Intelligent irrigation data model and corn-soybean water-saving interplanting system

Abstract

The invention discloses an intelligent irrigation data model and a corn-soybean water-saving interplanting system, which comprises a data collection module, a feature extraction module and a user interface and visualization module, and is characterized in that the data collection module is used for acquiring crop point cloud data based on real-time monitoring of crops in a field planting field, and displaying the crop point cloud data on the user interface and the visualization module; the point cloud data is used for carrying out preprocessing such as image correction, filtering and denoising, and the feature extraction module specifically comprises a three-dimensional reconstruction unit, a geometric feature extraction unit and a light energy distribution model unit. According to the invention, the method achieves the precise monitoring and analysis of the state of crops through the integration of data collection and acquisition of point cloud data, a feature extraction processing technology and light energy distribution simulation, thereby effectively improving the utilization efficiency of water resources, achieving the fine management, avoiding the adverse effects of excessive irrigation or drought on the canopy structure, and improving the reliability of the canopy structure. The growth quality and the light energy utilization efficiency of crops are improved.

Description

Technical Field

[0001] The present invention relates to the field of agricultural technology, and in particular to a smart irrigation data model and a corn-soybean water-saving interplanting system. Background Art

[0002] The utilization of agricultural water resources has always been characterized by low utilization rate, shortage and waste of water resources. The effective utilization of water resources is the main problem facing the development of irrigation agriculture in China. Saving water, reasonable irrigation and developing water-saving agriculture are strategic issues. One of the effective ways to solve this problem is to monitor the degree of crop water deficit and make accurate judgments.

[0003] In related technologies, an integrated data system is usually used for irrigation in corn-soybean intercropping groups, and statistical analysis of environmental data, crop data, and past operation data is combined with current environmental data to provide an optimal operation model to ensure that the fertilizer or water required at different stages in the production process of the corn-soybean intercropping group is separated and related operations are carried out according to the characteristics, so as to comprehensively improve the production efficiency and utilization rate of the corn-soybean intercropping group.

[0004] However, the traditional corn-soybean data model system requires on-site operation and direct measurement of crops to obtain characteristics and water requirements, which is time-consuming and labor-intensive. In addition, since it is a contact measurement, it also has a certain impact on the growth of crops. At the same time, the system still has shortcomings, and irrigation management and feature extraction are unscientific, which in turn affects the quality and yield of corn-soybeans. Summary of the invention

[0005] The present invention provides a smart irrigation data model and a corn-soybean water-saving interplanting system to solve the problem that the traditional corn-soybean data model system needs on-site operation and direct measurement of crops to obtain characteristics and water demand information, which is time-consuming and labor-intensive, and because it is a contact measurement, it also has a certain impact on the growth of crops. At the same time, the system still has deficiencies, and the irrigation management and feature extraction are unscientific. The technical scheme adopted is as follows: According to a first aspect of the present application, a smart irrigation data model is provided, including a data collection module, a feature extraction module, and a user interface and visualization module, wherein: the data collection module is used to obtain the crop point cloud data based on real-time monitoring of crops in a field planting area, and use the point cloud data for image correction, filtering, denoising and other pre-processing; The feature extraction module specifically includes: a three-dimensional reconstruction unit, a geometric feature extraction unit, and a light energy distribution model unit, wherein the three-dimensional reconstruction unit is used to generate a three-dimensional canopy model of the crop, and the geometric feature extraction unit is used to extract geometric feature parameters of the crop; The light energy distribution model unit is used to simulate the distribution and transmission of light energy in the three-dimensional canopy of the crop, and the establishment of the model unit information specifically includes: initializing the sun position, initializing radiation, adding radiation sources, and setting radiation parameters; By initializing the sun position, initializing the radiation, adding the radiation source, and setting the radiation parameters, the light energy distribution model is obtained; The user interface and visualization module are used to automatically generate smart irrigation data reports based on the crop detection and extraction results and intelligent control.

[0006] Preferably, it also includes a light energy utilization rate calculation module for calculating the light energy utilization efficiency based on the constructed light energy distribution model to obtain the impact of different canopy structures of the crops on the light energy utilization rate.

[0007] Preferably, the specific steps of the light energy utilization rate calculation module are: 1) Set the current time, obtain the sun direction vector and set the radiation source direction; 2) Calculate solar flux and diffuse fraction; 3) Set the flux of the radiation source; 4) Running the radiation model and calculating the radiation flux of different point cloud data of the crop.

[0008] Preferably, the point cloud data specifically includes longitude and latitude information, atmospheric pressure information, air temperature information, relative humidity information and atmospheric turbidity coefficient information.

[0009] Preferably, the crop is a corn-soybean intercropping population.

[0010] Preferably, the geometric characteristic parameters include canopy overlap area, canopy volume and density of corn above soybeans, width and area of ​​soybean canopy exposed to direct sunlight, and distance between leaves and soybeans.

[0011] Preferably, the user interface and visualization module specifically includes: a data uploading unit, a query unit and an exporting unit, wherein: the data uploading unit is used to automatically generate a smart irrigation data report based on the crop detection and extraction results and the intelligent control, and the smart irrigation data report includes current crop characteristics and related parameters; The query unit is used to obtain and view the model and feature extraction data of the crop; The exporting unit is used to export the information of the crops.

[0012] According to a second aspect of the present invention, a corn-soybean water-saving intercropping system is provided. The system performs digitized planting monitoring and optimization of corn-soybean intercropping based on the smart irrigation data model described in the first aspect, and is provided with a dedicated drip irrigation system.

[0013] Preferably, the plurality of drip irrigation belts include a first drip irrigation belt and a second drip irrigation belt, wherein the first drip irrigation belt is used for irrigating corn, and the second drip irrigation belt is used for irrigating soybeans; A pipeline connected to the plurality of drip irrigation belts, wherein the pipeline is provided with a solenoid valve, and the solenoid valve is used to connect or block the passage between the pipeline and the drip irrigation belt; A sensor is arranged between the corn and the soybean, wherein a ground film is arranged every two rows of the corn and every three rows of the soybean; The control system is arranged on one side of the pipeline and is electrically connected with the sensor and the solenoid valve.

[0014] Preferably, the pipeline includes a first branch pipeline, a second branch pipeline and a main pipeline, one end of the first branch pipeline is connected to the first drip irrigation belt, and the other end is connected to the main pipeline; One end of the second branch pipeline is connected to the second drip irrigation belt, and the other end is connected to the main pipeline; The sensor is a soil monitoring device, and two of the soil monitoring devices are provided to detect the soil moisture values ​​of the soybeans and the corns respectively.

[0015] Compared with the prior art, the present invention has the following technical advances: The present invention realizes accurate monitoring and analysis of crop status by integrating data collection to obtain point cloud data, feature extraction and processing technology, and light energy distribution simulation, thereby effectively improving the utilization efficiency of water resources while realizing refined management, avoiding the adverse effects of excessive irrigation or drought on the canopy structure, and improving the growth quality of crops and the efficiency of light energy utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0017] In the attached picture: Figure 1 It is a schematic diagram of the smart irrigation data model in the present invention; Figure 2 This is a schematic diagram of the structure of the corn-soybean water-saving interplanting system of the present invention; Figure 3 It is a schematic diagram of the corn-soybean water-saving interplanting system of the present invention; Figure 4 This is a result diagram of the intelligent irrigation data model and corn-soybean water-saving intercropping system in the present invention.

[0018] In the figure: 1. drip irrigation tape; 10. first drip irrigation tape; 11. second drip irrigation tape; 2. pipeline; 20. first branch pipeline; 21. second branch pipeline; 22. main pipeline; 3. sensor; 4. control system; 5. solenoid valve; 6. corn; 7. soybean; 8. ground film. DETAILED DESCRIPTION

[0019] The following specific embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. The embodiments of the present invention will be described below in conjunction with the accompanying drawings.

[0020] like Figure 1 As shown, the present invention discloses a smart irrigation data model, which provides precise irrigation guidance for crops to ensure the growth and yield of crops. The crops can be any one or a combination of corn and soybeans, including a data collection module, a feature extraction module, and a user interface and visualization module. The modules are closely coordinated in the entire smart irrigation process to improve the efficiency of light energy utilization during the growth of crops. The data collection module is used to obtain crop point cloud data based on real-time monitoring of crops in the field planting area. In one example, the data collection module can obtain three-dimensional point cloud data of crops through sensors, cameras or drones installed in the field. The point cloud data reflects the crop in detail. The growth morphology of crops, including the shape and size of leaves and the overall canopy structure, etc. In order to ensure the accuracy of subsequent data processing, the system pre-processes the collected point cloud data. The pre-processing includes image correction for adjusting the tilt and distortion in the sensor collected data to ensure that the acquired data accurately reflects the actual morphology of crops, and filtering for removing noise data, such as error points caused by environmental factors such as wind and rain, to enhance the quality of data. It also includes denoising, which can further optimize the data and remove invalid data points caused by equipment jitter or external interference, so that the data collection module provides high-quality crop point cloud data for feature extraction, thereby ensuring model accuracy and analysis results.

[0021] The feature extraction module is responsible for converting the pre-processed point cloud data into crop feature information with practical significance, including: 3D reconstruction unit, geometric feature extraction unit, and light energy distribution model unit. The 3D reconstruction unit is used to generate a 3D canopy model of crops, which provides a basis for subsequent crop analysis. The geometric feature extraction unit is used to extract the geometric feature parameters of crops, such as the area, angle, canopy height and volume of leaves. These geometric feature parameters can help the system analyze the growth status of crops and determine whether irrigation or other agricultural management measures are needed.

[0022] The light energy distribution model unit is used to simulate the distribution and transmission of light energy in the three-dimensional canopy of crops. The information for establishing the model unit specifically includes: initializing the sun's position, initializing radiation, adding radiation sources, and setting radiation parameters. The initialization of the sun's position determines the sun's position in the sky according to the geographical location and time, which affects the angle and intensity of light received by crops; initializing radiation initializes the solar radiation intensity according to meteorological data or external sensor information to ensure that the simulated light energy transmission process has practical reference value; adding radiation sources simulates the irradiation of crops with sunlight and possible artificial light sources according to different crop planting areas; setting radiation parameters sets light energy transmission parameters according to the physiological needs of different crops to ensure that the light energy distribution model meets the photosynthesis requirements of crops. By initializing the sun's position, initializing radiation, adding radiation sources, and setting radiation parameters, a light energy distribution model is obtained, thereby providing a basis for irrigation.

[0023] The user interface and visualization module is responsible for presenting complex agricultural data and analysis results to users in an intuitive and easy-to-understand way. Based on the output results of the aforementioned data collection and feature extraction modules, the user interface module generates detailed smart irrigation data reports based on information such as crop growth status, light energy distribution, and irrigation needs through data visualization technology. For example, users can view the real-time growth status of crops through the interface, including geometric characteristics and light energy absorption. For example, users can generate smart irrigation suggestions based on model analysis results, such as when to irrigate and how much to irrigate. For another example, users can use the interface to formulate agricultural management plans for the next few days, combining weather forecasts and crop status to provide precise management guidance. In addition, the user interface also supports automatic control. Users can perform manual operations based on the irrigation suggestions provided by the system, or enable the automatic control function. The system will automatically adjust the operation of irrigation equipment based on real-time monitoring data and model analysis results to ensure that crops receive the most appropriate water supply.

[0024] It should be noted that the present invention uses computer Python, C++ and MATLAB programs. First, the path and parameters are set and the Python script is run. The script will traverse the subdirectories under the specified directory, process the point cloud data, and call the C++ and MATLAB programs. Then, the C++ program is used to receive the parameters passed by the Python script, calculate the light energy distribution and utilization efficiency, and save the output results to the specified file. Next, the MATLAB program is used to receive the parameters passed by the Python script, extract and analyze geometric features, and finally, the output results are saved to the specified file.

[0025] Preferably, it also includes a light energy utilization rate calculation module, which is used to calculate the light energy utilization efficiency based on the constructed light energy distribution model to obtain the impact of different canopy structures of the crops on the light energy utilization rate. In one example, the light energy utilization rate calculation realizes dynamic monitoring and management of crop light energy utilization through optimization analysis of light energy absorption, utilization and canopy structure, providing strong data support and decision-making basis for precise management in smart agriculture. So that the entire model can achieve high-quality and high-yield crops and promote the intelligent process of modern agriculture.

[0026] Preferably, the specific steps of the light energy utilization rate calculation module are: 1. Set the current time, obtain the sun direction vector and set the radiation source direction; 2. Calculate the solar flux and diffuse fraction; 3. Set the flux of the radiation source; 4. Run the radiation model and calculate the radiation flux of different point cloud data of the crop. In one example, a C++ program is used to process the model construction, that is, the solar flux (`float Rflux = solarposition.getSolarFlux(pressure, temperature, humidity,turbidity);`) is calculated through the solar position model and atmospheric parameters (such as pressure, temperature, humidity, turbidity coefficient, etc.), and the direct flux and diffuse flux are distinguished. The direct flux is (`Rflux*(1fdiff)`) where (`fdiff` is the diffuse fraction, calculated by `float fdiff = solarposition.getDiffuseFraction(pressure,temperature,humidity,turbidity);`), and the diffuse flux is (`Rflux * fdiff`). The radiation model is used to calculate the radiation flux of different point clouds (such as corn and soybean point clouds) at different time points (such as from 7 am to 9 pm) according to the sun position and canopy structure. For example, in the C++ code, after running the radiation model through (`radiation.runBand("PAR");`), the radiation flux of different point clouds is calculated using (`context.calculatePrimitiveDataAreaWeightedSum(pc1, "radiation_flux_PAR", PAR_pc1);`) etc. (here `PAR_pc1` etc. represents the photosynthetically active radiation flux received by different point clouds).

[0027] Light use efficiency is calculated by comparing the ratio of the photosynthetically active radiation absorbed by corn and soybean to the total incident light energy under different canopy structures. For example, if the total incident light energy is assumed to be (`total_incident_light`), which can be estimated by integrating the solar flux at different points in time, and the photosynthetically active radiation absorbed by corn under a specific canopy structure is (`PAR_corn`), and the photosynthetically active radiation absorbed by soybean is (`PAR_soybean`), then the light use efficiency can be roughly expressed as: (`(PAR_corn + PAR_soybean) / total_incident_light`).

[0028] The actual calculation formula will also take into account the impact of other factors such as leaf area index, canopy overlap area and other geometric characteristic parameters on light energy utilization efficiency. At the same time, the specific calculation formula needs to be determined in combination with the specific application scenario and design purpose of the system.

[0029] Preferably, the point cloud data specifically includes latitude and longitude information, atmospheric pressure information, air temperature information, relative humidity information and atmospheric turbidity coefficient information.

[0030] Preferably, the crops are corn-soybean intercropping groups, that is, corn and soybean are planted alternately in the same field, which can achieve efficient use of resources, increase crop yields, improve soil structure and reduce the occurrence of pests and diseases.

[0031] Preferably, the geometric characteristic analysis of corn-soybean is performed using MATLAB program, and the geometric characteristic parameters include canopy overlap area, canopy volume and density of corn above soybean, width and area of ​​soybean canopy exposed to direct sunlight, and distance of leaves from soybean.

[0032] Preferably, the user interface and visualization module specifically includes a data upload unit, a query unit and an export unit, wherein: the data upload unit is used to automatically generate a smart irrigation data report based on crop detection and extraction results and intelligent control, the smart irrigation data report includes current crop characteristics and related parameters, the query unit is used to obtain and view crop models and feature extraction data, and the export unit is used to export crop information.

[0033] The processing steps of a smart irrigation data model in this application are as follows: First, data collection and preprocessing are performed to collect point cloud data, which can be obtained through unmanned aerial vehicles (UAVs) or other remote sensing technologies, and image correction, point cloud data filtering and denoising are performed to provide high-quality data for subsequent 3D reconstruction and analysis. Then, 3D reconstruction is performed, and a 3D reconstruction algorithm is used to generate a 3D canopy model of the corn-soybean intercropping group to better analyze its geometric spatial structure characteristics. At the same time, it supports viewing and adjusting the reconstructed model to ensure the accuracy of the model.

[0034] After that, the light energy distribution model is constructed, taking into account factors such as the sun's position, atmospheric conditions, and terrain, to simulate the distribution and transmission of light energy in the three-dimensional canopy of corn and soybeans, and to establish the initialization of the sun position model and radiation model. For example, in the C++ code, the sun position model is initialized by (`SolarPosition solarposition(UTC, latitude, longitude,&context);`), where (`UTC`) Coordinated Universal Time, (`latitude`) latitude, (`longitude`) longitude and other parameters are used to determine the sun's position. Then, the radiation model is initialized by (`RadiationModel radiation(&context);`), and the radiation source (sun) and various radiation parameters are set.

[0035] Finally, the light energy utilization efficiency is calculated. In the C++ code, by looping through different time points (such as from 7 o'clock to 21 o'clock), setting the current time and sun direction, calculating the solar flux and diffuse fraction, setting the flux of the radiation source, and then running the radiation model. Specifically, the radiation flux of different point clouds is calculated through the following steps: Set the current time and sun direction (`context.setTime(0, hour);`) Set the current time, (`vec3 sdir = solarposition.getSunDirectionVector();`) Get the sun direction vector, (`radiation.setSourcePosition(SunSource, sdir);`) Set the radiation source direction; Calculate the solar flux and diffuse fraction, (`float Rflux = solarposition.getSolarFlux(pressure, temperature,humidity, turbidity);`) Calculate the solar flux, (`float fdiff = solarposition.getDiffuseFraction(pressure,temperature,humidity,turbidity);`) Calculate the diffuse fraction; Set the flux of the radiation source, (`radiation.setSourceFlux(SunSource,"PAR",Rflux * (1fdiff));`) Set the direct flux, (`radiation.setDiffuseRadiationFlux("PAR", Rflux * fdiff);`) Set the diffuse flux; Run the radiation model, (`radiation.runBand("PAR");`) Run the radiation model to calculate the radiation flux of different point clouds.

[0036] In MATLAB, geometric feature extraction and analysis are performed in connection with the calculation of light energy utilization efficiency (calculation of canopy overlap area that affects the distribution and utilization efficiency of light energy in corn and soybean canopies, canopy characteristics of corn above soybeans, characteristics of soybean canopies that can be exposed to direct sunlight, etc.).

[0037] Based on the constructed light energy distribution model and calculated radiation flux and other data, the impact of different canopy structures on light energy utilization efficiency is analyzed (geometric characteristic parameters such as canopy height, canopy density, canopy volume, etc. will affect the absorption, reflection and transmission of light energy and thus affect the light energy utilization efficiency).

[0038] The light energy utilization efficiency of the three-dimensional canopy of the corn-soybean intercropping population is obtained through comprehensive calculations of multiple steps, including data collection and preprocessing, three-dimensional reconstruction, light energy distribution model construction, and light energy utilization efficiency calculation. It involves the collaborative work of three parts of code, Python, C++, and MATLAB, to accurately extract and analyze the features of corn and soybeans, thereby improving the growth quality of crops and light energy utilization efficiency.

[0039] like Figures 2 to 3 As shown, the present invention also provides a corn-soybean water-saving interplanting system, which performs digitized planting monitoring and optimization of corn-soybean interplanting based on a smart irrigation data model, and is also provided with a dedicated drip irrigation system. The crops are an intercropping group of corn 6 and soybean 7, that is, corn 6 and soybean 7 are planted crosswise, and the distance between corn 6 and soybean 7 can be adaptively set as needed. In the present application, the row spacing of corn 6 is 40 cm, the plant spacing is 12 cm, the row spacing of soybean 7 is 30 cm, and the plant spacing is 16 cm. The appropriate row ratio planting combination of corn 6 and soybean 7 is determined as needed, such as 2:2, 2:4, etc. In one example, corn 6 and soybean 7 adopt a row ratio of 2:3, and the effects on the canopy structure and light energy utilization of the intercropping group of corn 6 and soybean 7 are observed. The wider spacing between the rows of corn 6 can reduce the shading of soybean 7, so that soybean 7 can obtain more direct light, and it is also beneficial to air circulation and field management. It is adjusted according to factors such as light conditions and soil fertility in different regions. In areas with sufficient light, the planting density of corn 6 can be appropriately increased to improve land utilization, while in areas with relatively weak light, the planting density of corn 6 should be reduced to ensure that soybean 7 has sufficient light.

[0040] At the same time, corn varieties should be selected with compact plant shapes and upright leaves. Such varieties can reduce the occupation of surrounding space during growth and make the canopy more transparent. For example, some compact corn varieties have small leaf angles, which can reduce shading of the underlying soybeans and improve the penetration of light energy. Soybean varieties should be selected with strong shade tolerance and moderate plant shape. Shade-tolerant soybean varieties can still maintain good growth and development under the shade of corn, and moderate plant shape can avoid excessive competition with corn for space. For example, some soybean varieties have strong branching ability and can make full use of light for photosynthesis in a limited space.

[0041] In the cultivation management measures, adaptive control can also be carried out according to the sowing time, fertilization management, and water management. For example, water management, reasonable irrigation, and maintaining the appropriate moisture content of the soil. Adequate water supply can promote crop growth and make the canopy more lush. For example, in the key growth periods of corn6 and soybean7, such as jointing period and flowering period, timely watering can increase the growth rate and yield of crops. Water-saving irrigation technologies such as drip irrigation and sprinkler irrigation can be used to improve water use efficiency. At the same time, excessive irrigation can be avoided to cause soil compaction and root hypoxia, which will affect crop growth. For example, drip irrigation can accurately control the amount of irrigation water according to the water demand of crops and reduce water waste.

[0042] Continue to refer Figures 2 to 3The corn-soybean water-saving intercropping system of the smart irrigation data model includes multiple drip irrigation belts 1, pipelines 2, sensors 3 and a control system 4, wherein the multiple drip irrigation belts 1 include a first drip irrigation belt 10 and a second drip irrigation belt 11, the first drip irrigation belt 10 is located between two adjacent rows of corn 6, and the first drip irrigation belt 10 is used to irrigate corn 6. Corn 6, as a high water-consuming crop, requires sufficient water during the growth period, especially during the jointing period and the filling period. Therefore, the first drip irrigation belt 10 will accurately control the water volume according to the water demand of corn 6. The second drip irrigation belt 11 is located between two adjacent rows of soybeans 7. The second drip irrigation belt 11 is used to irrigate soybeans 7. Compared with corn 6, soybeans 7 have a relatively lower water demand, especially in the seed germination period and the seedling stage, the water demand is relatively small, so the irrigation volume of the second drip irrigation belt 11 can be flexibly adjusted according to the growth process of soybeans 7. The first drip irrigation belt 10 and the second drip irrigation belt 11 are similar in structure, and can independently adjust their respective irrigation volumes through the differentiated management of the control system 4 to adapt to the different growth stages and water demand characteristics of corn 6 and soybeans 7.

[0043] Pipeline 2 is responsible for transporting water resources to each drip irrigation belt 1. Pipeline 2 is connected to multiple drip irrigation belts 1 to ensure that water can be evenly distributed to the corn 6 and soybean 7 planting areas through pipeline 2. Solenoid valve 5 is provided on pipeline 2. Solenoid valve 5 is used to connect or block the channel between pipeline 2 and drip irrigation belt 1. Through solenoid valve 5, control system 4 can intelligently control the start or stop of water transport, so as to accurately adjust the irrigation amount of each drip irrigation belt 1, ensure that corn 6 and soybean 7 obtain the right amount of water, and avoid waste. In one example, solenoid valve 5 adopts an integrated intelligent irrigation valve, which integrates solar power supply, wireless communication, and two-way valve outlets. It has high durability, low energy consumption, precise control and multiple protection functions. During use, it can accurately control the water output, and has a built-in opening sensor, which can support remote opening control and is durable, thereby improving the intelligence and precision of irrigation.

[0044] The sensor 3 is arranged between the corn 6 and the soybean 7, and the sensor 3 is used to detect environmental data, wherein the corn 6 and the soybean 7 are both planted by drip irrigation under the film, that is, one ground film 8 is used for every two rows of corn 6, and one ground film 8 is used for every three rows of soybean 7, and the ground film 8 is made of polyethylene film, and the control system 4 is arranged on one side of the pipeline 2, and is electrically connected to the sensor 3 and the solenoid valve 5, and the control system 4 is used to receive data or other data from the sensor 3, and to establish a model based on the collected data to analyze the characteristics and parameters for automated and scientific management. It should be noted that in the present application, the corn 6 uses one film, one tube and two rows, and the soybean 7 uses one film, two tubes and three rows.

[0045] Preferably, Figure 2 and Figure 3As shown, the pipeline 2 includes a first branch pipeline 20, a second branch pipeline 21 and a main pipeline 22. The diameter of the main pipeline 22 is usually large so as to carry enough water and ensure that the branch pipelines can obtain a stable water supply during the peak period of irrigation demand. A solenoid valve 5 is configured between the main pipeline 22 and the branch pipelines so as to control the main switch of the water flow according to instructions when necessary. The outlet of the main pipeline 22 is connected to each branch pipeline so that water can be distributed to the first branch pipeline 20 and the second branch pipeline 21 in sequence, thereby realizing independent irrigation of different crops. One end of the first branch pipeline 20 is connected to the first drip irrigation belt 10, and the other end is connected to the main pipeline 22. The first branch pipeline 20 is specifically responsible for transporting water from the main pipeline 22 to the first drip irrigation belt 10 of the corn 6, ensuring that the root area of ​​the corn 6 obtains the required amount of water, and is controlled by the solenoid valve 5 between the first branch pipeline 20 and the main pipeline 22. The water flow of the first branch pipeline 20 can be opened or closed according to the actual water demand of the corn 6 to achieve precise irrigation. One end of the second branch pipe 21 is connected to the second drip irrigation belt 11, and the other end is connected to the main pipe 22. During the irrigation process, the second branch pipe 21 transports water to the soybean 7 planting area through the second drip irrigation belt 11, providing the required water source for the growth of soybean 7. Through the first branch pipe 20 and the second branch pipe 21, the irrigation amount of corn 6 and soybean 7 can be controlled separately, avoiding water loss and improving irrigation efficiency.

[0046] Sensor 3 may be a soil moisture sensor, a temperature sensor, a light sensor, etc., and may be adaptively set as required. In one example, sensor 3 is a soil monitoring device. The soil monitoring system can continuously monitor the moisture content of multiple sample plots and different soil depths for a long time. Two soil monitoring devices are provided, which are used to detect the soil moisture values ​​at soybeans 7 and corn 6 respectively. During the monitoring process, the soil detection device provides real-time information to the control system 4, ensuring that the control system 4 can automatically adjust the irrigation strategy according to actual conditions.

[0047] The specific steps of a smart irrigation data model and corn-soybean water-saving interplanting system provided in this application are: like Figures 1 to 3As shown, first, according to the intercropping group of two rows of corn 6 and three rows of soybeans 7, the sensor 3, the control system 4, the solenoid valve 5 and the pipeline 2 are arranged at the corn 6 and the soybean 7 in the field and connected to form a corn-soybean water-saving intercropping system, the first branch pipeline 20 in the pipeline 2 is connected to the first drip irrigation belt 10, so that each first drip irrigation belt 10 is located between two adjacent rows of corn 6, and at the same time, a ground film 8 is covered every two rows of corn 6 to facilitate irrigation of the corn 6, the second branch pipeline 21 in the pipeline 2 is connected to the second drip irrigation belt 11, so that each second drip irrigation belt 10 is located between two adjacent rows of soybeans 7, and at the same time, a ground film 8 is covered every three rows of soybeans 7 to facilitate irrigation of the soybeans 7. The sensor 3 and the solenoid valve 5 are both electrically connected to the control system 4. Then the sensor 3 obtains field data information and other data information and transmits them to the control system 4. The control system 4 uses a computer program to establish a model, collects and preprocesses the obtained information, and constructs a light energy distribution model. Finally, the light energy utilization rate is calculated, so as to accurately extract and analyze the characteristics of corn 6 and soybeans 7, so as to facilitate the subsequent accurate management of corn 6 and soybeans 7, avoid the adverse effects of excessive irrigation or drought on the canopy structure of corn 6 and soybeans 7, and thus improve the growth quality and light energy utilization efficiency of corn 6 and soybeans 7.

[0048] In one example, if Figures 1 to 4 In this application, corn 6 is selected from either Xianyu 335 or Longdan 4, and the "one film, one tube, two rows" model is adopted; soybean 7 is selected from Longhuang 3, and the "one film, two tubes, two rows" model is adopted.

[0049] The intercropping system with a 2:3 row ratio of corn and soybeans adopts a full film covering planting method with under-film drip irrigation and hole sowing on the film. Among them, the row spacing of corn 6 is 40 cm and the plant spacing is 12 cm. The row spacing of soybean 7 is 30 cm and the plant spacing is 16 cm. The spacing between corn 6 and soybean 7 is 70 cm. At the same time, under the same conditions, corn 6 and soybean 7 are planted separately for comparison with intercropping, and the intelligent irrigation data model and corn-soybean water-saving intercropping system are used for detection. Figure 4 The results are shown as follows: First, the total water consumption of intercropping is 23% lower than that of monocropping, including 24% lower than that of monocropping corn and 19% lower than that of monocropping soybean; the water use efficiency is 41% higher, 22% higher than that of monocropping corn and 641% higher than that of monocropping soybean; second, the total yield of intercropping is 31% higher than that of monocropping, including 6% lower than that of monocropping corn, but the economic benefit is 5% higher, 83% higher than that of monocropping soybean, and the economic benefit is 70% higher; third, in terms of water deficit regulation of intercropping, full irrigation during the entire growth period of corn and deficit irrigation during the non-critical growth period of soybean loses 8% of the economic benefit compared with full irrigation during the entire growth period, but saves 16% of irrigation water resources, reduces water consumption by 3% compared with other modes of deficit irrigation, but increases yield by 8%.

[0050] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein with equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the scope of protection of the claims of the present invention.

Claims

1. A smart irrigation data model, characterized in that: It includes a data collection module, a feature extraction module, and a user interface and visualization module, wherein: the data collection module is used to obtain the crop point cloud data based on real-time monitoring of crops in the on-site planting area, and use the point cloud data to perform pre-processing such as image correction, filtering and denoising; The feature extraction module specifically includes: a three-dimensional reconstruction unit, a geometric feature extraction unit, and a light energy distribution model unit, wherein the three-dimensional reconstruction unit is used to generate a three-dimensional canopy model of the crop, and the geometric feature extraction unit is used to extract geometric feature parameters of the crop; The light energy distribution model unit is used to simulate the distribution and transmission of light energy in the three-dimensional canopy of the crop, and the establishment of the model unit information specifically includes: initializing the sun position, initializing radiation, adding radiation sources, and setting radiation parameters; By initializing the sun position, initializing the radiation, adding the radiation source, and setting the radiation parameters, the light energy distribution model is obtained; The user interface and visualization module are used to automatically generate smart irrigation data reports based on the crop detection and extraction results and intelligent control.

2. The smart irrigation data model according to claim 1, characterized in that: It also includes a light energy utilization rate calculation module, which is used to calculate the light energy utilization efficiency based on the constructed light energy distribution model to obtain the impact of different canopy structures of the crops on the light energy utilization rate.

3. A smart irrigation data model according to claim 2, characterized in that: The specific steps of the light energy utilization rate calculation module are: 1) Set the current time, obtain the sun direction vector and set the radiation source direction; 2) Calculate solar flux and diffuse fraction; 3) Set the flux of the radiation source; 4) Running the radiation model and calculating the radiation flux of different point cloud data of the crop.

4. The smart irrigation data model according to claim 1, characterized in that: The point cloud data specifically includes latitude and longitude information, atmospheric pressure information, air temperature information, relative humidity information and atmospheric turbidity coefficient information.

5. A smart irrigation data model according to any one of claims 1 to 4, characterized in that: The crops are corn-soybean intercropping groups.

6. The smart irrigation data model according to claim 5, characterized in that: The geometric characteristic parameters include canopy overlap area, canopy volume and density of corn above soybeans, width and area of ​​soybean canopy exposed to direct sunlight, and distance of leaves from soybeans.

7. The smart irrigation data model according to claim 1, characterized in that: The user interface and visualization module specifically includes: a data uploading unit, a query unit and an exporting unit, wherein: the data uploading unit is used to automatically generate a smart irrigation data report based on the crop detection and extraction results and the intelligent control, and the smart irrigation data report includes current crop characteristics and related parameters; The query unit is used to obtain and view the model and feature extraction data of the crop; The exporting unit is used to export the information of the crops.

8. A corn-soybean water-saving interplanting system, characterized by: The system performs digitized planting monitoring and optimization of corn-soybean intercropping based on the smart irrigation data model described in any one of claims 1-7, and is also provided with a dedicated drip irrigation system.

9. A corn-soybean water-saving interplanting system according to claim 8, characterized in that: The drip irrigation system comprises: A plurality of drip irrigation belts, including a first drip irrigation belt and a second drip irrigation belt, wherein the first drip irrigation belt is used for irrigating corn, and the second drip irrigation belt is used for irrigating soybean; A pipeline connected to the plurality of drip irrigation belts, wherein the pipeline is provided with a solenoid valve, and the solenoid valve is used to connect or block the passage between the pipeline and the drip irrigation belt; A sensor is arranged between the corn and the soybean, wherein a ground film is arranged every two rows of the corn and every three rows of the soybean; The control system is arranged on one side of the pipeline and is electrically connected with the sensor and the solenoid valve.

10. A corn-soybean water-saving interplanting system according to claim 9, characterized in that: The pipeline comprises a first branch pipeline, a second branch pipeline and a main pipeline, one end of the first branch pipeline is connected to the first drip irrigation belt, and the other end is connected to the main pipeline; One end of the second branch pipeline is connected to the second drip irrigation belt, and the other end is connected to the main pipeline; The sensor is a soil monitoring device, and two of the soil monitoring devices are provided to detect the soil moisture values ​​of the soybeans and the corns respectively.

Images