A traceable crop planting technology evaluation method based on multi-dimensional data support

Abstract

The present invention relates to the field of agricultural technology, and in particular to a traceable crop planting technology evaluation method based on multi-dimensional data support, including the construction of an Internet of Things and a cloud database, data collection and processing, and evaluation index calculation; the method provided by the present invention is based on a multi-dimensional planting technology evaluation system based on yield, quality, phenological period, resistance, and pests and diseases, and evaluates the process and results in a more objective and quantifiable manner, making it easier to visualize the results and compare the effects horizontally, and providing data traceability capabilities.

Description

Technical Field

[0001] The present invention relates to the field of agricultural technology, and in particular to a traceable crop planting technology evaluation method based on multi-dimensional data support. Background Art

[0002] As the country and the market continue to raise their technical requirements for agricultural product output and its production process, the evaluation indicators of agricultural production technology are becoming increasingly diversified and refined. The method of judging the quality of technology by its output is no longer sufficient for the evaluation of new agricultural planting technologies. The quality, phenological period, stress resistance, disease and pest resistance of agricultural products and the impact of technology on the planting process are receiving more and more attention from planting managers.

[0003] The current evaluation method for agricultural technology or products mainly relies on statistics of production results and expert opinions. This traditional evaluation method can reflect the pros and cons of a technology to a certain extent and is also widely used in academia and industry. However, this method has four obvious defects.

[0004] First, the method of using expert opinions as the evaluation criteria is mixed with many subjective factors. Due to the influence of the expert's background and other reasons, the evaluation given is inevitably biased.

[0005] Second: The traditional evaluation method is to determine the level based on the results, ignoring the objective evaluation of the planting process, and the logical chain of evaluation is incomplete.

[0006] Third: The evaluation indicators composed of statistical results are discrete point data and nonlinear process data, which are obviously insufficient in visualization. Finally, due to the lack of data, the current evaluation system cannot trace the planting process.

[0007] In summary, developing a traceable crop planting technology evaluation method based on multi-dimensional data support is still a key issue that needs to be urgently addressed in the field of agricultural technology. Summary of the invention

[0008] In response to the above-mentioned shortcomings of the prior art, the method provided by the present invention is based on a multi-dimensional planting technology evaluation system based on yield, quality, phenological period, resistance and pests and diseases. It evaluates the process and results in a more objective and quantifiable manner, makes it easier to visualize the results and compare the effects horizontally, and provides data traceability capabilities.

[0009] To achieve the above object, the present invention provides the following technical solutions:

[0010] A traceable crop planting technology evaluation method based on multi-dimensional data support includes the following steps:

[0011] (1) IoT and cloud database construction: Build a communication protocol and a cloud database, which is then transmitted to the client through the cloud network for user access;

[0012] (2) Data collection and processing: Collect environmental data, soil data, and remote sensing data, and integrate, analyze, and process the collected data;

[0013] (3) Evaluation index calculation: including the calculation of yield index, quality index, phenological index, resistance index and pest and disease index, among which:

[0014] Production index production The calculation formula is:

[0015] y production =RUE*(1-exp(-α*NDVI))*I*A canopy +β*L water +γ, where α, β, γ are coupling coefficients, RUN is the crop efficiency parameter, k is the crop leaf extinction coefficient, I is the average daily plant visible light radiation value, A canopy is the canopy area, L water is the percentage of days with crop water stress, and NAVI is the Normalized Difference Vegetation Index;

[0016] Quality index quality The calculation formula is: Where a and b are coupling coefficients, P fruit is the dry matter yield of a single fruit, N f is the total number of fruits per unit area, RUN is the crop efficiency parameter, and NAVI is the normalized vegetation index;

[0017] Phenological period index development The calculation formula is: In the formula, r temp and r light is the crop development rate under different temperatures and photoperiods;

[0018] Resistance index p The calculation formula is: Where W is the crop yield, W o is the average yield of this type of crop, p w is the proportion of days with water stress, p t is the temperature stress ratio;

[0019] Pest and disease indicators DI The calculation formula is:

[0020] The insect index is the total statistical amount of pests and diseases per unit area, and the corresponding levels are defined as 1-10 levels according to different pests and diseases. The total number of leaves surveyed is the sum of the number of leaf samples, and the total level is 10.

[0021] The present invention is further configured as follows: in step (1), the Internet of Things and cloud database construction includes the following steps:

[0022] (11) Build the communication protocol between soil sensors, weather stations, fixed image acquisition platforms, mobile data acquisition platforms and gateways, and establish information interaction between hardware devices and various modules of the back-end platform;

[0023] (12) Using cloud servers to build cloud databases;

[0024] (13) The value is transmitted to the client through the cloud network for user access.

[0025] The present invention is further configured as follows: in step (2), the environmental data is collected by collecting solar radiation data, plant visible light radiation data and atmospheric temperature data through local meteorological stations and meteorological stations installed in the field.

[0026] The present invention is further configured as follows: in step (2), the soil data collection is to collect soil data of different soil depths through a fixed soil sensor, and the collected data includes soil temperature data, soil moisture content data and soil water potential data.

[0027] The present invention is further configured as follows: when collecting soil data for crops, the collection depths are 15 cm, 30 cm and 50 cm respectively; when collecting soil data for fruit crops, the collection depths are 30 cm, 60 cm and 100 cm respectively; the soil collection frequency is not less than one month, and one sample is collected for every ten mu of land on average; soil from ten points is randomly selected for each sample and mixed; and the interval between each randomly selected point is greater than 5 meters.

[0028] The present invention is further configured as follows: in step (2), the remote sensing data acquisition is to use a remote sensing data collection platform of satellites and unmanned aerial vehicles to collect crop remote sensing data, including canopy size, canopy volume and normalized vegetation index, and then use commercial mapping software PIX4D to integrate the remote sensing image set to generate point cloud data and texture processing, DSM orthophoto impact and spectral index.

[0029] The present invention is further configured as follows: in step (2), the method for integrating, analyzing and processing the data is:

[0030] The Internet of Things transmits sensor data distributed in various locations to cloud servers; cloud servers process the data, synchronize the data timeline, unify the start and end times, and convert data in different time units; integrate and summarize data from the same geographical location, and divide data blocks according to GPS coordinate information; use linear or nonlinear interpolation methods according to the data type, combine the data of adjacent data points, and fill in the interpolation through interpolation; use clustering algorithms to randomly generate several cluster centers, and calculate the distance from each point in each cluster to the cluster center, and find the cluster structure with the smallest sum of distances, so as to find and eliminate outliers.

[0031] The present invention is further configured as follows: in step (3), the water stress days ratio Temperature stress ratio Where, d o is the number of days in the planting cycle, d w With d t are the total days that crops are subjected to water stress and temperature stress, respectively. The criteria for determining water stress and temperature stress are: Where W soil is the soil water content, W w is the crop wilting moisture content, T is the crop temperature, T min is the minimum temperature that crops can adapt to, T max This is the highest temperature that crops can adapt to.

[0032] Beneficial Effects

[0033] Compared with the known public technology, the technical solution provided by the present invention has the following beneficial effects:

[0034] (1) The present invention not only adopts the yield index widely recognized by the industry, but also provides indicators including quality, phenological period, resistance and pests and diseases to evaluate the effect of an agricultural technology, so that the evaluation effect is more comprehensive.

[0035] (2) The present invention can demonstrate the performance of a technology in various indicators during the planting process, thereby realizing a method of evaluating the planting technology through the planting process.

[0036] (3) The present invention evaluates the planting process through five indicators and displays the evaluation results in a visual manner, which is conducive to horizontal comparison of technologies.

[0037] (4) Compared with the traditional subjective qualitative evaluation model, the present invention evaluates a planting technology in a more quantitative and objective mode.

[0038] (5) The cloud database of the present invention remotely stores various evaluation indicators and related process data, making it possible to trace the data. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 Schematic diagram of the effect of different irrigation technologies on the crop canopy normalized difference vegetation index (NDVI) of the present invention;

[0040] Figure 2 It is a schematic diagram of the growth progress of crops under three fertilizer formulas of the present invention;

[0041] Figure 3 It is a schematic diagram of the Internet of Things and cloud server framework of the present invention;

[0042] Figure 4 It is a schematic diagram of the growth rate and temperature function equation of the present invention;

[0043] Figure 5 It is a schematic diagram of the growth rate and photoperiod function equation of the present invention;

[0044] Figure 6 The present invention is a flowchart of the method provided by the present invention. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] The present invention will be further described below in conjunction with the embodiments.

[0047] Example

[0048] like Figure 6 As shown, the present invention provides a traceable crop planting technology evaluation method based on multi-dimensional data support, comprising the following steps:

[0049] (1) IoT and cloud database construction: Build a communication protocol and a cloud database, which is then transmitted to the client through the cloud network for user access.

[0050] Furthermore, the construction of IoT and cloud database includes the following steps:

[0051] (11) Build the communication protocol between soil sensors, weather stations, fixed image acquisition platforms, mobile data acquisition platforms and gateways, and establish information interaction between hardware devices and various modules of the back-end platform;

[0052] (12) Using cloud servers to build cloud databases;

[0053] (13) The value is transmitted to the client through the cloud network for user access.

[0054] It should be noted that the communication protocols between soil sensors, weather stations, fixed image acquisition platforms, mobile data acquisition platforms and gateways include http(s), websocket, MQTT application layer protocols, IPv4, IPv6, TCP / IP network transmission protocols, and ZigBee, LoRa, Wifi physical layer data link protocols, responsible for the information interaction between hardware devices and various modules of the back-end platform, including uploading data, sending commands and software updates (such as Figure 3 shown).

[0055] Build a cloud database, including database security module, data management module, device management module, comprehensive application module, data connection module and management module. The data connection module is responsible for providing the interaction between IoT device data and database, the data security module ensures the security of data interaction, the device management module is responsible for receiving IoT device status information and sending command information, the comprehensive application module provides different application services through algorithms, and the management module manages the daily operation of the server to ensure the normal operation of the server (such as Figure 3 shown).

[0056] The calculation results of the comprehensive application module are transmitted to the client through the cloud network for users to call.

[0057] (2) Data collection and processing: Collect environmental data, soil data and remote sensing data, and integrate, analyze and process the collected data.

[0058] Furthermore, environmental data collection is done by collecting solar radiation data (W / m 2 ), plant visible light radiation data (umol / m 2 ) and atmospheric temperature data (℃).

[0059] Furthermore, soil data collection is to collect soil data at different soil depths through fixed soil sensors, and the collected data includes soil temperature data, soil moisture content data and soil water potential data.

[0060] Furthermore, when collecting soil data for crops, the collection depths are 15cm, 30cm and 50cm respectively; when collecting soil data for fruit crops, the collection depths are 30cm, 60cm and 100cm respectively. The soil collection frequency is not less than one month, and one sample is collected for every ten acres of land on average. For each sample, the soil from ten randomly selected points is mixed, and the interval between each randomly selected point is greater than 5 meters.

[0061] Furthermore, remote sensing data collection is carried out using satellite and UAV-based remote sensing data collection platforms to collect crop remote sensing data, including canopy size, canopy volume, and normalized difference vegetation index (NDVI), and then the commercial mapping software PIX4D is used to integrate the remote sensing image set to generate point cloud data with texture processing, DSM orthophoto impact, and spectral index.

[0062] Further, the method of integrating, analyzing and processing data is as follows:

[0063] The Internet of Things transmits sensor data distributed in various locations to cloud servers; cloud servers process the data, synchronize the data timeline, unify the start and end times, and convert data in different time units; integrate and summarize data from the same geographical location, and divide data blocks according to GPS coordinate information; use linear or nonlinear interpolation methods according to the data type, combine the data of adjacent data points, and fill in the interpolation through interpolation; use clustering algorithms to randomly generate several cluster centers, and calculate the distance from each point in each cluster to the cluster center, and find the cluster structure with the smallest sum of distances, so as to find and eliminate outliers.

[0064] (3) Evaluation index calculation: including the calculation of yield index, quality index, phenological index, resistance index and pest and disease index, among which:

[0065] Using drone mapping technology, the reflectance of each spectral band of the fruit tree canopy was measured and the normalized difference vegetation index (NDVI) was calculated (such as Figure 1 As shown in the figure, A uses drip irrigation technology and B uses traditional sprinkler irrigation). Soil moisture and water potential sensors can also be used to construct the soil moisture content of fruit trees at different periods, analyze the impact of water stress on crop yield, evaluate the advantages and disadvantages of different irrigation technologies, and the yield index y production The calculation formula is:

[0066] y production =RUE*(1-exp(-α*NDVI))*I*A canopy +β*L water +γ, where α, β, γ are coupling coefficients, RUN is the crop efficiency parameter, k is the crop leaf extinction coefficient, I is the average daily plant visible light radiation value, A canopy is the canopy area, A canopy It can be calculated by the percentage of crop pixels per unit area of ​​remote sensing images. The crop pixel identification formula is based on the vegetation index (EXG). EXG greater than 0.1 is considered a crop canopy. water It is the percentage of days with water stress on crops. The number of days with water stress is determined by the average water content of the day being lower than the minimum water content. NAVI is the Normalized Difference Vegetation Index.

[0067] The industry's commonly used crop quality evaluation indicators are used, including fruit size, sweetness, soluble substances and color. Combined with digital comprehensive indicators, the changes in fruit tree physiological parameters throughout the planting process are displayed, and the factors that lead to differences in fruit quality are analyzed. Quality indicators quality The quality index y is determined by the light intensity, the normalized difference vegetation index (NDVI) of the fruit tree canopy, the number of fruits, and the photosynthesis efficiency RUE. quality The calculation formula is: Where a and b are coupling coefficients, P fruit is the dry matter yield of a single fruit, N f is the total number of fruits per unit area, RUN is the crop efficiency parameter, and NAVI is the normalized vegetation index;

[0068] Record the various growth periods and important physiological stages of crops, and compare the time points of budding, flowering, fruiting, and fruit drop of crops under different technologies. At the same time, use algorithms to calculate the growth period progress at each time point during the planting process based on environmental parameters including temperature and light, and transform the traditional phenological period statistics method from single-point information to a dynamic linear display of the entire process, which more intuitively shows the differences in crop growth speed under different technologies. The degree of development of crops during the growth period can be calculated based on the accumulated temperature and light cycle (such as Figure 2 As shown in the figure, the development progress of crops under three fertilizer formulas A, B, and C. A has a nitrogen-phosphorus-potassium ratio of 5-5-5, B has a nitrogen-phosphorus-potassium ratio of 5-5-2, and C has a nitrogen-phosphorus-potassium ratio of 10-5-5) Phenological period index y development The calculation formula is: In the formula, r temp and r light is the crop development rate under different temperatures and photoperiods, respectively taken from the corresponding development rate function equation (such as Figure 4 and Figure 5 ), the input variables of the function equation are the atmospheric temperature and the daily radiation duration;

[0069] Traditional crop stress resistance and disease resistance indicators tend to be more qualitative, but there has been a lack of relevant standards in terms of quantification. This paper draws on advanced foreign resistance standards, compares and analyzes soil data, climate data and crop health index, and uses the number of days of crop stress and NDVI as quantitative standards to construct a more objective and scientific crop resistance quantitative index. p The calculation formula is: Where W is the crop yield, W o is the average yield of this type of crop, p w is the proportion of days with water stress, p t is the temperature stress ratio;

[0070] Statistics on pests and diseases within a unit area, establish trend charts of pests and diseases in each area, and evaluate the effect of new plant protection technologies on orchard pest and disease control. DI , evaluate the disease and insect pest situation in a scientific way, and the disease and insect pest index DI The calculation formula is:

[0071] The insect index is the total statistical amount of pests and diseases per unit area, and the corresponding levels are defined as 1-10 levels according to different pests and diseases. The total number of leaves surveyed is the sum of the number of leaf samples, and the total level is 10.

[0072] Furthermore, the proportion of days with water stress Temperature stress ratio Where, d o is the number of days in the planting cycle, d w With d t are the total days that crops are subjected to water stress and temperature stress, respectively. The criteria for determining water stress and temperature stress are: Where W soil is the soil water content, W w is the crop wilting moisture content, T is the crop temperature, T min is the minimum temperature that crops can adapt to, T max This is the highest temperature that crops can adapt to.

[0073] It should be noted that the insect detection station and insect trap are used to monitor the development trend of orchard insect pests in real time. Insect samples are collected through insect traps, and various insect pests are automatically identified using image recognition technology and deep learning algorithms to count the development trend of the number of insect pests. Compared with traditional manual counting methods, the image recognition insect monitoring system saves more labor and is more accurate and efficient.

[0074] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A traceable crop planting technology evaluation method based on multi-dimensional data support, characterized in that: The following steps are involved: (1) Data collection and processing: Collect environmental data, soil data, and remote sensing data, and integrate, analyze, and process the collected data; (2) IoT and cloud database construction: Build a communication protocol and a cloud database, which is then transmitted to the client through the cloud network for user access; (3) Evaluation index calculation: including the calculation of yield index, quality index, phenological index, resistance index and pest and disease index, among which: Production index production The calculation formula is: y production = RUE * (1 - exp(-α * NDVI)) * I * A canopy + β * L water + γ, where α, β, γ are coupling coefficients, RUE is the crop efficiency parameter, k is the crop leaf extinction coefficient, I is the daily average plant visible light radiation value, A canopy is the canopy area, L water is the percentage of days with water stress on crops, and NDVI is the Normalized Difference Vegetation Index; Quality index quality The calculation formula is: Where a and b are coupling coefficients, P fruit is the dry matter yield of a single fruit, N f is the total number of fruits per unit area, RUE is the crop efficiency parameter, and NDVI is the normalized difference vegetation index; Phenological period index development The calculation formula is: In the formula, r temp and r light is the crop development rate under different temperatures and photoperiods; Resistance index p The calculation formula is: Where W is the crop yield, W o is the average yield of the crop, p w is the proportion of days with water stress, p t is the temperature stress ratio; Pest and disease indicators DI The calculation formula is: The insect index is the total statistical amount of pests and diseases per unit area, and the corresponding levels are defined as 1-10 levels according to different pests and diseases. The total number of leaves surveyed is the sum of the number of leaf samples, and the total level is 10.

2. According to claim 1, a traceable crop planting technology evaluation method based on multi-dimensional data support is characterized in that: In step (1), the environmental data is collected by collecting solar radiation data, plant visible light radiation data and atmospheric temperature data through local meteorological stations and meteorological stations installed in the field.

3. The method for evaluating crop planting technology based on traceability and multi-dimensional data support according to claim 1 is characterized in that: In step (1), the soil data is collected by using a fixed soil sensor to collect soil data at different soil depths. The collected data includes soil temperature data, soil moisture content data and soil water potential data.

4. The method for evaluating crop planting technology based on traceability and multi-dimensional data support according to claim 3 is characterized in that: When collecting soil data for crops, the collection depths are 15cm, 30cm and 50cm respectively; when collecting soil data for fruit crops, the collection depths are 30cm, 60cm and 100cm respectively. The soil collection frequency is not less than once a month, and an average of one sample is collected for every ten acres of land. For each sample, the soil from ten randomly selected points is mixed, and the interval between each randomly selected point is greater than 5 meters.

5. The method for evaluating crop planting technology based on traceability and multi-dimensional data support according to claim 1 is characterized in that: In step (1), the remote sensing data collection is performed using a satellite and UAV remote sensing data collection platform to collect crop remote sensing data, including canopy size, canopy volume, and normalized vegetation index, and then the commercial mapping software PIX4D is used to integrate the remote sensing image set to generate point cloud data with texture processing, DSM orthophoto impact, and spectral index.

6. The method for evaluating crop planting technology based on traceability and multi-dimensional data support according to claim 1, characterized in that: In step (1), the method for integrating, analyzing and processing the data is as follows: The Internet of Things transmits data from sensors distributed everywhere to cloud servers; The cloud server processes the data, synchronizes the data timeline, unifies the start and end time, and converts the data in different time units; integrates and summarizes the data in the same geographical location, and divides the data blocks according to the GPS coordinate information; uses linear or nonlinear interpolation methods according to the data type, combines the data of adjacent data points, and completes the interpolation through interpolation; uses a clustering algorithm to randomly generate several cluster centers, and calculates the distance from each point in each cluster to the cluster center, looking for the cluster structure with the smallest sum of distances, so as to find and eliminate outliers.

7. The method for evaluating crop planting technology based on traceability supported by multi-dimensional data according to claim 1, characterized in that: In step (2), the construction of the Internet of Things and cloud database includes the following steps: (21) Build the communication protocol between soil sensors, weather stations, fixed image acquisition platforms, mobile data acquisition platforms and gateways, and establish information interaction between hardware devices and various modules of the back-end platform; (22) Using cloud servers to build cloud databases; (23) The value is transmitted to the client through the cloud network for user access.

8. The method for evaluating crop planting technology based on traceability and multi-dimensional data support according to claim 1, characterized in that: In step (3), the water stress days ratio Temperature stress ratio Where, d o is the number of days in the planting cycle, d w With d t are the total days that crops are subjected to water stress and temperature stress, respectively. The criteria for determining water stress and temperature stress are: Where W soil is the soil water content, W w is the crop wilting moisture content, T is the crop temperature, T min is the minimum temperature that crops can adapt to, T max This is the highest temperature that crops can adapt to.

Images