Agricultural planting monitoring method and device based on big data

Abstract

The present invention provides an agricultural planting monitoring method and device based on big data, and relates to the technical field of agricultural planting monitoring. The present invention collects image data, soil data and water source data of an agricultural planting area, stores the image data, soil data and water source data in a big data storage platform, extracts features of the image data, soil data and water source data to obtain crop features, soil features and water source features; analyzes the crop features to generate crop state coefficients and determines the crop state based on these; establishes a database containing standard data for each state; calculates standard soil features and standard water source features according to the database, and scores the soil and water source according to the difference between the soil features and water source features and the corresponding standard features; generates an environmental assessment index according to the soil and water source rating results, compares the environmental assessment index with a preset threshold, and divides the planting conditions into good, normal and risky according to the comparison results.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural planting monitoring, and in particular to an agricultural planting monitoring method and device based on big data. Background Art

[0002] As the global population continues to grow, the demand for food and agricultural products has increased dramatically, and the challenges facing agricultural production have become increasingly severe. Modern agriculture must not only increase production, but also deal with multiple unfavorable factors such as limited land resources, increased environmental pollution, and climate change. Among them, the decline in soil fertility, unsustainable farming methods, excessive use of fertilizers and pesticides, and the increasing scarcity of water resources have led to the gradual deterioration of soil quality and water resources, seriously affecting the growth and yield of crops. In addition, extreme weather caused by climate change, such as droughts, floods, and high temperatures, has increased the uncertainty and risks of agricultural production.

[0003] Traditional agricultural management methods mainly rely on farmers' experience or local data for decision-making, such as soil composition analysis or simple meteorological data collection. This experience-driven and single-data-source approach is difficult to cope with the complex and changing environmental conditions in modern agriculture, especially in large farmlands and under conditions of significant regional climate differences, the growth status of crops cannot be accurately monitored and evaluated. In addition, existing agricultural monitoring technologies usually only focus on one aspect of factors, lacking a holistic view of the agricultural ecosystem and a comprehensive multi-dimensional analysis. For example, evaluating crop growth only through soil analysis or climate data ignores other key parameters such as crop coverage, crop health, soil moisture, nutrients, and disease status. This method leads to inaccurate agricultural production decisions and is unable to respond to environmental changes and risks in a timely and effective manner, ultimately affecting the efficiency of agricultural production and product quality.

[0004] Based on this, modern agriculture urgently needs a solution that integrates multi-dimensional data and can accurately monitor and predict crop growth status and environmental conditions, so as to improve the scientific and intelligent level of agricultural management, reduce resource waste, increase crop yield and quality, and promote the sustainable development of agriculture.

[0005] In the prior art, the publication number CN117993705B discloses a smart agricultural planting monitoring system and method based on big data, including an image acquisition module, a soil acquisition module, a weather acquisition module, a water source acquisition module, a big data analysis module, a database, an information processing module and an information sending module; the image acquisition module is an unmanned aerial vehicle image acquisition device, which is used to collect real-time image information of crop planting, the soil acquisition module is used to collect soil composition information in the planting area, the weather acquisition module is used to obtain weather forecast information, and the water source collection module is used to obtain water source quality information and water source distance information in the planting area. This prior art can better monitor agricultural planting, help promote the development of smart agriculture, realize the intelligence and refinement of agricultural production, reduce the time and cost of manual intervention, more accurately obtain crop planting conditions, and accurately adjust crops. However, the prior art still has defects. The environmental conditions required for each state of plant growth are different. If the identification of the plant state is wrong, the monitoring will lose its meaning, and thus the actual needs of the plant cannot be effectively met. This technical defect not only affects the accuracy of environmental regulation, but also may lead to waste of resources, reduced yields and deterioration of plant health.

[0006] The above data disclosed in the background technology section is only used to enhance the understanding of the background of the present disclosure and thus it may include data that does not constitute the prior art already known to a person of ordinary skill in the art. Summary of the invention

[0007] The purpose of the present invention is to provide an agricultural planting monitoring method and device based on big data to solve the problems raised in the above-mentioned background technology.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] A method and device for agricultural planting monitoring based on big data, the specific steps include:

[0010] Step 1: Collect image data, soil data and water source data of the agricultural planting area, wherein the image data includes remote sensing images of the planting area; the soil data includes N content, P content, K content, organic matter content, soil pH value and density; the water source data includes dissolved oxygen content, water source pH value and heavy metal content;

[0011] Step 2: storing the image data, soil data and water source data in a big data storage platform, extracting features from the image data, soil data and water source data to obtain crop features, soil features and water source features; the crop features include crop coverage and crop color coefficient; the soil features include soil nutrient index and soil growth barrier index; the water source features are beneficial plant growth index;

[0012] Step 3: Generate a crop state coefficient by analyzing crop characteristics, and determine the growth period of the crop by comparing the crop state coefficient with a preset threshold. The growth period includes the infancy period, growth period and maturity period, and obtain standard soil data and standard water source data for the corresponding growth period;

[0013] Step 4: Calculate the standard soil characteristics and standard water source characteristics, and score the soil and water source respectively according to the difference between the soil characteristics and the standard soil characteristics, and the difference between the water source characteristics and the standard water source characteristics;

[0014] Step 5: Comprehensively analyze the soil and water source rating results to generate an environmental assessment index, compare the environmental assessment index with the preset threshold, and classify the planting conditions into good, normal, and risk based on the comparison results.

[0015] Furthermore, the specific logic for extracting crop features is as follows: grayscale the remote sensing image of the planting area, calculate the inter-class variance of each threshold in the grayscale histogram, select the best separation threshold by the inter-class variance, use the best separation threshold to perform threshold segmentation on the remote sensing image of the planting area, divide the remote sensing image of the planting area into the crop part and other parts, calculate the ratio of the pixel points of the crop part to the pixel points of the remote sensing image of the total area as the crop coverage rate; calculate the average grayscale value of the crop part to obtain the crop color coefficient; the specific logic for obtaining the crop coverage rate is as follows:

[0016]

[0017] Among them, G is the crop coverage, Q is the number of pixels in the crop part, and M is the number of pixels in the remote sensing image of the total area;

[0018] The specific logic for obtaining the crop color coefficient is:

[0019]

[0020] Among them, Cl is the crop color coefficient, H i is the gray value of the i-th pixel of the crop part.

[0021] Furthermore, the N content, P content, K content, and organic matter content are dedimensionalized to generate the soil nutrient index; the soil pH value and density are mathematically analyzed to generate the soil resistance index; the specific formula for generating the soil nutrient index is:

[0022]

[0023] Among them, Ns is the soil nutrient index, N is the N content, P is the P content, K is the K content, and CH is the organic matter content;

[0024] The specific formula for generating the soil resistance index is:

[0025]

[0026] Among them, Hz is the soil resistance index, PH is the soil pH value, and σ is the density.

[0027] Furthermore, the specific logic for extracting water source characteristics is: generating a beneficial plant growth index through dissolved oxygen, water source pH and heavy metal content; the specific formula for generating is:

[0028]

[0029] Among them, Gow is the beneficial plant growth index, C O is the dissolved oxygen content, pH w is the water source pH, and Z is the heavy metal content.

[0030] Furthermore, the specific logic for classifying crop states is: analyzing crop characteristics to generate crop state coefficients, and the specific formula is:

[0031] Su=G*Cl

[0032] Among them, Su is the crop state coefficient, G is the crop coverage rate, and Cl is the crop color coefficient;

[0033] Preset crop status threshold Su 0 , when Su<0.2Su 0 When 0.2Su 0 ≤Su<0.7Su 0 When the crop state is defined as the growth stage, when 0.7Su 0 ≤Su <Su 0 When the crop state is defined as maturity.

[0034] Further,

[0035] The specific logic for scoring soil and water sources is as follows: calculate standard soil characteristics based on standard soil data, calculate the difference between soil characteristics and standard soil characteristics, and generate a soil score based on the difference between soil characteristics and standard soil characteristics; calculate standard water source characteristics based on standard water source data, calculate the difference between water source characteristics and standard water source characteristics, and generate a water source score based on the difference between water source characteristics and standard water source characteristics; the specific formula for generating soil scores is as follows:

[0036] Ss=|Ns-Ns 0 |+(Hz-Hz 0 ) 2

[0037] Among them, Sco is the soil score, Ns is the soil nutrient index, and Ns 0 is the standard soil nutrient index, Hz is the soil resistance index, Hz 0 is the standard soil resistance index;

[0038] The specific formula used to generate the water source score is:

[0039]

[0040] Among them, Sw is the water source score, Gow is the beneficial plant growth index, and Gow 0 It is the standard beneficial vegetation index.

[0041] Furthermore, the soil and water source rating results are comprehensively analyzed to generate an environmental assessment index. The specific formula for generating the environmental assessment index is:

[0042]

[0043] Among them, Sz is the environmental assessment index, Sco is the soil score, and Sw is the water source score;

[0044] Set the environmental assessment threshold Sz 0 , Sz<0.3Sz 0 When the crop planting situation is defined as risk; 0.2Sz 0 ≤Sz<0.8Sz 0 When the crop planting situation is defined as normal; when the crop planting situation is defined as normal; 0 ≤Sz <Sz 0 When the crop planting situation is good.

[0045] The present invention further provides an agricultural planting monitoring device based on big data, which is used in any step of the agricultural planting monitoring method based on big data, specifically including:

[0046] Data acquisition module: used to collect image data, soil data and water source data of agricultural planting areas, the image data includes remote sensing images of planting areas; the soil data includes N content, P content, K content, organic matter content, soil pH value and density; the water source data includes dissolved oxygen content, water source pH and heavy metal content;

[0047] Feature extraction module: used to store image data, soil data and water source data into the big data storage platform, and extract features from the image data, soil data and water source data to obtain crop features, soil features and water source features; the crop features include crop coverage and crop color coefficient; the soil features include soil nutrient index and soil growth barrier index; the water source features are beneficial plant growth index;

[0048] State determination module: used to generate crop state coefficients by analyzing crop characteristics, and determine the growth period of crops by comparing the crop state coefficients with preset thresholds. The growth period includes the infancy period, growth period and maturity period, and obtain standard soil data and standard water source data for the corresponding growth period;

[0049] Data scoring module: used to calculate standard soil characteristics and standard water source characteristics, and score the soil and water sources respectively according to the difference between soil characteristics and standard soil characteristics, and the difference between water source characteristics and standard water source characteristics;

[0050] Status classification module: used to conduct a comprehensive analysis of the soil and water source rating results, generate an environmental assessment index, compare the environmental assessment index with the preset threshold, and classify the planting conditions into good, normal, and risky based on the comparison results. Further.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] The present invention generates a crop state coefficient that can quantify the growth time of crops through image information that can be collected in real time, and divides crops into infancy, growth and maturity stages by threshold processing of the crop state coefficient. It can not only accurately identify the growth stage of crops, but also provide corresponding monitoring according to different stages, thereby improving the yield and quality of crops, optimizing resource utilization, and promoting intelligent and refined management of agricultural production. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 It is a schematic diagram of the overall method flow of the present invention.

[0054] Figure 2 It is a schematic diagram of the overall structure of the device of the present invention. DETAILED DESCRIPTION

[0055] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0056] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0057] Example:

[0058] See also Figure 1 , the present invention provides a technical solution:

[0059] A method for monitoring agricultural planting based on big data, the specific steps include:

[0060] Step 1: Collect image data, soil data and water source data of the agricultural planting area, wherein the image data includes remote sensing images of the planting area; the soil data includes N content, P content, K content, organic matter content, soil pH value and density; the water source data includes dissolved oxygen content, water source pH value and heavy metal content;

[0061] The remote sensing image of the planting area is taken by a drone from high altitude, and the soil data and water source data are directly obtained by sensors. The N content, P content and K content are nitrogen content, phosphorus content and potash fertilizer content respectively.

[0062] Step 2: storing the image data, soil data and water source data in a big data storage platform, extracting features from the image data, soil data and water source data to obtain crop features, soil features and water source features; the crop features include crop coverage and crop color coefficient; the soil features include soil nutrient index and soil growth barrier index; the water source features are beneficial plant growth index;

[0063] The specific logic for extracting crop features is as follows: grayscale the remote sensing image of the planting area, calculate the inter-class variance of each threshold in the grayscale histogram, select the best separation threshold by the inter-class variance, use the best separation threshold to perform threshold segmentation on the remote sensing image of the planting area, divide the remote sensing image of the planting area into the crop part and other parts, calculate the ratio of the pixel points of the crop part to the pixel points of the remote sensing image of the total area as the crop coverage rate; calculate the average grayscale value of the crop part to obtain the crop color coefficient; the specific logic for calculating the best separation threshold is as follows:

[0064] Traverse all possible thresholds, divide the remote sensing image of the planting area into other parts and crop parts according to the value of each threshold, count the number of pixels in other parts and crop parts, calculate the mean of the grayscale value of the pixels in other parts and crop parts, and calculate the inter-class variance of the corresponding threshold. The specific formula is:

[0065] σ(t) 2 =w B (t)*w F (t)*(μ B (t)-μ F (t)) 2

[0066] Among them, σ(t) 2 represents the inter-class variance when the threshold is t, t∈[0, 255], and t∈N + ,w B (t), w F (t) are the number of pixels in other parts and crop parts when the threshold is t, μ B (t), μ F (t) are the mean gray values ​​of the pixels of other parts and crop parts when the threshold is t;

[0067] Calculate the value of the threshold when the between-class variance reaches the maximum, and define this value as the optimal separation threshold.

[0068] The specific logic for obtaining crop coverage is:

[0069]

[0070] Among them, G is the crop coverage, Q is the number of pixels in the crop part, and M is the number of pixels in the remote sensing image of the total area;

[0071] The crop coverage rate G reflects the size of crops in the planting area. The larger the crop, the larger the area it occupies, and the higher the crop coverage rate;

[0072] The specific logic for obtaining the crop color coefficient is:

[0073]

[0074] Among them, Cl is the crop color coefficient, H i is the gray value of the i-th pixel of the crop part. The crop color coefficient Cl reflects the color depth of the crop. The larger its value, the darker the crop color.

[0075] The N content, P content, K content, and organic matter content are dedimensionalized to generate the soil nutrient index; the soil pH value and density are mathematically analyzed to generate the soil resistance index; the specific formula for generating the soil nutrient index is:

[0076]

[0077] Among them, Ns is the soil nutrient index, N is the N content, P is the P content, K is the K content, and CH is the organic matter content; the soil nutrient index Ns reflects the nutrients contained in the soil. The larger the value, the more nutrients it contains; N, P, K and organic matter are the most important nutrients for crop growth; the higher their content, the higher the nutrient content in the soil, and the higher the soil nutrient index Ns.

[0078] The specific formula for generating the soil resistance index is:

[0079]

[0080] Among them, Hz is the soil resistance index, PH is the soil pH value, and σ is the density. The soil resistance index Hz reflects the impact of factors that prevent crop growth on crops. The larger the value, the less suitable the soil conditions are for crop growth.

[0081] The specific logic for extracting water source characteristics is to generate a beneficial plant growth index through dissolved oxygen, water source pH and heavy metal content; the specific formula for the generation is:

[0082]

[0083] Among them, Gow is the beneficial plant growth index, C O is the dissolved oxygen content, pH w is the pH of the water source, and Z is the heavy metal content. The beneficial plant growth index Gow reflects the degree to which the water source in the environment is suitable for the growth of crops. The larger the value, the more suitable the water source in the environment is for the growth of crops.

[0084] Step 3: Generate a crop state coefficient by analyzing crop characteristics, and determine the growth period of the crop by comparing the crop state coefficient with a preset threshold. The growth period includes the infancy period, growth period and maturity period, and obtain standard soil data and standard water source data for the corresponding growth period;

[0085] The standard soil data and standard water source data are determined by inviting agricultural experts to conduct demonstration and analysis on the soil data and water source data of the corresponding period. This is the existing technology and will not be elaborated here.

[0086] The specific logic for classifying crop states is: analyzing crop characteristics to generate crop state coefficients, and the specific formula is:

[0087] Su=G*Cl

[0088] Among them, Su is the crop state coefficient, G is the crop coverage rate, and Cl is the crop color coefficient; the crop state coefficient Su reflects the existence time of the crop. The larger its value, the longer the crop exists. The generation of this coefficient can provide an important basis for judging the growth stage of the crop. The crop color coefficient Cl reflects the depth of the crop color. The larger its value, the darker the crop color. As the existence time of the crop increases, the color of the crop will become darker and darker, and the crop color coefficient Cl will also increase accordingly; the crop coverage rate G reflects the size of the crops in the planting area. The larger the crop, the larger the area it occupies, the higher the crop coverage rate, and the longer the crop exists. When the crop coverage rate G becomes smaller due to aging, the crop has been harvested and does not need to be tested.

[0089] Preset crop status threshold Su 0 , when Su<0.2Su 0 When 0.2Su 0 ≤Su<0.7Su 0 When the crop state is defined as the growth stage, 0.7Su 0 ≤Su <Su 0 When the crop state is defined as the maturity stage, each growth stage of crops requires different environmental conditions. In this embodiment, the crop state threshold Su 0 Dividing crops into juvenile, growing and mature stages facilitates monitoring at each stage.

[0090] Step 4: Calculate the standard soil characteristics and standard water source characteristics, and score the soil and water source respectively according to the difference between the soil characteristics and the standard soil characteristics, and the difference between the water source characteristics and the standard water source characteristics;

[0091] The specific logic for scoring soil and water sources is as follows: calculate standard soil characteristics based on standard soil data, calculate the difference between soil characteristics and standard soil characteristics, and generate a soil score based on the difference between soil characteristics and standard soil characteristics; calculate standard water source characteristics based on standard water source data, calculate the difference between water source characteristics and standard water source characteristics, and generate a water source score based on the difference between water source characteristics and standard water source characteristics; the specific formula for generating soil scores is as follows:

[0092] Ss=|Ns-Ns 0 |+(Hz-Hz 0 ) 2

[0093] Among them, Sco is the soil score, Ns is the soil nutrient index, and Ns 0 is the standard soil nutrient index, Hz is the soil resistance index, Hz 0 It is the standard soil resistance index; the soil score Sco reflects the comprehensive impact of soil conditions on crop growth. The larger the value, the more suitable the soil conditions are for crop growth.

[0094] The specific formula used to generate the water source score is:

[0095]

[0096] Among them, Sw is the water source score, Gow is the beneficial irrigation index, and Gow 0 The water source score Sw reflects the comprehensive impact of the water source environment on crop growth. The larger the value, the more suitable the water source environment is for crop growth.

[0097] Step 5: Comprehensively analyze the soil and water source rating results to generate an environmental assessment index, compare the environmental assessment index with the preset threshold, and classify the planting conditions into good, normal, and risk based on the comparison results.

[0098] The environmental assessment index is generated by comprehensively analyzing the soil and water source rating results. The specific formula for generating the environmental assessment index is:

[0099]

[0100] Among them, Sz is the environmental assessment index, Sco is the soil score, and Sw is the water source score; the environmental assessment index Sz reflects the comprehensive impact of environmental conditions on the growth status of crops. The larger the value, the more suitable the environment around the crops is for crop growth.

[0101] Set the environmental assessment threshold Sz 0 , Sz<0.3Sz 0 When the crop planting situation is defined as risk; 0.2Sz 0≤Sz<0.8Sz 0 When the crop planting situation is defined as normal; when the crop planting situation is defined as normal; 0 ≤Sz <Sz 0 When the crop planting situation is good, the crop planting situation is defined as good. This implementation quantifies the impact of the environmental conditions around crops on crop growth through the environmental assessment index Sz, and divides the crop growth environment into clear and intuitive good, normal and risky through threshold comparison, which is conducive to taking timely measures to protect and promote the growth of crops. Such a method can provide more intuitive and clear information for the assessment of the crop growth environment, and help improve the management and regulation of the crop growth environment.

[0102] See also Figure 2 The present invention further provides an agricultural planting monitoring device based on big data, which is used in any step of the agricultural planting monitoring method based on big data, specifically including:

[0103] Data acquisition module: used to collect image data, soil data and water source data of agricultural planting areas, the image data includes remote sensing images of planting areas; the soil data includes N content, P content, K content, organic matter content, soil pH value and density; the water source data includes dissolved oxygen content, water source pH and heavy metal content;

[0104] Feature extraction module: used to store image data, soil data and water source data into the big data storage platform, and extract features from the image data, soil data and water source data to obtain plant features, soil features and water source features; the plant features include plant coverage and plant color coefficient; the soil features include soil nutrient index and soil barrier index; the water source features are beneficial irrigation index;

[0105] State determination module: used to generate plant state coefficients through plant characteristics analysis, and determine the growth period of crops by comparing the plant state coefficients with preset thresholds. The growth period includes the juvenile period, the growth period and the mature period, and obtain the standard soil data and standard water source data of the corresponding growth period; Data scoring module: used to calculate the standard soil characteristics and the standard water source characteristics, and score the soil and water source respectively according to the difference between the soil characteristics and the standard soil characteristics, and the difference between the water source characteristics and the standard water source characteristics;

[0106] Status classification module: used to conduct a comprehensive analysis of the soil and water source rating results, generate an environmental assessment index, compare the environmental assessment index with the preset threshold, and classify the planting conditions into good, normal, and risky according to the comparison results.

[0107] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0108] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0109] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0110] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for monitoring agricultural planting based on big data, characterized in that: The specific steps include: Step 1: Collect image data, soil data and water source data of the agricultural planting area, wherein the image data includes remote sensing images of the planting area; the soil data includes N content, P content, K content, organic matter content, soil pH value and density; the water source data includes dissolved oxygen content, water source pH value and heavy metal content; Step 2: storing the image data, soil data and water source data in a big data storage platform, extracting features from the image data, soil data and water source data to obtain crop features, soil features and water source features; the crop features include crop coverage and crop color coefficient; the soil features include soil nutrient index and soil growth barrier index; the water source features are beneficial plant growth index; Step 3: Generate a crop state coefficient by analyzing crop characteristics, and determine the growth period of the crop by comparing the crop state coefficient with a preset threshold. The growth period includes the infancy period, growth period and maturity period, and obtain standard soil data and standard water source data for the corresponding growth period; Step 4: Calculate the standard soil characteristics and standard water source characteristics, and score the soil and water source respectively according to the difference between the soil characteristics and the standard soil characteristics, and the difference between the water source characteristics and the standard water source characteristics; Step 5: Comprehensively analyze the soil and water source rating results to generate an environmental assessment index, compare the environmental assessment index with the preset threshold, and classify the planting conditions into good, normal, and risk based on the comparison results; The specific logic for classifying crop states is: analyzing crop characteristics to generate crop state coefficients, and the specific formula is: Su=G*Cl Among them, Su is the crop state coefficient, G is the crop coverage rate, and Cl is the crop color coefficient.

2. The agricultural planting monitoring method based on big data according to claim 1 is characterized in that: The specific logic for extracting crop features is as follows: grayscale the remote sensing image of the planting area, calculate the inter-class variance of each threshold in the grayscale histogram, select the best separation threshold by the inter-class variance, use the best separation threshold to perform threshold segmentation on the remote sensing image of the planting area, divide the remote sensing image of the planting area into the crop part and other parts, calculate the ratio of the pixel points of the crop part to the pixel points of the remote sensing image of the total area as the crop coverage rate; calculate the average grayscale value of the crop part to obtain the crop color coefficient; the specific logic for obtaining the crop coverage rate is as follows: Among them, G is the crop coverage, Q is the number of pixels in the crop part, and M is the number of pixels in the remote sensing image of the total area; The specific logic for obtaining the crop color coefficient is: Among them, Cl is the crop color coefficient, H i is the gray value of the i-th pixel of the crop part.

3. The agricultural planting monitoring method based on big data according to claim 1 is characterized in that: The specific logic for extracting soil characteristics is as follows: N content, P content, K content, and organic matter content are dedimensionalized to generate the soil nutrient index; soil pH value and density are mathematically analyzed to generate the soil resistance index; the specific formula for generating the soil nutrient index is: Among them, Ns is the soil nutrient index, N is the N content, P is the P content, K is the K content, and CH is the organic matter content; The specific formula for generating the soil resistance index is: Among them, Hz is the soil resistance index, PH is the soil pH value, and σ is the density.

4. The agricultural planting monitoring method based on big data according to claim 1 is characterized in that: The specific logic for extracting water source characteristics is as follows: Generate a beneficial vegetation index based on dissolved oxygen content, water source pH, and heavy metal content; the specific formula for generation is: Among them, Gow is the beneficial plant growth index, C O is the dissolved oxygen content, pH w is the water source pH, and Z is the heavy metal content.

5. A big data-based agricultural planting monitoring method according to claim 1, characterized in that: Preset a crop status threshold Su0. When Su < 0.2Su0, the crop status is defined as the juvenile stage; when 0.2Su0 ≤ Su < 0.7Su0, the crop status is defined as the growth stage; when 0.7Su0 ≤ Su < Su0, the crop status is defined as the mature stage.

6. The agricultural planting monitoring method based on big data according to claim 1 is characterized in that: The specific logic for scoring the soil and water source is as follows: Calculate the standard soil characteristics based on the standard soil data, calculate the difference between the soil characteristics and the standard soil characteristics, and generate a soil score according to the difference between the soil characteristics and the standard soil characteristics; calculate the standard water source characteristics based on the standard water source data, calculate the difference between the water source characteristics and the standard water source characteristics, and generate a water source score according to the difference between the water source characteristics and the standard water source characteristics; the specific formula for generating the soil score is: Ss=|Ns-Ns0|+(Nz-Nz0) 2 Where Sco is the soil score, Ns is the soil nutrient index, Ns0 is the standard soil nutrient index, Hz is the soil inhibition index, and Hz0 is the standard soil inhibition index; The specific formula for generating the water source score is: Where Sw is the water source score, Gow is the beneficial vegetation index, and Gow0 is the standard beneficial vegetation index.

7. The agricultural planting monitoring method based on big data according to claim 1 is characterized in that: Perform a comprehensive analysis on the soil and water source rating results to generate an environmental assessment index. The specific formula for generating the environmental assessment index is: Where Sz is the environmental assessment index, Sco is the soil score, and Sw is the water source score; Set an environmental assessment threshold Sz0. When Sz < 0.3Sz0, the crop planting situation is defined as risky; when 0.2Sz0 ≤ Sz < 0.8Sz0, the crop planting situation is defined as normal; when 0.8Sz0 ≤ Sz < Sz0, the crop planting situation is defined as good.

8. An agricultural planting monitoring device based on big data, characterized in that: The device is used to implement any step of the big data-based agricultural planting monitoring method described in claims 1-7, specifically including: A data collection module: used to collect image data, soil data, and water source data of the agricultural planting area. The image data includes remote sensing images of the planting area; the soil data includes N content, P content, K content, organic matter content, soil pH value, and compactness; the water source data includes dissolved oxygen content, water source pH, and heavy metal content; A feature extraction module: used to store the image data, soil data, and water source data in a big data storage platform, and perform feature extraction on the image data, soil data, and water source data to obtain crop characteristics, soil characteristics, and water source characteristics; the crop characteristics include crop coverage and crop color coefficient; the soil characteristics include soil nutrient index and soil inhibition index; the water source characteristic is the beneficial vegetation index; State determination module: used to generate crop state coefficients by analyzing crop characteristics, and determine the growth period of crops by comparing the crop state coefficients with preset thresholds. The growth period includes the infancy period, growth period and maturity period, and obtain standard soil data and standard water source data for the corresponding growth period; Data scoring module: used to calculate standard soil characteristics and standard water source characteristics, and score the soil and water sources respectively according to the difference between soil characteristics and standard soil characteristics, and the difference between water source characteristics and standard water source characteristics; Status classification module: used to conduct a comprehensive analysis of soil and water source rating results, generate an environmental assessment index, compare the environmental assessment index with the preset threshold, and classify planting conditions into good, normal, and risky based on the comparison results.

Images