A tobacco planting meteorological suitability degree analysis method and system

Abstract

This invention relates to a method and system for analyzing the meteorological suitability of tobacco cultivation, specifically a method for evaluating and spatially predicting the climate suitability of tobacco cultivation based on multi-source data fusion. It addresses the problems of insufficient spatial resolution of meteorological data, static evaluation models, inadequate multi-source data fusion, separation of disaster early warning and suitability evaluation, and lack of intelligent service capabilities in existing technologies. This invention collects and fuses multi-source data, filters key meteorological elements, constructs fuzzy membership functions and spatial distribution models, calculates grid meteorological element values, and calculates a comprehensive suitability index. Based on this, it classifies the data into levels and generates a climate suitability zoning map. This invention is applicable to fields such as climate suitability evaluation for tobacco cultivation, crop planting zoning, and agricultural meteorological disaster risk assessment.

Description

Technical Field

[0001] This invention relates to the field of agricultural meteorology and geographic information system application technology, specifically to a method for evaluating and spatially predicting the climate suitability of tobacco cultivation based on multi-source data fusion. Background Technology

[0002] As an important economic crop, tobacco's growth and development are closely related to climatic conditions, and changes in meteorological elements directly affect the yield and quality of tobacco leaves. Northeast my country is a major tobacco-growing region, characterized by severe, dry winters, short summers, concentrated rainfall, and relatively insufficient heat resources. Spatial and temporal fluctuations in meteorological conditions have a significant impact on tobacco production. Therefore, conducting refined evaluation and dynamic monitoring of meteorological suitability for tobacco cultivation is of great significance for optimizing planting layout and improving tobacco leaf quality and yield.

[0003] Currently, while there is some research foundation for meteorological suitability assessment technology for tobacco cultivation, several technical bottlenecks remain. Traditional methods largely rely on observational data from county-level meteorological stations, with spatial resolution typically exceeding 10-25 km, which is insufficient to support the needs of refined planting planning at the township level. Existing assessment models are mostly static analyses, failing to integrate numerical weather prediction data for dynamic updates, thus hindering their ability to effectively address the uncertainties brought about by climate change. Regarding data utilization, the integration of meteorological data with geographic information data (such as topography and soil) is insufficient, failing to fully reflect the complexity of the tobacco growing environment. Furthermore, meteorological disaster early warning and climate suitability assessment are often conducted as two independent processes, lacking an integrated comprehensive evaluation system. Existing technologies largely rely on manual calculation and analysis, failing to achieve intelligent and digital service models, thus failing to meet the demands of modern agriculture for refined services.

[0004] In summary, the core problems faced by existing technologies are: insufficient spatial resolution of meteorological data, static evaluation models, inadequate fusion of multi-source data, separation of disaster early warning and suitability assessment, and a lack of intelligent service capabilities. These problems restrict the accuracy and practicality of meteorological services for tobacco cultivation, necessitating a high-resolution, dynamic, and multi-source data fusion-based method for evaluating the meteorological suitability of tobacco cultivation. Summary of the Invention

[0005] This invention solves the problems of insufficient spatial resolution of meteorological data, static evaluation models, insufficient fusion of multi-source data, separation of disaster early warning and suitability evaluation, and lack of intelligent service capabilities in the prior art.

[0006] A method for analyzing meteorological suitability for tobacco cultivation, the method comprising the following steps: Step 1: Collect meteorological data, geographic information data, and crop data for the target area; Step 2: Perform fusion processing and quality control on the meteorological data, geographic information data, and crop data to generate a fused standardized dataset; the fused standardized dataset includes meteorological element raster data and geographic attribute data that spatially matches the meteorological element raster data; Step 3: Based on the fused standardized dataset, identify the key meteorological factors affecting tobacco yield and quality; Step 4: Based on the aforementioned key meteorological elements, construct the following model: Construct fuzzy membership functions for each key meteorological element, determine the weight coefficients of each key meteorological element, and establish a comprehensive suitability evaluation model. Analyze the statistical relationship between key meteorological elements and geographic attribute data, and establish a spatial distribution model of meteorological elements; Step 5: Based on the spatial distribution model of meteorological elements and the geographic attribute data, calculate the meteorological element values ​​of each preset grid unit within the target area; Step 6: Based on the meteorological element values ​​and the comprehensive suitability evaluation model, calculate the comprehensive suitability index of each preset grid unit; Step 7: Divide the suitability levels according to the comprehensive suitability index and determine the suitability level of each preset grid unit in the target area.

[0007] Based on the aforementioned comprehensive suitability index and suitability level, those skilled in the art can also create climate suitability zoning maps of the target area.

[0008] Further optimization of the scheme: In step 1, the meteorological data includes historical daily meteorological data and numerical forecast data; the geographic information data includes township administrative division maps, digital elevation model data and topographic data; and the crop data includes tobacco planting area, yield and quality data.

[0009] Further optimizing the scheme, in step 2, the method for fusing and quality-controlling the meteorological data, geographic information data, and crop data is as follows: Anomaly identification and missing data filling methods are used to perform quality control on the meteorological data, geographic information data and crop data to obtain quality-controlled meteorological data, geographic information data and crop data; The meteorological data after quality control is used to generate spatially continuous meteorological element raster data using a multi-source data fusion algorithm; Spatial matching is performed between the meteorological element raster data and the quality-controlled geographic information data.

[0010] In a further optimized scheme, the multi-source data fusion algorithm includes Bayesian estimation and spatiotemporal co-kriging; the anomaly identification includes a method combining physiological threshold screening and statistical testing; and the missing data imputation is achieved by using a hierarchical interpolation strategy based on the duration of the missing data.

[0011] Further optimization of the scheme: In step 3, the key meteorological elements include: average temperature from May to September, average temperature from July to August, precipitation in July, total precipitation from May to September, relative humidity in July, and sunshine percentage from May to September.

[0012] Further optimization of the scheme: In step 4, the comprehensive suitability evaluation model is a weighted summation model.

[0013] in, To form a comprehensive suitability index, For the first Suitability index of each meteorological element For the first The weighting coefficients of each meteorological element This represents the number of meteorological elements.

[0014] Further optimization of the scheme: In step 4, the spatial distribution model of meteorological elements is a multiple quadratic regression equation with longitude, latitude, and altitude as independent variables.

[0015] In a further optimized scheme, in step 5, the spatial resolution of the preset grid unit is 100m×100m.

[0016] Further optimization of the scheme: In step 7, the target area is divided into four levels: most suitable area, suitable area, second most suitable area, and unsuitable area according to the comprehensive suitability index.

[0017] A meteorological suitability analysis system for tobacco cultivation, the system comprising the following modules: The data acquisition module is used to collect meteorological data, geographic information data, and crop data for the target area; The data fusion processing module is used to perform fusion processing and quality control on the meteorological data, geographic information data and crop data to generate a fused standardized dataset; the fused standardized dataset includes meteorological element raster data and geographic attribute data that spatially matches the meteorological element raster data; The key meteorological element determination module is used to determine the key meteorological elements affecting tobacco yield and quality based on the fused standardized dataset. The model building module is used to build the following model based on the key meteorological elements: Construct fuzzy membership functions for each key meteorological element, determine the weight coefficients of each key meteorological element, and establish a comprehensive suitability evaluation model. Analyze the statistical relationship between key meteorological elements and geographic attribute data, and establish a spatial distribution model of meteorological elements; The meteorological element value estimation module is used to estimate the meteorological element values ​​of each preset grid unit within the target area based on the spatial distribution model of the meteorological elements and the geographic attribute data. The index calculation module is used to calculate the comprehensive suitability index of each preset grid unit based on the meteorological element values ​​and the comprehensive suitability evaluation model. The grading module is used to classify suitability levels according to the comprehensive suitability index and determine the suitability level of each preset grid unit in the target area.

[0018] The beneficial effects of this invention compared to the prior art are as follows: The analytical method described in this application constructs a spatial distribution model of meteorological elements, divides the study area into grid units at the 100-meter level, and realizes the refined extrapolation of meteorological data from the traditional county level to the township level and even the field level, which significantly improves the spatial resolution of the climate suitability assessment for tobacco planting.

[0019] The analytical method described in this application combines historical meteorological data with numerical forecast data and re-evaluates based on meteorological observation data of the events that have occurred each year. This enables rolling monitoring and dynamic evaluation of climate conditions throughout the entire tobacco growth process, overcoming the shortcomings of traditional static models in dealing with the uncertainties of climate change.

[0020] The analytical method described in this application fuses multi-source meteorological data using Bayesian estimation and spatiotemporal co-kriging, and spatially matches the fused meteorological element raster data with geographic information data, thereby achieving deep integration of meteorological data with geographic factors such as topography and altitude, and comprehensively improving the evaluation model's ability to represent the complexity of the tobacco growth environment.

[0021] The analytical method described in this application constructs fuzzy membership functions of each key meteorological element and determines weight coefficients to establish a comprehensive suitability evaluation model in the form of a weighted summation. This organically integrates the individual evaluations of multiple meteorological elements into a comprehensive climate suitability evaluation, thereby realizing the overall assessment and integrated zoning of climate conditions throughout the entire growth period of tobacco.

[0022] The analytical method described in this application automates the entire process from data fusion processing, model building, grid extrapolation, index calculation, and zoning generation. It iteratively optimizes model parameters using actual yield and quality data, achieving intelligent services from data acquisition to zoning output, and providing scientific and precise decision support for tobacco cultivation. The analytical method described in this invention is applicable to fields such as climate suitability evaluation for tobacco cultivation, crop planting zoning, and agricultural meteorological disaster risk assessment. Attached Figure Description

[0023] Figure 1 This is a flowchart of a method for analyzing the meteorological suitability of tobacco planting as described in Implementation Method 1. Detailed Implementation

[0024] Various embodiments of the present invention will now be clearly and completely described with reference to the accompanying drawings. The embodiments described with reference to the drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0025] Implementation Method 1: This implementation method provides a method for analyzing the meteorological suitability of tobacco cultivation. (See attached document.) Figure 1 This embodiment describes an analysis method that includes the following steps: Step 1: Collect meteorological data, geographic information data, and crop data for the target area; Step 2: Perform fusion processing and quality control on the meteorological data, geographic information data, and crop data to generate a fused standardized dataset; the fused standardized dataset includes meteorological element raster data and geographic attribute data that spatially matches the meteorological element raster data; Step 3: Based on the fused standardized dataset, identify the key meteorological factors affecting tobacco yield and quality; Step 4: Based on the aforementioned key meteorological elements, construct the following model: Construct fuzzy membership functions for each key meteorological element, determine the weight coefficients of each key meteorological element, and establish a comprehensive suitability evaluation model. Analyze the statistical relationship between key meteorological elements and geographic attribute data, and establish a spatial distribution model of meteorological elements; Step 5: Based on the spatial distribution model of meteorological elements and the geographic attribute data, calculate the meteorological element values ​​of each preset grid unit within the target area; Step 6: Based on the meteorological element values ​​and the comprehensive suitability evaluation model, calculate the comprehensive suitability index of each preset grid unit; Step 7: Divide the suitability levels according to the comprehensive suitability index and determine the suitability level of each preset grid unit in the target area.

[0026] Based on the aforementioned comprehensive suitability index and suitability level, those skilled in the art can also create climate suitability zoning maps of the target area.

[0027] Implementation Method 2: This implementation method further defines Implementation Method 1 and provides examples of the meteorological data, geographic information data, and crop data mentioned in step 1.

[0028] The meteorological data includes historical daily meteorological data and numerical weather forecast data; The historical daily meteorological data is derived from the historical daily meteorological data of 190 national meteorological stations in Northeast China since 1965. The meteorological elements include temperature, precipitation, relative humidity, sunshine percentage, and wind speed. The numerical forecast data is obtained through the API interface of the National Meteorological Information Center and supplemented by meteorological densification stations, self-built microclimate stations, and fine-grid multi-element fusion simulation meteorological data. The geographic information data includes township administrative division maps, digital elevation model (DEM) data, and topographic data; The DEM data is at a scale of 1:250,000 and includes longitude, latitude, digital elevation, and administrative boundary information; the terrain data resolution is 100m×100m. The data acquisition methods are as follows: DEM data is obtained through the National Basic Geographic Database, and ASTER GDEM data with a resolution of 30 meters is obtained through the Geospatial Data Cloud. The crop data includes data on tobacco planting area, yield, and quality in the Changbai Mountains over the past 30 years. The quality data includes total sugar content, nicotine content, and potassium content data; The data acquisition methods are as follows: county-level tobacco production data are obtained from the provincial statistics bureaus, county-level tobacco planting area data are obtained from the county agricultural bureaus, and tobacco quality data are obtained from the provincial tobacco companies.

[0029] The meteorological data, geographic information data, and crop data are classified and stored, and a unified data indexing system is established. The data structure is as follows: Meteorological data tables: record historical and forecast data of various meteorological elements at each meteorological station; Geographic information table: Records information such as geographical coordinates, elevation, slope, and aspect of each township; Crop data table: Records information such as tobacco planting area, yield, and quality in each township.

[0030] Implementation Method 3: This implementation method further defines Implementation Method 1 and provides an example of the fusion processing and quality control of the meteorological data, geographic information data, and crop data in step 2.

[0031] The method for fusing and quality-controlling the meteorological data, geographic information data, and crop data is as follows: Anomaly identification and missing data filling methods are used to perform quality control on the meteorological data, geographic information data and crop data to obtain quality-controlled meteorological data, geographic information data and crop data; The meteorological data after quality control is used to generate spatially continuous meteorological element raster data using a multi-source data fusion algorithm; Spatial matching is performed between the meteorological element raster data and the quality-controlled geographic information data.

[0032] Implementation Method Four: This implementation method further defines Implementation Method Three and provides examples of the multi-source data fusion algorithm, anomaly identification, and missing data imputation.

[0033] The multi-source data fusion algorithm includes Bayesian estimation and spatiotemporal co-kriging. First, using the observation data from the national meteorological stations as a benchmark, the Bayesian estimation method is used to correct the bias in the contemporaneous observation data from the densified stations, eliminating systematic errors caused by differences in observation instruments and observation environments at different stations. The correction formula is as follows:

[0034] in For the corrected data, The original observation data, This is the average of the baseline data from the national meteorological stations. The standard deviation of the national meteorological station baseline data. The mean of the data from the site to be corrected. The standard deviation of the data from the site to be corrected; Secondly, for the corrected station data and fine grid simulation data, the spatiotemporal co-kriging method is adopted. Combining the spatiotemporal correlation of meteorological elements, the discrete station data and grid simulation data are fused to generate spatially continuous and uniformly resolution meteorological element raster data. During the fusion process, terrain auxiliary variables such as altitude and slope are introduced to improve the fusion accuracy of mountain meteorological data. The step of spatially matching the meteorological element raster data with geographic information data includes: First, the meteorological element raster data, DEM data, and administrative division data are matched with latitude and longitude coordinates and Gaussian plane coordinates to establish a unified spatial reference system. The WGS84 coordinate system is adopted to ensure the consistency of spatial location of data from different sources. Secondly, by using the GIS spatial overlay analysis function, meteorological element raster data is overlaid with topographic raster data and administrative division vector data, and the meteorological element values ​​and geographic attributes corresponding to each grid unit are extracted to generate a meteorological element-geographic attribute association data table. Finally, to address the spatial misalignment issue that arises during the fusion process, a quadratic linear correction method is adopted, using meteorological station coordinates and township center points as feature points to correct the deviation and ensure spatial consistency of the data. The anomaly identification includes a method that combines physiological threshold screening with statistical testing. Based on the tobacco growth characteristics in the Changbai Mountains, physiological threshold ranges for various meteorological elements were set; data exceeding these ranges were preliminarily identified as abnormal. A 3... The principles and Grubbs test are used to verify the initially identified abnormal data, eliminate falsely identified data, and confirm the real abnormal data. For single-point or single-day abnormal data, linear interpolation is used for correction; for continuous multi-day abnormal data, BP neural network interpolation is used, and an interpolation model is constructed by combining the normal data of 3-5 neighboring sites in the same period to ensure the continuity of the data. The missing data filling adopts a hierarchical interpolation strategy based on the duration of the missing data. For missing values ​​in the original data, select the appropriate imputation method based on the duration of the missing value and the data type: For short-term missing data, with a duration of ≤3 days, linear interpolation is used to fill the missing data by linear fitting using effective data before and after the missing period. For intermediate-term missing data, where 4 ≤ missing duration ≤ 15 days, a moving average interpolation method is used with a window size of 7 days, and the missing data is corrected and filled by combining the historical average of the same period. For long-term missing data (missing data duration > 15 days), a neighboring site interpolation method based on geographical similarity is used to select the three neighboring sites with the closest altitude, latitude, and climate type, calculate their average data for the same period, and combine them with the average historical data of the missing sites for weighted filling. The weights are set based on the geographical distance between the sites, with the closer the distance, the greater the weight. For missing values ​​in crop and geographic data, the nearest neighbor township matching method is used to fill in the missing values, taking into account the geographic and meteorological similarities of the townships.

[0035] Implementation Method 5: This implementation method further defines Implementation Method 1 and provides an example of the key meteorological elements mentioned in step 3.

[0036] Correlation analysis was used to calculate the correlation coefficients between average temperature, precipitation, relative humidity, sunshine percentage and tobacco yield and quality. The calculation period included the entire tobacco growth period (May-September) and each month (May, June, July, August, and September). Perform a significance test on the correlation coefficients (α=0.05 or 0.01) and mark the significantly correlated meteorological elements; By analyzing the magnitude and significance of correlation coefficients, meteorological elements closely related to tobacco yield and quality are preliminarily screened. In this embodiment, the key meteorological elements screened include: average temperature from May to September, average temperature from July to August, precipitation in July, total precipitation from May to September, relative humidity in July, and sunshine percentage from May to September.

[0037] Implementation Method Six: This implementation method is a further limitation of Implementation Method One, and provides an example of the comprehensive suitability evaluation model in step 4.

[0038] A fuzzy membership function model for the suitability of key meteorological elements for tobacco planting is established, mapping the measured or forecasted values ​​of meteorological elements to a suitability index. The membership functions for each key meteorological element are as follows: Average temperature from May to September (reflecting heat conditions during the tobacco field):

[0039] Average temperature in July and August (reflecting the temperature conditions during the peak tobacco growing season):

[0040] July precipitation (reflecting the moisture conditions during the peak growing season for tobacco):

[0041] Total precipitation from May to September (reflecting the total precipitation during the tobacco's vegetative growth period to maturity and harvest):

[0042] K=0.85 indicates that the effect of a unit water surplus is less than that of a unit water deficit; Sunshine percentage from May to September (reflecting light conditions during the tobacco growing season):

[0043] July relative humidity (reflecting humidity conditions during the peak tobacco growing season):

[0044] in, For temperature, For precipitation, For Rizhao, Humidity; The weighting coefficients of the key meteorological elements are determined based on the correlation coefficients between meteorological elements and tobacco yield and quality. In this embodiment, the weighting coefficients are set separately for each key meteorological element, taking into account the climate characteristics of the Changbai Mountains and practical experience in tobacco cultivation. The preferred weighting coefficients are shown in Table 1.

[0045] Table 1

[0046] The combined weight of each key meteorological element is 1.

[0047] It should be noted that those skilled in the art can adjust the above weighting coefficients according to actual application scenarios and regional climate characteristics, which still fall within the protection scope of this invention.

[0048] The comprehensive suitability evaluation model is a weighted summation model:

[0049] in, To form a comprehensive suitability index, For the first Suitability index of each meteorological element For the first The weighting coefficients of each meteorological element This represents the number of meteorological elements.

[0050] Implementation Method Seven: This implementation method is a further limitation of Implementation Method One, and provides an example of the spatial distribution model of meteorological elements in step 4.

[0051] The spatial distribution model of meteorological elements is a multiple quadratic regression equation with longitude, latitude, and altitude as independent variables. The expression for the spatial distribution model of meteorological elements is: July-August temperature model:

[0052] Temperature model from May to September:

[0053] July precipitation model:

[0054] Precipitation model from May to September:

[0055] Sunlight model:

[0056] Humidity model:

[0057] in, Longitude As a dimension, This refers to altitude.

[0058] Implementation Method 8: This implementation method is a further limitation of Implementation Method 1, and provides an example of the preset grid unit in step 5.

[0059] Based on the spatial distribution model of meteorological elements, the spatial distribution of meteorological element values ​​in a preset grid unit in the study area is calculated under a GIS platform; the spatial resolution of the preset grid unit is 100m×100m. The operation steps are as follows: import DEM data and the spatial distribution model of meteorological elements, generate raster maps of each meteorological element, calculate the meteorological element values ​​of each grid point, and ensure that the model passes the significance test.

[0060] Implementation Method Nine: This implementation method is a further limitation of Implementation Method One, and provides an example of the comprehensive suitability index and suitability level in step 7.

[0061] Based on the fuzzy membership function values ​​and weight coefficients of each key meteorological element, the comprehensive suitability index of each preset grid unit is calculated. The operation steps are as follows: calculate the fuzzy membership function values ​​of each key meteorological element; obtain the comprehensive suitability index by weighted summation; and ensure that the calculation process conforms to fuzzy mathematics theory. The comprehensive suitability index is divided into four levels: most suitable area, suitable area, second most suitable area, and unsuitable area. The zoning standards are shown in Table 2.

[0062] Table 2

[0063] Based on the comprehensive suitability index range, four levels are divided to generate a climate suitability zoning map, ensuring that the zoning results are consistent with the actual planting areas.

[0064] Implementation Method 10: This implementation method is a further limitation of Implementation Method 1. It uses actual tobacco production and quality data to verify the zoning results, and adjusts the boundary thresholds, weight coefficients, and spatial distribution model parameters of the fuzzy membership function for dividing the most suitable interval, suitable transition interval, and unsuitable interval based on the verification results. The verification metrics are: Correlation coefficient (R): measures the degree of correlation between predicted and measured values; Root mean square error (RMSE): measures the magnitude of prediction error; Coefficient of determination (R²): measures the explanatory power of a model; Typical areas were selected as validation samples. The suitability index predicted by the model was calculated. Actual tobacco yield and quality data were collected. Correlation coefficient, RMSE, R² and other indicators were calculated to verify the consistency between the zoning results and the actual planting areas. Since tobacco yield and quality are the result of multiple factors, including meteorological conditions, soil, and cultivation practices, and this model focuses on evaluating the suitability of "meteorological conditions," the core of the validation lies in verifying the climate suitability index calculated by the model. The statistical significance and spatial consistency between the actual production performance (output, quality) and the actual production performance.

[0065] Specific verification process: Correlation test: Calculate the correlation at each validation point. The correlation coefficient between the value and the actual yield per mu, the main chemical components (total sugar, nicotine, etc.) and the sensory evaluation score; if the correlation coefficient is significantly positive (P<0.05), it indicates that the model can effectively reflect the limiting or promoting effect of climate on production; Level matching degree analysis: Statistically analyze the average yield and average quality score within different suitability level zones to verify whether they meet the decreasing rule of "most suitable zone > suitable zone > second most suitable zone > unsuitable zone".

[0066] Goodness-of-fit assessment: Constructing " The "yield / quality" regression equation is used to quantify the model's ability to explain actual production differences using the coefficient of determination R²; an R² of 0.5 or higher indicates that the model has good predictive and guiding value.

[0067] Based on the validation results, the model parameters were optimized: the threshold of the fuzzy membership function was adjusted, the weight coefficients of meteorological elements were adjusted, the spatial distribution model of meteorological elements was optimized, and the model prediction accuracy was improved.

[0068] Implementation Method Eleven: This implementation method provides a tobacco planting meteorological suitability analysis system, which includes the following modules: The data acquisition module is used to collect meteorological data, geographic information data, and crop data for the target area; The data fusion processing module is used to perform fusion processing and quality control on the meteorological data, geographic information data and crop data to generate a fused standardized dataset; the fused standardized dataset includes meteorological element raster data and geographic attribute data that spatially matches the meteorological element raster data; The key meteorological element determination module is used to determine the key meteorological elements affecting tobacco yield and quality based on the fused standardized dataset. The model building module is used to build the following model based on the key meteorological elements: Construct fuzzy membership functions for each key meteorological element, determine the weight coefficients of each key meteorological element, and establish a comprehensive suitability evaluation model. Analyze the statistical relationship between key meteorological elements and geographic attribute data, and establish a spatial distribution model of meteorological elements; The meteorological element value estimation module is used to estimate the meteorological element values ​​of each preset grid unit within the target area based on the spatial distribution model of the meteorological elements and the geographic attribute data. The index calculation module is used to calculate the comprehensive suitability index of each preset grid unit based on the meteorological element values ​​and the comprehensive suitability evaluation model. The grading module is used to classify suitability levels according to the comprehensive suitability index and determine the suitability level of each preset grid unit in the target area.

Claims

1. A tobacco cultivation meteorological suitability analysis method, characterized by, The analytical method includes the following steps: Step 1: Collect meteorological data, geographic information data, and crop data for the target area; Step 2: Perform fusion processing and quality control on the meteorological data, geographic information data, and crop data to generate a fused standardized dataset; the fused standardized dataset includes meteorological element raster data and geographic attribute data that spatially matches the meteorological element raster data; Step 3: Based on the fused standardized dataset, identify the key meteorological factors affecting tobacco yield and quality; Step 4: Based on the aforementioned key meteorological elements, construct the following model: Construct fuzzy membership functions for each key meteorological element, determine the weight coefficients of each key meteorological element, and establish a comprehensive suitability evaluation model. Analyze the statistical relationship between key meteorological elements and geographic attribute data, and establish a spatial distribution model of meteorological elements; Step 5: Based on the spatial distribution model of meteorological elements and the geographic attribute data, calculate the meteorological element values ​​of each preset grid unit within the target area; Step 6: Based on the meteorological element values ​​and the comprehensive suitability evaluation model, calculate the comprehensive suitability index of each preset grid unit; Step 7: Divide the suitability levels according to the comprehensive suitability index and determine the suitability level of each preset grid unit in the target area.

2. The method for analyzing the agrometeorological suitability of tobacco cultivation according to claim 1, characterized in that, In step 1, the meteorological data includes historical daily meteorological data and numerical forecast data; the geographic information data includes township administrative division maps, digital elevation model data, and topographic data; and the crop data includes tobacco planting area, yield, and quality data.

3. The method according to claim 1, wherein, In step 2, the method for fusing and quality-controlling the meteorological data, geographic information data, and crop data is as follows: Anomaly identification and missing data filling methods are used to perform quality control on the meteorological data, geographic information data and crop data to obtain quality-controlled meteorological data, geographic information data and crop data; The meteorological data after quality control is used to generate spatially continuous meteorological element raster data using a multi-source data fusion algorithm; Spatial matching is performed between the meteorological element raster data and the quality-controlled geographic information data.

4. A method of tobacco planting agrometeorological suitability analysis according to claim 3, characterized in that, The multi-source data fusion algorithm includes Bayesian estimation and spatiotemporal co-kriging; the anomaly identification includes a method combining physiological threshold screening and statistical testing; and the missing data imputation is achieved by using a hierarchical interpolation strategy based on the duration of the missing data.

5. The method for analyzing meteorological suitability for tobacco cultivation according to claim 1, characterized in that, In step 3, the key meteorological elements include: average temperature from May to September, average temperature from July to August, precipitation in July, total precipitation from May to September, relative humidity in July, and sunshine percentage from May to September.

6. The method for analyzing meteorological suitability for tobacco cultivation according to claim 1, characterized in that, In step 4, the comprehensive suitability evaluation model is a weighted summation model: in, To form a comprehensive suitability index, For the first Suitability index of each meteorological element For the first The weighting coefficients of each meteorological element This represents the number of meteorological elements.

7. The method for analyzing meteorological suitability for tobacco cultivation according to claim 1, characterized in that, In step 4, the spatial distribution model of meteorological elements is a multiple quadratic regression equation with longitude, latitude, and altitude as independent variables.

8. The method for analyzing meteorological suitability for tobacco cultivation according to claim 1, characterized in that, In step 5, the spatial resolution of the preset grid unit is 100m×100m.

9. The method for analyzing meteorological suitability for tobacco cultivation according to claim 1, characterized in that, In step 7, the target area is divided into four levels: most suitable area, suitable area, second most suitable area, and unsuitable area, based on the comprehensive suitability index.

10. A system for analyzing meteorological suitability for tobacco cultivation, characterized in that, The analysis system includes the following modules: The data acquisition module is used to collect meteorological data, geographic information data, and crop data for the target area; The data fusion processing module is used to perform fusion processing and quality control on the meteorological data, geographic information data and crop data to generate a fused standardized dataset; the fused standardized dataset includes meteorological element raster data and geographic attribute data that spatially matches the meteorological element raster data; The key meteorological element determination module is used to determine the key meteorological elements affecting tobacco yield and quality based on the fused standardized dataset. The model building module is used to build the following model based on the key meteorological elements: Construct fuzzy membership functions for each key meteorological element, determine the weight coefficients of each key meteorological element, and establish a comprehensive suitability evaluation model. Analyze the statistical relationship between key meteorological elements and geographic attribute data, and establish a spatial distribution model of meteorological elements; The meteorological element value estimation module is used to estimate the meteorological element values ​​of each preset grid unit within the target area based on the spatial distribution model of the meteorological elements and the geographic attribute data. The index calculation module is used to calculate the comprehensive suitability index of each preset grid unit based on the meteorological element values ​​and the comprehensive suitability evaluation model. The grading module is used to classify suitability levels according to the comprehensive suitability index and determine the suitability level of each preset grid unit in the target area.

Images