Grain storage sub-ecological region intelligent division method based on spatial analysis and clustering technology

Abstract

The invention discloses a grain storage sub-ecological region intelligent division method based on a spatial analysis and clustering technology, and the method comprises the following steps: 1, obtaining the geographic position data, meteorological data and grain condition data of each sampling point in a research region, and enabling the data to serve as the sample data of each sampling point; taking the meteorological data and the grain condition data of each sampling point as grain storage variables of the sample; wherein the geographic position information comprises the longitude, the latitude and the altitude of the sampling point, the meteorological data comprises the air temperature, the relative humidity, the precipitation and the sunshine duration of the sampling point, and the grain condition data comprises the grain temperature of the granary corresponding to the sampling point; step 2, calculating a global Moran index of each grain storage variable in each sampling point, and respectively screening out characteristic indexes in the meteorological data and the grain condition data according to the global Moran index; and step 3, determining a clustering target number K, clustering sampling points in the research area by using a K-means clustering algorithm, and dividing the research area into K grain storage sub-ecological areas.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of grain storage, and particularly relates to an intelligent division method of a sub-ecological zone of grain storage based on spatial analysis and clustering technology. BACKGROUND

[0002] The stability and efficient management of the ecological environment of grain storage are important links for guaranteeing the quality of grain storage and reducing post-production losses. Under the background of intensified climate change, diversified grain varieties and iterative storage technology, the traditional extensive division taking administrative regions or climate zones as units has failed, and its limitations are reflected in three aspects: first, the quantitative characterization of the microenvironment factors of grain storage is lacked, and the single-factor threshold division cannot capture the interactive effects of multiple factors; second, the empirical boundary is highly subjective and has poor repeatability, and lacks the dynamic modeling capability based on GIS spatial analysis, resulting in deviations between the division results and the actual grain storage conditions; and third, the technical scale still stays in the macro framework of "large zone and small zone", and neither the concept of "sub-ecological zone" nor the division standard is proposed, and the fine management technology of the micro-ecological unit is also lacked. 2

[0003] Grain safety storage is essentially the result of the synergistic effect of geographical environment, climate factors, grain factors and storage management. The existing research exposes three defects in this chain: in the index system, it presents single-dimension, and follows the "geographical location dominant" or "single meteorological element driven" mode, ignoring the shaping of the micro-ecology in the warehouse by the local microclimate circulation; in time, it uses static indicators such as annual mean temperature and annual precipitation, and lacks real-time coupling mechanism of meteorological factors and grain factors. In data correlation, there is a fault, and the causal chain of "meteorological driving-grain response" cannot be established. In data chain, there is a fault, the time and space resolution of the collection end is low, the data span is short, the processing end lacks outlier processing and feature selection, and the application end lacks dynamic updating mechanism of multi-source data fusion, which is difficult to cope with the frequent extreme climate and rapid iteration of quality.

[0004] Therefore, it is urgent to build a "meteorological driving-grain response-dynamic optimization" three-in-one grain storage ecological zoning system. The system can realize the precise configuration of grain storage environment regulation and control measures, improve the safety of grain storage and the efficiency of resource utilization, provide customized environment regulation and control strategies for different micro-ecological units, and finally form a new fine grain storage management mode that adapts to climate change and variety diversification. SUMMARY

[0005] The purpose of the present application is to overcome the defects of the prior art, and provide an intelligent division method of a sub-ecological zone of grain storage based on spatial analysis and clustering technology, which can realize the precise division of the sub-ecological zone of grain storage by deeply mining the internal correlation among meteorological data, grain data and geographical space.

[0006] The technical scheme provided by the present application is:​ An intelligent method for dividing sub-ecological zones of stored grain based on spatial analysis and clustering technology, comprising the following steps: Step one, obtaining the geographic position data, meteorological data and grain condition data of each sampling point in the study area as sample data of each sampling point; taking the meteorological data and grain condition data of each sampling point as sample storage variables; Wherein, the geographic position data includes the longitude, latitude and altitude of the sampling point, the meteorological data includes the air temperature, relative humidity, precipitation and sunshine duration of the sampling point, and the grain condition data includes the grain temperature of the corresponding grain warehouse of the sampling point; Step two, calculating the global Moran's index of each storage variable in each sampling point, and screening out the characteristic indicators in the meteorological data and grain condition data according to the global Moran's index respectively; Step three, determining the clustering target number based on the characteristic indicators K , using K-means clustering algorithm to cluster the sampling points in the study area, and dividing the study area into K sub-ecological zones of stored grain.

[0007] Preferably, before the step two, it also includes standardizing the storage variables of the sample to remove the dimension.

[0008] Preferably, in the step two, for a single storage variable, the calculation formula of the global Moran's index is: ; Wherein, is the number of samples in the study area, is the spatial weight matrix, and are the standardized values of the storage variables of the th sample and the th sample respectively, is the mean value of the standardized values of the storage variables of all samples in the study area.

[0009] Preferably, the calculation formula of the spatial weight matrix is: ; Wherein, is the horizontal distance between the th sample and the th sample, is the absolute value of the altitude difference between the th sample and the th sample, is the altitude difference attenuation coefficient.

[0010] Preferably, in the step two, the characteristic indicators in the meteorological data that meet The grain storage variables and grain status data meet the requirements The grain storage variable is used as the characteristic indicator.

[0011] Preferably, in step 3, the clustering target is determined by the elbow rule. ,include: calculate The rate of change of the sum of squared errors when the value changes ; ; in, The number of clusters is The sum of squared errors when The number of clusters is The sum of squared errors when The number of clusters is The sum of squared errors when when When the elbow point is determined, the elbow point corresponding to Values ​​are used as clustering targets; in, is the set rate of change threshold.

[0012] Preferably, in step 3, when performing K-means clustering, the distance formula used is: ; in, Represents a sample With Cluster Center The weighted distance, is the feature index weight, is the geographical feature weight, For samples No. The standardized value of the characteristic index, is the cluster center No. The standardized value of the characteristic index; For samples and cluster centers geographical distance; is the geographic attenuation function; For samples Latitude; For samples longitude; is the cluster center Latitude; is the cluster center longitude.

[0013] Preferably, .

[0014] Preferably, in the step three, further comprising boundary correction of the clustered sub-ecological region of stored grain according to the topography, and the boundary correction meets the topography consistency principle.

[0015] The beneficial effects of the present application are: The present application provides a sub-ecological region intelligent division method of stored grain based on spatial analysis and clustering technology, which can realize accurate division of the sub-ecological region of stored grain by deeply mining the internal correlation between meteorological data, grain condition data and geographic space, and overcome the defects of single dimension of division index, decoupling of meteorological data and grain condition data correlation, and three faults of data chain in the links of "collection-processing-application" in the prior art, resulting in insufficient division accuracy and poor adaptability. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 The flow chart of the sub-ecological region division of stored grain according to the present application.

[0017] Figure 2 The flow chart of the spatial correlation of meteorological data and grain condition data according to the present application.

[0018] Figure 3 The flow chart of determining the number of sub-ecological regions of stored grain according to the present application.

[0019] Figure 4 The interpolation result diagram of the annual average grain temperature in the embodiment of the present application.

[0020] Figure 5 The LISA cluster analysis diagram of the index (average value of winter balanced moisture) with high I value in the embodiment of the present application.

[0021] Figure 6 The LISA cluster analysis diagram of the index (average humidity in summer) with low I value in the embodiment of the present application.

[0022] Figure 7 The spatial cluster distribution diagram of the sampling points in the embodiment of the present application. DETAILED DESCRIPTION

[0023] The present application will be further described in detail below with reference to the accompanying drawings, so that those skilled in the art can implement the present application according to the description.

[0024] The sub-ecological region of stored grain is a micro unit of stored grain with similar meteorological driving and grain response characteristics in geographic space. Figure 1 As shown in the drawings, the present application provides a sub-ecological region intelligent division method of stored grain based on spatial analysis and clustering technology, and the specific implementation process is as follows.

[0025] I. Data collection and preprocessing A plurality of sampling points are set in the research area, and the geographic position data and the grain storage variable of each sampling point in the research area are obtained as samples. Then, the obtained sample data is preprocessed.

[0026] In an embodiment, for the research area, each meteorological station in the research area is taken as a sampling point. First, the geographic position data of each sampling point in the research area is determined, and then the grain storage variable of each sampling point is obtained, which includes meteorological observation data and grain condition data. As shown in FIG. 1, in some areas, the number of grain depots is less than the number of meteorological stations. In order to ensure the integrity of the grain condition data of each sampling point, it is necessary to spatially correlate the meteorological data and the grain condition data. For each meteorological station, the area within 50 kilometers of the meteorological station is taken as a buffer zone. If there is a grain depot in the buffer zone, the grain condition data of the grain depot closest to the meteorological station (sampling point) in the buffer zone is taken as the grain condition data of the sampling point. If there is no grain depot in the buffer zone, the data is completed by interpolation. The geographic information system data covers longitude, latitude information and altitude; the meteorological observation data includes air temperature, relative humidity, precipitation and sunshine duration; and the grain condition data includes grain temperature, equilibrium moisture and the like. By removing outliers, interpolating missing values and standardizing, data noise and dimension differences are eliminated, and a high-quality data set is provided for subsequent analysis. Figure 2

[0027] Among them, for the sampling points around which there is no grain depot, the grain temperature of the sampling points without grain depots is completed by spatial interpolation.

[0028] ; Among them, is the grain temperature interpolation result of the sampling point, is the number of sample points participating in the interpolation calculation (within a distance threshold radius of 50 kilometers), is the grain temperature of the sample point participating in the difference calculation, is the spatial distance weight. In an embodiment, the calculation formula of the spatial distance weight is:

[0029] ; ; Among them, is the horizontal distance between the sample and the sample , is the absolute value of the altitude difference between the sample and the sample , and is the altitude difference attenuation coefficient.

[0030] ​​​In one embodiment, the altitude difference attenuation is set to 0.005.

[0031] 2. Screening characteristic indicators The global Moran's I is used to quantify the spatial clustering characteristics of grain storage variables. The global Moran's I of each grain storage variable is calculated one by one. The formula is: ; in, n is the number of samples in the study area, is the spatial weight matrix, and Respectively samples and The standardized value of the grain storage variable of the sample, is the mean of the standardized values ​​of the grain storage variable for all samples in the study area. For example, to calculate the global Moran index of the average winter temperature, and Respectively samples and The standardized value of the average winter temperature of samples, is the mean of the standardized values ​​of the average winter temperature of all samples in the study area.

[0032] Each grain storage variable (meteorological observation data and grain condition data) is calculated separately value. ; I >0 indicates positive correlation, I <0 indicates negative correlation, I =0 indicates random distribution.

[0033] By calculating the global Moran index, the spatial concentration of stored grain variables such as air temperature, relative humidity, and grain temperature in the study area is quantified. I The quantity with high value is used as the characteristic indicator, because its spatial aggregation characteristics can directly reflect the regional differences in grain storage environment.

[0034] 3. Establishing Zoning Criteria The optimal clustering K value is determined by the Elbow Method. Figure 3 As shown, confirm The specific process of the value is: starting from the input feature matrix F, initializing the number of clusters The search interval is [1, 10]. Then iteratively calculate each candidate The sum of squared errors (SSE) corresponding to the values ​​are calculated by The value corresponds to the curvature of SSE , through the change Δ( ) Identify the inflection point: If Δ( ) is less than a set empirical threshold , then it is determined that the current value is the optimal solution; otherwise, the value of is increased and the above calculation process is repeated until the convergence condition is met.

[0035] The rate of change of the sum of squared errors within the cluster SSE is calculated , and the formula is: ; wherein, is the sum of squared errors when the number of clusters is , is the sum of squared errors when the number of clusters is , is the sum of squared errors when the number of clusters is K- 1.

[0036] ; wherein, denotes the th cluster, denotes the standardized value of the feature index of the sampling point in the cluster , denotes the standardized value of the feature index of the center in the cluster .

[0037] When , the elbow point is determined. Wherein, is a set rate threshold; in an embodiment, it is set to .

[0038] Four, regional division and optimizationBased on the screened feature index and the formulated zoning criteria, a geographic distance weight matrix is constructed. First, based on the feature index obtained by the spatial autocorrelation method, a feature matrix is constructed.

[0039] ; wherein, n is the number of samples, m is the number of screened feature indexes, denotes the n th feature index of the m th sample (here the feature index is the standardized value after de-dimensioning); is the longitude of the n th sample, is the latitude of the n th sample.

[0040] Using the K-means algorithm, each sample (corresponding to a sampling point) is assigned to the nearest cluster center. The clustering result is the sub-ecological division result, that is, each cluster corresponds to a sub-ecological region. Clustering allows the sampling points to be divided into different sub-ecological regions.

[0041] In the K-means process, the improved distance formula is used to calculate the sample To cluster center The distance is calculated as follows: ; in, For samples and cluster centers The weighted distance of is the feature index weight, is the geographical feature weight, For samples No. characteristic indicators, is the cluster center No. characteristic indicators; For samples and cluster centers geographical distance; is the geographic attenuation function; For samples Latitude; For samples Latitude; is the cluster center Latitude; is the cluster center The characteristic index in the formula is the dimensionless normalized value.

[0042] As a preferred method, the silhouette coefficient method is used to determine the optimal weight combination ( α, β ).

[0043] To ensure the accuracy and rationality of the division results, the present invention also includes spatial analysis technology based on the geographic information system (GIS), superimposing geographical feature data such as mountains and deserts to correct the sub-ecological zone boundaries, analyzing the impact of topography on meteorological data and grain data, and boundary corrections must meet the principle of terrain consistency.

[0044] 5. Establish a feature database The database integrates and stores geographic data, meteorological data, grain condition data, and classification results for each grain storage sub-ecological region. The database uses a hybrid architecture, with a relational database storing static geographic data and a time series database storing dynamic meteorological and grain condition data.

[0045] Sixth, revision and release of sub-ecological zoning results Periodically iterate and optimize the partition model based on the latest data, develop scientific grain sub-ecological zoning standards and management modes, and release them regularly through the geographic information system platform. Embodiment

[0046] This embodiment takes Xinjiang Uygur Autonomous Region (east longitude 73°40'~96°18', north latitude 34°25'~49°10') as the research area, and divides the research area into sub-ecological zones, which includes the following processes.

[0047] I. Data collection and preprocessing Data sources and collection specifications: Geographic data: 30m resolution DEM data from the National Basic Geographic Information Center. Meteorological data: daily data from 105 national meteorological stations in Xinjiang (2021-2024), fields include: daily average temperature (℃), daily maximum / minimum temperature (℃), daily average relative humidity (%), daily precipitation (mm), sunshine hours (h). Grain condition data: Internet of Things monitoring data from 30 grain stores (2022-2023), including: upper, middle, and lower layer temperatures (℃), and average grain temperature calculated from upper, middle, and lower layer grain temperatures.

[0048] Data cleaning and standardization process: outlier rejection (dynamic 3σ principle): [μ-3σ, μ+3σ], missing value interpolation.

[0049] Standardization: Z-score standardization of all indicators to eliminate dimensional effects.

[0050] Missing data completion: Due to the small number of grain stores in Xinjiang compared to the number of meteorological stations, spatial correlation between meteorological data and grain condition data is needed to ensure the integrity of grain condition data for each sampling point. For each meteorological station, if there is a grain store within 50 kilometers, the grain condition data of the closest grain store to the meteorological station (sampling point) is used as the grain condition data for that sampling point. If there is no grain store, the grain temperature is completed by spatial interpolation. Based on the spatial coordinates of the meteorological station, the sparse grain condition data is mapped to the location of each meteorological station by interpolation.

[0051] ; where, is the grain temperature interpolation result of the sampling point , is the number of sample points participating in the interpolation calculation (within a distance threshold of 50 kilometers), is the grain temperature of the sample point participating in the difference calculation, is the spatial distance weight.

[0052] ​​In one embodiment, the calculation formula of the spatial distance weight is: ; in, For the samples and The horizontal distance between samples, For the samples and The absolute value of the altitude difference of samples, is the altitude difference attenuation coefficient. The altitude difference attenuation coefficient in the formula is set to 0.005.

[0053] like Figure 4 The figure shows the interpolation results of the average grain temperature. It can be seen from this figure that the missing grain data and meteorological data were aligned through spatial interpolation. The aligned station data were used as the sample point data for analysis.

[0054] 2. Feature Index Screening In the target area, spatial autocorrelation analysis is calculated. The global Moran's index (Moran's I) is used to assess spatial aggregation, and its formula is: ; in, is the spatial weight matrix, and n is the number of samples.

[0055] Molecular part: middle: Indicates the difference between the temperature of a sample and the average temperature of the whole Xinjiang; It means that two neighbors have high / low temperatures at the same time → the product is positive (changing in the same direction), one has high temperature and the other has low temperature → the product is negative (changing in opposite directions).

[0056] Denominator: Calculating the total deviation of the temperature of all stations from the average value is equivalent to a "normalization coefficient": scaling the numerator result according to the overall fluctuation to avoid inflated values ​​due to large temperature differences in Xinjiang.

[0057] Coefficient adjustment: : The total number of all neighbor pairs.

[0058] The calculation results of the correlation between meteorological data, grain data and geographic space are shown in Table 1.

[0059] Table 1 Spatial autocorrelation variables

[0060] Based on the Moran's I index values ​​of various meteorological and grain indicators provided, the selection of reasonable spatial characteristic variables requires comprehensive consideration of spatial autocorrelation intensity, indicator representativeness, and application objectives.

[0061] Selection principles and criteria: High spatial autocorrelation (Moran's I value > 0.7): indicates that the index presents a significant clustering pattern in space, which is suitable as the core basis for dividing the partition boundaries; Moderate autocorrelation (0.4 ≤ Moran's I value ≤ 0.7): needs to be combined with other indicators or domain knowledge to verify its stability; Low autocorrelation (Moran's I value < 0.4): spatial distribution is close to random, and is not suitable for being used alone as a partition indicator. I I I

[0062] Practical significance of indicators: Temperature and humidity: directly affect the safety of grain storage (such as mold and insect damage). Balanced moisture and accumulated temperature: reflect the risk of grain moisture balance and heat accumulation. Grain condition indicators (such as grain temperature): are directly related to warehouse management needs.

[0063] Avoid redundancy: preferentially select the variable with the strongest spatial autocorrelation among similar indicators.

[0064] In this embodiment, indicators with Moran's I value > 0.7 in meteorological observation data are selected as characteristic indicators, and indicators with Moran's I value > 0.6 in grain condition data are selected as characteristic indicators. The selected characteristic indicators are shown in Table 2. I I

[0065] According to the Moran's I value and the practical significance, the selected characteristic indicators are analyzed: Table 2 Characteristic indicator table The spatial difference results of the selected characteristic indicators are analyzed, taking the winter balanced moisture as an example (as shown in Figure 5 ). The figure clearly presents the spatial clustering phenomenon: the red area (HH, i.e. high value clustering area) is concentrated in northern Xinjiang (high winter balanced moisture zone), while the light red / white area (LL / LH, i.e. low value clustering area) is mainly distributed in southern Xinjiang (low winter balanced moisture zone). This spatial differentiation feature shows that the index is not randomly distributed, but follows the regional law of "high in the north and low in the south, with mountain transition", and has significant spatial heterogeneity. In contrast, the summer average humidity distribution (as shown in Figure 6 ) shows an alternating distribution pattern of red clustering points and white clustering points, and does not show significant spatial differentiation characteristics. Based on the image analysis results, it can be seen that the variables with larger Moran's I index values present significant spatial clustering, indicating that Moran's I index is suitable for grain storage area division.

[0066] III. Construction of zoning criteria The elbow method (Elbow Method) is used to gradually calculate​​​​​K = SSE change rate of 2~10, until Stop at Δ: ; when K =4, (satisfy ).like Figure 7 As shown in Figure 1, Xinjiang is divided into four grain storage sub-ecological zones.

[0067] IV. Regional Division and Optimization Based on the characteristic indicators and zoning criteria screened by the global Moran index, the geographically weighted K-means clustering algorithm was used to divide Xinjiang into grain storage sub-ecological zones.

[0068] The key meteorological factors and geographic coordinates are integrated to construct a feature matrix: ; in, n is the sample size, m is the number of characteristic indicators screened out, Indicates the n The first sample m Characteristic index, where the characteristic index is the standardized value after dimensioning; For the n The longitude of the samples, For the n The latitude of the samples.

[0069] Four data points are randomly selected from the dataset as initial cluster centers.

[0070] Using the K-means algorithm, each sample (corresponding to a sampling point) is assigned to the nearest cluster center. The clustering result is the sub-ecological division result, that is, each cluster corresponds to a sub-ecological region. Clustering allows the sampling points to be divided into different sub-ecological regions.

[0071] In the K-means process, the improved distance formula is used to calculate the sample To cluster center The distance is calculated as follows: ; in, For samples and cluster centers The weighted distance of is the feature index weight, is the geographical feature weight, For samples No. characteristic indicators, is the cluster center the first feature index; the geographical distance between the sample and the cluster center; is a geographical attenuation function; the latitude of the sample ; the latitude of the sample ; the latitude of the cluster center ; the longitude of the cluster center . The feature index in the formula is the standardized value after de-dimensioning. The optimal weight combination is determined by the contour coefficient method

[0072] , which satisfies: α, β ; The contour coefficient (S) is used to measure the accuracy of the clustering result: ; wherein represents the average feature distance between the sample corresponding sampling point and other sampling points in the same sub-ecological zone; represents the average feature distance between the sample corresponding sampling point and the nearest sub-ecological zone site. The combination of each is calculated, and the corresponding contour coefficient is output as shown in Table 3. α, β Table 3 Parameter Response Surface Table

[0073] The weight combination corresponding to the largest contour coefficient is selected, i.e. the weight

[0074] = 0.7 (feature factor), α = 0.3 (geographical feature). β The weight index is included in the determination process of the geographical weighted K-means clustering algorithm coefficient, and the winter average temperature, extreme high temperature, winter average humidity, winter equilibrium moisture, average grain temperature, and summer sunshine duration are selected as the feature index. The corresponding meteorological stations and grain collection points are classified. The classification results are shown in

[0075] , and then the classification results are converted into 5 km x 5 km grid data resolution, and the Kriging interpolation method (Kriging) is used to construct a continuous partition surface to realize the division of the sub-ecological region of Xinjiang region. Figure 7

[0076] ​Subsequently, the boundaries of the sub-ecological zones are corrected by superimposing geographical feature data such as mountains, deserts, and altitude based on GIS spatial analysis technology. The boundary correction process strictly follows the principle of topographical consistency.

[0077] V. Establishing a feature database The geographical data, meteorological data, grain condition data, and division results of each sub-ecological grain storage region are integrated and stored in a database. The database adopts a hybrid architecture, with a relational database storing static geographical data and a time series database storing dynamic meteorological and grain condition data.

[0078] VI. Periodic optimization and release of zoning results The sub-ecological zoning is iteratively optimized based on the latest data on a regular basis, and a scientific sub-ecological zoning division standard and management mode are developed, which are released in a timely manner through a geographic information system platform.

[0079] Although the embodiments of the present application have been disclosed as above, they are not limited to the application listed in the specification and embodiments, and can be fully applied to various fields suitable for the present application, and additional modifications can be easily made by those skilled in the art, and therefore the present application is not limited to specific details and the figures shown and described herein, without departing from the general concept defined by the claims and the equivalent scope.

Claims

1. A method for intelligent division of grain storage sub-ecological zones based on spatial analysis and clustering technology, characterized in that: The steps include: Step 1: Obtain the geographical location data, meteorological data, and grain condition data of each sampling point in the study area as the sample data of each sampling point; use the meteorological data and grain condition data of each sampling point as the grain storage variables of the sample; The geographical location data includes the longitude, latitude and altitude of the sampling point, the meteorological data includes the temperature, relative humidity, precipitation and sunshine hours of the sampling point, and the grain condition data includes the grain temperature of the granary corresponding to the sampling point; Step 2: Calculate the global Moran index of each grain storage variable at each sampling point, and filter out characteristic indicators in meteorological data and grain condition data according to the global Moran index; Step 3: Determine the number of clustering targets based on the characteristic indicators K , the K-means clustering algorithm is used to cluster the sampling points in the study area and divide the study area into K grain storage sub-ecological region.

2. The method for intelligent division of grain storage sub-ecological zones based on spatial analysis and clustering technology according to claim 1 is characterized in that: Before the step 2, the stored grain variables of the sample are also standardized to remove the dimensions.

3. The method for intelligent division of grain storage sub-ecological zones based on spatial analysis and clustering technology according to claim 2 is characterized in that: In step 2, for a single grain storage variable, the calculation formula of the global Moran index is: ； in, is the number of samples in the study area, is the spatial weight matrix, and Respectively samples and The standardized value of the grain storage variable of the sample, is the mean of the standardized values ​​of the stored grain variable for all samples in the study area.

4. The method for intelligent division of grain storage sub-ecological zones based on spatial analysis and clustering technology according to claim 3 is characterized in that: The calculation formula of the spatial weight matrix is: ； in, For samples and samples The horizontal distance between For samples and samples The absolute value of the altitude difference between is the altitude difference attenuation coefficient.

5. The method for intelligent division of grain storage sub-ecological zones based on spatial analysis and clustering technology according to claim 4 is characterized in that: In step 2, select the meteorological data that meets The grain storage variables and grain status data meet the requirements The grain storage variable is used as the characteristic indicator.

6. The method for intelligent division of grain storage sub-ecological zones based on spatial analysis and clustering technology according to claim 4 or 5, characterized in that: In step 3, the clustering target is determined by the elbow rule ,include: calculate The rate of change of the sum of squared errors when the value changes ; ； in, The number of clusters is The sum of squared errors when The number of clusters is The sum of squared errors when The number of clusters is The sum of squared errors when when When the elbow point is determined, the elbow point corresponding to Values ​​are used as clustering targets; in, is the set rate of change threshold.

7. The method for intelligent division of grain storage sub-ecological zones based on spatial analysis and clustering technology according to claim 6 is characterized in that: In step 3, when performing K-means clustering, the distance formula used is: ； in, Representation sample and Cluster Center The weighted distance, is the feature index weight, is the geographical feature weight, For samples No. The standardized value of the characteristic index, is the cluster center No. The standardized value of the characteristic index; For samples and cluster centers geographical distance; is the geographic attenuation function; For samples Latitude; For samples longitude; is the cluster center Latitude; is the cluster center longitude.

8. The method for intelligent division of grain storage sub-ecological zones based on spatial analysis and clustering technology according to claim 7 is characterized in that: 。 9. The method for intelligent division of grain storage sub-ecological zones based on spatial analysis and clustering technology according to claim 8, in step three, further includes correcting the boundaries of the grain storage sub-ecological zones obtained by clustering according to the topography, and the boundary correction satisfies the principle of terrain consistency.

Images