A smart agriculture big data cloud service supervision platform integrating aerial remote sensing and spatial ranging information

Abstract

The present invention relates to the technical field of spatial ranging, and specifically, to a smart agriculture big data cloud service supervision platform that integrates aerial remote sensing and spatial ranging information. It includes: a data acquisition unit that obtains agricultural data based on a multi-source acquisition module; a data processing unit that performs cleaning, calibration, and matching processing on the agricultural data collected by the data acquisition unit; a data analysis unit that performs multi-faceted evaluation and analysis on the agricultural data processed by the data processing unit through multi-party analysis techniques; and a storage management unit that manages and protects agricultural data through cloud computing distributed storage technology based on the analysis results of the data analysis unit. The design of the present invention uses multi-party analysis techniques to perform multi-dimensional evaluation and prediction on agricultural data, providing a scientific basis and intelligent decision-making support for agricultural production; through cloud computing distributed storage technology, it realizes the rapid access, backup, and sharing of large-scale agricultural data, while ensuring the security and privacy of the data.

Description

Technical Field

[0001] The present invention relates to the technical field of spatial ranging, and specifically, to a smart agriculture big data cloud service supervision platform that integrates aerial remote sensing and spatial ranging information. Background Art

[0002] A smart agriculture big data cloud service supervision platform that integrates aerial remote sensing and spatial ranging information is a comprehensive agricultural management solution constructed based on the new generation of information technology. This platform integrates aerial remote sensing technologies (such as drones or multispectral satellite images) and spatial ranging technologies (such as GNSS global navigation satellite system, LiDAR, etc.) to achieve all-round and high-precision monitoring of farmland environment, crop growth conditions, soil characteristics, and meteorological conditions. At the same time, relying on cloud computing, big data analysis, and artificial intelligence algorithms, the platform can integrate multi-source data, conduct in-depth mining and intelligent analysis, and provide precise decision-making support for agricultural production. Specifically, it can not only monitor the growth of crops, the occurrence of pests and diseases, and the status of soil moisture and nutrients in real time, but also predict yield trends, optimize irrigation and fertilization plans, and support the traceability of agricultural product quality and market supply and demand analysis. In addition, with the help of geographic information system (GIS) and visualization technologies, the platform can generate intuitive three-dimensional digital twin models to help managers comprehensively master the distribution and dynamic changes of agricultural resources.

[0003] In the prior art, there are problems such as insufficient data acquisition accuracy, low processing efficiency, limited analysis ability, and weak data security in the smart agriculture big data cloud service supervision platform that integrates aerial remote sensing and spatial ranging information. Therefore, the present invention proposes an improved solution. Summary of the Invention

[0004] The purpose of the present invention is to provide a smart agriculture big data cloud service supervision platform that integrates aerial remote sensing and spatial ranging information to solve the problems of insufficient data acquisition accuracy, low processing efficiency, limited analysis ability, and weak data security in the existing smart agriculture big data cloud service supervision platform that integrates aerial remote sensing and spatial ranging information as mentioned in the above background art.

[0005] To achieve the above purpose, the present invention aims to provide a smart agriculture big data cloud service supervision platform that integrates aerial remote sensing and spatial ranging information, including a data acquisition unit, and the data acquisition unit obtains agricultural data based on a multi-source acquisition module;

[0006] A data processing unit, and the data processing unit performs cleaning, calibration, and matching processing on the agricultural data collected by the data acquisition unit;

[0007] The data analysis unit, which is based on the agricultural data processed by the data processing unit, conducts multi-faceted evaluation and analysis through multi-party analysis techniques;

[0008] The storage management unit, which is based on the analysis results of the data analysis unit, manages and protects agricultural data through cloud computing distributed storage technology.

[0009] As a further improvement of this technical solution, the multi-source acquisition module includes an aerial remote sensing module, a spatial ranging module, and a ground sensor module;

[0010] Among them, the agricultural data includes farmland area, soil humidity, temperature, and nutrient content;

[0011] The aerial remote sensing module is used to collect high-resolution multi-spectral, thermal infrared, and visible light images;

[0012] The spatial ranging module is used to obtain farmland area information;

[0013] The ground sensor module is used to monitor soil humidity, temperature, nutrient content, and meteorological conditions.

[0014] As a further improvement of this technical solution, the data processing unit includes a data cleaning module, a data correction module, and a data matching module;

[0015] Among them, the data cleaning module is used to remove noise, outliers, and redundant data;

[0016] Among them, the specific process of removing noise, outliers, and redundant data is as follows:

[0017] Use the mean filter algorithm to remove noise in the remote sensing image:

[0018] ;

[0019] In the formula, represents the pixel value after denoising; represents the pixel value in the window centered on in the original image; represents the neighborhood window centered on ; represents the window the total number of pixel points in;

[0020] Use the standard deviation method to detect outliers:

[0021] ;

[0022] In the formula, represents the value of the current data point; Represents the standardized value; Represents the mean value of the data; Represents the standard deviation of the data;

[0023] Use correlation analysis to remove redundant features:

[0024] ;

[0025] In the formula, Represents the feature And the feature The correlation coefficient of; Represents the feature And the feature The covariance of; Represents the feature The standard deviation of; Represents the feature The standard deviation of; Represents the feature index variable; Represents another feature index variable;

[0026] The data correction module is used to perform radiometric correction, geometric correction and atmospheric correction on the images of the aerial remote sensing module;

[0027] The data matching module is used to match agricultural data in the temporal and spatial dimensions.

[0028] As a further improvement of the technical solution, the specific processes of performing radiometric correction, geometric correction and atmospheric correction are as follows:

[0029] Radiometric correction:

[0030] ;

[0031] In the formula, Represents the illumination radiance value; Represents the sensor-specific scale factor; Represents the digital value; Represents the sensor-specific offset;

[0032] Geometric correction:

[0033] ;

[0034] In the formula, Represents the corrected coordinate matrix; Represents the original coordinate matrix; Represents the affine transformation matrix; Represents the translation matrix;

[0035] Atmospheric correction:

[0036] ;

[0037] In the formula, represents the surface albedo; represents the atmospheric path radiation value; represents the atmospheric transmittance.

[0038] As a further improvement of this technical solution, the specific process of matching agricultural data in the spatio-temporal dimension is as follows:

[0039] Use spatial interpolation method to register time series data:

[0040] ;

[0041] In the formula, represents the eigenvalue at the target time point ; represents the farmland area eigenvalue at time point ; represents the soil moisture eigenvalue at time point ; represents the temperature eigenvalue at time point ; represents the nutrient content eigenvalue at time point ; represents the weight at time point ; represents the weight at time point ; represents the weight at time point ; represents the weight at time point ; represents the time index variable.

[0042] As a further improvement of this technical solution, the specific steps of performing multi-faceted evaluation and analysis through multi-party analysis technology are as follows:

[0043] Among them, the multi-party analysis technology includes a crop growth dynamic model, a remote sensing image machine learning algorithm, and a soil quality assessment method;

[0044] S6.1. Combine agricultural data and evaluate and analyze soil quality through the soil quality assessment method;

[0045] S6.2. Identify the occurrence area and severity of pests and diseases through the remote sensing image machine learning algorithm;

[0046] S6.3. Use historical agricultural data and real-time agricultural data to construct a crop growth dynamic model to predict crop growth and yield.

[0047] As a further improvement of this technical solution, in S6.1, the specific process of evaluating and analyzing soil quality through the soil quality assessment method is as follows:

[0048] Calculate the comprehensive soil nutrient index:

[0049] ;

[0050] In the formula, represents the comprehensive soil nutrient index; represents the nitrogen content; represents the phosphorus content; represents the potassium content; represents the weight of nitrogen; represents the weight of phosphorus; represents the weight of potassium;

[0051] Use the remote sensing inversion model to estimate the organic matter content:

[0052] ;

[0053] In the formula, represents the organic content; represents the influence degree of the normalized difference vegetation index on the organic matter content; represents at the base value of the soil organic matter content when it is zero; represents the vegetation index;

[0054] Standardize each index and then perform weighted summation to obtain the comprehensive soil quality score:

[0055] ;

[0056] In the formula, represents the comprehensive soil quality score; represents the standardized value of the th index; represents the weight of the th index; represents the total number of indexes; represents the index index variable.

[0057] As a further improvement of this technical solution, in S6.2, the specific process of identifying the occurrence area and severity of pests and diseases through the remote sensing image machine learning algorithm is as follows:

[0058] Extract the spectral features in the remote sensing image and normalize the difference vegetation index :

[0059] ;

[0060] In the formula, represents the reflectance in the near-infrared band;

[0061] Use a support vector machine to classify the pest and disease area:

[0062] ;

[0063] In the formula, represents the classification function; represents the input feature vector; represents the number of input feature vectors; represents the number index variable of the input feature vector; represents the Lagrange multiplier; represents the kernel function; represents the bias term; represents the training sample label; represents the input feature vector label;

[0064] Among them, the input feature vector is:

[0065] ;

[0066] Judge whether the pixel point belongs to the pest and disease area according to the classification result:

[0067] ;

[0068] Calculate the proportion of the pest and disease coverage area in the total planting area:

[0069] ;

[0070] In the formula, represents the proportion of the pest and disease coverage area in the total planting area; represents the resolution;

[0071] Considering that the pesticide coverage area affects the occurrence area and severity of pests and diseases, a pesticide coverage area variable is introduced to optimize the remote sensing image machine learning algorithm:

[0072] ;

[0073] In the formula, represents the classification function with the pesticide coverage area variable introduced; represents the pesticide coverage area variable;

[0074] After introducing the pesticide coverage area variable, judge whether the pixel point belongs to the pest and disease area according to the classification result:

[0075] ;

[0076] Calculate the proportion of the pest and disease coverage area in the total planting area:

[0077] ;

[0078] In the formula, represents the proportion of the pest and disease coverage area in the total planting area after introducing the pesticide coverage area variable; represents the pesticide effectiveness coefficient.

[0079] As a further improvement of this technical solution, in the S6.3, the specific process of constructing the crop growth dynamic model is:

[0080] Use the crop growth dynamic model to predict the final yield:

[0081] ;

[0082] In the formula, represents the predicted yield; represents the proportionality coefficient; represents the offset; represents the growth of the crop at time ;

[0083] Among them, is specifically:

[0084] ;

[0085] In the formula, represents the maximum growth value; represents the growth rate; represents the time to reach the half-saturation value;

[0086] Considering that soil oxygen concentration, temperature, light radiation brightness, soil nutrients, soil acidity and alkalinity, and soil humidity have an impact on crop growth, variables of soil oxygen concentration, temperature, light radiation brightness, soil nutrients, soil acidity and alkalinity, and soil humidity are introduced to optimize the crop growth dynamic model:

[0087] ;

[0088] In the formula, represents the growth of the crop introduced with soil oxygen concentration, temperature, light radiation brightness, soil nutrients, soil acidity and alkalinity, and soil humidity at time ; represents the proportionality coefficient affected by soil oxygen concentration, temperature, and soil nutrients; represents the offset affected by soil nutrients and soil acidity and alkalinity;

[0089] Among them, is:

[0090] ;

[0091] In the formula, represents the maximum growth value affected by soil oxygen concentration, light radiation brightness, soil nutrients, and soil humidity; represents the growth rate affected by soil oxygen concentration, temperature, and soil acidity and alkalinity; represents the soil oxygen concentration; represents the temperature; represents the soil acidity and alkalinity; represents the soil humidity;

[0092] And considering that the pest and disease coverage area has an inhibitory effect on the maximum growth value and growth rate of crops, the pest and disease coverage area is introduced to optimize the crop growth dynamic model:

[0093] ;

[0094] In the formula, represents the final predicted yield; represents the inhibition coefficient of pests and diseases on the yield; represents the growth amount optimized again after introducing the pest and disease coverage area;

[0095] Among them, is:

[0096] ;

[0097] In the formula, represents the inhibition coefficient of pests and diseases on the maximum growth value; represents the inhibition coefficient of pests and diseases on the growth rate;

[0098] Considering that the yield is affected by the multi-stage cumulative effect, the multi-stage cumulative effect is introduced to optimize the crop growth dynamic model:

[0099] ;

[0100] In the formula, represents the predicted yield considering the influence of soil oxygen concentration, temperature, light radiation brightness, soil nutrients, soil acidity and alkalinity, soil humidity, and multi-stage cumulative effect; represents the growth amount at the tillering stage; represents the growth amount at the flowering stage; represents the growth amount at the filling stage;

[0101] The root mean square error is used to evaluate the prediction accuracy of the model:

[0102] ;

[0103] In the formula, represents the root mean square error; represents the actual observed value; represents the model predicted value; represents the number of samples; represents the sample index variable.

[0104] As a further improvement of the present technical solution, the specific steps for managing and protecting agricultural data through cloud computing distributed storage technology are as follows:

[0105] S10.1. Efficiently store agricultural data using cloud computing distributed storage technology;

[0106] Among them, cloud computing distributed storage technology includes cloud object storage technology, relational databases, and distributed file systems;

[0107] S10.2. Classify, manage the life cycle, and provide sharing services for agricultural data;

[0108] S10.3. Use encryption technology to protect the security of data during transmission and storage.

[0109] Compared with the prior art, the beneficial effects of the present invention are:

[0110] 1. In the intelligent agricultural big data cloud service supervision platform that integrates aerial remote sensing and spatial ranging information, the multi-source acquisition module obtains agricultural-related data from multiple channels to provide a comprehensive, real-time, and high-precision agricultural data foundation for the platform, ensuring reliable data support for subsequent analysis and decision-making. The original agricultural data obtained by the data acquisition unit is cleaned, corrected, and matched, and the chaotic original data is transformed into a structured and high-quality data set.

[0111] 2. In the intelligent agricultural big data cloud service supervision platform that integrates aerial remote sensing and spatial ranging information, by adopting multi-party analysis technology, multi-dimensional evaluation and prediction of agricultural data are carried out to provide a scientific basis and intelligent decision-making support for agricultural production; through cloud computing distributed storage technology, rapid access, backup, and sharing of large-scale agricultural data are realized, while ensuring the security and privacy of the data. BRIEF DESCRIPTION OF THE DRAWINGS

[0112] Figure 1 is the overall flow block diagram of the present invention;

[0113] The meanings of each label in the figure are as follows:

[0114] 1. Data acquisition unit; 11. Multi-source acquisition module; 111. Aerial remote sensing module; 112. Spatial ranging module; 113. Ground sensor module; 2. Data processing unit; 21. Data cleaning module; 22. Data correction module; 23. Data matching module; 3. Data analysis unit; 4. Storage management unit. Detailed implementation mode

[0115] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0116] Embodiment

[0117] Please refer to Figure 1 As shown, a smart agriculture big data cloud service supervision platform integrating aerial remote sensing and spatial ranging information is provided, including a data acquisition unit 1. The data acquisition unit 1 acquires agricultural data based on the multi-source acquisition module 11;

[0118] In this example, the multi-source acquisition module 11 includes an aerial remote sensing module 111, a spatial ranging module 112, and a ground sensor module 113;

[0119] Among them, the agricultural data includes farmland area, soil humidity, temperature, and nutrient content;

[0120] The aerial remote sensing module 111 is used to collect high-resolution multi-spectral, thermal infrared, and visible light images;

[0121] The spatial ranging module 112 is used to obtain farmland area information;

[0122] The ground sensor module 113 is used to monitor soil humidity, temperature, nutrient content, and meteorological conditions.

[0123] Specifically, in a smart agriculture big data cloud service supervision platform that integrates aerial remote sensing and spatial ranging information, the data acquisition unit 1 comprehensively obtains agricultural data through the multi-source acquisition module 11. Among them, the aerial remote sensing module 111 is responsible for collecting high-resolution multi-spectral, thermal infrared, and visible light images to monitor crop growth status, health conditions, and environmental changes; the spatial ranging module 112 provides farmland area and crop height information to assist in precise farmland planning and crop structure analysis; the ground sensor module 113 real-time monitors soil humidity, temperature, nutrient content, and meteorological conditions to provide refined environmental data support for agricultural production. The three work together to build a "sky-ground integrated" data acquisition system, providing comprehensive and accurate basic data for subsequent data processing, analysis, and decision-making, thereby improving the intelligent level of agricultural production and resource utilization efficiency.

[0124] The data processing unit 2 processes the agricultural data collected by the data acquisition unit 1 through cleaning, calibration, and matching;

[0125] In this example, the data processing unit 2 includes a data cleaning module 21, a data calibration module 22, and a data matching module 23;

[0126] Among them, the data cleaning module 21 is used to remove noise, outliers, and redundant data;

[0127] Among them, the specific process of removing noise, outliers, and redundant data is as follows:

[0128] Use the mean filtering algorithm to remove noise in the remote sensing image:

[0129] ;

[0130] In the formula, represents the pixel value after denoising; represents the pixel value in the window centered on in the original image; represents the neighborhood window centered on ; represents the window the total number of pixels in;

[0131] Use the standard deviation method to detect outliers:

[0132] ;

[0133] In the formula, represents the value of the current data point; represents the value after standardization; represents the mean value of the data; represents the standard deviation of the data;

[0134] Remove redundant features using correlation analysis:

[0135] ;

[0136] In the formula, represents the correlation coefficient between feature and feature ; represents the covariance between feature and feature ; represents the standard deviation of feature ; represents the standard deviation of feature ; represents the feature index variable; represents another feature index variable;

[0137] The data correction module 22 is used to perform radiometric correction, geometric correction, and atmospheric correction on the images of the aerial remote sensing module 111;

[0138] In this example, the specific processes of performing radiometric correction, geometric correction, and atmospheric correction are as follows:

[0139] Radiometric correction:

[0140] ;

[0141] In the formula, represents the illumination radiance value; represents the sensor-specific scale factor; represents the digitized value; represents the sensor-specific offset;

[0142] Specifically, the illumination radiance value is obtained through the aerial remote sensing module 111;

[0143] Geometric correction:

[0144] ;

[0145] In the formula, represents the corrected coordinate matrix; represents the original coordinate matrix; represents the affine transformation matrix; represents the translation matrix;

[0146] Atmospheric correction:

[0147] ;

[0148] In the formula, represents the surface reflectance; represents the atmospheric path radiation value; represents the atmospheric transmittance.

[0149] Among them, the atmospheric path radiation value and the atmospheric transmittance are obtained through the aerial remote sensing module 111;

[0150] Specifically, in a smart agriculture big data cloud service supervision platform that integrates aerial remote sensing and spatial ranging information, the specific processes of radiometric correction, geometric correction, and atmospheric correction ensure the quality and reliability of remote sensing image data. Radiometric correction converts digital values into light radiation luminance values through formulas to eliminate the influence of sensor characteristics on the data; geometric correction uses an affine transformation matrix and a translation matrix to convert the original coordinates into corrected coordinates to correct the geometric distortion of the image caused by sensor or terrain factors; atmospheric correction removes the influence of atmospheric scattering and absorption on the surface reflectance through formulas to improve the authenticity of the image. The combined effect of these three correction processes significantly improves the accuracy and usability of remote sensing images, providing high-quality basic data for subsequent data analysis, crop monitoring, and decision support, and is an important technical guarantee for realizing precise management of smart agriculture.

[0151] The data matching module 23 is used to match agricultural data in the spatio-temporal dimension.

[0152] In this example, the specific process of matching agricultural data in the spatio-temporal dimension is as follows:

[0153] Use spatial interpolation method for the registration of time series data:

[0154] ;

[0155] In the formula, represents the eigenvalue at the target time point ; represents the farmland area eigenvalue at time point ; represents the soil moisture eigenvalue at time point ; represents the temperature eigenvalue at time point ; represents the nutrient content eigenvalue at time point ; represents the weight at time point ; represents the weight at time point ; represents the weight at time point ; represents the weight at time point ; represents the time index variable.

[0156] Specifically, in a smart agriculture big data cloud service supervision platform that integrates aerial remote sensing and spatial ranging information, through time series data registration, feature extraction and matching, matching is achieved in the spatio-temporal dimension of agricultural data. Specifically, the spatial interpolation method is used to register data at different time points, and continuous data at the target time point is generated through weighted summation to make up for the data missing caused by the time sampling interval; it provides high-quality and high-precision comprehensive data support for crop monitoring, environmental analysis and precision agriculture decision-making, and is the core technical link to realize the intelligent management of smart agriculture.

[0157] Furthermore, in a smart agriculture big data cloud service supervision platform that integrates aerial remote sensing and spatial ranging information, the data cleaning module uses the mean filter algorithm to remove remote sensing image noise, the standard deviation method to detect outliers, and correlation analysis to eliminate redundant features to ensure the accuracy and effectiveness of the data; the data correction module performs radiometric correction, geometric correction and atmospheric correction on aerial remote sensing images to improve the image quality and eliminate external environmental interference; the data matching module matches agricultural data from different sources and spatio-temporal dimensions to achieve seamless connection and unified expression of the data. This series of processing flows provides a high-quality and highly reliable data basis for subsequent data analysis and decision support, and significantly improves the data processing ability and intelligent level of the smart agriculture big data cloud service supervision platform.

[0158] The data analysis unit 3, based on the agricultural data processed by the data processing unit 2, conducts multi-faceted evaluation and analysis through multi-party analysis techniques;

[0159] In this example, the specific steps for conducting multi-faceted evaluation and analysis through multi-party analysis techniques are as follows:

[0160] Among them, the multi-party analysis techniques include crop growth dynamic models, remote sensing image machine learning algorithms and soil quality assessment methods;

[0161] S6.1. Combine agricultural data and evaluate and analyze soil quality through the soil quality assessment method;

[0162] In this example, the specific process of evaluating and analyzing soil quality through the soil quality assessment method is as follows:

[0163] Calculate the comprehensive soil nutrient index:

[0164] ;

[0165] In the formula, represents the comprehensive soil nutrient index; represents the nitrogen content; represents the phosphorus content; Indicates the potassium content; Indicates the weight of nitrogen; Indicates the weight of phosphorus; Indicates the weight of potassium;

[0166] Judge the soil acidity and alkalinity:

[0167] Acidic: ;

[0168] Neutral: ;

[0169] Alkaline: ;

[0170] Use the remote sensing inversion model to estimate the organic matter content:

[0171] ;

[0172] Wherein, Indicates the organic content; Indicates the influence degree of the normalized difference vegetation index on the organic matter content; Indicates at The basic value of the soil organic matter content when it is zero; Indicates the vegetation index;

[0173] Standardize each index and then perform weighted summation to obtain the comprehensive soil quality score:

[0174] ;

[0175] Wherein, Indicates the comprehensive soil quality score; Indicates the Standardized value of the th index; Indicates the Weight of the th index; Indicates the total number of indexes; Indicates the index index variable.

[0176] Specifically, in a smart agriculture big data cloud service supervision platform that integrates aerial remote sensing and spatial ranging information, the soil quality assessment method provides a scientific basis for precision agriculture through the quantitative analysis of key indicators such as the comprehensive soil nutrient index (NPI), acidity and alkalinity (pH value), and organic matter content (OM). These indicators are standardized and weighted and summed to generate a comprehensive soil quality score (SQI), which can comprehensively reflect the soil health status and help the platform achieve dynamic monitoring, precise diagnosis, and optimized management of the farmland soil status. Combining the spatial coverage ability of aerial remote sensing data and the high-precision positioning function of spatial ranging information, this method can support regional soil quality assessment, guide fertilization, improvement measure formulation, and crop planting planning, thereby improving agricultural production efficiency and sustainable development level.

[0177] S6.2. Identify the occurrence area and severity of pests and diseases through the remote sensing image machine learning algorithm;

[0178] In this example, the specific process of identifying the occurrence area and severity of pests and diseases through the remote sensing image machine learning algorithm is as follows:

[0179] Extract the spectral features in the remote sensing image and normalize the vegetation index :

[0180] ;

[0181] In the formula, represents the reflectance in the near-infrared band;

[0182] Use the support vector machine to classify the pest and disease areas:

[0183] ;

[0184] In the formula, represents the classification function; represents the input feature vector; represents the number of input feature vectors; represents the number index variable of the input feature vector; represents the Lagrange multiplier; represents the kernel function; represents the bias term; represents the training sample label; represents the input feature vector label;

[0185] Among them, the input feature vector is:

[0186] ;

[0187] Judge whether the pixel point belongs to the pest and disease area according to the classification result:

[0188] ;

[0189] Calculate the proportion of the pest and disease coverage area in the total planting area:

[0190] ;

[0191] In the formula, represents the proportion of the pest and disease coverage area in the total planting area; represents the resolution;

[0192] Considering that the pesticide coverage area affects the occurrence area and severity of pests and diseases, a pesticide coverage area variable is introduced to optimize the remote sensing image machine learning algorithm:

[0193] ;

[0194] In the formula, represents the classification function with the pesticide coverage area variable introduced; represents the pesticide coverage area variable;

[0195] After introducing the pesticide coverage area variable, judge whether the pixel point belongs to the pest and disease area according to the classification result:

[0196] ;

[0197] Calculate the proportion of the pest and disease coverage area in the total planting area:

[0198] ;

[0199] In the formula, represents the proportion of the pest and disease coverage area in the total planting area after introducing the pesticide coverage area variable; represents the pesticide effectiveness coefficient.

[0200] Specifically, in this embodiment, the specific process of identifying the occurrence area and severity of pests and diseases through the remote sensing image machine learning algorithm can achieve precise monitoring and evaluation of the farmland health status. First, use the normalized difference vegetation index (NDVI) to extract the key features of crop growth status, and combine with the support vector machine model to classify the pest and disease areas to generate a high-precision pest and disease distribution map. Further introduce the pesticide coverage area variable to optimize the algorithm, considering the impact of pesticide use effect on pests and diseases, so as to more accurately calculate the proportion of the pest and disease coverage area. This method combines the large-scale data acquisition ability of aerial remote sensing and the high-precision positioning function of spatial ranging information, can provide real-time and dynamic pest and disease monitoring data for the platform, help formulate scientific prevention and control strategies, reduce the abuse of pesticides, improve agricultural production efficiency and sustainability, and at the same time provide important support for intelligent agricultural decision-making. Among them,P The physical meaning of P is the actual sprayed and covered area of pesticides in the farmland area obtained through remote sensing technology (unit: hectare or square meter), and its value range is η ≥0 (non-negative value). η The physical meaning of η is the actual effectiveness ratio of pesticides in the target area (the actual utilization rate after considering environmental losses), and its value range should be 0 ≤ η ≤ 1, where

[0201] S6.3. Use historical agricultural data and real-time agricultural data to construct a crop growth dynamic model to predict crop growth and yield.

[0202] In this example, the specific process of constructing a crop growth dynamic model is as follows:

[0203] Use the crop growth dynamic model to predict the final yield:

[0204] ;

[0205] In the formula, represents the predicted yield; represents the proportional coefficient; represents the offset; represents the growth amount of the crop at time ;

[0206] Among them, is specifically:

[0207] ;

[0208] In the formula, represents the maximum growth value; represents the growth rate; represents the time to reach the semi-saturation value;

[0209] Considering that soil oxygen concentration, temperature, light radiation brightness, soil nutrients, soil acidity and alkalinity, and soil humidity have an impact on crop growth, variables of soil oxygen concentration, temperature, light radiation brightness, soil nutrients, soil acidity and alkalinity, and soil humidity are introduced to optimize the crop growth dynamic model:

[0210] ;

[0211] In the formula, represents the growth amount of the crop introduced with soil oxygen concentration, temperature, light radiation brightness, soil nutrients, soil acidity and alkalinity, and soil humidity at time ; Represents the proportionality coefficient affected by soil oxygen concentration, temperature, and soil nutrients; Represents the offset affected by soil nutrients and soil acidity / alkalinity;

[0212] Specifically, The specific mathematical expression of

[0213] ;

[0214] In the formula, Represents the reference proportionality coefficient; Represents the temperature adjustment coefficient; Represents the half-saturation constant of soil nutrients; Represents the oxygen synergistic coefficient; Represents the optimal oxygen concentration; Represents the reference temperature of crop metabolic efficiency;

[0215] Among them, The specific mathematical expression of

[0216] ;

[0217] In the formula, Represents the basic offset; Represents Nutrient synergy coefficient; Represents neutral Value;

[0218] Among them, The specific mathematical expression of

[0219] ;

[0220] In the formula, Represents the maximum growth value affected by soil oxygen concentration, light radiation brightness, soil nutrients, and soil humidity; Represents the growth rate affected by soil oxygen concentration, temperature, and soil acidity / alkalinity; Represents the soil oxygen concentration; Represents the temperature; Represents the soil acidity / alkalinity; Represents the soil humidity;

[0221] Specifically, The specific mathematical expression of

[0222] ;

[0223] In the formula, Represents the theoretical maximum growth amount; Represents the half-saturation constant of light radiation brightness; Represents the optimal soil moisture; Represents the humidity deviation penalty coefficient; Represents the half-saturation constant of oxygen;

[0224] Among them, The specific mathematical expression of

[0225] ;

[0226] In the formula, Represents the theoretical maximum growth rate; Represents the temperature sensitivity coefficient; Represents the optimal temperature; Represents the minimum value of soil acidity and alkalinity; Represents the maximum value of soil acidity and alkalinity; Represents the low oxygen stress coefficient; Represents the oxygen response coefficient;

[0227] And considering that the pest and disease coverage area has an inhibitory effect on the maximum growth value and growth rate of crops, the pest and disease coverage area is introduced to optimize the crop growth dynamic model:

[0228] ;

[0229] In the formula, Represents the final predicted yield; Represents the inhibition coefficient of pests and diseases on the yield; Represents the growth amount optimized again after introducing the pest and disease coverage area;

[0230] Among them, The specific mathematical expression of

[0231] ;

[0232] In the formula, Represents the inhibition coefficient of pests and diseases on the maximum growth value; Represents the inhibition coefficient of pests and diseases on the growth rate;

[0233] Considering that the yield is affected by the multi-stage cumulative effect, the multi-stage cumulative effect is introduced to optimize the crop growth dynamic model:

[0234] ;

[0235] In the formula, Represents the predicted yield considering the influence of soil oxygen concentration, temperature, light radiation brightness, soil nutrients, soil acidity and alkalinity, soil moisture and multi-stage cumulative effect; Represents the growth amount at the tillering stage; Represents the growth amount during the flowering period; Represents the growth amount during the filling period;

[0236] Specifically, , , Are respectively:

[0237] ;

[0238] ;

[0239] ;

[0240] In the formula, Represents the maximum growth value during the tillering period; Represents the maximum growth value during the flowering period; Represents the maximum growth value during the filling period; Represents the growth rate during the tillering period; Represents the growth rate during the flowering period; Represents the growth rate during the filling period; Represents the starting time of the tillering period; Represents the starting time of the flowering period; Represents the starting time of the filling period;

[0241] The root mean square error is used to evaluate the prediction accuracy of the model:

[0242] ;

[0243] In the formula, Represents the root mean square error; Represents the actual observed value; Represents the model predicted value; Represents the number of samples; Represents the sample index variable.

[0244] Specifically, in a smart agriculture big data cloud service supervision platform that integrates aerial remote sensing and spatial ranging information, the specific process of constructing a crop growth dynamic model can achieve accurate prediction of crop growth status and final yield. By introducing the influence of multiple factors such as soil oxygen concentration, temperature, light radiation brightness, soil nutrients, soil acidity and alkalinity, soil humidity, and pest and disease coverage area, and optimizing the Logistic growth model with the phased cumulative effect, the model is more in line with the actual agricultural production conditions. This model uses the high-resolution data provided by remote sensing images and the precise positioning ability of spatial ranging technology to monitor the crop growth dynamics in real time, evaluate the impact of environmental factors on crops, and predict the final yield. The results can provide scientific decision-making support for the platform, assist in precise fertilization, irrigation management, and pest and disease prevention and control, thereby improving resource utilization efficiency, reducing waste of agricultural inputs, and promoting the intelligent and sustainable development of agricultural production. At the same time, the accuracy of the model is evaluated by the root mean square error (RMSE) to ensure the reliability of the prediction results and further improve the service quality of the platform.

[0245] Furthermore, in the smart agriculture big data cloud service supervision platform that integrates aerial remote sensing and spatial ranging information, key indicators such as soil nutrients, acidity and alkalinity, and organic matter content are quantitatively analyzed through the soil quality assessment method to provide a scientific basis for precise fertilization and soil improvement; the occurrence area and severity of pests and diseases are identified by using remote sensing image machine learning algorithms to achieve early warning and precise prevention and control of pests and diseases; a crop growth dynamic model is constructed based on historical and real-time agricultural data, and combined with environmental factors (such as soil and meteorological conditions) and multi-stage cumulative effects to predict crop growth and yield, assisting in agricultural production decision-making. The three work together synergistically to give full play to the spatial coverage ability of remote sensing data and the high-precision positioning advantage of ranging information, providing comprehensive and dynamic farmland monitoring and management support for the platform, and promoting the intelligent, precise, and sustainable development of agricultural production.

[0246] A storage management unit 4, and the storage management unit 4 manages and protects agricultural data through cloud computing distributed storage technology based on the analysis results of the data analysis unit 3.

[0247] In this example, the specific steps for managing and protecting agricultural data through cloud computing distributed storage technology are as follows:

[0248] S10.1. Efficiently store agricultural data using cloud computing distributed storage technology;

[0249] Among them, cloud computing distributed storage technology includes cloud object storage technology, relational databases, and distributed file systems;

[0250] Specifically, efficiently storing agricultural data using cloud computing distributed storage technology is as follows:

[0251] Store unstructured data such as remote sensing images and sensor data in cloud object storage (such as Alibaba Cloud OSS);

[0252] Use a relational database (such as MySQL) to store structured data, such as crop growth model parameters and soil quality scores;

[0253] Implement distributed storage of large-scale data with the help of a distributed file system (such as HDFS).

[0254] S10.2. Classify, manage the lifecycle, and provide sharing services for agricultural data;

[0255] Specifically, classify and manage data according to data types (remote sensing images, sensor data, etc.), time dimensions (historical, real-time, predictive), and regions (farmland plots).

[0256] Implement a data lifecycle management strategy, regularly archive historical data to cold storage, and clean up useless data to optimize storage space.

[0257] Provide a standardized API interface to support the secure sharing of agricultural data and interaction with external systems.

[0258] S10.3. Use encryption technology to protect the security of data during transmission and storage.

[0259] Specifically, use encryption technology (such as SSL / TLS, AES) to protect the security of data during transmission and storage.

[0260] Implement role-based access control (RBAC) to restrict unauthorized data access.

[0261] Configure a disaster recovery mechanism in a different location, regularly back up important data and test the recovery process to ensure quick business recovery in case of emergencies.

[0262] Furthermore, in an intelligent agricultural big data cloud service supervision platform that integrates aerial remote sensing and spatial ranging information, through cloud computing distributed storage technology (including cloud object storage, relational databases, and distributed file systems), achieve efficient storage and management of massive agricultural data, ensuring the reliability and scalability of the data. At the same time, classify, manage the lifecycle, and provide sharing services for agricultural data, optimize the data usage efficiency, and meet the needs of different users. In addition, adopt encryption technology to ensure the security of data during transmission and storage, prevent data leakage or tampering, and provide a secure and stable data support environment for agricultural production, decision-making analysis, and information services. This series of functions ensures the intelligence, efficiency, and security of the platform in data management, and helps the sustainable development of intelligent agriculture.

[0263] The basic principles, main features and advantages of the present invention have been shown and described above. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and the descriptions in the specification are only preferred examples of the present invention and are not used to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed.

Claims

1. A smart agriculture big data cloud service supervision platform integrating aerial remote sensing and space ranging information, characterized in that: include A data collection unit (1), wherein the data collection unit (1) acquires agricultural data based on a multi-source collection module (11); A data processing unit (2), wherein the data processing unit (2) performs cleaning, correction and matching processing on the agricultural data collected by the data collection unit (1); A data analysis unit (3), wherein the data analysis unit (3) performs multi-faceted evaluation and analysis based on the agricultural data processed by the data processing unit (2) by using a multi-faceted analysis technique; A storage management unit (4), wherein the storage management unit (4) manages and protects the agricultural data through cloud computing distributed storage technology based on the analysis results of the data analysis unit (3); The specific steps of the data analysis unit (3) performing multi-faceted evaluation and analysis using multi-faceted analysis technology are as follows: Among them, multi-analysis techniques include crop growth dynamic models, remote sensing image machine learning algorithms, and soil quality assessment methods; S6.

1. Combine agricultural data and use soil quality assessment methods to assess soil quality; S6.

2. Identify the occurrence area and severity of pests and diseases through remote sensing image machine learning algorithms; S6.

3. Use historical agricultural data and real-time agricultural data to build a crop growth dynamic model to predict crop growth and yield. In S6.3, the specific process of building the crop growth dynamic model is as follows: Use crop growth dynamics models to predict final yields: ； In the formula, represents the predicted output; represents the proportionality coefficient; Indicates the offset; Indicates the crop at time The amount of growth; in, Specifically: ； In the formula, Indicates the maximum growth value; represents the growth rate; Indicates the time to reach half-saturation value; Considering that soil oxygen concentration, temperature, light radiation brightness, soil nutrients, soil acidity and soil moisture have an impact on crop growth, soil oxygen concentration, temperature, light radiation brightness, soil nutrients, soil acidity and soil moisture variables are introduced to optimize the crop growth dynamic model: ； In the formula, represents the predicted yield after optimization, Indicates the effect of soil oxygen concentration, temperature, light radiation brightness, soil nutrients, soil acidity and soil moisture on crops over time. The amount of growth; represents the proportionality coefficient affected by soil oxygen concentration, temperature and soil nutrients; Indicates the offset affected by soil nutrients and soil acidity and alkalinity; in, for: ； In the formula, It indicates the maximum growth value affected by soil oxygen concentration, light radiation brightness, soil nutrients and soil moisture; Indicates growth rate affected by soil oxygen concentration, temperature, and soil acidity; Indicates soil oxygen concentration; Indicates temperature; Indicates soil acidity and alkalinity; Indicates soil moisture; Considering that the coverage area of ​​pests and diseases has an inhibitory effect on the maximum growth value and growth rate of crops, the dynamic model of crop growth optimization based on the coverage area of ​​pests and diseases is introduced: ； In the formula, represents the final predicted output; It indicates the inhibition coefficient of pests and diseases on yield; It indicates the amount of growth that is optimized again after the introduction of pest and disease coverage area; in, for: ； In the formula, It indicates the inhibition coefficient of pests and diseases on the maximum growth value; It indicates the inhibition coefficient of pests and diseases on growth rate; Considering that the yield is affected by the multi-stage cumulative effect, the multi-stage cumulative effect is introduced to optimize the crop growth dynamic model: ； In the formula, It indicates the predicted yield of introducing soil oxygen concentration, temperature, light radiation brightness, soil nutrients, soil acidity and alkalinity, soil moisture and multi-stage cumulative effects; Indicates the growth amount during the tillering stage; Indicates the amount of growth during the flowering period; It indicates the amount of growth during the filling period; Use the root mean square error to evaluate the model prediction accuracy: ； In the formula, represents the root mean square error; represents the actual observed value; represents the model prediction value; represents the number of samples; Represents the sample index variable.

2. The smart agriculture big data cloud service supervision platform integrating aerial remote sensing and space ranging information according to claim 1 is characterized by: The multi-source acquisition module (11) comprises an aerial remote sensing module (111), a space ranging module (112) and a ground sensor module (113); Among them, agricultural data include farmland area, soil moisture, temperature and nutrient content; The aerial remote sensing module (111) is used to collect high-resolution multi-spectral, thermal infrared and visible light images; The spatial distance measurement module (112) is used to obtain farmland area information; The ground sensor module (113) is used to monitor soil moisture, temperature and nutrient content.

3. The smart agriculture big data cloud service supervision platform integrating aerial remote sensing and space ranging information according to claim 1 is characterized by: The data processing unit (2) comprises a data cleaning module (21), a data correction module (22) and a data matching module (23); Wherein, the data cleaning module (21) is used to remove noise, outliers and redundant data; The specific process of removing noise, outliers and redundant data is as follows: Use the mean filter algorithm to remove noise from remote sensing images: ； In the formula, Represents the pixel value after denoising; Indicates that the original image Centered window The pixel value within Indicates The neighborhood window centered at ; Display Window The total number of pixels in the Detect outliers using the standard deviation method: ； In the formula, Indicates the value of the current data point; Represents the standardized value; represents the mean of the data; Indicates the standard deviation of the data; Use correlation analysis to remove redundant features: ； In the formula, Representation characteristics and Features The correlation coefficient of Representation characteristics and Features The covariance of Representation characteristics The standard deviation of Representation characteristics The standard deviation of Represents the feature index variable; represents another feature index variable; The data correction module (22) is used to perform radiation correction, geometric correction and atmospheric correction on the image of the aerial remote sensing module (111); The data matching module (23) is used to match agricultural data in time and space dimensions.

4. The smart agriculture big data cloud service supervision platform integrating aerial remote sensing and space ranging information according to claim 3 is characterized in that: The specific process of the data correction module (22) performing radiation correction, geometric correction and atmospheric correction is as follows: Radiometric correction: ； In the formula, Indicates the light radiation brightness value; represents the sensor-specific scaling factor; Represents a digital value; Indicates the sensor-specific offset; Geometric correction: ； In the formula, represents the corrected coordinate matrix; Represents the original coordinate matrix; represents the affine transformation matrix; represents the translation matrix; Atmospheric correction: ； In the formula, Represents the surface reflectivity; Indicates the atmospheric path radiation value; represents the atmospheric transmittance.

5. The smart agriculture big data cloud service supervision platform integrating aerial remote sensing and space ranging information according to claim 4 is characterized in that: The specific process of the data matching module (23) matching agricultural data in the time and space dimensions is as follows: Use spatial interpolation to align time series data: ； In the formula, Indicates the target time point The characteristic value of Indicates time point The characteristic value of farmland area; Indicates time point The characteristic value of soil moisture; Indicates time point The temperature characteristic value of Indicates time point Characteristic value of nutrient content; Indicates time point The weight of Indicates time point The weight of Indicates time point The weight of Indicates time point The weight of Represents a time-indexed variable.

6. The smart agriculture big data cloud service supervision platform integrating aerial remote sensing and space ranging information according to claim 5 is characterized by: In S6.1, the specific process of evaluating and analyzing soil quality by the soil quality evaluation method is as follows: Calculate the soil nutrient comprehensive index: ； In the formula, It represents the comprehensive index of soil nutrients; Indicates the nitrogen content; Indicates the phosphorus content; Indicates the potassium content; represents the weight of nitrogen; represents the weight of phosphorus; represents the weight of potassium; Estimation of organic matter content using remote sensing inversion models: ； In the formula, Indicates organic content; It indicates the influence of normalized difference vegetation index on organic matter content; Indicated in The basic value of soil organic matter content at zero; represents vegetation index; After standardizing each indicator, a weighted sum is performed to obtain a comprehensive soil quality score: ； In the formula, It represents the comprehensive score of soil quality; Indicates Standardized values ​​of the indicators; Indicates The weight of each indicator; Indicates the total number of indicators; Represents an indicator index variable.

7. The smart agriculture big data cloud service supervision platform integrating aerial remote sensing and space ranging information according to claim 6 is characterized by: In S6.2, the specific process of identifying the occurrence area and severity of pests and diseases through remote sensing image machine learning algorithm is as follows: Extract spectral features from remote sensing images and normalize vegetation index : ； In the formula, Represents the reflectivity in the near-infrared band; Use support vector machines to classify pest and disease areas: ； In the formula, represents the classification function; represents the input feature vector; represents the number of input feature vectors; A variable that represents the number of input feature vectors; represents the Lagrange multiplier; represents the kernel function; represents the bias term; Represents the training sample label; represents the input feature vector label; Among them, the input feature vector for: ; Determine whether the pixel belongs to the pest area based on the classification result: ； Calculate the proportion of area covered by pests and diseases to the total planted area: ； In the formula, It indicates the proportion of the area covered by pests and diseases to the total planted area; Indicates resolution; Considering that the pesticide coverage area has an impact on the occurrence area and severity of pests and diseases, the pesticide coverage area variable is introduced to optimize the remote sensing image machine learning algorithm: ； In the formula, represents the classification function of the introduced pesticide coverage area variable; represents the variable of pesticide coverage area; After introducing the pesticide coverage area variable, we can determine whether the pixel belongs to the pest and disease area based on the classification results: ； Calculate the proportion of area covered by pests and diseases to the total planted area: ； In the formula, It represents the proportion of pest and disease covered area to the total planted area after the introduction of the pesticide coverage area variable; Represents the pesticide effectiveness coefficient.

8. The smart agriculture big data cloud service supervision platform integrating aerial remote sensing and space ranging information according to claim 1 is characterized in that: The specific steps of managing and protecting agricultural data through cloud computing distributed storage technology are: S10.

1. Use cloud computing distributed storage technology to efficiently store agricultural data; Among them, cloud computing distributed storage technologies include cloud object storage technology, relational databases, and distributed file systems; S10.

2. Classify, manage and share agricultural data; S10.

3. Use encryption technology to protect the security of data during transmission and storage.

Images