Nut pest and disease damage prediction method and system

Abstract

The invention relates to the technical field of pest and disease damage prediction, and discloses a nut pest and disease damage prediction method and system, temperature data information WD, humidity data information SD and illumination intensity data GZ of a nut planting field are collected, pest number HS statistics and pest natural enemy number TS calculation are carried out, a prediction value Y is calculated according to the data in the step S1, and the prediction value Y is calculated according to the data in the step S2. The predicted value Y is compared with the first comparison value D1 and the second comparison value D2, and image shooting of the nut planting field is carried out in real time; according to the method, when the pest and disease damage prediction is carried out, comprehensive consideration is carried out according to the external environment data, the pest damage data and the natural enemy data of the pest damage, so that the prediction result is more accurate, the nut planting field can be well predicted, and when an emergency occurs, the nut planting field can be shot in real time; therefore, when the pests suddenly migrate to a nut planting field or gnaw nut trees, the pests can be found in time and treated in time.

Description

Technical Field

[0001] The present invention relates to the technical field of pest and disease prediction, and more specifically to a method and system for predicting pest and disease of nuts. Background Art

[0002] Nut pests and diseases mainly include a variety of diseases and pests, which will have a serious impact on the growth and yield of nuts. Pests and diseases are the combination of diseases and pests, which often have adverse effects on agriculture, forestry, animal husbandry, etc., so they need to be prevented and controlled. Pest and disease control is to reduce or prevent pathogenic microorganisms and pests from harming crops or humans and livestock, and artificially take certain measures. Generally, it can be divided into chemical control using chemical substances such as pesticides and physical control using physical energy such as light or rays or building barriers;

[0003] Before carrying out pest control, it is necessary to make a prediction. Pest prediction is a comprehensive science and technology that analyzes the epidemic patterns of plant pests and diseases and infers the distribution, spread and damage trends of pests and diseases in the future. It requires the application of relevant biological and ecological knowledge, mathematical statistics, system analysis and other methods. The prediction results should be notified as quickly as possible so that various prevention and control preparations can be made in a timely manner;

[0004] Nowadays, when predicting nut pests and diseases, the accuracy of predictions based on traditional epidemic pattern analysis is limited. After the prediction, there are many factors affecting pests and diseases. For example, if a swarm of insects suddenly migrates to a nut planting area, sudden situations may occur. Nowadays, it is impossible to handle emergencies well. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, the implementation regulations of the present invention provide a method and system for predicting nut diseases and pests to solve the technical problems raised in the background technology.

[0006] To achieve the above object, the present invention provides the following technical solution: a method for predicting nut diseases and insect pests, comprising the following steps:

[0007] Step S1, collecting temperature data information WD, humidity data information SD and light intensity data GZ of the nut planting site, and performing pest count HS and pest natural enemy count TS;

[0008] Step S2, calculating a predicted value Y according to the data in step S1, and comparing the predicted value Y with the first comparison value D1 and the second comparison value D2;

[0009] Step S3, when the predicted value Y is less than the first comparison value D1, a first-level pest instruction is sent to manually remove the pests; when the first comparison value D1≤predicted value Y≤second comparison value D2, a second-level pest instruction is sent to spray pesticides; when the predicted value Y>second comparison value D2, large-area pesticide spraying is performed;

[0010] Step S4, taking images of the nut planting area in real time, graying the taken images, binarizing the grayed image data, and calculating a percentage value BS of the black area in the binarized image to the overall image area;

[0011] Step S5, comparing the percentage value BS with the internal danger threshold WX. When the percentage value BS ≥ the danger threshold WX, directly go to the nut planting site for pest control. When the danger threshold WX < the danger threshold WX, no treatment is performed.

[0012] Step S6: collect the dates on which the first-level pest instructions, second-level pest instructions, third-level pest instructions and early warning instructions were sent within three years, give each instruction a score and add them up, and arrange the dates in descending order of importance according to the added scores.

[0013] A nut pest prediction system comprises a collection unit, an analysis unit, a statistics unit, a shooting unit, a binarization unit, a central unit, a processing unit, an alarm unit and a recording unit, wherein the collection unit is used to collect environmental data information of a nut planting site, the analysis unit receives the data collected by the collection unit and calculates a predicted value Y, the statistics unit is used to perform statistics on the number of pests per square meter in the nut planting site HS and calculate the number of natural enemies of pests per square meter in the nut planting site TS, the shooting unit is used to collect image data information of the nut planting site and perform grayscale processing, the binarization unit performs binarization processing on the grayscale processed image data, the central unit receives the predicted value Y and the binarized image data and sends an instruction, the processing unit receives the instruction sent by the central unit and performs pest treatment, the alarm unit receives the instruction sent by the central unit and performs pest control at the nut planting site, and the recording unit performs date marking;

[0014] The acquisition unit collects temperature data information WD, humidity data information SD and light intensity data GZ of the nut planting site, and the acquisition unit sends all the collected data information to the analysis unit, and the analysis unit receives the data sent by the acquisition unit and calculates the predicted value Y. The calculation formula of the predicted value Y is: In the formula, k1, k2 and k3 are weights, HS is the number of pests per square meter of the current nut planting area, TS is the number of natural enemies of pests per square meter of the current nut planting area, PS is the number of pests eaten by each natural enemy of pests every day, and GZB is the standard light intensity data for the most suitable growth of pests.

[0015] In a preferred embodiment, the central unit receives the predicted value Y and compares it with the first comparison value D1 and the second comparison value D2 inside it, the first comparison value D1<the second comparison value D2, when the predicted value Y<the first comparison value D1, the central unit sends a first-level pest instruction to the processing unit, when the first comparison value D1≤predicted value Y≤second comparison value D2, the central unit sends a second-level pest instruction to the processing unit, when the predicted value Y>the second comparison value D2, the central unit sends a third-level pest instruction to the processing unit, the processing unit receives the first-level pest instruction and notifies the staff to manually remove the pests, the processing unit receives the second-level pest instruction and performs targeted pesticide spraying, and the processing unit receives the third-level pest instruction and performs large-area pesticide spraying.

[0016] In a preferred embodiment, the statistical unit performs statistics on the number of pests HS per square meter of the current nut planting site and calculates the number of natural enemies of pests TS per square meter of the current nut planting site, and when the statistical unit performs statistics on the number of pests HS, the statistical unit randomly takes five one-square-meter numbers of pests under the ground in the nut field, and calculates the average number of pests under one square meter as the number of pests HS per square meter of the current nut planting site.

[0017] In a preferred embodiment, the calculation formula for the number of natural enemies of pests per square meter of the current nut planting area in the statistical unit is: In the formula, n is all types of pest natural enemies, i represents the current i-th pest natural enemy, Li is the correlation coefficient between the current i-th pest natural enemy and the number of pests, WYi is the influence coefficient of the temperature environment on the i-th pest natural enemy, SY is the influence coefficient of the humidity environment on the i-th pest natural enemy, the temperature data information WD and the humidity data information SD in the statistical unit are from the acquisition unit, and the statistical unit will count the number of pests per square meter HS of the current nut planting field and the calculated number of pests per square meter TS of the current nut planting field and send them to the analysis unit.

[0018] In a preferred embodiment, the shooting unit captures images of the nut planting site in real time, and the shooting unit grayscales the captured images. The calculation formula for the grayscale processing is W=0.3R+0.58G+0.12B, wherein W is the grayscale value after processing, R is the red image, G is the green image, and B is the blue image, and R, G, and B are all within the grayscale value range of 0-255. When the grayscale value W is 0, it is black, and when the grayscale value W is 225, it is white. The shooting unit sends the grayscale image data to the binarization unit.

[0019] In a preferred embodiment, the binarization unit performs binarization processing on the grayscale image, the binarization processing threshold is the standard grayscale value H of a healthy nut tree, the grayscale value W calculated by the central unit is adjusted to 225 when it is higher than or equal to the standard grayscale value H, and the grayscale value W is adjusted to 0 when it is lower than the standard grayscale value H, and the binarization unit sends the binarized image to the central unit.

[0020] In a preferred embodiment, the central unit receives the binarized image and calculates the percentage value BS of the black area in the total area of ​​the image. The central unit compares the percentage value BS with its internal danger threshold WX. When the percentage value BS ≥ the danger threshold WX, the central unit sends a warning instruction to the alarm unit. When the danger threshold WX < the danger threshold WX, the central unit does not send an instruction. The alarm unit receives the warning instruction and goes directly to the nut planting site for pest control.

[0021] In a preferred embodiment, the recording unit collects the dates on which the central unit sends the first-level pest instruction, the second-level pest instruction, the third-level pest instruction and the early warning instruction each year, and the recording unit records the date on which the first-level pest instruction is sent as 1 point, the date on which the second-level pest instruction is sent as 3 points, the date on which the third-level pest instruction is sent as 5 points, the date on which the early warning instruction is sent as 5 points, and the date on which no instruction is sent as 0 point, the recording unit adds up the scores of each identical date in three years, and the central unit sends each date and the score of the date to the central unit.

[0022] In a preferred embodiment, the central unit receives the sent date and the score sum of the date, and the central unit arranges the score sum in descending order. When the score sums of different dates are the same, the latest year is used as the first comparison target. If they are all the same, they are arranged in parallel. When the central unit makes a pest and disease prediction for the next year, the importance of the date is determined according to the order in which the dates are arranged.

[0023] Technical effects and advantages of the present invention:

[0024] 1. When predicting pests and diseases, the present invention comprehensively considers the external environment data, pest data, and natural enemy data of pests. Therefore, the prediction result of the present application is more accurate, and a good prediction can be made for nut planting areas. In case of emergencies, the present application will take real-time photos of the nut planting areas. Therefore, when pests suddenly migrate to the nut planting areas or eat the nut trees, they can be discovered in time and handled in time.

[0025] 2. The environmental data information collected by the present invention is the temperature data information WD, humidity data information SD and light intensity data GZ of the nut planting site, and the number of pests themselves and the number of natural enemies of pests are taken into consideration. The calculated prediction value Y more accurately reflects the situation of pests and diseases. Different control methods are adopted according to different situations, and the overall prediction process is more reasonable;

[0026] 3. The present invention captures images of nut planting areas in real time, performs grayscale processing after capturing, and directly performs binarization processing after grayscale processing. The threshold of the binarization processing is the standard grayscale value H of a healthy nut tree. The diseased part is changed to black. At this time, the percentage value BS of the black area calculated to account for the entire image area is the proportion of the diseased and insect-infested part. Timely processing can be carried out, real-time management can be carried out, and the nuts can be better protected. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a schematic diagram of the prediction method flow of the present invention.

[0028] Figure 2 It is a schematic diagram of the prediction system composition of the present invention. DETAILED DESCRIPTION

[0029] The technical scheme of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention. In addition, the forms of the various structures recorded in the following embodiments are merely illustrative. The nut disease and pest prediction method and system involved in the present invention are not limited to the various structures recorded in the following embodiments. All other implementations obtained by ordinary technicians in this field without making creative work belong to the scope of protection of the present invention.

[0030] Reference Figure 1 The present invention provides a method for predicting nut diseases and insect pests, comprising the following steps:

[0031] Step S1, collecting temperature data information WD, humidity data information SD and light intensity data GZ of the nut planting site, and performing pest count HS and pest natural enemy count TS;

[0032] Step S2, calculating a predicted value Y according to the data in step S1, and comparing the predicted value Y with the first comparison value D1 and the second comparison value D2;

[0033] Step S3, when the predicted value Y is less than the first comparison value D1, a first-level pest instruction is sent to manually remove the pests; when the first comparison value D1≤predicted value Y≤second comparison value D2, a second-level pest instruction is sent to spray pesticides; when the predicted value Y>second comparison value D2, large-area pesticide spraying is performed;

[0034] Step S4, taking images of the nut planting area in real time, graying the taken images, binarizing the grayed image data, and calculating a percentage value BS of the black area in the binarized image to the overall image area;

[0035] Step S5, comparing the percentage value BS with the internal danger threshold WX. When the percentage value BS ≥ the danger threshold WX, directly go to the nut planting site for pest control. When the danger threshold WX < the danger threshold WX, no treatment is performed.

[0036] Step S6: collect the dates on which the first-level pest instructions, second-level pest instructions, third-level pest instructions and early warning instructions were sent within three years, give each instruction a score and add them up, and arrange the dates in descending order of importance according to the added scores.

[0037] In the embodiments of the present application, when predicting pests and diseases, the present application comprehensively considers the external environment data, pest data, and natural enemy data of pests. Therefore, the prediction results of the present application are more accurate, and a good prediction can be made for the nut planting site. In the event of an emergency, the present application will take real-time photos of the nut planting site. Therefore, when pests suddenly migrate to the nut planting site or gnaw on the nut trees, they can be discovered in time and can be dealt with in time. In addition, the future is predicted based on the occurrence of pests and diseases in the previous three years, ensuring the accuracy of the prediction in multiple directions and being able to prepare in advance.

[0038] Reference Figure 2, a nut pest prediction system, characterized in that it includes a collection unit, an analysis unit, a statistics unit, a shooting unit, a binarization unit, a central unit, a processing unit, an alarm unit and a recording unit, wherein the collection unit is used to collect environmental data information of a nut planting site, the analysis unit receives the data collected by the collection unit and calculates a predicted value Y, the statistics unit is used to perform statistics on the number of pests per square meter in the nut planting site HS and calculate the number of natural enemies of pests per square meter in the nut planting site TS, the shooting unit is used to collect image data information of the nut planting site and perform grayscale processing, the binarization unit performs binarization processing on the grayscale processed image data, the central unit receives the predicted value Y and the binarized image data and sends an instruction, the processing unit receives the instruction sent by the central unit and performs pest treatment, the alarm unit receives the instruction sent by the central unit and goes to the nut planting site for pest control, and the recording unit performs date marking;

[0039] The acquisition unit collects temperature data information WD, humidity data information SD and light intensity data GZ of the nut planting site, and the acquisition unit sends all the collected data information to the analysis unit, and the analysis unit receives the data sent by the acquisition unit and calculates the predicted value Y. The calculation formula of the predicted value Y is: Wherein, k1, k2 and k3 are weights, HS is the number of pests per square meter of the current nut planting land, TS is the number of natural enemies of pests per square meter of the current nut planting land, PS is the number of pests eaten by each natural enemy of pests every day, GZB is the standard light intensity data for the most suitable growth of pests, the central unit receives the predicted value Y and compares it with the first comparison value D1 and the second comparison value D2 inside it, the first comparison value D1<the second comparison value D2, when the predicted value Y<the first comparison value D1, the central unit sends a first-level pest instruction to the processing unit, when the first comparison value D1≤predicted value Y≤second comparison value D2, the central unit sends a second-level pest instruction to the processing unit, when the predicted value Y>the second comparison value D2, the central unit sends a third-level pest instruction to the processing unit, the processing unit receives the first-level pest instruction and notifies the staff to manually remove the pests, the processing unit receives the second-level pest instruction and sprays pesticides, and the processing unit receives the third-level pest instruction and sprays pesticides over a large area.

[0040] In the embodiment of the present application, when predicting nut diseases and pests according to the external environment, the environmental data information first collected is the temperature data information WD, humidity data information SD and light intensity data GZ of the nut planting site. The above three groups of data will directly affect the growth of pests. Pests grow under high temperature and high humidity, but light has two sides. Strong or weak light will make pests unfavorable for production, but the number of pests is easily affected by their natural enemies. Therefore, the present application takes into account the number of pests themselves and the number of natural enemies of pests. The calculated prediction value Y more accurately reflects the situation of the occurrence of diseases and pests. The larger the calculated prediction value Y, the higher the temperature, the higher the humidity and the stronger the light. The temperature is suitable for the growth of pests, and the natural enemies of pests are smaller. The smaller the calculated predicted value Y is, the lower the temperature, the lower the humidity, the greater or less light intensity, and the more natural enemies of pests. This application compares the calculated predicted value Y with the first comparison value D1 and the second comparison value D2. When the predicted value Y is less than the first comparison value D1, the impact of pests on nut trees is small, and the number of pests themselves is small, so manual removal is sufficient. When the first comparison value D1≤predicted value Y≤second comparison value D2, the pests will have a certain impact on the nuts, so pesticide spraying is required. When the predicted value Y>the second comparison value D2, the impact of pests and diseases will be greater, and large-scale pesticide spraying and timely pest control are carried out to avoid a greater impact.

[0041] Furthermore, the statistical unit performs statistics on the number of pests HS per square meter of the current nut planting site and calculates the number of natural enemies of pests TS per square meter of the current nut planting site. When the statistical unit performs statistics on the number of pests HS, the statistical unit randomly selects five numbers of pests under the ground of one square meter in the nut field, and calculates the average number of pests under the ground of one square meter as the number of pests HS per square meter of the current nut planting site. The calculation formula of the number of natural enemies of pests TS per square meter of the current nut planting site in the statistical unit is: In the formula, n is all types of pest natural enemies, i represents the current i-th pest natural enemy, Li is the correlation coefficient between the current i-th pest natural enemy and the number of pests, WYi is the influence coefficient of the temperature environment on the i-th pest natural enemy, SY is the influence coefficient of the humidity environment on the i-th pest natural enemy, the temperature data information WD and the humidity data information SD in the statistical unit are from the acquisition unit, and the statistical unit will count the number of pests per square meter HS of the current nut planting field and the calculated number of pests per square meter TS of the current nut planting field and send them to the analysis unit.

[0042] In the embodiments of the present application, when performing statistics on the number of pests HS and calculations on the number of natural enemies TS, it is relatively easy to count the number of pests HS, and therefore the number of pest types in the nut-growing areas is limited, so they can be directly counted. However, each type of pest has different natural enemies, and therefore it is difficult to directly count the number of natural enemies. The present application, based on the statistics of the number of pests HS, combines the current temperature and humidity environment, and based on the number of pests themselves, when there are more pests, the number of their natural enemies will also increase relatively. Therefore, the calculated number of natural enemies TS is relatively easy and has a high degree of accuracy, thereby ensuring the accuracy of the final prediction.

[0043] Furthermore, the shooting unit takes images of the nut planting site in real time, and the shooting unit performs grayscale processing on the captured images. The calculation formula for the grayscale processing is W=0.3R+0.58G+0.12B, wherein W is the grayscale value after processing, R is a red image, G is a green image, and B is a blue image, and R, G, and B are all within the grayscale value range of 0-255. When the grayscale value W is 0, it is black, and when the grayscale value W is 225, it is white. The shooting unit sends the grayscale image data to the binarization unit, and the binarization unit performs binarization processing on the grayscale image. The binarization processing threshold is the standard grayscale value H of a healthy nut tree. When the grayscale value W calculated by the core unit is higher than or equal to the standard grayscale value H, it is adjusted to 225, and when the grayscale value W is lower than the standard grayscale value H, it is adjusted to 0. The binarization unit sends the binarized image to the central unit, and the central unit receives the binarized image and calculates the percentage value BS of the black area to the overall area of ​​the image. The central unit compares the percentage value BS with its internal danger threshold WX. When the percentage value BS is ≥ the danger threshold WX, the central unit sends an early warning instruction to the alarm unit. When the danger threshold WX is < the danger threshold WX, the central unit does not send an instruction. The alarm unit receives the early warning instruction and directly goes to the nut planting site for pest control.

[0044] In the embodiment of the present application, although the present application can predict pests and diseases, it cannot handle emergencies. Therefore, the shooting unit of the present application captures images of the nut planting area in real time, and performs grayscale processing after shooting. The grayscale processing can increase the data of image transmission, which is convenient for shooting in the external environment. After the grayscale processing, the binary processing is directly performed, and the threshold of the binary processing is the standard grayscale value H of the healthy nut tree. Therefore, when the grayscale value W is higher than or equal to the standard grayscale value H, it is adjusted to 225. At this time, the color is lighter, and the color of the trees affected by pests and diseases will deepen. Therefore, the healthy part is changed to white, and the grayscale value W is adjusted to 0 below the standard grayscale value H, and the diseased part is changed to black. At this time, the calculated percentage value BS of the black area in the overall area of ​​the image is the proportion of the pest and disease part. When the percentage value BS ≥ the danger threshold WX, the pest is greatly affected at this time and is handled in time. Therefore, the present application can be managed in real time to better protect the nuts.

[0045] Furthermore, the recording unit collects the dates on which the central unit sends the first-level pest instruction, the second-level pest instruction, the third-level pest instruction and the early warning instruction each year, and the recording unit records the date on which the first-level pest instruction is sent as 1 point, the date on which the second-level pest instruction is sent as 3 points, the date on which the third-level pest instruction is sent as 5 points, the date on which the early warning instruction is sent as 5 points, and the date on which no instruction is sent as 0 point. The recording unit adds the scores of each identical date in three years, and the central unit sends each date and the score of the date to the central unit. The central unit receives the sent date and the sum of the scores of the date, and the central unit arranges the sum of the scores in descending order. When the sums of the scores of different dates are the same, the latest year is used as the first comparison target. If they are all the same, they are arranged in parallel. When the central unit makes a pest and disease prediction for the next year, the importance of the date is determined according to the order in which the dates are arranged.

[0046] In the embodiment of the present application, the present application will record the results of the previous three years, record the dates on which the first-level pest instruction, the second-level pest instruction, the third-level pest instruction and the early warning instruction are sent, and when the above instructions are sent, different situations of pests and diseases appear at this time, and the severity of the pests and diseases represented by each instruction is different, so different scores are given, and the scores of each same date in three years are added together. For example, in the previous three years, May 1st of the first year is 5 points, May 1st of the second year is 5 points, and May 1st of the third year is 1 point. points, then May 1st is 11 points, and similarly June 1st is 13 points. When arranged in descending order, June 1st is before May 1st. At this time, more attention should be paid to the disease and insect pest situation on June 1st of the next year. When May 1st and June 1st are both 11 points, it depends on which one has a higher score in the most recent year. Therefore, this application makes a prediction for the next year based on the situation in the previous three years, and preparations can be made in advance. In addition, it should be noted that if February 29th happens to be on a certain year, the 28th will be used instead.

[0047] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The units and algorithm steps of each example described in the embodiment can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0048] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0049] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for predicting nut diseases and insect pests, characterized in that: The following steps are involved: Step S1, collecting temperature data information WD, humidity data information SD and light intensity data GZ of the nut planting site, and performing pest count HS and pest natural enemy count TS calculation; Step S2, calculating a predicted value Y according to the data in step S1, and comparing the predicted value Y with the first comparison value D1 and the second comparison value D2; Step S3, when the predicted value Y is less than the first comparison value D1, a first-level pest instruction is sent to manually remove the pests; when the first comparison value D1≤predicted value Y≤second comparison value D2, a second-level pest instruction is sent to spray pesticides; when the predicted value Y>second comparison value D2, large-area pesticide spraying is performed; Step S4, taking images of the nut planting area in real time, graying the taken images, binarizing the grayed image data, and calculating a percentage value BS of the black area in the binarized image to the overall image area; Step S5, comparing the percentage value BS with the internal danger threshold WX. When the percentage value BS ≥ the danger threshold WX, directly go to the nut planting site for pest control. When the danger threshold WX < the danger threshold WX, no treatment is performed. Step S6: collect the dates on which the first-level pest instructions, second-level pest instructions, third-level pest instructions and early warning instructions were sent within three years, give each instruction a score and add them up, and arrange the dates in descending order of importance according to the added scores.

2. A nut disease and insect pest prediction system, using a nut disease and insect pest prediction method as claimed in claim 1, characterized in that: It includes a collection unit, an analysis unit, a statistics unit, a shooting unit, a binarization unit, a central unit, a processing unit, an alarm unit and a recording unit, wherein the collection unit is used to collect environmental data information of a nut planting site, the analysis unit receives the data collected by the collection unit and calculates a predicted value Y, the statistics unit is used to perform statistics on the number of pests per square meter in the nut planting site HS and calculate the number of natural enemies of pests per square meter in the nut planting site TS, the shooting unit is used to collect image data information of the nut planting site and perform grayscale processing, the binarization unit performs binarization processing on the grayscale processed image data, the central unit receives the predicted value Y and the binarized image data and sends an instruction, the processing unit receives the instruction sent by the central unit and performs pest treatment, the alarm unit receives the instruction sent by the central unit and performs pest control at the nut planting site, and the recording unit performs date marking; The acquisition unit collects temperature data information WD, humidity data information SD and light intensity data GZ of the nut planting site, and the acquisition unit sends all the collected data information to the analysis unit, and the analysis unit receives the data sent by the acquisition unit and calculates the predicted value Y. The calculation formula of the predicted value Y is: In the formula, k1, k2 and k3 are weights, HS is the number of pests per square meter of the current nut planting area, TS is the number of natural enemies of pests per square meter of the current nut planting area, PS is the number of pests eaten by each natural enemy of pests every day, and GZB is the standard light intensity data for the most suitable growth of pests.

3. A nut disease and insect pest prediction system according to claim 2, characterized in that: The central unit receives the predicted value Y and compares it with the first comparison value D1 and the second comparison value D2 inside it, the first comparison value D1<the second comparison value D2, when the predicted value Y<the first comparison value D1, the central unit sends a first-level pest instruction to the processing unit, when the first comparison value D1≤predicted value Y≤second comparison value D2, the central unit sends a second-level pest instruction to the processing unit, when the predicted value Y>the second comparison value D2, the central unit sends a third-level pest instruction to the processing unit, the processing unit receives the first-level pest instruction and notifies the staff to manually remove the pests, the processing unit receives the second-level pest instruction and performs targeted pesticide spraying, and the processing unit receives the third-level pest instruction and performs large-area pesticide spraying.

4. A nut disease and insect pest prediction system according to claim 2, characterized in that: The statistical unit performs statistics on the number of pests HS per square meter of the current nut planting field and calculates the number of natural enemies of pests TS per square meter of the current nut planting field. When the statistical unit performs statistics on the number of pests HS, the statistical unit randomly selects five numbers of pests per square meter under the ground in the nut field, and calculates the average number of pests per square meter as the number of pests per square meter of the current nut planting field HS.

5. A nut pest and disease prediction system according to claim 4, characterized in that: The calculation formula for the number of natural enemies of pests per square meter of the current nut planting area in the statistical unit is: In the formula, n is all types of pest natural enemies, i represents the current i-th pest natural enemy, Li is the correlation coefficient between the current i-th pest natural enemy and the number of pests, WYi is the influence coefficient of the temperature environment on the i-th pest natural enemy, SY is the influence coefficient of the humidity environment on the i-th pest natural enemy, the temperature data information WD and the humidity data information SD in the statistical unit are from the acquisition unit, and the statistical unit will count the number of pests per square meter HS of the current nut planting field and the calculated number of pests per square meter TS of the current nut planting field and send them to the analysis unit.

6. A nut pest and disease prediction system according to claim 2, characterized in that: The shooting unit captures images of the nut planting site in real time, and grayscales the captured images. The calculation formula for the grayscale processing is W=0.3R+0.58G+0.12B, where W is the grayscale value after processing, R is a red image, G is a green image, and B is a blue image, and R, G, and B are all within the grayscale value range of 0-255. When the grayscale value W is 0, it is black, and when the grayscale value W is 225, it is white. The shooting unit sends the grayscale image data to the binarization unit.

7. A nut pest prediction system according to claim 2, characterized in that: The binarization unit performs binarization processing on the grayscale image, and the binarization processing threshold is the standard grayscale value H of a healthy nut tree. When the grayscale value W calculated by the central unit is higher than or equal to the standard grayscale value H, it is adjusted to 225, and when the grayscale value W is lower than the standard grayscale value H, it is adjusted to 0. The binarization unit sends the binarized image to the central unit.

8. A nut pest and disease prediction system according to claim 7, characterized in that: The central unit receives the binarized image and calculates the percentage value BS of the black area in the total area of ​​the image. The central unit compares the percentage value BS with its internal danger threshold WX. When the percentage value BS is ≥ the danger threshold WX, the central unit sends a warning instruction to the alarm unit. When the danger threshold WX is < the danger threshold WX, the central unit does not send an instruction. The alarm unit receives the warning instruction and directly goes to the nut planting site to carry out pest control.

9. A nut pest and disease prediction system according to claim 2, characterized in that: The recording unit collects the dates on which the central unit sends the first-level pest instruction, the second-level pest instruction, the third-level pest instruction and the early warning instruction each year, and the recording unit records the date on which the first-level pest instruction is sent as 1 point, the date on which the second-level pest instruction is sent as 3 points, the date on which the third-level pest instruction is sent as 5 points, the date on which the early warning instruction is sent as 5 points, and the date on which no instruction is sent as 0 point. The recording unit adds up the scores of each identical date in three years, and the central unit sends each date and the score of the date to the central unit.

10. A nut pest and disease prediction system according to claim 9, characterized in that: The central unit receives the sent date and the score sum of the date, and arranges the score sum in descending order. When the score sums of different dates are the same, the latest year is used as the first comparison target. If they are all the same, they are arranged in parallel. When the central unit predicts pests and diseases for the next year, the importance of the date is determined according to the order in which the dates are arranged.

Images