Field crop growth management method and system based on satellite remote sensing monitoring
Through satellite remote sensing technology, the growth status and soil nutrients of crops are monitored, and the amount of fertilizer is adjusted in real time, which solves the problems of inaccurate fertilization and environmental pressure in traditional field crop management, and improves agricultural production efficiency and ecological protection.
Patent Information
- Application Number
- CN202410991179.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-23
- Publication Date
- 2024-11-15
AI Technical Summary
Traditional field crop management methods are inefficient and cannot monitor crop growth status and environmental changes in real time and accurately. In particular, the fertilization process lacks real-time monitoring and dynamic adjustment capabilities, resulting in poor fertilization effects and limited yield improvement.
The field crop growth management method based on satellite remote sensing monitoring is adopted. By acquiring and preprocessing remote sensing images, the effective leaf area index and crop height are calculated, the growth potential analysis model is constructed, and the fertilizer amount calculation model is constructed based on soil nutrient data, and the fertilizer amount is output in real time for management. .
It improves the accuracy and efficiency of fertilization, reduces resource waste and environmental pollution, realizes real-time monitoring and sustainable management of crop growth, improves agricultural production efficiency and output, and protects the ecological environment.
Smart Images

Figure CN118968331A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of crop growth management, and in particular relates to a field crop growth management method and system based on satellite remote sensing monitoring. Background Art
[0002] Traditional field crop management relies on manual on-site inspections and empirical judgments, which is not only inefficient but also difficult to monitor crop growth and environmental changes in real time and accurately. In particular, traditional fertilization methods lack the ability to monitor and adjust in real time in the fertilization process of field crop management.
[0003] Traditional fertilization is usually only carried out at a specific stage of crop growth and cannot be flexibly adjusted according to the real-time growth of crops. This static fertilization method often cannot respond to the actual changes in crop nutrient demand in a timely manner, nor can it effectively respond to sudden environmental pressures, thus limiting the improvement of fertilization effects and the increase of crop yields.
[0004] With the rapid development of satellite remote sensing technology and artificial intelligence technology, a new method of field crop growth management has emerged, bringing revolutionary changes to modern agricultural management. However, although the combination of these two technologies shows great potential, in practical applications, the deep integration of satellite remote sensing and field crop growth management still needs more research and optimization. Summary of the invention
[0005] Purpose of the invention: In order to solve the above problems, the present invention provides a method and system for managing the growth of field crops based on satellite remote sensing monitoring.
[0006] Technical solution: A method for managing the growth of field crops based on satellite remote sensing monitoring, comprising the following steps: Acquire original remote sensing images of crops in the target field in sequence according to time sequence, and preprocess the original remote sensing images to obtain effective remote sensing images; Calculating the effective leaf area index and crop height at different time points based on the effective remote sensing image; constructing a growth analysis model based on the effective leaf area index and crop height; and outputting a crop growth factor based on the growth analysis model; Acquiring soil nutrient data of the target field, and calculating soil nutrient factors based on the soil nutrient data; and constructing a fertilizer amount calculation model based on the soil nutrient factors and crop growth factors; The fertilizer amount is output based on the fertilizer amount calculation model, and fertilization management is performed on the target land based on the fertilizer amount.
[0007] In a further embodiment, the calculation process of the effective leaf area index comprises the following steps: Extracting features from the effective remote sensing image to obtain a crop leaf image, setting a circumscribed circle at the edge of the leaf in the crop leaf image, and sequentially setting a plurality of concentric circles with the same spacing along the direction toward the center of the leaf; defining the image between adjacent concentric circles as a ring; and calculating the void fraction and effective leaf area index of the leaf in the effective remote sensing image using the following formula; ; In the formula, represents the crop leaf area, represents the area of the ring, is the satellite altitude angle, At satellite altitude The porosity below ; In the formula, is the projection function; For at time point t The effective leaf area index at ; The projection function Expand to get the following calculation expression: ; ; ; ; In the formula, is the satellite altitude angle The average projected area of the leaves below; is the average blade inclination angle.
[0008] In a further embodiment, the crop height calculation process comprises the following steps: An observation terminal suspended above a target field is set to obtain the distance between the observation terminal and the target field; the crop height is calculated using the following formula: ; ; In the formula, is the speed of light, The geometric delay of the reflected signal received by the observation terminal relative to the direct signal is: is the height difference between the direct signal and the reflected signal to the observation terminal, is the distance between the observation terminal and the target field, For at time point t The height of the crop at .
[0009] In a further embodiment, constructing a growth analysis model comprises the following steps: At time point t -1. Time pointt Get the effective leaf area index of crops in the target field , , and crop height , ; Then the growth analysis model is: ; In the formula, For time point t Crop growth factors at α , β is the weight coefficient, For time point t -1 and time point t The time interval between.
[0010] In a further embodiment, calculating the soil nutrient factor based on the soil nutrient data comprises the following steps: At time point t The nutrient content of the target field soil is measured, wherein the nutrient content includes the measured values of a plurality of different nutrient indicators; the nutrient content is compared with the grading standard value and converted, and the comparison and conversion process is as follows: ; In the formula, Nutrient index in the soil of the target field i The measured value of , , Nutrient index i The grading standard value of ; Nutrient index in the soil of the target field i The conversion value of .
[0011] In a further embodiment, constructing a fertilizer amount prediction model comprises the following steps: Calculate the time point t Crop growth factors , and nutrient indicators in the soil of the target field i The conversion value of , then the fertilizer amount prediction model is: ; In the formula, Nutrient index i The amount of fertilizer applied, , is the weight coefficient.
[0012] In a further embodiment, preprocessing the original remote sensing image comprises the following steps: The original remote sensing image is grayed to obtain a grayed image; the grayed image is binarized using the following formula: ; In the formula, is the number of leaf pixels of crops, is the number of background pixels, is the average gray value of leaf pixels, is the average gray value of background pixels; ; The grayscale image is binarized to obtain a binarized image, and the binarized image is segmented to obtain an effective remote sensing image.
[0013] In another technical solution, a field crop growth management system based on satellite remote sensing monitoring is provided, which is used to implement the field crop growth management method based on satellite remote sensing monitoring as described above, including: The first module is configured to sequentially acquire original remote sensing images of crops in a target field in a time sequence, and preprocess the original remote sensing images to obtain effective remote sensing images; The second module is configured to calculate the effective leaf area index and crop height at different time points based on the effective remote sensing image; construct a growth analysis model based on the effective leaf area index and crop height; and output a crop growth factor based on the growth analysis model; The third module is configured to obtain soil nutrient data of the target field, calculate soil nutrient factors based on the soil nutrient data, and construct a fertilizer amount calculation model based on the soil nutrient factors and crop growth factors; The fourth module is configured to output the fertilizer amount based on the fertilizer amount calculation model, and perform fertilization management on the target land based on the fertilizer amount.
[0014] Beneficial effects: (1) The present invention introduces satellite remote sensing technology to make the measurement of effective leaf area index and crop height more accurate and efficient. Through high-resolution satellite images and advanced image processing algorithms, the leaf coverage area and vertical growth of crops can be accurately calculated, thereby directly reflecting the growth trend of crops. This non-contact measurement method not only reduces human errors, but also greatly improves the coverage and frequency of monitoring. (2) Combine the leaf area index and crop height data of crops to evaluate the growth status of crops; through time series monitoring, track the changing trends of crop growth in real time, discover growth abnormalities or potential problems in time, and provide a reliable basis for precise management; (3) On the basis of obtaining the crop growth factors of crops, combined with the soil nutrient content data, the required amount of fertilizer is calculated based on the actual needs of crops and soil conditions. This not only improves the utilization rate of fertilizers and reduces resource waste, but also effectively avoids environmental pollution caused by excessive fertilization; (4) The present invention utilizes satellite remote sensing technology to monitor crop growth and manage fertilization, which can significantly improve the efficiency and sustainability of agricultural production. Through real-time monitoring and precise management, planting strategies and management measures can be adjusted in a timely manner to ensure that crops grow in the best conditions, thereby improving yield and quality. At the same time, precise fertilization reduces the excessive use of chemical fertilizers, helps protect the ecological environment, and promotes green agricultural development. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] Figure 1 It is a system architecture diagram of the present invention. DETAILED DESCRIPTION
[0016] Example 1 Modern satellite remote sensing technology has high-resolution imaging capabilities, which can capture subtle changes in crops and monitor key indicators such as crop growth rate, growth volume, leaf area index, etc. In order to deeply integrate satellite remote sensing with field crop growth management, the following technical solutions are proposed: like Figure 1 As shown, this embodiment provides a method for managing the growth of field crops based on satellite remote sensing monitoring, comprising the following steps: S 100. Acquire original remote sensing images of crops in the target field in sequence according to a time sequence, and preprocess the original remote sensing images to obtain effective remote sensing images.
[0017] Traditional fertilization is usually only carried out at a specific stage of crop growth and cannot be flexibly adjusted according to the real-time situation of crop growth. In this embodiment, satellite remote sensing technology is used to monitor crops regularly; through periodic monitoring, the changes in nutrient requirements of crops at different growth stages can be understood in real time. This allows fertilization to be carried out more accurately according to the actual needs of crops, avoiding the problem of nutrient deficiency or excess caused by the inability to respond to demand in time in traditional fertilization.
[0018] Before satellite photography, the location of the target field, the time of photography, the satellite altitude angle and other parameters must be clearly defined; the satellite regularly photographs the crops in the target field, and the satellite will capture the reflection information of the crops in different spectral bands and obtain the original remote sensing image; after the photography is completed, the satellite will send the original remote sensing image to the ground receiving station for storage and processing. In order to clearly display the growth status of crops from the original remote sensing image, the original remote sensing image is preprocessed, the specific contents are as follows: Furthermore, preprocessing the original remote sensing image includes the following steps: The original remote sensing image is grayed to obtain a grayed image; the grayed image is binarized using the following formula: ; In the formula, is the number of leaf pixels of crops, is the number of background pixels, is the average gray value of leaf pixels, is the average gray value of background pixels; ; The grayscale image is binarized to obtain a binary image, and the binary image is segmented to obtain an effective remote sensing image. The value of is used to obtain a threshold suitable for the original remote sensing image, and the image is binarized to obtain a valid remote sensing image.
[0019] S 200. Calculate the effective leaf area index and crop height at different time points based on the effective remote sensing image; construct a growth analysis model based on the effective leaf area index and crop height; and output a crop growth factor based on the growth analysis model.
[0020] Furthermore, the calculation process of the effective leaf area index includes the following steps: Extracting features from the effective remote sensing image to obtain a crop leaf image, setting a circumscribed circle at the edge of the leaf in the crop leaf image, and sequentially setting a plurality of concentric circles with the same spacing along the direction toward the center of the leaf; defining the image between adjacent concentric circles as a ring; and calculating the void fraction and effective leaf area index of the leaf in the effective remote sensing image using the following formula; ; In the formula, represents the crop leaf area, represents the area of the ring, is the satellite altitude angle (the satellite altitude angle described in this embodiment is the angle between the satellite shooting direction and the horizontal plane, which is an acute angle), At satellite altitude The porosity below ; In the formula, is the projection function; For at time point t The effective leaf area index at ; The projection function Expand to get the following calculation expression: ; ; ; ; In the formula, is the satellite altitude angle The average projected area of the leaves below; is the average blade inclination angle.
[0021] The crop height calculation process includes the following steps: An observation terminal suspended above a target field is set to obtain the distance between the observation terminal and the target field; the crop height is calculated using the following formula: ; ; In the formula, is the speed of light, The geometric delay of the reflected signal received by the observation terminal relative to the direct signal is: is the height difference between the direct signal and the reflected signal to the observation terminal, is the distance between the observation terminal and the target field, For at time point t The height of the crop at .
[0022] The observation terminal is used to receive direct signals transmitted directly from the satellite to the observation terminal, and to receive reflected signals transmitted from the satellite to the crops and reflected by the crops.
[0023] The construction of the growth analysis model includes the following steps: At time point t -1. Time point t Get the effective leaf area index of crops in the target field , , and crop height , ; Then the growth analysis model is: ; In the formula, For time point t Crop growth factors at α , β is the weight coefficient, For time point t -1 and time point t The time interval between.
[0024] S 300. Obtain soil nutrient data of the target field, calculate soil nutrient factors based on the soil nutrient data; and construct a fertilizer amount calculation model based on the soil nutrient factors and crop growth factors.
[0025] Further, calculating the soil nutrient factor based on the soil nutrient data comprises the following steps: At time point t The nutrient content of the target field soil is measured, wherein the nutrient content includes the measured values of a plurality of different nutrient indicators; the nutrient content is compared with the grading standard value and converted, and the comparison and conversion process is as follows: ; In the formula, Nutrient index in the soil of the target field i The measured value of , , Nutrient index i The grading standard value of ; Nutrient index in the soil of the target field i The conversion value of .
[0026] Nutrient indicators include at least: total nitrogen, total phosphorus, total potassium, alkaline nitrogen, available phosphorus, available potassium, and organic matter. The classification standard values of the above nutrient indicators can be found in the Second National Soil Survey Standards.
[0027] S 302. Constructing a fertilizer amount prediction model includes the following steps: Calculate the time point t Crop growth factors , and nutrient indicators in the soil of the target field i The conversion value of , then the fertilizer amount prediction model is: ; In the formula, Nutrient index i The amount of fertilizer applied, , is the weight coefficient.
[0028] S 400. Output a fertilizer amount based on the fertilizer amount calculation model, and perform fertilization management on the target land based on the fertilizer amount.
[0029] Example 2 This embodiment provides a field crop growth management system based on satellite remote sensing monitoring, which is used to implement the field crop growth management method based on satellite remote sensing monitoring as described above. The system includes: The first module is configured to sequentially acquire original remote sensing images of crops in a target field in a time sequence, and preprocess the original remote sensing images to obtain effective remote sensing images; The second module is configured to calculate the effective leaf area index and crop height at different time points based on the effective remote sensing image; construct a growth analysis model based on the effective leaf area index and crop height; and output a crop growth factor based on the growth analysis model; The third module is configured to obtain soil nutrient data of the target field, calculate soil nutrient factors based on the soil nutrient data, and construct a fertilizer amount calculation model based on the soil nutrient factors and crop growth factors; The fourth module is configured to output the fertilizer amount based on the fertilizer amount calculation model, and perform fertilization management on the target land based on the fertilizer amount.
Claims
1. A method for managing the growth of field crops based on satellite remote sensing monitoring, characterized in that: The following steps are involved: Acquire original remote sensing images of crops in the target field in sequence according to time sequence, and preprocess the original remote sensing images to obtain effective remote sensing images; Calculating the effective leaf area index and crop height at different time points based on the effective remote sensing image; constructing a growth analysis model based on the effective leaf area index and crop height; and outputting a crop growth factor based on the growth analysis model; Acquiring soil nutrient data of the target field, and calculating a soil nutrient factor based on the soil nutrient data; Constructing a fertilizer amount calculation model based on the soil nutrient factors and crop growth factors; The fertilizer amount is output based on the fertilizer amount calculation model, and fertilization management is performed on the target land based on the fertilizer amount.
2. The method for managing the growth of field crops based on satellite remote sensing monitoring according to claim 1, characterized in that: The calculation process of the effective leaf area index comprises the following steps: Extracting features from the effective remote sensing image to obtain a crop leaf image, setting a circumscribed circle at the edge of the leaf in the crop leaf image, and sequentially setting a plurality of concentric circles with the same spacing along the direction toward the center of the leaf; defining the image between adjacent concentric circles as a ring; and calculating the void fraction and effective leaf area index of the leaf in the effective remote sensing image using the following formula; ; In the formula, represents the crop leaf area, represents the area of the ring, is the satellite altitude angle, At satellite altitude The porosity below ; In the formula, is the projection function; For at time point t The effective leaf area index at ; The projection function Expand to get the following calculation expression: ; ; ; ; In the formula, is the satellite altitude angle The average projected area of the leaves below; is the average blade inclination angle.
3. The method for managing the growth of field crops based on satellite remote sensing monitoring according to claim 1, characterized in that: The crop height calculation process includes the following steps: An observation terminal suspended above a target field is set to obtain the distance between the observation terminal and the target field; the crop height is calculated using the following formula: ; ; In the formula, is the speed of light, The geometric delay of the reflected signal received by the observation terminal relative to the direct signal is: is the height difference between the direct signal and the reflected signal to the observation terminal, is the distance between the observation terminal and the target field, For at time point t The height of the crop at .
4. The method for managing the growth of field crops based on satellite remote sensing monitoring according to claim 1, characterized in that: The construction of the growth analysis model includes the following steps: At time point t -1. Time point t Get the effective leaf area index of crops in the target field , , and crop height , ; Then the growth analysis model is: ; In the formula, For time point t Crop growth factors at α , β is the weight coefficient, For time point t -1 and time point t The time interval between.
5. The method for managing the growth of field crops based on satellite remote sensing monitoring according to claim 1, characterized in that: Calculating soil nutrient factors based on the soil nutrient data comprises the following steps: At time point t The nutrient content of the target field soil is measured, wherein the nutrient content includes the measured values of a plurality of different nutrient indicators; the nutrient content is compared with the grading standard value and converted, and the comparison and conversion process is as follows: ; In the formula, Nutrient index in the soil of the target field i The measured value of , , Nutrient index i The grading standard value of ; Nutrient index in the soil of the target field i The conversion value of .
6. The method for managing the growth of field crops based on satellite remote sensing monitoring according to claim 1, characterized in that: Building a fertilizer amount prediction model includes the following steps: Calculate the time point t Crop growth factors , and nutrient indicators in the soil of the target field i The conversion value of , then the fertilizer amount prediction model is: ; In the formula, Nutrient index i The amount of fertilizer applied, , is the weight coefficient.
7. The method for managing the growth of field crops based on satellite remote sensing monitoring according to claim 1, characterized in that: Preprocessing the original remote sensing image includes the following steps: The original remote sensing image is grayed to obtain a grayed image; the grayed image is binarized using the following formula: ; In the formula, is the number of leaf pixels of crops, is the number of background pixels, is the average gray value of leaf pixels, is the average gray value of background pixel value; ; The grayscale image is binarized to obtain a binarized image, and the binarized image is segmented to obtain an effective remote sensing image.
8. A field crop growth management system based on satellite remote sensing monitoring, characterized in that: The method for managing the growth of field crops based on satellite remote sensing monitoring as claimed in any one of claims 1 to 7 comprises: The first module is configured to sequentially acquire original remote sensing images of crops in a target field in a time sequence, and preprocess the original remote sensing images to obtain effective remote sensing images; The second module is configured to calculate the effective leaf area index and crop height at different time points based on the effective remote sensing image; construct a growth analysis model based on the effective leaf area index and crop height; and output a crop growth factor based on the growth analysis model; The third module is configured to obtain soil nutrient data of the target field, calculate soil nutrient factors based on the soil nutrient data, and construct a fertilizer amount calculation model based on the soil nutrient factors and crop growth factors; The fourth module is configured to output the fertilizer amount based on the fertilizer amount calculation model, and perform fertilization management on the target land based on the fertilizer amount.
