, the discovery process of the above problems and the solutions proposed in the embodiments of this application below for the above problems should all be the contributions made by the inventors to this application in the process of invention and creation, and should not be understood as technical contents known to those skilled in the art.

[0033] In view of this, the embodiment of the present application (hereinafter referred to as the present embodiment) provides a method for estimating the ground thermal state distribution in a regular grid-type permafrost region. Figure 1 As shown, the method includes:

[0034] S1, obtain the measured temperature information and predicted temperature information of the target permafrost area.

[0035] The measured temperature information includes the measured ground temperature at various observation scales, and the predicted temperature information includes the predicted ground temperature at various observation scales.

[0036] S2, correcting the predicted temperature information through the pre-built semivariogram model to obtain the optimized predicted temperature information.

[0037] Among them, the semivariogram model characterizes the distance of measurement error, spatial variability, and spatial autocorrelation of ground temperature in the target permafrost area.

[0038] S3, fusing the optimized predicted temperature information with the measured temperature information to obtain the ground temperature information of the target permafrost area.

[0039] S4, generating a ground thermal state distribution map of the target permafrost area according to the ground temperature information of the target permafrost area.

[0040] In this way, by using the predicted ground temperature and the measured ground temperature at different scales, the thermal state of permafrost can be obtained non-destructively, and a ground thermal state distribution map can be generated at a reasonably set monitoring spatial scale, thereby effectively guiding engineering construction practice and ecological environmental assessment.

[0041] For the regular grid type permafrost area ground thermal state distribution estimation method provided in this embodiment, the electronic device implementing the method may be, but is not limited to, a mobile terminal, a tablet computer, a laptop computer, a desktop computer, and a server, etc. The server may be a single server or a server group. The server group may be centralized or distributed (for example, the server may be a distributed system). In some embodiments, the server may be local or remote relative to the user terminal. In some embodiments, the server may be implemented on a cloud platform; as an example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud (Community Cloud), a distributed cloud, an inter-cloud (Inter-Cloud), a multi-cloud (Multi-Cloud), etc., or any combination thereof. In some embodiments, the server may be implemented on an electronic device having one or more components.

[0042] In order to make the solution provided by this embodiment clearer, the following uses a server as an electronic device to implement the method. Figure 1 Each step in the flowchart is described in detail. However, it should be understood that the operations in the flowchart can be implemented in a non-sequential manner, and steps that have no logical contextual relationship can be reversed or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart or remove one or more operations from the flowchart under the guidance of the content of this application. Therefore, continue to refer to Figure 1 , the method comprising:

[0043] S1, obtain the measured temperature information and predicted temperature information of the target permafrost area.

[0044] The measured temperature information includes the measured ground temperature at various observation scales, and the predicted temperature information includes the predicted ground temperature at various observation scales.

[0045] In this embodiment, the target permafrost area refers to an area where the ground thermal state is unknown. First, a pre-trained temperature prediction model is used to generate predicted temperature information at multiple observation scales based on vegetation, soil, climate, and terrain information. However, since the prediction model may contain certain errors, it needs to be corrected using measured temperature information obtained by a multi-stage temperature sensor array. Therefore, as an optional embodiment, step S1 may include:

[0046] S1-1, obtain vegetation information, soil information, climate information and terrain information of the target permafrost area.

[0047] S1-2 processes vegetation information, soil information, climate information and terrain information through a pre-trained temperature prediction model to obtain the predicted temperature information of the target permafrost area.

[0048] The following describes how to train the temperature prediction model. Training the model involves data collection, data preprocessing, feature extraction and dimensionality reduction, and model training to ensure the model can accurately predict ground temperatures in permafrost areas.

[0049] Before explaining the training method of the above temperature prediction model, it should be noted that the ground temperature in this embodiment refers to the temperature at a specific depth. Figure 2 As shown, the temperature distribution layers in the permafrost zone include the boundary layer, land surface, ground, active layer, and permafrost layer. Among them, the detection position of the ground temperature is located at a depth of 0-10 cm from the root system of vegetation, and near-ground air temperature and land surface temperature observations are arranged according to the differences in altitude and terrain. However, the current methods based on MODIS thermal infrared land surface temperature calculation or using it to drive frozen soil simulation mapping, the thermal infrared land surface temperature that can be detected is the temperature of the vegetation or snow canopy. These studies do not take into account the complex thermal effects of vegetation or snow, so there is an essential difference between the thermal infrared land surface temperature and the ground temperature. The ground temperature in this embodiment is the temperature at a depth of 0-10 cm from the root system of vegetation, which is the real upper boundary condition for empirical or physical process frozen soil simulation mapping.

[0050] Furthermore, the aforementioned multiple observation scales exhibit a gradual transition pattern. Therefore, training samples also need to be collected at multiple observation scales to reveal the scale effect of ground temperature. To this end, a multi-level temperature sensor array is deployed in the target permafrost area. The lower-level arrays in the multi-level temperature sensor array are distributed within the grid of the upper-level array. The lower and upper arrays contain the same number of temperature sensors with the same distribution pattern.

[0051] In this way, data collection at different observation scales is achieved by deploying multi-level temperature sensor arrays within the target permafrost region. These sensor arrays are distributed according to a specific pattern to ensure that data collection at each scale complements and supports each other. For example, a higher-level array may cover a wider area, while lower-level arrays perform more detailed measurements within the grid of the higher-level array. Therefore, this hierarchical sensor deployment not only improves the richness and accuracy of data but also helps identify temperature variation patterns and anomalies at different scales, temperature measurement errors, and spatial autocorrelation distances.

[0052] (1) During the data collection phase, in order to better reveal the scale effect of ground temperature, a regular grid was laid out in the target permafrost area for monitoring. Figure 3 As shown in the figure, for the target permafrost region, the proposed scheme uses a progressive multi-scale regular grid for sensor deployment. Specifically, three grid cell sizes (10m×10m, 100m×100m, and 1000m×1000m) are set up within the study area, with temperature sensors evenly distributed within each grid cell. Small-scale (10m×10m) grids are used to capture microenvironmental changes and are suitable for studying the thermal characteristics of local permafrost. Medium-scale (100m×100m) grids are used for long-term trend analysis and are suitable for monitoring the thermal state of large-scale permafrost regions. Large-scale (1000m×1000m) grids are used for regional spatial distribution estimation, providing data support for large-scale permafrost modeling.

[0053] Second, within each regular grid cell, sensors are placed in a hierarchical nested pattern. That is, sensors in lower-level grids are distributed across sub-cells of higher-level grids, maintaining the same number and distribution pattern. For example, within a 100m×100m grid, temperature sensors are evenly distributed within selected 10m×10m sub-grids, ensuring comparability and consistency of data at multiple scales. This nested sensor placement not only increases the spatial resolution of the data but also improves prediction accuracy by fusing data at different scales.

[0054] In addition, since the near-surface air temperature is less affected by turbulence and surface cover, only 1-2 near-surface air temperature and land surface temperature observations are deployed in each 100m×100m and 1000m×1000m site. Additional near-surface air temperature and land surface temperature observations are only considered when the terrain is highly undulating (the altitude difference exceeds 50m).

[0055] At the same time, we use a variety of data collection methods, such as remote sensing images, ground observations, drone mapping, weather station monitoring, and historical data collection, to obtain vegetation information, soil information, climate information, and terrain information for each grid node (also known as an observation point). The following is a detailed description of how to obtain this information:

[0056] Vegetation information is primarily obtained through ground sample surveys, satellite remote sensing imagery, and drone multispectral mapping. Vegetation indices (NDVI and EVI) are calculated using satellite remote sensing data from Landsat, MODIS, and other satellites to assess vegetation coverage and health. High-resolution vegetation indices are also obtained through drone hyperspectral imaging. Combined with ground sample surveys to measure vegetation height and aboveground biomass, these indices refine the impact of vegetation on surface temperature.

[0057] Soil information is obtained through a combination of ground sampling, laboratory analysis, and remote sensing inversion. Ground surveys utilize root drilling sampling to measure key parameters such as soil texture, moisture content, organic matter content, and dry bulk density. Laboratory analysis further determines soil thermophysical properties such as thermal conductivity and thermal diffusivity. Furthermore, soil moisture information is extracted using thermal infrared and microwave remote sensing, and spatial interpolation is performed through geostatistical analysis to compensate for the limitations of observation points.

[0058] Climate information can be collected through ground-based meteorological station monitoring, long-term meteorological data, and reanalysis data. Specifically, automatic weather stations can be deployed in the study area to monitor key meteorological parameters such as air temperature, precipitation, wind speed and direction, and relative humidity in real time. Global meteorological reanalysis data, such as ERA5-Land and GLDAS, can also be collected to provide long-term climate background information. This data can then be integrated with measured data to improve its spatial and temporal resolution.

[0059] Topographic information is primarily obtained through digital elevation models (DEMs), drone mapping, and ground-based RTK measurements. Basic topographic factors such as elevation, slope, and aspect are extracted using global DEM data such as SRTM and ASTERGDEM. Furthermore, for key research areas, drone LiDAR scanning provides high-precision microtopographic information. This is combined with RTK (Real-Time Kinematic Positioning) and CORS (Continuously Operating Reference Station) technology for precise measurements to analyze the impact of local topography on ground temperature.

[0060] (2) In the data preprocessing stage, a series of data cleaning and standardization measures were taken in this example to improve data quality and consistency. First, missing data were filled by removing outliers and interpolating methods to reduce data noise. Then, time series alignment was performed for data at different time scales (such as ground monitoring data at the hourly level, while satellite remote sensing data is usually only at the daily level) to ensure data matching. In the spatial dimension, point data and raster data were unified by resampling methods to make them consistent with regular grid-type observation data to ensure the effectiveness of subsequent model training.

[0061] (3) In the feature extraction and dimensionality reduction stage, in order to improve the generalization ability of the model, this example uses principal component analysis (PCA) to reduce the dimensionality of high-dimensional environmental variables (such as multiple meteorological, soil, and vegetation indicators) and extract the key factors that mainly affect ground temperature changes. At the same time, new feature variables are constructed, such as the interaction term between vegetation index and air temperature, and the combined factor of slope and soil moisture, to enhance the predictive ability of the model. In addition, correlation analysis and SHAP (Shapley Additive Explanations) method are used to evaluate the contribution of each feature to ground temperature prediction, and the most representative variables are selected to reduce redundant information and improve computational efficiency.

[0062] (4) In the model training phase, this example uses XGBoost (Extreme Gradient Boosting Decision Tree) as the core temperature prediction model. It should be understood that XGBoost was chosen because the model can effectively process high-dimensional data, use nonlinear relationships to improve prediction accuracy, and has the ability to automatically handle missing values and reduce the risk of overfitting through regularization. The training process first divides the data set into 75% training set and 25% test set to ensure the generalization ability of the model. Subsequently, the model hyperparameters, including the maximum depth of the tree, learning rate, and subsampling rate, are initialized, and error minimization optimization is performed on the training data.

[0063] The sensor array deployed above can not only be used to collect data for model training, but also, after model training is complete, continue to collect measured temperature information to calibrate the predicted temperature information at other locations in the target permafrost area. Therefore, the server can also obtain the measured temperature information of the target permafrost area through a multi-level temperature sensor array deployed in the target permafrost area, where the lower-level arrays in the multi-level temperature sensor array are distributed in the grid of the upper-level array, and the lower-level arrays and the upper-level arrays include the same number and distribution of temperature sensors.

[0064] Based on the above description of step S1, the following Figure 1 Step S2 in the following is explained:

[0065] S2, correcting the predicted temperature information through the pre-built semivariogram model to obtain the optimized predicted temperature information.

[0066] Among them, the semivariogram model characterizes the measurement error, spatial variability, and distance of spatial autocorrelation of ground temperature in the target permafrost area. The first thing to understand here is that the semivariogram model is a tool in geostatistics used to describe the autocorrelation of spatial data, that is, how the similarity between data values changes with the increase of spatial distance. The model calculates the semivariance between data points of different spacings, draws a semivariogram curve, and fits it using a mathematical model (such as an exponential model, a Gaussian model, or a spherical model). The semivariogram model is widely used in spatial interpolation (such as Kriging interpolation) and error correction, and can be used to optimize the prediction results of environmental variables (such as temperature, humidity, soil moisture, etc.) and improve the spatial consistency and accuracy of the data.

[0067] Therefore, in Figure 1 Before step S2, the server also performs spatial variation analysis based on the measured temperature information to obtain a semivariogram curve; and fits a semivariogram model based on the semivariogram curve.

[0068] In the implementation details, the server can first perform data normality and trend effect analysis on the measured temperature information to evaluate the distribution characteristics of the measured temperature information obtained and its overall change trend in space. Among them, data normality analysis takes into account that when performing spatial statistical modeling (such as Kriging interpolation), many geostatistical methods require the data to satisfy the normal distribution. If the data deviates from the normal distribution, it may affect the accuracy of spatial interpolation. Therefore, it is first necessary to verify whether the measured temperature information conforms to the normal distribution. The trend effect analysis is used to indicate whether there is a systematic change pattern in the ground temperature data in space. For example, whether the ground temperature shows an upward or downward trend with changes in latitude, longitude, altitude or other geographical factors. If there is an obvious trend effect in the data, directly using spatial interpolation methods such as Kriging interpolation may lead to errors, so the trend needs to be modeled and removed before interpolation.

[0069] Then, a spatial variability analysis is conducted on the target permafrost area to determine the variation patterns of ground temperature at different spatial scales. Since the ground temperature in permafrost areas is affected by a variety of environmental factors (such as altitude, soil moisture, vegetation coverage, etc.), it often presents a non-uniform distribution in space. Therefore, it is necessary to use the semivariogram as a tool to measure the spatial autocorrelation distance of temperature. Its core idea is to calculate the temperature difference between any two observation points and thereby reveal the correlation of temperature at different spatial distances. The calculation formula of the semivariogram is as follows:

[0070]

[0071] Where y(h) represents the semivariogram, N(h) represents the number of observation points with a distance of h, and Z(x i) and Z(x i +h) represents the ground temperature at a distance h. Therefore, by calculating the semivariogram at different distances h, we can obtain a semivariogram curve, thereby analyzing the spatial autocorrelation of ground temperature. In this example, to further analyze whether spatial heterogeneity is directional, we calculated the semivariogram at different angles (0°, 45°, 90°, and 135°).

[0072] Next, the server needs to select an appropriate mathematical model to fit the calculated semivariogram curve, such as an exponential model, a spherical model, or a Gaussian model, to construct a semivariogram model. This is to study the spatial distribution and correlation of ground temperatures at different grid points. For example, using an exponential model:

[0073]

[0074] In the formula, a represents the range, which indicates the maximum distance of spatial autocorrelation; when this distance is exceeded, the correlation between temperature data tends to disappear; C represents the structural variance, C0 is the nugget value, which represents the semivariogram value when the distance is zero, reflecting the measurement error or temperature fluctuation at the microscopic scale; (C+C0) is the base value, which represents the maximum value of the semivariogram, reflecting the overall variation of ground temperature. Therefore, C / (C + C0) represents the degree of spatial correlation of the system variables. <25%, 25-75%, and >75% indicate weak, moderate, and strong spatial correlation of ground temperature, respectively. This example uses the least squares method to fit model parameters and employs cross-validation and residual analysis for model validation and optimization. Therefore, the key parameters of the semivariogram model can be used to assess measurement error and the variability of measured values, while also determining the maximum distance of spatial autocorrelation, providing a basis for setting distances between observation points.

[0075] Based on the obtained semivariogram model, the server can use it to correct the predicted temperature information. It should be understood that since the predicted temperature information is typically derived from environmental variables (such as vegetation, soil, climate, and topography) using machine learning models like XGBoost, it may contain certain deviations. Therefore, the predicted temperature information corrected by the semivariogram model can more accurately reflect the true spatial distribution characteristics of ground temperature.

[0076] Based on the above description of step S3, Figure 1 Steps S3 and S4 in FIG. 1 are described as follows:

[0077] S3, fusing the optimized predicted temperature information with the measured temperature information to obtain the ground temperature information of the target permafrost area.

[0078] In this regard, it can be understood that what the grid measures is the ground temperature data of a small range in the target permafrost area, that is, local, discrete high-precision observation point data collected by sensors arranged in a regular grid. These data have high temporal resolution (such as collecting once every half hour), but have limited coverage and are limited to the area where the sensors are arranged. The predicted surface temperature information is large-scale, that is, based on remote sensing data (such as MODIS, Landsat thermal infrared images) and machine learning models (XGBoost), the ground temperature of the entire permafrost area is inferred. Therefore, the present embodiment can match and fuse the optimized predicted temperature information with the measured temperature information on a spatial and temporal scale to improve the accuracy and completeness of the ground temperature estimation.

[0079] S4, generating a ground thermal state distribution map of the target permafrost area according to the ground temperature information of the target permafrost area.

[0080] In this embodiment, the server can perform spatial interpolation based on the spatial autocorrelation information of the ground temperature in the target permafrost area and the ground temperature information of the target permafrost area to obtain the temperature distribution information of the target permafrost area; and generate a ground thermal state distribution map of the target permafrost area based on the temperature distribution information.

[0081] This means that when generating a ground thermal distribution map for a target permafrost region, the server first processes the ground temperature information using spatial autocorrelation analysis to determine its spatial correlation and changing trends. Since spatial autocorrelation analysis focuses on determining the similarity of ground temperatures between adjacent regions—that is, the degree of spatial clustering or dispersion of temperature data—it can reveal the distribution characteristics of ground temperature at different spatial scales, providing theoretical support for subsequent interpolation calculations.

[0082] After obtaining spatial autocorrelation information, the next step is to interpolate the ground temperature of the target permafrost area based on this information. This involves spatially supplementing and optimizing the temperature data through interpolation to improve the accuracy of the temperature distribution. During this process, the server can use kriging interpolation, which uses the temperature values of known points based on a semivariogram model to infer the temperature values of unknown points. Kriging interpolation not only accounts for spatial autocorrelation but also fine-tunes the spatial variability of temperature data through range, nugget value, and sill value, thereby obtaining more accurate temperature distribution information.

[0083] After completing the interpolation calculation, the temperature distribution information of the target permafrost area is obtained. The server can further use the geographic information system (GIS) to visualize the data and ultimately generate a ground thermal state distribution map of the target permafrost area. In the GIS environment, different spatial mapping methods can be used, such as isotherm drawing, heat maps, or graded color filling, to make the spatial distribution characteristics of ground temperature more intuitive. At the same time, combined with environmental factors such as vegetation, soil, and topography, the relationship between temperature distribution and environmental factors can be further analyzed, providing a scientific basis for ecological and environmental monitoring, engineering construction, and climate change research in permafrost areas.

[0084] This method, developed in this paper, can provide high-precision predictions and spatial distribution mapping of ground thermal conditions in permafrost regions, improving the accuracy and spatial consistency of temperature estimates. Furthermore, through multi-scale data fusion, the integrity and reliability of temperature monitoring are enhanced, while reducing the ecological impact of traditional temperature measurement methods.

[0085] Based on the same inventive concept as the method for estimating the ground thermal state distribution in a regular grid type frozen soil area provided in this embodiment, this embodiment also provides a device for estimating the ground thermal state distribution in a regular grid type frozen soil area, which includes at least one software function module that can be stored in a memory or solidified in an electronic device in the form of software. The processor in the electronic device is used to execute the executable module stored in the memory. For example, the software function module and computer program included in the device. Please refer to Figure 4 Functionally, the device can include:

[0086] A temperature acquisition module 11 is configured to acquire measured temperature information and predicted temperature information of a target frozen ground area, wherein the measured temperature information includes measured ground temperatures at various observation scales, and the predicted temperature information includes predicted ground temperatures at various observation scales;

[0087] a temperature optimization module 12, configured to correct the predicted temperature information using a pre-built semivariogram model to obtain optimized predicted temperature information, wherein the semivariogram model characterizes the measurement error, spatial variability, and maximum distance of spatial autocorrelation of the ground temperature in the target permafrost region;

[0088] The temperature optimization module 12 is further used to fuse the optimized predicted temperature information with the measured temperature information to obtain the ground temperature information of the target frozen soil area;

[0089] The image drawing module 13 is used to generate a ground thermal state distribution map of the target frozen soil area according to the ground temperature information of the target frozen soil area.

[0090] In this embodiment, the temperature acquisition module 11 is used to implement Figure 1 Step S1 in the temperature optimization module 12 is used to achieve Figure 1 Steps S2 and S3 in the image drawing module 13 are used to implement Figure 1 Therefore, for a detailed description of each of the above modules, please refer to the specific implementation of the corresponding step.

[0091] In addition, since the method for estimating the ground thermal state distribution in a regular grid type permafrost area provided in this embodiment has the same inventive concept, the device for estimating the ground thermal state distribution in a regular grid type permafrost area can also implement other steps or sub-steps of the method through the above-mentioned modules.

[0092] Optionally, the temperature acquisition module 11 is further specifically configured to:

[0093] The measured temperature information of the target permafrost area is obtained through a multi-level temperature sensor array deployed in the target permafrost area, wherein the lower array in the multi-level temperature sensor array is distributed in the grid in the upper array, and the lower array and the upper array include the same number of temperature sensors and have the same distribution pattern.

[0094] Optionally, the temperature acquisition module 11 is further specifically configured to:

[0095] Obtain vegetation information, soil information, climate information and terrain information of the target permafrost area;

[0096] The vegetation information, soil information, climate information and terrain information are processed through a pre-trained temperature prediction model to obtain the predicted temperature information of the target permafrost area.

[0097] Optionally, before correcting the predicted temperature information using the pre-built semivariogram model, the temperature optimization module 12 is further configured to:

[0098] According to the measured temperature information, spatial variation analysis is carried out to obtain the semivariogram curve;

[0099] According to the semivariogram curve, the semivariogram model is fitted.

[0100] Optionally, the image drawing module 13 is further specifically configured to:

[0101] performing spatial interpolation based on the spatial autocorrelation information of the ground temperature of the target frozen soil area and the ground temperature information of the target frozen soil area to obtain the temperature distribution information of the target frozen soil area;

[0102] Based on the temperature distribution information, a ground thermal state distribution map of the target permafrost area is generated.

[0103] In addition, the functional modules in each embodiment of the present 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.

[0104] It should also be understood that if the above embodiments are implemented in the form of software function 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 the present application, 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, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application.

[0105] Therefore, this embodiment further provides a storage medium storing a computer program that, when executed by a processor, implements the method for estimating ground thermal state distribution in a regular grid-type frozen soil region provided in this embodiment. The storage medium can be any medium capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0106] This embodiment provides an electronic device for implementing a method for estimating the ground thermal state distribution in a regular grid-type frozen soil area. Figure 5 As shown, the electronic device may include a processor 22 and a memory 21. In addition, the memory 21 stores a computer program, and the processor implements the method for estimating the ground thermal state distribution in a regular grid-type frozen soil area provided in this embodiment by reading and executing the computer program corresponding to the above embodiment in the memory 21.

[0107] Continue to see Figure 5 The electronic device further includes a communication unit 23. The memory 21, the processor 22 and the communication unit 23 are electrically connected to each other directly or indirectly via a system bus 24 to achieve data transmission or interaction.

[0108] The memory 21 may be an information recording device based on any electronic, magnetic, optical or other physical principles, for recording execution instructions, data, etc. In some embodiments, the memory 21 may be, but is not limited to, a volatile memory, a non-volatile memory, a storage drive, etc.

[0109] In some embodiments, the volatile memory may be a random access memory (RAM); in some embodiments, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, etc.; in some embodiments, the storage drive may be a magnetic disk drive, a solid-state drive, any type of storage disk (such as a CD, DVD, etc.), or a similar storage medium, or a combination thereof.

[0110] The communication unit 23 is used to send and receive data through 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 wide area network (WAN), 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 a wired or wireless network access point, such as a base station and / or a network switching node, through which one or more components of the service request processing system can connect to the network to exchange data and / or information.

[0111] The processor 22 may be an integrated circuit chip having 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 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 physical 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 computer (RISC), or a microprocessor, or any combination thereof.

[0112] I understand. Figure 5 The structure shown is for illustration only. The electronic device 100 may also have Figure 5 More or fewer components than shown, or with Figure 5 Different configurations shown. Figure 5 The components shown may be implemented in hardware, software, or a combination thereof.

[0113] It should be understood that the devices and methods disclosed in the above embodiments may also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of the devices, methods, and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a portion of code, which contains 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 box may also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes may actually be executed substantially in parallel, or they may sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, may be implemented using a dedicated hardware-based system that performs a specified function or action, or may be implemented using a combination of dedicated hardware and computer instructions.

[0114] The above descriptions are merely examples of various embodiments of the present application, but the scope of protection of the present application is not limited thereto. Any modifications or substitutions that can be readily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included within the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A method for estimating the ground thermal state distribution in a regular grid-type frozen soil area, characterized in that: The method comprises: Obtaining measured temperature information and predicted temperature information for the target permafrost area, wherein the measured temperature information includes measured ground temperatures at multiple observation scales, and the predicted temperature information includes predicted ground temperatures at the multiple observation scales, wherein the multiple observation scales exhibit a gradual transition pattern. This step specifically includes: Obtaining measured temperature information of the target frozen soil area through a multi-stage temperature sensor array deployed in the target frozen soil area, wherein a lower-stage array in the multi-stage temperature sensor array is distributed in a grid in an upper-stage array, and the lower-stage array and the upper-stage array include the same number of temperature sensors and have the same distribution pattern; Obtaining vegetation information, soil information, climate information, and terrain information of the target permafrost area; Processing the vegetation information, soil information, climate information, and terrain information through a pre-trained temperature prediction model to obtain predicted temperature information of the target permafrost area; Correcting the predicted temperature information using a pre-constructed semivariogram model to obtain optimized predicted temperature information, wherein the semivariogram model characterizes the measurement error, spatial variability, and maximum distance of spatial autocorrelation of the ground temperature in the target permafrost area; fusing the optimized predicted temperature information with the measured temperature information to obtain ground temperature information of the target frozen soil area; A ground thermal state distribution map of the target permafrost area is generated based on the ground temperature information of the target permafrost area.

2. The method for estimating ground thermal state distribution in a regular grid-type frozen soil region according to claim 1, characterized in that: The temperature prediction model is obtained by training the XGboost model with sample data.

3. The method for estimating ground thermal state distribution in a regular grid-type frozen soil region according to claim 1, characterized in that: Before correcting the predicted temperature information using a pre-built semivariogram model, the method further includes: Performing spatial variation analysis based on the measured temperature information to obtain a semivariogram curve; The semivariogram model is fitted according to the semivariogram curve.

4. The method for estimating ground thermal state distribution in a regular grid-type frozen soil region according to claim 1, characterized in that: Generating a ground thermal state distribution map of the target permafrost area according to the ground temperature information of the target permafrost area includes: performing spatial interpolation based on the spatial autocorrelation information of the ground temperature of the target frozen soil area and the ground temperature information of the target frozen soil area to obtain the temperature distribution information of the target frozen soil area; A ground thermal state distribution map of the target permafrost area is generated based on the temperature distribution information.

5. A regular grid-type permafrost region ground thermal state distribution estimation device, characterized in that: The device comprises: A temperature acquisition module is configured to acquire measured temperature information and predicted temperature information of a target frozen ground area, wherein the measured temperature information includes measured ground temperatures at multiple observation scales, and the predicted temperature information includes predicted ground temperatures at the multiple observation scales, wherein the multiple observation scales exhibit a gradual transition pattern. The temperature acquisition module is further configured to: Obtaining measured temperature information of the target frozen soil area through a multi-stage temperature sensor array deployed in the target frozen soil area, wherein a lower-stage array in the multi-stage temperature sensor array is distributed in a grid in an upper-stage array, and the lower-stage array and the upper-stage array include the same number of temperature sensors and have the same distribution pattern; Obtaining vegetation information, soil information, climate information, and terrain information of the target permafrost area; Processing the vegetation information, soil information, climate information, and terrain information through a pre-trained temperature prediction model to obtain predicted temperature information of the target permafrost area; a temperature optimization module, configured to correct the predicted temperature information using a pre-constructed semivariogram model to obtain optimized predicted temperature information, wherein the semivariogram model characterizes the measurement error, spatial variability, and maximum distance of spatial autocorrelation of the ground temperature in the target permafrost area; The temperature optimization module is further configured to fuse the optimized predicted temperature information with the measured temperature information to obtain ground temperature information of the target frozen soil area; The image drawing module is used to generate a ground thermal state distribution map of the target permafrost area according to the ground temperature information of the target permafrost area.

6. A storage medium, characterized in that The storage medium stores a computer program, and when the computer program is executed by the processor, the method for estimating the ground thermal state distribution in a regular grid-type permafrost area according to any one of claims 1 to 4 is implemented.

7. An electronic device, characterized in that: The electronic device includes a processor and a memory, the memory stores a computer program, and when the computer program is executed by the processor, the method for estimating the ground thermal state distribution in a regular grid-type permafrost area according to any one of claims 1 to 4 is implemented.

Images