Freeze-thaw risk identification and evaluation system and method for black soil high-standard farmland construction

Abstract

The invention relates to the technical field of risk analysis suitable for administrative purposes, and provides a freezing and thawing risk identification and evaluation system and method for black soil high-standard farmland construction. The system comprises a black soil high-standard farmland construction freeze-thaw area identification unit, a freeze-thaw risk area delimiting subunit, a freeze-thaw hazard prediction unit, a construction risk early warning and prevention measure suggestion unit and a freeze-thaw area black soil high-standard farmland construction comprehensive evaluation unit. Drawing a freeze-thaw space-time distribution diagram; performing overlay analysis on the freeze-thaw space-time distribution diagram, the regional black soil distribution diagram and the high-standard farmland plot distribution diagram; constructing a freeze-thaw hazard prediction model; according to a freeze-thaw hazard prediction result, a freeze-thaw prevention measure is given; and comprehensively evaluating the freeze-thaw risk resistance of the high-standard farmland. The system can accurately identify the freeze-thaw risk area of black soil high-standard farmland construction, and effectively assesses the freeze-thaw risk resistance of the high-standard farmland.

Description

Technical Field

[0001] This application relates to the technical field of risk analysis applicable to administrative purposes, and particularly relates to a system and method for identifying and evaluating freeze-thaw risks in the construction of high-standard farmland on black soil. Background Art

[0002] Black soil plays an extremely important role in agricultural production. By constructing a high-standard farmland, a perfect irrigation and drainage system, field roads and ecological protection systems are built, effectively improving the grain production capacity of black soil and achieving stable yields in both drought and flood.

[0003] The black soil in China is mainly concentrated in the Northeast region, which is a typical seasonal freeze-thaw area. Its freeze-thaw process has an important impact on agricultural production and farmland infrastructure construction. In particular, the damage to high-standard farmland roads and irrigation channels caused by freeze-thaw is extremely high, and problems such as thaw settlement, cracks, and deformation are common. The existing high-standard farmland construction evaluation system mainly evaluates the general high-standard farmland construction. Experience shows that directly applying the general high-standard farmland construction technology to the construction of high-standard farmland on black soil is prone to deviation and cannot meet the actual needs of high-standard farmland construction in the black soil area. Therefore, there is an urgent need to provide an improved technical solution to address the deficiencies of the above existing technologies. Summary of the Invention

[0004] The purpose of this application is to solve the problem of the lack of a response mechanism for freeze-thaw risks in the planning and evaluation process of high-standard farmland construction in the Northeast black soil area. Based on the above goal, a system and method for identifying and evaluating freeze-thaw risks in the construction of high-standard farmland on black soil are provided. This technical solution is used to improve the planning and evaluation mechanism of high-standard farmland construction on black soil in seasonal freeze-thaw areas and meet the actual needs of high-standard farmland construction in the black soil area.

[0005] To achieve the above purpose, this application provides the following technical solutions: This application provides a system for identifying and evaluating freeze-thaw risks in the construction of high-standard farmland on black soil, including: A freeze-thaw area identification unit for high-standard farmland construction on black soil, which is used to identify freeze-thaw risk areas based on meteorological data through the fusion index method, and then draw a freeze-thaw spatio-temporal distribution map; the fusion index method refers to comprehensively determining freeze-thaw risk areas based on multiple freeze-thaw indices; A freeze-thaw risk area delineation sub-unit, which is used to perform overlay analysis on the freeze-thaw spatio-temporal distribution map, the regional black soil distribution map, and the high-standard farmland plot distribution map to obtain the freeze-thaw risk area for high-standard farmland construction on black soil; A freeze-thaw hazard prediction unit, which is used to construct a freeze-thaw hazard prediction model and perform freeze-thaw hazard prediction based on the freeze-thaw risk area for high-standard farmland construction on black soil to obtain a freeze-thaw hazard prediction result; A construction risk early warning and prevention measure suggestion unit, which is used to give freeze-thaw prevention measures according to the freeze-thaw hazard prediction result and in combination with the freeze-thaw risk prevention measure knowledge base for the construction of high-standard farmland on black soil. A comprehensive evaluation unit for the construction of high-standard farmland in the freeze-thaw black soil area, which is used to comprehensively evaluate the freeze-thaw risk resistance ability of the high-standard farmland constructed in the freeze-thaw black soil area.

[0006] Preferably, based on meteorological data, the freeze-thaw risk areas are identified by the fusion index method, specifically: Based on meteorological data, multiple freeze-thaw indices are calculated; According to the multiple freeze-thaw indices and a preset judgment rule, the freeze-thaw risk areas are divided into multiple risk levels to obtain the freeze-thaw risk regions.

[0007] Preferably, the freeze-thaw indices include: freezing index, freeze-thaw ratio, and freeze-thaw daily cycle days.

[0008] Preferably, the preset judgment rule includes: If the freezing index of the target area is greater than the first threshold, or the freeze-thaw ratio of the target area is less than the second threshold, or the freeze-thaw daily cycle days are greater than the third threshold, then it is judged that the target area is a freeze-thaw risk area.

[0009] Preferably, the freeze-thaw spatio-temporal distribution map is obtained through the following steps: Based on the multi-year historical meteorological data of the study area, historical freeze-thaw risk areas are obtained; Based on the future meteorological data of the study area, future freeze-thaw risk areas are predicted; The historical meteorological data and the future meteorological data are compared to obtain a comparison result; If the comparison result is less than the preset difference threshold, then the historical freeze-thaw risk area is used as the delineation result of the final freeze-thaw risk area; If the comparison result is greater than the preset difference threshold, then the union of the historical freeze-thaw risk area and the future freeze-thaw risk area is processed to obtain the delineation result of the final freeze-thaw risk area; Based on the delineation result of the final freeze-thaw risk area, the freeze-thaw spatio-temporal distribution map is output.

[0010] Preferably, the freeze-thaw hazard prediction unit further includes: a data preparation and preprocessing subunit, a model construction and verification subunit, and an application and prediction subunit; The data preparation and preprocessing subunit is used to preprocess the pre-acquired farmland environment data and farmland damage data to form modeling data, and divide the modeling data into training set data and validation set data; The model construction and verification subunit is used to construct a freeze-thaw hazard prediction model for the mapping relationship between farmland environmental variables and the damage situation of farmland freeze-thaw disasters, and use the verification set data to evaluate the accuracy of the prediction model to obtain a trained prediction model; The application and prediction subunit is used to predict the damage situation of freeze-thaw disasters in the target area by using the trained prediction model, and thus obtain the freeze-thaw hazard prediction result.

[0011] Preferably, the knowledge base for preventing freeze-thaw risks in the construction of high-standard black soil farmland is constructed based on knowledge graph technology.

[0012] This embodiment provides a method for identifying and evaluating freeze-thaw risks in the construction of high-standard black soil farmland, and the method includes: Based on meteorological data, through the fusion index method, identify the freeze-thaw risk areas, and then draw the freeze-thaw spatio-temporal distribution map; Perform overlay analysis on the freeze-thaw spatio-temporal distribution map, the regional black soil distribution map, and the high-standard farmland plot distribution map to obtain the freeze-thaw risk areas for the construction of high-standard black soil farmland; Construct a freeze-thaw hazard prediction model, and perform freeze-thaw hazard prediction based on the freeze-thaw risk areas for the construction of high-standard black soil farmland to obtain the freeze-thaw hazard prediction result; According to the freeze-thaw hazard prediction result, combined with the knowledge base for preventing freeze-thaw risks in the construction of high-standard black soil farmland, give freeze-thaw prevention measures; Comprehensively evaluate the freeze-thaw risk resistance ability of the high-standard farmland constructed in the freeze-thaw black soil area.

[0013] This embodiment provides an electronic device, including: a memory for storing instructions executed by one or more processors of the electronic device; a processor, when the processor executes the instructions in the memory, can enable the electronic device to implement the steps of the method for identifying and evaluating freeze-thaw risks in the construction of high-standard black soil farmland described in any of the above embodiments.

[0014] This embodiment provides a computer-readable storage medium, and instructions are stored on the computer-readable storage medium, and when the instructions are executed on a computer, the steps of the method for identifying and evaluating freeze-thaw risks in the construction of high-standard black soil farmland described in any of the above embodiments are implemented.

[0015] The technical solution of the embodiment of the present application has the following beneficial effects: The freeze-thaw risk identification and assessment system for black soil high-standard farmland construction provided in this embodiment aims at the deviation problems existing in applying the general high-standard farmland construction assessment to the black soil high-standard farmland construction work. By identifying the freeze-thaw risk areas and using the superposition of the freeze-thaw spatio-temporal distribution map, the regional black soil distribution map, and the high-standard farmland plot distribution map, the system obtains the accurate scope of the freeze-thaw risk area for black soil high-standard farmland construction, realizes the effective identification of freeze-thaw risks, and lays a data foundation for risk early warning and management assessment. The system uses the freeze-thaw hazard prediction model to predict the freeze-thaw hazards, obtains the prediction results of freeze-thaw hazards, and combines with the pre-constructed knowledge base of freeze-thaw risk prevention measures for black soil high-standard farmland construction to give freeze-thaw prevention measures. At the same time, based on the relevant data generated by freeze-thaw risk identification, hazard prediction, and prevention measures, the system accurately evaluates the impact of freeze-thaw in the black soil area on high-standard farmland construction, so as to meet the actual needs of high-standard farmland construction in the freeze-thaw black soil area. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 FIG. is a structural block diagram of a freeze-thaw risk identification and assessment system for black soil high-standard farmland construction according to some embodiments of the present application.

[0017] Figure 2 FIG. is a logical block diagram of a freeze-thaw risk identification and assessment system for black soil high-standard farmland construction according to some embodiments of the present application.

[0018] Figure 3 FIG. is a schematic structural diagram of an electronic device according to some embodiments of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] High-standard farmland refers to the modern agricultural production requirements of "stable production capacity, perfect facilities, good ecology, strong disaster resistance, and suitable for machine operation" achieved by comprehensively renovating and improving the original cultivated land in a certain area according to the standards of unified planning, unified design, unified construction, and unified acceptance.

[0020] The technical path of high-standard farmland construction usually includes preliminary investigation, planning and design, project construction, post-construction management, and evaluation stage. Hazard prediction and risk early warning are the key technologies to enhance the resilience of the farmland system and the disaster adaptation ability, thereby enhancing the sustainable agricultural ability. The comprehensive evaluation of high-standard farmland construction is an important link to realize the closed-loop of the technical path and promote continuous optimization.

[0021] At present, the construction work of high-standard farmland in black soil areas is usually carried out by simply transplanting the general technical path of high-standard farmland construction. There is a lack of response mechanisms for freeze-thaw damage in important links such as construction planning, construction process, and construction quality assessment, and there is no effective assessment method to characterize the impact of seasonal freeze-thaw on agricultural production and farmland infrastructure construction. However, due to the special geographical location of the black soil area, seasonal freeze-thaw has a great impact on the construction of high-standard farmland in the black soil area. If the existing general technical path of high-standard farmland construction is still used, it may lead to the inability to effectively guarantee and improve the grain production capacity of the black soil.

[0022] In view of this, this embodiment provides a freeze-thaw risk identification and assessment system for high-standard farmland construction in black soil areas. By setting up technical units such as freeze-thaw area identification for high-standard farmland construction in black soil areas, delineation of freeze-thaw risk areas, prediction of freeze-thaw hazards, construction risk warning and prevention measure suggestions, and comprehensive assessment of high-standard farmland construction in freeze-thaw areas (comprehensive construction quality assessment), it can accurately identify the freeze-thaw hazard areas and the degree of hazards. At the same time, the freeze-thaw response ability is added to the construction quality assessment system to provide technical guarantee for the high and stable yield of high-standard farmland in freeze-thaw black soil.

[0023] Taking a certain county as the research object, the embodiments of the present application will be described below with reference to the accompanying drawings.

[0024] This embodiment provides a freeze-thaw risk identification and assessment system for high-standard farmland construction in black soil areas, including: a freeze-thaw area identification unit 10 for high-standard farmland construction in black soil areas, a sub-unit 20 for delineating freeze-thaw risk areas, a freeze-thaw hazard prediction unit 30, a construction risk warning and prevention measure suggestion unit 40, and a comprehensive assessment unit 50 for high-standard farmland construction in freeze-thaw areas of black soil. Specifically: The freeze-thaw area identification unit 10 for high-standard farmland construction in black soil areas is used to identify the freeze-thaw risk areas based on meteorological data through the fusion index method, and then draw the freeze-thaw spatio-temporal distribution map; the fusion index method refers to comprehensively determining the freeze-thaw risk areas based on multiple freeze-thaw indexes.

[0025] In this embodiment, the freeze-thaw area identification unit 10 for high-standard farmland construction in black soil areas analyzes the regional freeze-thaw risk based on meteorological data, and then performs overlay analysis with the black soil distribution and the high-standard farmland plot distribution to identify the freeze-thaw areas for high-standard farmland construction in black soil.

[0026] It should be noted that meteorological data refers to various data information describing the state of the atmosphere and its changes collected through manual observations, automatic weather stations, remote sensing satellites, etc. In this embodiment, the meteorological data includes both historical meteorological data of the black soil area and future meteorological data of the black soil area. Among them, historical meteorological data are meteorological data measured in the past, usually recorded and archived in units of hours, days, and months, and these data can be obtained through relevant meteorological departments, academic research organizations, or public data. Future meteorological data can be calculated based on numerical weather prediction models (such as ECMWF, GRAPES, etc.), or obtained from public data sets of relevant departments or interfaces provided by third parties. This embodiment does not limit the acquisition method of meteorological data.

[0027] Exemplarily, meteorological data may include air temperature, precipitation, wind speed / direction, humidity, sunshine hours, air pressure, surface temperature / evapotranspiration, etc.

[0028] In this embodiment, historical meteorological data can be, for example, historical meteorological data of the study area in the past N (such as N = 10) years, including: daily average temperature and hourly temperature grid data for the number of days. Among them, the daily average temperature refers to the average value of the air temperature in a day, and the hourly temperature for the number of days refers to the measured or predicted temperature at each whole-hour point (such as 0:00, 1:00, 2:00... 23:00) in a certain day. Grid data (GridData) refers to dividing the study area into regular grids (such as 100×100 meters, 50×50 meters), and providing a meteorological value (such as temperature, humidity, etc.) at the center position of each grid.

[0029] Future meteorological data can be long-term meteorological forecast data. In addition to including the same indicators as historical meteorological data, considering the adjustment of the freeze-thaw risk area, it can also include: future monthly average temperature, temperature deviation compared with the historical same period, and extreme temperature events, etc. Among them, the future monthly average temperature refers to the predicted average air temperature for a whole month in the future. The temperature deviation compared with the historical same period refers to the difference between the temperature in the current or future period and the average temperature of the historical same period, and can also be measured by combining the average temperature and the standard deviation. Extreme temperature events refer to high-temperature or low-temperature events exceeding a certain critical value. The above meteorological data can be used not only to identify the freeze-thaw risk area, but also to determine whether the freeze-thaw risk area in the preliminary identification result of the freeze-thaw risk area needs to be adjusted.

[0030] Exemplarily, the average air temperature in January in a certain area is -3.4°C (i.e., the average temperature of the historical same period), and the standard deviation is 0.5°C. In the long-term meteorological forecast data, the monthly average temperature in January is -3.2°C, then it is determined that there is no typical difference in the climate of this area, and the preliminary identification result of the freeze-thaw risk area does not need to be adjusted.

[0031] In this embodiment, through the fusion index method, multiple indices are comprehensively analyzed to identify the risk areas. Among them, the fusion index method refers to comprehensively determining the freeze-thaw risk areas based on multiple freeze-thaw indices.

[0032] Here, the freeze-thaw index refers to an index used to quantify the number and intensity of times the temperature in a certain area crosses the 0°C critical point (freezing point). By using the fusion index method and adopting multiple freeze-thaw indices to comprehensively determine the freeze-thaw risk areas, it can alleviate the deficiency that a single index cannot comprehensively reflect the freeze-thaw risk, accurately identify the freeze-thaw disaster risk areas, and provide a basis for the construction of high-standard farmland in the black soil area of Northeast China.

[0033] Preferably, the freeze-thaw index includes: the freezing index, the freeze-thaw ratio, and the number of freeze-thaw daily cycles. These freeze-thaw indices can effectively characterize the characteristics such as the duration, degree, and frequency of freeze-thaw, laying a foundation for subsequent analysis.

[0034] Among them, the freezing index (FI) refers to the sum of the products of the number of days when the temperature is below 0°C in a year and its daily average temperature. The freeze-thaw ratio (N) refers to the ratio of the freezing index (FI) to the thawing index, which is used to reflect the heat contrast relationship between freezing and thawing in a region. The thawing index refers to the sum of the products of the number of days when the temperature is above 0°C in a year and its daily average temperature. The number of freeze-thaw daily cycles (D) refers to the number of days when the soil or the ground surface experiences the freezing and thawing processes within one day during a certain period. Specifically, it refers to the number of days when the daily maximum temperature is above 0°C and the daily minimum temperature is below 0°C.

[0035] In some embodiments, based on meteorological data, the freeze-thaw risk areas are identified through the fusion index method. Specifically: Based on meteorological data, multiple freeze-thaw indices are calculated; According to multiple freeze-thaw indices and a preset judgment rule, the freeze-thaw risk areas are divided into multiple risk levels to obtain the freeze-thaw risk regions.

[0036] Specifically, taking historical / future meteorological data (grid data) as input, multiple freeze-thaw indices are then calculated.

[0037] Furthermore, the calculation formula of the freezing index is as follows: , In the formula, is the freezing index, The daily average temperature of the th day,

[0038] The calculation formula of the freeze-thaw ratio (N) is as follows: , In the formula, N is the freeze-thaw ratio, is the melt index.

[0039] In this embodiment, the calculation time of the freeze-thaw daily cycle days (D) is one year, that is, the number of days when the soil or the ground surface experiences the freezing and thawing processes within one day is calculated.

[0040] In this embodiment, the freeze-thaw risk area is obtained through comprehensive judgment by using the fusion index method, based on multiple freeze-thaw indices, and in combination with preset judgment rules. Specifically, the preset judgment rules include: if the freezing index of the target area is greater than the first threshold, or the freeze-thaw ratio of the target area is less than the second threshold, or the freeze-thaw daily cycle days are greater than the third threshold, then it is determined that the target area is a freeze-thaw risk area.

[0041] Here, the target area refers to a certain sub-area within the study area.

[0042] In this embodiment, the freezing index being greater than the first threshold indicates a strong and continuous low-temperature process, which can reveal the development of deep frozen soil; the freeze-thaw ratio being less than the second threshold indicates a longer thawing period or a higher thawing intensity, representing stronger structural destructiveness; the freeze-thaw daily cycle days being greater than the third threshold reflects the repeated freezing and thawing of the ground surface, which is extremely likely to cause material fatigue and soil disintegration.

[0043] In this embodiment, as long as the target area meets any one of the above three conditions, it can be determined as a freeze-thaw risk area. Preferably, multiple conditions can be used for cross and comprehensive judgment of the freeze-thaw risk area.

[0044] Exemplarily, the judgment rule for the freeze-thaw risk area can be described as: If the freezing index of this area reaches 1600 °C·day, then it is determined that this area is a freeze-thaw risk area; and / or, If the freeze-thaw ratio is less than 1, then it is determined that this area is a freeze-thaw risk area; and / or, If the freeze-thaw daily cycle days are greater than 100 days, then it is determined that this area is a freeze-thaw risk area.

[0045] The judgment rule for this freeze-thaw risk area provides a quantitative and threshold-based judgment criterion, which is easy to implement batch judgment in GIS, remote sensing systems or farmland evaluation models, and the comprehensive judgment and cross judgment of multiple freeze-thaw indices can avoid misjudgment caused by a single index.

[0046] Further, based on the synthesis of the above conditions, the levels of each freeze-thaw risk area can be determined. Specifically, if the target area simultaneously meets the above three conditions, that is: the freezing index of the target area is greater than the first threshold, and the freeze-thaw ratio of the target area is less than the second threshold, and the number of freeze-thaw daily cycles is greater than the third threshold, then this area can be determined as a high freeze-thaw risk area; if it meets two of the above conditions simultaneously, then this area can be judged as a medium freeze-thaw risk area; if it only meets any one of the above conditions, then this area is judged as a low freeze-thaw risk area.

[0047] For example, based on historical meteorological data, the freezing index, freeze-thaw ratio, and number of freeze-thaw daily cycles of each grid point can be calculated, and then combined with the above judgment rules to determine the freeze-thaw risk area and its level. For example, for a certain grid point with a freezing index = 1800, a freeze-thaw ratio = 0.76, and a number of freeze-thaw daily cycles = 110, then this grid point area is determined as a high freeze-thaw risk area.

[0048] In this embodiment, based on the comprehensive determination of risks using three indices, and then dividing the levels (high, medium, low) of the freeze-thaw risk areas, it can comprehensively cover various types of freeze-thaw disasters (such as shallow freeze-thaw, deep frost heave, thermokarst subsidence, etc.), and improve the accuracy of identifying freeze-thaw risk areas.

[0049] Further, the result of dividing the levels (high, medium, low) of the freeze-thaw risk areas obtained based on historical meteorological data is called the preliminary identification result of the freeze-thaw risk area, and a preliminary identification distribution map of the freeze-thaw risk is output.

[0050] Among them, the preliminary identification distribution map of the freeze-thaw risk is a visual expression of the preliminary identification result of the freeze-thaw risk in the form of a map. For example, the high freeze-thaw risk area can be represented by red, the medium freeze-thaw risk area by orange, and the low freeze-thaw risk area by green.

[0051] Specifically, tools such as ArcGIS / QGIS / Python (matplotlib + geopandas) can be used for drawing to output the preliminary identification distribution map of the freeze-thaw risk.

[0052] Based on the preliminary identification result of the high freeze-thaw risk area, further delimit the freeze-thaw risk area and draw the freeze-thaw spatio-temporal distribution map. Preferably, the freeze-thaw spatio-temporal distribution map can be obtained through the following steps: Based on the historical meteorological data of the study area for many years (such as 10 years), identify the historical freeze-thaw risk areas; Based on the long-term meteorological forecast data (future meteorological data) of the study area, identify the future freeze-thaw risk areas; Compare the historical meteorological data with the future meteorological data to obtain the comparison result; If the comparison result is less than the preset difference threshold, the historical freeze-thaw risk area is used as the delineation result of the final freeze-thaw risk area; If the comparison result is greater than the preset difference threshold, the union of the historical freeze-thaw risk area and the future freeze-thaw risk area is processed to obtain the delineation result of the final freeze-thaw risk area; Based on the delineation result of the final freeze-thaw risk area, the freeze-thaw spatio-temporal distribution map is finally output.

[0053] In this embodiment, the identification of the historical freeze-thaw risk area and the future freeze-thaw risk area both adopts the fusion index method. The specific method refers to the description of the foregoing embodiment and will not be elaborated here.

[0054] In this embodiment, based on the historical meteorological data of the study area for many years (such as 10 years), the historical freeze-thaw risk area is identified, which is the preliminary identification result of the freeze-thaw risk area.

[0055] The purpose of comparing the historical meteorological data with the future meteorological data is to determine the difference between the historical climate and the forecast climate, so as to judge whether the preliminary identification result of the freeze-thaw risk area needs to be adjusted. If the comparison result is less than the preset difference threshold, it is determined that there is no typical difference between the future meteorological data and the historical meteorological data of the same period. At this time, the historical freeze-thaw risk area is used as the delineation result of the final freeze-thaw risk area. Among them, the difference threshold can be a range value, such as the average value ± 2 times the standard deviation.

[0056] That is to say, if the comparison result has a small difference (for example, it does not exceed the average value ± 2 times the standard deviation), the historical freeze-thaw risk area is used as the delineation result of the final freeze-thaw risk area; otherwise, if the long-term meteorological forecast data has a large difference from the historical meteorological data (for example, it exceeds the average value ± 2 times the standard deviation), the freeze-thaw risk area is adjusted. The specific adjustment method is to take the union of the historical freeze-thaw risk area and the future freeze-thaw risk area, and finally output the freeze-thaw spatio-temporal distribution map.

[0057] For example, taking temperature as an example, according to the historical meteorological data, the average temperature in January in a certain area is -3.4°C, and the standard deviation is 0.5°C. The long-term forecast data shows that the average monthly temperature in January in this area is -3.2°C, then it is determined that there is no typical difference (small difference). Then, the deviation between the long-term forecast data and the corresponding months (such as February, March... December) in the historical meteorological data is judged month by month (such as February, March... December) in the same way. If there is no typical difference between the annual (January to December) climate and the historical climate, the preliminary identification distribution result of the freeze-thaw risk is the final result. The freeze-thaw risk area identified in this step is used as the key research area for subsequent risk prediction and assessment.

[0058] If the climate of the forecast data for the whole year (January - December) is significantly different from the historical climate, it is necessary to adjust the preliminary identification results of the freeze-thaw risk area. The specific adjustment method is as follows: Take the union of the historical freeze-thaw risk area and the future freeze-thaw risk area to obtain the final delineation result of the freeze-thaw risk area.

[0059] It should be noted that the difference between historical meteorological data and future meteorological data can also be judged based on the comparison results of meteorological data such as air pressure, humidity, wind speed / direction, etc. The specific operation method is the same as that for air temperature determination and will not be elaborated here.

[0060] Based on the accurate identification of the freeze-thaw risk area and the drawing of the freeze-thaw spatio-temporal distribution map, in this embodiment, the freeze-thaw risk area delineation sub-unit 20 is used to perform an overlay analysis on the freeze-thaw spatio-temporal distribution map, the regional black soil distribution map, and the high-standard farmland plot distribution map to obtain the freeze-thaw risk area for black soil high-standard farmland construction.

[0061] The purpose of the freeze-thaw risk area delineation sub-unit 20 is to obtain the freeze-thaw risk zoning for black soil high-standard farmland construction.

[0062] Here, the overlay analysis (Spatial Overlay) is one of the analysis methods of the Geographic Information System (GIS), which refers to overlaying two or more layers with spatial position relationships (such as the freeze-thaw spatio-temporal distribution map, the regional black soil distribution map, and the high-standard farmland plot distribution map) in the geographical space, and extracting new spatial features through spatial relationship operations (such as intersection, union, difference, etc.).

[0063] Specifically, by performing an overlay analysis on the freeze-thaw spatio-temporal distribution map, the regional black soil distribution map, and the high-standard farmland plot distribution map, the freeze-thaw risk area for black soil high-standard farmland construction is obtained. This method combines the spatio-temporal characteristics of the freeze-thaw process with the black soil distribution and farmland planning through multi-layer overlay analysis, realizing the accurate positioning of the freeze-thaw risk of black soil high-standard farmland.

[0064] It should be noted that the freeze-thaw spatio-temporal distribution map reflects the distribution of freeze-thaw risk areas in the entire study area. These freeze-thaw risk areas may be located in the black soil distribution area or in other landform distribution areas. Among the black soil distribution areas, there are high-standard farmland plots and non-high-standard farmland plots. Therefore, by overlaying the three, the freeze-thaw risk area for black soil high-standard farmland construction can be accurately positioned.

[0065] Among them, the regional black soil distribution map can be obtained in the following way: Obtain the soil type map from the soil census result data, extract the areas where the soil type attribute field value is black soil, and generate the regional black soil distribution map.

[0066] The distribution map of high-standard farmland plots can be obtained by extracting the distribution of high-standard farmland plots. For example, if there is already a vector map of cultivated land plots in the high-standard farmland project plan in the area to be studied, then the vector maps of all high-standard farmland cultivated land plots in the area can be spliced to obtain the distribution map. Otherwise, on the high-precision remote sensing images of the study area, the cultivated land plots can be identified through machine learning algorithms to obtain the distribution map.

[0067] On the basis of obtaining the freeze-thaw spatio-temporal distribution map, the regional black soil distribution map, and the high-standard farmland plot distribution map, the three are superimposed and analyzed to obtain the freeze-thaw risk area for black soil high-standard farmland construction.

[0068] The delineation of the freeze-thaw risk area for black soil high-standard farmland construction provides a spatial framework for freeze-thaw hazard prediction and risk warning. In this embodiment, the freeze-thaw hazard prediction unit 30 is used to construct a freeze-thaw hazard prediction model and perform freeze-thaw hazard prediction based on the freeze-thaw risk area for black soil high-standard farmland construction to obtain the freeze-thaw hazard prediction result.

[0069] In this embodiment, the freeze-thaw hazard prediction unit 30 is used to construct a freeze-thaw hazard prediction model for black soil high-standard farmland (abbreviation: freeze-thaw hazard prediction model), and use this model to perform freeze-thaw hazard prediction on the freeze-thaw risk area for black soil high-standard farmland construction.

[0070] Specifically, the freeze-thaw hazard prediction unit further includes: a data preparation and preprocessing subunit, a model construction and verification subunit, and an application and prediction subunit. Among them: The data preparation and preprocessing subunit is used to preprocess the pre-obtained farmland environment data and farmland damage data to form modeling data, and divide the modeling data into training set data and validation set data; The model construction and verification subunit is used to construct a freeze-thaw hazard prediction model that maps the relationship between farmland environmental variables and the damage situation of farmland freeze-thaw disasters, and use the validation set data to evaluate the accuracy of the prediction model to obtain a trained prediction model; The application and prediction subunit is used to use the trained prediction model to predict the damage situation of freeze-thaw disasters in the target area, and the freeze-thaw hazard prediction result can be obtained.

[0071] The execution process of the above subunits can be described exemplarily as follows: First, collect farmland environment data and farmland damage data in areas with similar climate, geography, etc. to the study area. Among them, the farmland environment data can include meteorology, soil, high-standard farmland construction, crops, etc., and the farmland damage data can include: ditch damage rate, total length and maximum width of ditch cracks, damage rate of field roads, total length and maximum width of field road cracks, damage rate of production roads, total length and maximum width of production road cracks, etc.

[0072] Exemplarily, the specific content of the farmland environmental data is as follows: Meteorological data: Collect historical meteorological data of the research area, including average temperature, freezing index, fusion index, rainfall, etc. Climate data is the most important variable data for modeling.

[0073] Soil data: Specifically refers to the black soil parameters, including soil bulk density, soil texture and other data.

[0074] Crop data: Includes data such as regional crop types and planting systems.

[0075] High-standard farmland construction data: Includes data such as construction years, farmland slope, irrigation canal type, width of field roads, width of production roads, etc.

[0076] Subsequently, the data preparation and preprocessing subunit cleans and preprocesses the obtained farmland environmental data and farmland damage data to form modeling data. The cleaning and preprocessing specifically include the following operations: removing outliers, unifying data units, data standardization, etc. Then, according to the cleaning and preprocessing results, taking the high-standard farmland construction plots as the statistical unit, the data for modeling (i.e., modeling data) is formed.

[0077] It should be noted that in this embodiment, the statistical unit refers to the calculation unit for processing and analyzing data, and is also called the calculation unit. That is to say, during modeling and subsequent evaluation steps, the plots are used as the unit.

[0078] The model construction and verification subunit constructs a relationship model between high-standard farmland facility damage and the farmland environment. Among them, farmland facility damage refers to the farmland damage data, and the farmland environment refers to the farmland environmental data. That is, taking the farmland environmental data as the independent variable and the farmland damage data as the dependent variable, a freeze-thaw hazard prediction model for the mapping relationship between farmland environmental variables and the damage situation of farmland freeze-thaw disasters is constructed.

[0079] Preferably, the freeze-thaw hazard prediction model is a machine learning model.

[0080] Specifically, the model construction and verification subunit constructs machine learning models for each variable of the farmland damage data (including: ditch damage rate, total length and maximum width of ditch cracks, field road damage rate, total length and maximum width of field road cracks, production road damage rate, total length and maximum width of production road cracks) and the farmland environmental data.

[0081] It should be noted that the machine learning model can be any one of a random forest model, a multiple linear regression model, and an Extreme Gradient Boosting model.

[0082] Furthermore, multiple sets of model training data can be selected for accuracy evaluation, and the model with the highest accuracy can be chosen as the application model (i.e., the trained freeze-thaw hazard prediction model).

[0083] Specifically, the modeling data can be divided into a training set and a validation set. Multiple models such as random forest, multiple linear regression, and eXtreme Gradient Boosting can be selected. The training set data is used to train the models to construct a freeze-thaw hazard prediction model for the farmland environmental variables (such as regional climate, soil, high-standard farmland construction, crop data, etc.) and the freeze-thaw damage conditions of high-standard farmland with black soil (such as the damage rate of ditches, the total length and maximum width of ditch cracks, the damage rate of field roads, the total length and maximum width of field road cracks, the damage rate of production roads, the total length and maximum width of production road cracks). The validation set data is used to evaluate the model accuracy, and the model with the highest accuracy is selected for subsequent prediction of the freeze-thaw damage conditions of high-standard farmland with black soil to obtain the trained prediction model.

[0084] Using the trained prediction model, input the farmland environmental data (such as regional climate, soil, high-standard farmland construction, crop data) of the area to be predicted to predict the freeze-thaw damage conditions of the area (such as the damage rate of ditches, the total length and maximum width of ditch cracks, the damage rate of field roads, the total length and maximum width of field road cracks, the damage rate of production roads, the total length and maximum width of production road cracks), obtain the freeze-thaw hazard prediction result, and output the prediction result.

[0085] After obtaining the freeze-thaw hazard prediction result, in this embodiment, the construction risk warning and prevention measure suggestion unit 40 is used to give freeze-thaw prevention measures according to the freeze-thaw hazard prediction result in combination with the knowledge base of freeze-thaw risk prevention measures for high-standard farmland construction with black soil.

[0086] The purpose of the construction risk warning and prevention measure suggestion unit 40 is to generate construction risk warning and prevention measure suggestions. Specifically, the predicted farmland damage conditions are input into the knowledge base of freeze-thaw risk prevention for high-standard farmland construction with black soil to obtain prevention measure suggestions, providing guidance for the process of high-standard farmland construction with black soil.

[0087] Among them, the knowledge base of freeze-thaw risk prevention measures for high-standard farmland construction with black soil is used to collect, organize, store, and associate prevention measures related to freeze-thaw disasters. In this embodiment, the knowledge base of freeze-thaw risk prevention measures for high-standard farmland construction with black soil is constructed based on knowledge graph technology.

[0088] It should be noted that knowledge graph technology is an artificial intelligence technology that expresses entities and their relationships through a graph structure (nodes + edges).

[0089] Specifically, first, analyze and organize the knowledge of freeze-thaw disasters to form a knowledge system for preventing freeze-thaw risks in the construction of high-standard black soil farmland. Then, extract relevant knowledge information from multi-source heterogeneous data (such as national / local farmland construction specifications, scientific research literature, expert knowledge, etc.) and integrate it into the knowledge system according to preset rules. Extract entity content (such as freeze-thaw risk levels) and relationships, and then conduct knowledge modeling. Finally, store the knowledge system in the knowledge base to obtain a knowledge base of preventive measures for freeze-thaw risks in the construction of high-standard black soil farmland.

[0090] Input the freeze-thaw hazard prediction results (i.e., the damage situation of freeze-thaw disasters) output by the freeze-thaw hazard prediction unit 30 into the knowledge base of preventive measures for freeze-thaw risks in the construction of high-standard black soil farmland, make inferences in the graph information, obtain the knowledge output that meets the requirements, and generate suggestions for preventive measures for freeze-thaw risks in the construction of high-standard black soil farmland, that is, freeze-thaw prevention measures.

[0091] Based on the identification of freeze-thaw areas, prediction of freeze-thaw hazards, early warning of construction risks, and suggestions for preventive measures in the construction of high-standard black soil farmland, conduct a comprehensive evaluation of the construction of high-standard black soil farmland in the freeze-thaw area based on relevant data, that is, evaluate the anti-freeze-thaw risk ability of the high-standard farmland constructed in the freeze-thaw black soil area, so as to provide guarantee for achieving high and stable yields of high-standard farmland.

[0092] In this embodiment, the comprehensive evaluation unit 50 for the construction of high-standard black soil farmland in the freeze-thaw area is used to comprehensively evaluate the anti-freeze-thaw risk ability of the high-standard farmland constructed in the freeze-thaw black soil area.

[0093] It should be noted that in the evaluation of traditional general high-standard farmland construction, according to relevant technical standards (such as GB / T 33130-2024), the evaluation index system of high-standard farmland construction consists of factors such as fields (field surface conditions), soil (soil properties), water (irrigation and drainage capabilities), roads (road accessibility), grains (production capabilities), and other infrastructure (matching degree of transmission lines, supporting of efficient water-saving irrigation facilities, and proportion of farmland protection area). These current standards do not consider the impact of freeze-thaw on high-standard farmland construction.

[0094] In this embodiment, anti-freeze-thaw risk indicators are supplemented on the basis of the traditional high-standard farmland construction evaluation index system to optimize the evaluation index system to meet the actual needs of the construction of high-standard black soil farmland in the freeze-thaw area.

[0095] Specifically, the anti-freeze-thaw risk indicators supplemented on the basis of the traditional high-standard farmland construction evaluation index system are shown in the following table: Table 1 Supplemented Anti-freeze-thaw Risk Indicators

[0096] After the construction is completed, the optimized evaluation index system (adding the anti-freeze-thaw capacity index) is used to evaluate the comprehensive construction of high-standard farmland in this area. Collect data on fields, soil, water, roads, grains, and other infrastructure in this area, and based on the technical realization of freeze-thaw risk area identification, demarcation, hazard prediction, risk early warning, and preventive measure suggestions, collect data related to anti-freeze-thaw capacity. Specifically, numerical values can be obtained by conventional measurement methods, and then scores for each index are calculated and the scores are accumulated to output the evaluation result.

[0097] Specifically, based on the above table, the scores of each index are determined, and the sum of the scores of all indexes is the total score (I 1 ), with a full score of 20 points. The score obtained based on the "Evaluation Specification for the Construction of High-Standard Farmland (GB / T 33130 - 2024)" is (I 2 ). The comprehensive evaluation score (I) of high-standard farmland in the black soil of the freeze-thaw area is: I = I 1 + 0.8 * I 2 . The evaluation results are divided into five grades: a score of ≥ 90 is excellent, 80 ≤ score < 90 is good, 70 ≤ score < 80 is medium, 60 ≤ score < 70 is average, and score < 60 is unqualified.

[0098] That is to say, in this embodiment, the comprehensive score of the supplementary anti-freeze-thaw risk index is calculated and denoted as the first score I 1 , and the comprehensive score calculated by all the original general indexes is denoted as the second score I 2 . The weighted sum result of the first score and the second score is used as the total comprehensive evaluation score of high-standard farmland in the black soil of the freeze-thaw area.

[0099] In this embodiment, the freeze-thaw response ability is added to the quality evaluation system of high-standard farmland construction. After identifying the freeze-thaw area of high-standard farmland in black soil, by supplementing anti-freeze-thaw risk indexes such as the anti-freeze-thaw degree of ditches and the frost resistance of road materials, and collecting and measuring relevant data during the design, construction, and management of high-standard farmland, an accurate evaluation of the comprehensive construction of high-standard farmland in the freeze-thaw risk area is achieved.

[0100] As an example, the system provided in this embodiment will be further described below in combination with Figure 2 .

[0101] Such as Figure 2As shown in the figure, the system includes four parts: identification of freeze-thaw areas in high-standard farmland construction, prediction of freeze-thaw hazards, early warning and prevention measures suggestions for construction risks, and comprehensive evaluation of high-standard farmland construction in black soil areas with freeze-thaw. Among them, the identification of freeze-thaw areas includes two components: preliminary identification of high-risk freeze-thaw areas and delineation of freeze-thaw risk areas; the prediction of freeze-thaw hazards includes three parts: data preparation and preprocessing, model construction and verification, and application and prediction; the early warning and prevention measures suggestions for construction risks include the construction of a freeze-thaw risk prevention knowledge system (i.e., knowledge base), knowledge information extraction, and knowledge output; the comprehensive evaluation of high-standard farmland construction in black soil areas with freeze-thaw includes two parts: improvement of evaluation indicators and generation and feedback of evaluation results.

[0102] In summary, the system provided in this embodiment has the following beneficial effects: Improve the quality of high-standard farmland construction. Timely identify the freeze-thaw risks in the construction of high-standard farmland in black soil, and put forward early warnings and prevention suggestions, reduce the damage to high-standard farmland roads, water conservancy facilities, etc. due to freeze-thaw hazards, reduce the investment in farmland construction maintenance, and ensure the long-term stable utilization of farmland.

[0103] Improve agricultural production capacity. The technical solution provided in this embodiment can give full play to the characteristics of high-standard farmland, such as perfect infrastructure, fertile soil, and strong disaster resistance, while improving the comprehensive construction quality of high-standard farmland, improve agricultural production capacity, and provide a solid guarantee for food security.

[0104] Improve the ecological environment of black soil. The identification and prevention of freeze-thaw risks can also reduce the impact of soil freeze-thaw erosion in black soil areas and promote the sustainable development of the black soil ecological environment.

[0105] Based on the same inventive concept, this embodiment provides a method for identifying and evaluating freeze-thaw risks in the construction of high-standard farmland in black soil, and the method includes the following steps: Based on meteorological data, identify the freeze-thaw risk areas through the fusion index method, and then draw the freeze-thaw spatio-temporal distribution map; Overlay and analyze the freeze-thaw spatio-temporal distribution map, the regional black soil distribution map, and the high-standard farmland plot distribution map to obtain the freeze-thaw risk areas for high-standard farmland construction in black soil; Construct a freeze-thaw hazard prediction model, and conduct freeze-thaw hazard prediction based on the freeze-thaw risk areas for high-standard farmland construction in black soil to obtain the freeze-thaw hazard prediction results; According to the freeze-thaw hazard prediction results, combined with the knowledge base of freeze-thaw risk prevention measures for high-standard farmland construction in black soil, give freeze-thaw prevention measures; Comprehensively evaluate the freeze-thaw risk resistance ability of high-standard farmland constructed in freeze-thaw black soil areas.

[0106] Based on the same inventive concept, this embodiment also provides an electronic device, including: a memory for storing instructions executed by one or more processors of the electronic device; a processor, when the processor executes the instructions in the memory, enabling the electronic device to implement the steps of the method for freeze-thaw risk identification and assessment in high-standard farmland construction for black soil provided in any of the above embodiments.

[0107] The embodiment of the present application also provides a computer program product containing computer-executable instructions. In one embodiment, the computer-executable instructions are used to cause a computer to execute the functions in the embodiments of the above method for freeze-thaw risk identification and assessment in high-standard farmland construction for black soil.

[0108] The computer-executable instructions can be stored in a computer-readable storage medium. The embodiment of the present application also provides a computer-readable storage medium, and the computer-readable storage medium stores executable instructions. In one embodiment, the computer-executable instructions are used to cause a computer to execute the functions in the embodiments of the above method for freeze-thaw risk identification and assessment in high-standard farmland construction for black soil.

[0109] Figure 3 FIG. is a schematic structural diagram of an electronic device provided according to some embodiments of the present application. The electronic device may be, but is not limited to, mobile terminals such as mobile phones, tablet computers, handheld computers, personal digital assistants (PDAs), etc., smart home devices such as smart TVs, smart cameras, etc., wearable devices such as smart bracelets, smart watches, smart glasses, or other computer devices such as desktop computers, laptop computers, ultra-mobile personal computers (UMPCs), netbooks, and smart screens.

[0110] As Figure 3 shown, the electronic device 200 may include one or more of the following components: a processor 201, a memory 203, a communication interface 202, and a communication bus 204. Among them, the memory 203 may be connected to the processor 201 through the bus 204. The bus can transmit data between the processor 201 and the memory 203. The bus can be divided into an address bus, a data bus, a control bus, etc.

[0111] The processor 201 may include one or more processing cores. The processor 201 can connect various parts within the entire electronic device 200 using various interfaces and lines. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 203, and by invoking the data stored in the memory 203, it can perform various functions of the electronic device 200 and process data. Exemplarily, the processor 201 may include an application processor (AP), a modem processor, a CPU, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a field-programmable gate array (FPGA), a programmable logic array (PLA), and / or a neural-network processing unit (NPU), etc. Among them, the CPU mainly processes the operating system, user interface, and application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed; the NPU is used to implement artificial intelligence (AI) functions; the modem is used to process wireless communications. Different processing units can be independent devices or integrated in one or more processors. For example, the multiple processing units shown above are all integrated in one SoC, or the AP is a separate semiconductor chip, and other processing units are integrated in one SoC. This application does not make any limitations in this regard.

[0112] The memory 203 (also referred to as a computer-readable storage medium) may include a random access memory (RAM), may also include a read-only memory (ROM), and may further include a non-transitory computer-readable storage medium. The memory 203 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 203 may include a program storage area and a data storage area. Among them, the program storage area can store instructions for implementing the operating system, instructions for at least one function, such as the method for identifying and evaluating freeze-thaw risks in the construction of high-standard farmland for black soil, etc.; the data storage area can store data created according to the use of the electronic device 200, such as meteorological data, intermediate results of model outputs, etc.

[0113] In addition, those skilled in the art can understand that the structure of the electronic device 200 shown in the above drawings does not limit the electronic device 200. The electronic device may include more or fewer components than shown in the drawings, or combine some components, or have different component arrangements. For example, the electronic device 200 also includes components such as a microphone, a speaker, a radio frequency circuit, a sensor, an audio circuit, a power supply, and a Bluetooth module, which will not be elaborated here.

[0114] The above are only the preferred embodiments of the present application and are not used to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

Claims

1. A freeze-thaw risk identification and assessment system for black soil high-standard farmland construction, characterized in that: include: The freeze-thaw area identification unit for high-standard black soil farmland construction is used to identify freeze-thaw risk areas based on meteorological data through the fusion index method, and then draw a freeze-thaw spatiotemporal distribution map; The fusion index method refers to comprehensively determining the freeze-thaw risk area based on multiple freeze-thaw indices; The freeze-thaw risk zoning subunit is used to overlay and analyze the freeze-thaw spatiotemporal distribution map, the regional black soil distribution map, and the high-standard farmland plot distribution map to obtain the freeze-thaw risk area for the construction of black soil high-standard farmland; A freeze-thaw hazard prediction unit is used to construct a freeze-thaw hazard prediction model, and to perform freeze-thaw hazard prediction based on the freeze-thaw risk area of ​​the black soil high-standard farmland construction to obtain a freeze-thaw hazard prediction result; Constructing a risk warning and prevention measure suggestion unit, which is used to provide freeze-thaw prevention measures based on the freeze-thaw hazard prediction results and the freeze-thaw risk prevention measures knowledge base for black soil high-standard farmland construction; The comprehensive assessment unit for the construction of high-standard farmland in black soil areas in freeze-thaw zones is used to comprehensively assess the ability of high-standard farmland constructed in freeze-thaw black soil areas to resist freeze-thaw risks.

2. The system according to claim 1, characterized in that Based on meteorological data, the freeze-thaw risk area is identified through the fusion index method, specifically: Calculate multiple freeze-thaw indices based on meteorological data; According to the multiple freeze-thaw indexes and preset judgment rules, the freeze-thaw risk area is divided into multiple risk levels to obtain a freeze-thaw risk area.

3. The system according to claim 2, characterized in that The freeze-thaw index includes: freezing index, freeze-thaw ratio, and freeze-thaw daily cycle days.

4. The system according to claim 3, characterized in that The preset judgment rules include: If the freezing index of the target area is greater than the first threshold, or the freeze-thaw ratio of the target area is less than the second threshold, or the number of freeze-thaw daily cycles is greater than the third threshold, the target area is judged to be a freeze-thaw risk area.

5. The system according to claim 2, characterized in that The freeze-thaw spatiotemporal distribution diagram is obtained by the following steps: Based on the historical meteorological data of the study area for many years, the historical freeze-thaw risk areas were obtained; Based on the future meteorological data of the study area, predict the future freeze-thaw risk areas; Comparing the historical meteorological data with the future meteorological data to obtain a comparison result; If the comparison result is less than a preset difference threshold, the historical freeze-thaw risk area is used as the final freeze-thaw risk area delineation result; If the comparison result is greater than a preset difference threshold, the historical freeze-thaw risk area and the future freeze-thaw risk area are combined to obtain a final freeze-thaw risk area delineation result; Based on the delineation result of the final freeze-thaw risk zone, the freeze-thaw spatiotemporal distribution map is output.

6. The system according to claim 1, characterized in that The freeze-thaw hazard prediction unit further includes: a data preparation and preprocessing subunit, a model building and verification subunit, and an application and prediction subunit; The data preparation and preprocessing subunit is used to preprocess the pre-acquired farmland environmental data and farmland freeze-thaw disaster damage data to form modeling data, and divide the modeling data into training set data and verification set data; The model building and verification subunit is used to build a freeze-thaw hazard prediction model that maps the relationship between farmland environmental variables and farmland freeze-thaw disaster damage, and use the verification set data to evaluate the accuracy of the prediction model to obtain a trained prediction model; The application and prediction subunit is used to use the trained prediction model to predict the damage caused by freeze-thaw disasters in the target area, so as to obtain the freeze-thaw hazard prediction result.

7. The system according to claim 1, characterized in that The knowledge base of freeze-thaw risk prevention measures for black soil high-standard farmland construction is constructed based on knowledge graph technology.

8. A method for identifying and assessing freeze-thaw risks in the construction of high-standard black soil farmland, characterized in that: include: Based on meteorological data, the freeze-thaw risk areas are identified through the fusion index method, and then the freeze-thaw spatiotemporal distribution map is drawn; The freeze-thaw spatiotemporal distribution map, regional black soil distribution map, and high-standard farmland plot distribution map were superimposed and analyzed to obtain the freeze-thaw risk areas for the construction of black soil high-standard farmland; Constructing a freeze-thaw hazard prediction model, and performing freeze-thaw hazard prediction based on the freeze-thaw risk area of ​​the black soil high-standard farmland construction, to obtain freeze-thaw hazard prediction results; Based on the freeze-thaw hazard prediction results and combined with the knowledge base of freeze-thaw risk prevention measures for black soil high-standard farmland construction, freeze-thaw prevention measures are given; A comprehensive assessment is conducted on the ability of high-standard farmland constructed in frozen-thaw black soil areas to resist freeze-thaw risks.

9. An electronic device, characterized in that: include: a memory for storing instructions executed by one or more processors of the electronic device; The processor, when the processor executes the instructions in the memory, can enable the electronic device to implement the steps of the freeze-thaw risk identification and assessment method for the construction of high-standard black soil farmland as described in claim 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions which, when executed on a computer, implement the steps of the freeze-thaw risk identification and assessment method for the construction of high-standard black soil farmland as described in claim 8.

Images