A method for predicting the occurrence of pepper powdery mildew

Abstract

The invention provides a method for predicting the occurrence of pepper powdery mildew, which relates to the technical field of powdery mildew prevention and control, comprising: collecting the proportion of lesions on pepper leaves at the same time interval, and determining the disease level of each leaf according to the size of the lesion proportion; assigning a corresponding disease level value to each disease level, and generating a first disease level forecast coefficient according to the disease level to which the leaf belongs and the corresponding disease level value; analyzing the growth of lesions on the leaf according to the lesion proportion, and generating a second disease level forecast coefficient; analyzing the lesion proportion and the increase and decrease of the number of leaves in each disease level, and generating a third disease level forecast coefficient; generating a comprehensive disease level forecast coefficient according to the above three coefficients; comparing the above four coefficients with preset thresholds respectively, and judging whether to issue a powdery mildew warning forecast, so as to achieve the effect of fully considering multiple reference factors to comprehensively analyze pepper powdery mildew, thereby improving the accuracy of pepper powdery mildew forecast.

Description

Technical Field

[0001] The invention relates to the technical field of powdery mildew prevention and control, and in particular to a method for predicting the occurrence of pepper powdery mildew. Background Art

[0002] Chili pepper is a common condiment and one of the indispensable ingredients in many cuisines. In addition, chili pepper is rich in vitamin C and vitamin A, as well as some minerals and antioxidants, which have certain nutritional value for the body. The capsaicin in chili pepper has some health benefits, such as promoting metabolism, increasing appetite, and even relieving some pain symptoms. However, during the planting process, peppers are often affected by powdery mildew, resulting in reduced production, causing serious economic losses to growers. Therefore, there is an urgent need for a forecasting method for the occurrence of pepper powdery mildew to forecast powdery mildew, so that growers can do a good job of protection in advance to prevent pepper powdery mildew from further deteriorating, thereby reducing economic losses.

[0003] In the prior art, a method for predicting the occurrence of tobacco powdery mildew, disclosed in publication number "CN108647814B", comprises the following steps: in the tobacco planting season, forecast indicator plants are planted or placed around tobacco fields, and the period when tobacco powdery mildew is about to occur is predicted by observing the time when powdery mildew symptoms appear on the front of the leaves of the indicator plants; the severity of the upcoming tobacco powdery mildew is predicted by measuring the disease index of the powdery mildew on the leaves of the indicator plants; and the prevention and control period of tobacco powdery mildew is then guided. The method has a good forecasting effect, and the method is simple, reliable and easy to operate.

[0004] However, the existing technology still has major defects. For example, the existing technology uses the growth rate of the disease index to judge the severity of the upcoming tobacco powdery mildew. Specifically, the disease level is matched according to the ratio of the lesion area on the leaf to the leaf area, and then the disease level value is introduced to calculate the disease index. However, this method is too general and does not take into account the growth rate of the lesions on a single leaf, nor does it analyze the increase and decrease trend of the number of leaves in each disease level. That is, the data processing and analysis of the existing technology does not fully consider multiple reference factors, and there is a problem of inaccurate prediction of pepper powdery mildew. Summary of the invention

[0005] The object of the present invention is to provide a method for predicting the occurrence of pepper powdery mildew to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A method for predicting the occurrence of pepper powdery mildew comprises the following steps:

[0008] S1, the percentage of lesions on pepper leaves collected at the same time interval And by the proportion of lesions The size of the leaves is used to determine the disease level of each leaf;

[0009] Wherein, i represents the number of different collection moments, i=1, 2, 3, ..., n;

[0010] Wherein, j represents the number of different leaves on the whole pepper plant, j = 1, 2, 3, ..., m;

[0011] S2, assigning a corresponding disease level value to each disease level, and generating a first disease prediction coefficient YB1 according to the disease level of the leaf and the corresponding disease level value;

[0012] S3, according to the proportion of lesions Analyze the growth of disease spots on leaves and generate the second disease prediction coefficient YB2;

[0013] S4, percentage of lesions Analyze the increase and decrease of the number of leaves in each disease level to generate the third disease prediction coefficient YB3;

[0014] S5, generating a comprehensive disease prediction coefficient YBzh according to the first disease prediction coefficient YB1, the second disease prediction coefficient YB2, and the third disease prediction coefficient YB3;

[0015] S6, comparing the disease forecast first coefficient YB1, the disease forecast second coefficient YB2, the disease forecast third coefficient YB3, and the disease forecast comprehensive coefficient YBzh with preset thresholds respectively, so as to determine whether to issue a powdery mildew warning forecast.

[0016] Preferably, the evaluation criteria for the disease level are as follows:

[0017] When satisfied When the leaf is infected with the virus, it will be classified into the 0th disease level;

[0018] When satisfied When the leaf is infected with the virus, it will be classified as the first disease level;

[0019] When satisfied When the leaf is infected with the virus, it will be classified as the second disease level;

[0020] When satisfied When the leaf is infected with the virus, it will be classified as the third disease level;

[0021] When satisfied When the leaf is infected with the virus, it will be classified as the 4th disease level;

[0022] When satisfied When the leaf is infected with the disease, it will be included in the 5th disease level.

[0023] Preferably, a corresponding disease level value is assigned to each disease level, and the specific logic for generating the first disease prediction coefficient YB1 according to the disease level of the leaf and the corresponding disease level value is as follows:

[0024] S21, assign a corresponding disease level value to each disease level, and generate the disease evaluation coefficient BQpj for the whole plant according to the disease level of the leaf and the corresponding disease level value i , as follows:

[0025] The number of leaves in each disease level is multiplied by the disease level value corresponding to the disease level to generate the disease index of each disease level, and then the disease indexes are summed to generate the disease evaluation coefficient BQpj for the whole plant. i , the calculation formula is as follows:

[0026]

[0027] Where z represents the number of different disease levels, z = 1, 2, 3, ..., 6, α z represents the number of leaves in the i-th disease level, β z Indicates the disease level value corresponding to the i-th disease level;

[0028] S22, based on the whole plant disease evaluation coefficient BQpj i , generate the first coefficient YB1 of disease prediction, the calculation formula is as follows:

[0029]

[0030] It should be noted that λ is a preset proportional coefficient, and 0<λ≤1, and C1 is a constant correction parameter.

[0031] Preferably, the disease level value is selected as follows:

[0032] For the 0th disease level, the value 0 is selected as the disease level value;

[0033] For the first disease level, the value 1 is selected as the disease level value;

[0034] For the second level of disease, the value 2 is selected as the disease level value;

[0035] For the 3rd level of illness, the value 4 is selected as the illness level value;

[0036] For the 4th level of illness, the value 10 is selected as the illness level value;

[0037] For the 5th grade disease level, a value of 20 is selected as the disease level value.

[0038] Preferably, according to the proportion of lesions BYB i j The specific logic of analyzing the growth of disease spots on leaves and generating the second disease prediction coefficient YB2 is as follows:

[0039] S31, based on the percentage of lesions on pepper leaves Generate a single leaf spot growth rate coefficient, the calculation formula is as follows:

[0040]

[0041] Among them, PC j YBzs is the deviation coefficient of the lesion growth on the jth leaf, j represents the single leaf spot growth rate coefficient of the jth leaf, PCyz is the preset spot growth deviation threshold;

[0042] S32, generating a second disease prediction coefficient YB2 according to the single leaf spot growth rate coefficient, the calculation formula is as follows:

[0043]

[0044] Preferably, the proportion of lesions The specific logic of analyzing the increase and decrease of the number of leaves in each disease level and generating the third coefficient YB3 of disease prediction is as follows:

[0045]

[0046] Among them, k1 represents the number of leaves in the 0th disease level at the first acquisition time, k2 represents the number of leaves in the 5th disease level at the first acquisition time, k3 represents the number of leaves in the 0th disease level at the nth acquisition time, k4 represents the number of leaves in the 5th disease level at the nth acquisition time, BYBmax n BYBmax1 represents the maximum value of the disease spot percentage data collected at the nth collection time, and BYBmax2 represents the maximum value of the disease spot percentage data collected at the first collection time;

[0047] Among them, a1, a2, and a3 are all preset proportional coefficients greater than 0, and C2 is a constant correction parameter.

[0048] Preferably, the specific logic for generating the comprehensive disease prediction coefficient YBzh according to the first disease prediction coefficient YB1, the second disease prediction coefficient YB2, and the third disease prediction coefficient YB3 is:

[0049]

[0050] Among them, b1, b2, and b3 are all preset proportional coefficients greater than 0.

[0051] Preferably, the specific logic of comparing the first disease prediction coefficient YB1, the second disease prediction coefficient YB2, the third disease prediction coefficient YB3, and the disease prediction comprehensive coefficient YBzh with the preset thresholds to determine whether to issue a powdery mildew warning forecast is:

[0052] If any of the following conditions is not met: YB1≤TTH1, YB2≤TTH2, YB3≤TTH3, and YBzh≤TTH4, a powdery mildew warning forecast will be issued;

[0053] Among them, TTH1 is the first threshold for condition prediction, TTH2 is the second threshold for condition prediction, TTH3 is the third threshold for condition prediction, and TTH4 is the comprehensive threshold for condition prediction.

[0054] Compared with the prior art, the present invention has the following beneficial effects:

[0055] The method for predicting the occurrence of pepper powdery mildew of the present invention generates a first disease prediction coefficient according to the disease level to which the leaves belong and the corresponding disease level value, and generates a second disease prediction coefficient by analyzing the growth of disease spots on the leaves according to the disease spot ratio, and generates a third disease prediction coefficient by analyzing the disease spot ratio and the increase in the number of leaves in each disease level, and finally generates a comprehensive disease prediction coefficient through the three coefficients, so as to achieve the effect of fully considering multiple reference factors to conduct a comprehensive analysis of pepper powdery mildew, thereby improving the accuracy of pepper powdery mildew prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 The present invention is a flow chart of the method for predicting the occurrence of pepper powdery mildew. DETAILED DESCRIPTION

[0057] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0058] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0059] Example:

[0060] See also Figure 1 The present invention provides a method for predicting the occurrence of pepper powdery mildew according to an embodiment, comprising the following steps:

[0061] S1, the percentage of lesions on pepper leaves collected at the same time interval And by the proportion of lesions The size of the leaves is used to determine the disease level of each leaf;

[0062] It should be noted that the proportion of collected lesions The time interval can be 1 day, 2 days, 3 days, etc., and there is no limitation here. i represents the number of different collection moments, i=1, 2, 3, ..., n, and the best value of n is about 5 times. The collection starting point is the moment when the pepper begins to show symptoms of powdery mildew;

[0063] It should be noted that j represents the number of different leaves on the whole pepper plant, j = 1, 2, 3, ..., m, m represents the number of collected pepper leaves, and m ≥ 10, m ∈ N + ;

[0064] It should be noted that the proportion of lesions It is the ratio of the diseased spot area on the leaf to the leaf area. The staff can directly observe and estimate it with the naked eye, or perform non-contact measurement through image processing software. There is no restriction here.

[0065] As an implementation method, the evaluation criteria for disease level are as follows:

[0066]

[0067] S2, assigning a corresponding disease level value to each disease level, and generating a first disease prediction coefficient YB1 according to the disease level of the leaf and the corresponding disease level value, including the following steps:

[0068] S21, assign a corresponding disease level value to each disease level, and generate the first disease prediction coefficient YB1 and the whole plant disease evaluation coefficient BQpj according to the disease level of the leaf and the corresponding disease level value i , as follows:

[0069] The number of leaves in each disease level is multiplied by the disease level value corresponding to the disease level to generate the disease index of each disease level, and then the disease indexes are summed to generate the disease evaluation coefficient BQpj for the whole plant. i , the whole plant disease evaluation coefficient BQpj i The calculation formula is as follows:

[0070]

[0071] Where z represents the number of different disease levels, z = 1, 2, 3, ..., 6, α z represents the number of leaves in the i-th disease level, β z Indicates the disease level value corresponding to the i-th disease level;

[0072] It should be noted that the more leaves with disease spots on the whole pepper plant, the greater the proportion of disease spots on the leaves, indicating that the powdery mildew on the pepper is more serious, and the disease evaluation coefficient of the whole plant BQpj i The bigger it is.

[0073] As an implementation method, the disease level value is selected as follows:

[0074]

[0075] S22, based on the whole plant disease evaluation coefficient BQpj i , generate the first coefficient YB1 of disease prediction, the calculation formula is as follows:

[0076]

[0077] It should be noted that λ is a preset proportional coefficient, and 0<λ≤1, and C1 is a constant correction parameter;

[0078] It should be noted that the larger the ratio between the two adjacent whole-plant disease evaluation coefficients, the greater the severity of pepper powdery mildew, and the larger the first disease prediction coefficient YB1.

[0079] S3, according to the proportion of lesions The growth of the disease spots on the leaves is analyzed to generate the second disease prediction coefficient YB2, as follows:

[0080] S31, based on the percentage of lesions on pepper leaves Generate a single leaf spot growth rate coefficient, the calculation formula is as follows:

[0081]

[0082] It should be noted that PC j is the lesion growth deviation coefficient of the jth leaf, which represents the ratio of the lesion growth rate of the jth leaf from time n-1 to time n to the average lesion growth rate during the entire acquisition time. The lesion growth deviation coefficient PC j The larger the value is, the greater the difference between the lesion growth rate of the jth leaf from time n-1 to time n and the average lesion growth rate during the entire collection time is.

[0083] It should be noted that YBzs jrepresents the single leaf spot growth rate coefficient of the jth leaf, PCyz is the preset spot growth deviation threshold, and when PCyz is satisfied j When PCyz<PCyz, it means that the difference between the lesion growth rate of the jth leaf from time n-1 to time n and the average lesion growth rate during the entire collection time is small. The average lesion growth rate during the entire collection time is used as the single leaf lesion growth rate coefficient. j When ≥PCyz, it means that the growth rate of the lesion on the jth leaf from time n-1 to time n is significantly different from the average growth rate of the lesion during the entire acquisition time. In this case, the growth rate of the lesion on the jth leaf from time n-1 to time n is used as the growth rate coefficient of the lesion on a single leaf, so as to improve the accuracy of the calculation of the growth rate coefficient of the lesion on a single leaf.

[0084] S32, generating a second disease prediction coefficient YB2 according to the single leaf spot growth rate coefficient, the calculation formula is as follows:

[0085]

[0086] It should be noted that the larger the growth rate coefficient of each single leaf spot, the faster the growth rate of the spot on the leaf, the greater the aggravation of pepper powdery mildew, and the larger the second disease prediction coefficient YB2.

[0087] S4, percentage of lesions Analyze the increase and decrease of the number of leaves in each disease level to generate the third disease prediction coefficient YB3. The calculation formula is as follows:

[0088]

[0089] It should be noted that k1 represents the number of leaves in the 0th disease level at the first acquisition time, k2 represents the number of leaves in the 5th disease level at the first acquisition time, k3 represents the number of leaves in the 0th disease level at the nth acquisition time, k4 represents the number of leaves in the 5th disease level at the nth acquisition time, BYBmax n BYBmax1 represents the maximum value of the disease spot percentage data collected at the nth collection time, and BYBmax2 represents the maximum value of the disease spot percentage data collected at the first collection time. The above data can be directly obtained;

[0090] It should be noted that a1, a2, and a3 are all preset proportional coefficients greater than 0, and C2 is a constant correction parameter;

[0091] It should be noted that k1-k3, k4-k2, and BYBmax n The larger the -BYBmax1 is, the greater the severity of pepper powdery mildew is, and the larger the third disease prediction coefficient YB3 is.

[0092] S5, generating a comprehensive disease prediction coefficient YBzh according to the first disease prediction coefficient YB1, the second disease prediction coefficient YB2, and the third disease prediction coefficient YB3, and the calculation formula is as follows:

[0093]

[0094] It should be noted that b1, b2, and b3 are all preset proportional coefficients greater than 0;

[0095] It should be noted that the larger the first disease prediction coefficient YB1, the second disease prediction coefficient YB2, and the third disease prediction coefficient YB3 are, the greater the severity of pepper powdery mildew is, and the larger the comprehensive disease prediction coefficient YBzh is.

[0096] S6, comparing the first disease prediction coefficient YB1, the second disease prediction coefficient YB2, the third disease prediction coefficient YB3, and the disease prediction comprehensive coefficient YBzh with the preset thresholds, so as to determine whether to issue a powdery mildew warning forecast, as follows:

[0097] If any one of the following conditions is not met: YB1≤TTH1, YB2≤TTH2, YB3≤TTH3, and YBzh≤TTH4, it indicates that the pepper powdery mildew is getting worse and worse, and a powdery mildew warning forecast is issued to remind growers to pay attention to the fact that the pepper powdery mildew is getting worse and worse, and to take protective measures in time to avoid further losses;

[0098] Among them, TTH1 is the first threshold for condition prediction, TTH2 is the second threshold for condition prediction, TTH3 is the third threshold for condition prediction, and TTH4 is the comprehensive threshold for condition prediction.

[0099] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0100] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by computer software, electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software depends on the specific application and design constraints of the technical solution.

[0101] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0102] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for predicting the occurrence of pepper powdery mildew, characterized in that: The steps include: S1, the percentage of lesions on pepper leaves collected at the same time interval And by the proportion of lesions The size of the leaves is used to determine the disease level of each leaf; Wherein, i represents the number of different collection moments, i=1, 2, 3, ..., n; Wherein, j represents the number of different leaves on the whole pepper plant, j = 1, 2, 3, ..., m; The proportion of lesions is the ratio of the lesion area on the leaf to the leaf area; S2, assigning a corresponding disease level value to each disease level, and generating a first disease prediction coefficient YB1 according to the disease level of the leaf and the corresponding disease level value; The specific logic for generating the first coefficient YB1 of the disease prediction is: S21, assign a corresponding disease level value to each disease level, and generate the disease evaluation coefficient BQpj for the whole plant according to the disease level of the leaf and the corresponding disease level value i , as follows: The number of leaves in each disease level is multiplied by the disease level value corresponding to the disease level to generate the disease index of each disease level, and then the disease indexes are summed to generate the disease evaluation coefficient BQpj for the whole plant. i , the calculation formula is as follows: Where z represents the number of different disease levels, z = 1, 2, 3, ..., 6, α z represents the number of leaves in the i-th disease level, β z Indicates the disease level value corresponding to the i-th disease level; S22, based on the whole plant disease evaluation coefficient BQpj i , generate the first coefficient YB1 of disease prediction, the calculation formula is as follows: It should be noted that λ is a preset proportional coefficient, and 0<λ≤1, and C1 is a constant correction parameter; S3, according to the proportion of lesions Analyze the growth of disease spots on leaves and generate the second disease prediction coefficient YB2; The specific logic for generating the second coefficient YB2 of the disease prediction is: S31, based on the percentage of lesions on pepper leaves Generate a single leaf spot growth rate coefficient, the calculation formula is as follows: Among them, PC j YBzs is the deviation coefficient of the lesion growth on the jth leaf, j represents the single leaf spot growth rate coefficient of the jth leaf, PCyz is the preset spot growth deviation threshold; S32, generating a second disease prediction coefficient YB2 according to the single leaf spot growth rate coefficient, the calculation formula is as follows: S4, percentage of lesions Analyze the increase and decrease of the number of leaves in each disease level to generate the third disease prediction coefficient YB3; The specific logic for generating the third coefficient YB3 of the disease prediction is: Among them, k1 represents the number of leaves in the 0th disease level at the first acquisition time, k2 represents the number of leaves in the 5th disease level at the first acquisition time, k3 represents the number of leaves in the 0th disease level at the nth acquisition time, k4 represents the number of leaves in the 5th disease level at the nth acquisition time, BYBmax n BYBmax1 represents the maximum value of the disease spot percentage data collected at the nth collection time, and BYBmax2 represents the maximum value of the disease spot percentage data collected at the first collection time; Among them, a1, a2, and a3 are all preset proportional coefficients greater than 0, and C2 is a constant correction parameter; S5, generating a comprehensive disease prediction coefficient YBzh according to the first disease prediction coefficient YB1, the second disease prediction coefficient YB2, and the third disease prediction coefficient YB3; S6, comparing the disease forecast first coefficient YB1, the disease forecast second coefficient YB2, the disease forecast third coefficient YB3, and the disease forecast comprehensive coefficient YBzh with preset thresholds respectively, so as to determine whether to issue a powdery mildew warning forecast.

2. The method for predicting the occurrence of pepper powdery mildew according to claim 1, characterized in that: The evaluation criteria for the disease level are as follows: When satisfied When the leaf is infected with the virus, it will be classified into the 0th disease level; When satisfied When the leaf is infected with the virus, it will be classified as the first disease level; When satisfied When the leaf is infected with the virus, it will be classified as the second disease level; When satisfied When the leaf is infected with the virus, it will be classified as the third disease level; When satisfied When the leaf is infected with the virus, it will be classified as the 4th disease level; When satisfied When the leaf is infected with the disease, it is classified into the 5th disease level.

3. The method for predicting the occurrence of pepper powdery mildew according to claim 1, characterized in that: The disease level values ​​are selected as follows: For the 0th disease level, the value 0 is selected as the disease level value; For the first disease level, the value 1 is selected as the disease level value; For the second level of disease, the value 2 is selected as the disease level value; For the 3rd level of illness, the value 4 is selected as the illness level value; For the 4th level of illness, the value 10 is selected as the illness level value; For the 5th grade disease level, a value of 20 is selected as the disease level value.

4. The method for predicting the occurrence of pepper powdery mildew according to claim 1, characterized in that: The specific logic of generating the comprehensive coefficient of disease prediction YBzh according to the first disease prediction coefficient YB1, the second disease prediction coefficient YB2, and the third disease prediction coefficient YB3 is as follows: Among them, b1, b2, and b3 are all preset proportional coefficients greater than 0.

5. The method for predicting the occurrence of pepper powdery mildew according to claim 1, characterized in that: The specific logic of comparing the first disease forecast coefficient YB1, the second disease forecast coefficient YB2, the third disease forecast coefficient YB3, and the comprehensive disease forecast coefficient YBzh with the preset thresholds to determine whether to issue a powdery mildew warning forecast is as follows: If any of the following conditions is not met: YB1≤TTH1, YB2≤TTH2, YB3≤TTH3, and YBzh≤TTH4, a powdery mildew warning forecast will be issued; Among them, TTH1 is the first threshold for condition prediction, TTH2 is the second threshold for condition prediction, TTH3 is the third threshold for condition prediction, and TTH4 is the comprehensive threshold for condition prediction.

Images