Apple yield prediction method, device, storage medium and electronic device

Abstract

The present application provides a method, device, storage medium and electronic device for predicting apple yield, wherein the method comprises: obtaining data to be predicted; the data to be predicted comprises disaster sample data within a target time period and meteorological sample data of each day; inputting the data to be predicted into a yield prediction model to obtain a prediction result of apple yield within the time period to be predicted; the disaster sample data within the target time period and the meteorological sample data of each day are used to predict the apple yield within the time period to be predicted in the same year; the yield prediction model is trained by a plurality of sample data, each of which comprises disaster sample data within a preset time period and meteorological sample data of each day and apple yield sample data of the same year as the preset time period. The method for predicting apple yield provided by the present application solves the problem that the current apple yield prediction method is not universal and cannot accurately predict apple yield.

Description

Technical Field

[0001] The present application relates to the field of agricultural technology, and in particular to a method, device, storage medium and electronic device for predicting apple yield. Background Art

[0002] China is the world's largest apple producer and consumer, with apple planting area and output accounting for more than 40% of the world's total, and plays an important role in the world's apple industry. The current apple yield prediction method usually only considers common meteorological factors such as temperature, precipitation, and light, and the meteorological factors selected are restricted by the region and climate. Therefore, the current apple yield estimation method is not universal and cannot accurately and objectively predict apple yield. Summary of the invention

[0003] The embodiments of the present application provide a method, device, storage medium and electronic device for predicting apple yield, which solve the problem that the current apple yield prediction method is not universal and cannot accurately predict apple yield.

[0004] To solve the above technical problems, this application includes the following technical solutions:

[0005] In a first aspect, an embodiment of the present application provides a method for predicting apple yield, the method comprising:

[0006] Acquire the data to be predicted; the data to be predicted includes disaster sample data within the target time period and meteorological sample data for each day;

[0007] The data to be predicted is input into the yield prediction model to obtain the apple yield prediction result within the time period to be predicted; the disaster sample data within the target time period and the meteorological sample data of each day are used to predict the apple yield within the time period to be predicted in the same year; the yield prediction model is trained by multiple sample data, each of the sample data includes the disaster sample data within the preset time period and the meteorological sample data of each day and the apple yield sample data of the same year as the preset time period.

[0008] In a second aspect, an embodiment of the present application provides a device for predicting apple yield, the device comprising:

[0009] An acquisition module is used to acquire data to be predicted; the data to be predicted includes disaster sample data within a target time period and meteorological sample data for each day;

[0010] The prediction module is used to input the data to be predicted into the yield prediction model to obtain the apple yield prediction result within the time period to be predicted; the disaster sample data within the target time period and the meteorological sample data of each day are used to predict the apple yield within the time period to be predicted in the same year; the yield prediction model is trained by multiple sample data, each of the sample data includes the disaster sample data within a preset time period and the meteorological sample data of each day and the apple yield sample data of the same year as the preset time period.

[0011] In a third aspect, an embodiment of the present application provides an electronic device, the electronic device comprising: a processor, a memory, and a communication interface:

[0012] The processor is connected to the memory and the communication interface;

[0013] The memory is used to store executable program code;

[0014] The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the apple yield prediction method as described in the first aspect above.

[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the program is executed by a processor, the method for predicting apple yield as described in the first aspect above is implemented.

[0016] The apple yield prediction method provided in the present application comprehensively considers the effects of hail disasters, frost disasters and flower and fruit thinning on the amount of apple fruit, and the effect of precipitation on the weight of single apple fruit, and uses the historical apple yield data and corresponding meteorological data in the required area to construct an apple yield prediction model for the area, and combines the meteorological data and disaster data of the predicted year to predict the apple yield of that year. The apple yield prediction method provided in the present application solves the problem that the current apple yield prediction method is not universal and cannot accurately predict apple yield. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is a flow chart of a method for predicting apple yield provided in an embodiment of the present application;

[0019] Figure 2It is a flow chart of a method for predicting apple yield provided in an embodiment of the present application;

[0020] Figure 3 It is a structural schematic diagram of an apple yield prediction device provided in an embodiment of the present application;

[0021] Figure 4 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application will be described in detail below with reference to the accompanying drawings.

[0023] The terms "first", "second", "third", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0024] Please refer to Figure 1 As shown, Figure 1 : is a flow chart of a method for predicting apple yield provided in an embodiment of the present application, the method comprising:

[0025] S101, obtaining data to be predicted; the data to be predicted includes disaster sample data within a target time period and meteorological sample data for each day.

[0026] Specifically, the user inputs the data to be predicted into the electronic device, and the electronic device obtains the data to be predicted. The data to be predicted includes disaster sample data within the target time period and meteorological sample data of each day.

[0027] Furthermore, before obtaining the data to be predicted, it also includes: obtaining a plurality of the sample data; training the plurality of the sample data to obtain the yield prediction model. Wherein, the sample data includes a plurality of, and each sample data includes disaster sample data within a preset time period, meteorological sample data of each day, and apple yield sample data of the same year as the preset time period. Wherein, in the process of model training, it also includes: solving the parameters in the yield model. The method of solving the parameters may include but is not limited to: using the Mini-batch Gradient Descent (MGDB) algorithm to obtain multiple groups of parameter combinations, each parameter combination includes multiple parameters, and then randomly obtaining part of the data in the apple yield sample data to estimate the multiple parameter values ​​in the yield prediction model, wherein the parameter value estimation adopts the least squares method, that is, finding a group of parameters with the smallest error in multiple parameter combinations so that the error between the actual value and the simulated value of the apple yield is minimized, and this group of parameters is the target parameter sought in this scheme.

[0028] Specifically, this application selects key environmental factors to construct an apple yield estimation model for a specific main production city. Its basic assumption is that the apple yield per unit area should be determined by the number of apple trees, the amount of fruit on each apple tree, and the weight of each apple. The apple fruit phenological period is generally divided into two periods: the red-opening period-young fruit period and the fruit expansion period. Among them, the amount of fruit on each apple tree is calculated during the red-opening period-young fruit period, and the weight of each apple is calculated during the fruit expansion period. This application is based on the apple yield estimation model of plant physiological processes. The step length is calculated, and the amount of fruit on each apple tree and the weight of each apple are simulated respectively, and the yield prediction model shown below is obtained:

[0029] Yield=Plant num ×Num end ×Weight end

[0030] Among them, Yield is the apple yield; Plant num Plant a tree for apples; Num end is the amount of fruit on each apple tree, Weight end for the weight of each apple.

[0031] Furthermore, the yield prediction model can also include an improvement coefficient and a prediction year; the improvement coefficient combined with the prediction year characterizes the impact of non-environmental factors on apple yield. With the improvement of technology and the management level of apples, apple yield will continue to grow. When the improvement coefficient is carried, the yield prediction model shown below can be obtained:

[0032] Yield=Plant num ×Numend ×Weight end +C×year

[0033] Among them, Yield is the apple yield; Plant num Plant a tree for apples; Num end is the amount of fruit on each apple tree, Weight end is the weight of each apple; C is the improvement coefficient; year is the year. The improvement coefficient combined with the predicted year represents the impact of non-environmental factors on apple yield.

[0034] S102, inputting the data to be predicted into a yield prediction model to obtain an apple yield prediction result within a time period to be predicted.

[0035] Specifically, after the electronic device obtains the data to be predicted, it inputs the data to be predicted into the yield prediction model. The data to be predicted includes the disaster sample data within the target time period and the meteorological sample data of each day, which are input into the yield prediction model. The yield prediction model analyzes and calculates the data to be predicted and obtains the apple yield prediction result within the time period to be predicted. Among them, the disaster sample data within the target time period and the meteorological sample data of each day are used to predict the apple yield within the time period to be predicted in the same year. The yield prediction model is trained by multiple sample data, and each of the sample data includes the disaster sample data within the preset time period, the meteorological sample data of each day, and the apple yield sample data of the same year as the preset time period.

[0036] Furthermore, the data to be predicted is input into a yield prediction model to obtain an apple yield prediction result within the time period to be predicted, including: inputting disaster sample data within the time period to be predicted and each day's meteorological sample data into the yield prediction model to obtain frost mortality rate, hail mortality rate, flower and fruit thinning rate and fruit growth rate; determining the amount of fruit on each apple tree according to the frost mortality rate, hail mortality rate and flower and fruit thinning rate; determining the weight of each apple according to the fruit growth rate; obtaining the apple yield prediction result within the time period to be predicted according to the amount of fruit on each apple tree, the weight of each apple and the number of apple trees.

[0037] Further, the meteorological sample data includes at least one of the following: the lowest temperature of each day, the total duration of each day when the temperature is below a preset threshold, and the daily precipitation; the disaster sample data includes at least one of the following: the number of frost disasters during apple flowering period, the number of hail disasters during apple flowering period, and the amount of fruit on each apple tree after experiencing frost and hail disasters; the disaster sample data within the time period to be predicted and the meteorological sample data of each day are input into the yield prediction model to obtain the frost mortality rate, hail mortality rate, flower and fruit thinning rate and fruit growth rate, including: obtaining the frost mortality rate based on the lowest temperature of each day, the total duration of each day when the temperature is below the preset threshold, and the number of frost disasters during apple flowering period; obtaining the hail mortality rate based on the number of hail disasters during apple flowering period; obtaining the flower and fruit thinning rate based on the amount of fruit on each apple tree after experiencing frost and hail disasters; and obtaining the fruit growth rate based on the daily precipitation.

[0038] Specifically, the amount of fruit on each apple tree depends on the initial flowering, frost mortality, hail mortality, and flower and fruit thinning rate. The formula for calculating the amount of fruit on each apple tree is as follows:

[0039] Num end =Num start ×{(1–Rate1)×(1–Rate2)×…(1–Rate n )}×(1-Hail) m ×(1-Thin)

[0040] Among them, Num start The initial amount of flowers; Rate 1-n are the mortality rates of the 1st to nth frost damage; Hail is the mortality rate of hail; Thin is the flower and fruit thinning rate; n is the number of frost damage disasters occurring during the apple flowering period; m is the number of hail disasters occurring during the apple flowering period.

[0041] Specifically, the freezing mortality rate is positively correlated with the lowest temperature of each day and the total duration of each day when the temperature is below the preset threshold, wherein the preset threshold of the lowest temperature can be but is not limited to 0°C, that is, the total duration of each day when the temperature is below 0°C is counted. The calculation formula for the freezing mortality rate is as follows:

[0042] Rate i =p×Tmin i +q×Hour i

[0043] Among them, Rate i Hour i is the mortality rate of the frost injury for the i-th time, Tmin i The lowest temperature of each day is Hour iIt is the total time that the temperature is below the preset threshold each day; p and q are both unknown parameters.

[0044] Specifically, the adverse effects of hail on apples depend on the size of the hail, the intensity of the hail and the speed at which the hailstones fall. Therefore, in order to simplify the calculation, in this application, it is assumed that the apple drop rate caused by different hail disasters is a constant, that is, the mortality rate of each hailstorm is a constant, and this constant is a to-be-determined parameter.

[0045] Specifically, flower and fruit thinning will improve the quality and yield of apples in that year to a certain extent. Since the flower and fruit thinning rate is affected by multiple factors, in order to simplify the calculation, the artificial flower and fruit thinning rate in this application is set to only consider the impact of frost damage and hail disasters on the amount of apples falling. The calculation formula of the flower and fruit thinning rate is as follows:

[0046]

[0047] Among them, Thin is the flower and fruit thinning rate; Num start Num is the initial amount of flowers; state The number of fruits after frost damage and hail damage; Num base is the minimum expected fruiting amount; Thin a and Thin b To be determined parameter.

[0048] Specifically, the growth of apple fruit diameter presents an "S" curve. The young fruit stage is within 30 days after fruit setting. During the young fruit stage, apples grow rapidly. Then, apples enter the early stage of fruit expansion. This stage is mainly characterized by an increase in the number of cells. The fruit mainly grows longitudinally, which is the critical period of apple moisture. At the same time, the growth rate of apples generally reaches its maximum around the 60th day after fruit setting. The late stage of fruit expansion begins 75 days after fruit setting. This stage is mainly characterized by an increase in the overall volume of cells. The fruit mainly expands laterally, with a slow growth rate, and enters a slow growth stage. According to the above analysis, the growth stage of apple fruit can be divided into the initial growth stage, the exponential growth stage, and the stable growth stage. For calculating the weight of each apple, the Richards theoretical growth equation can be used for calculation. The Richards theoretical growth equation is an equation constructed by Richards FJ based on the Bertalanffy growth theory and is widely used in biological growth simulation. The Richards theoretical growth equation is a four-parameter nonlinear equation, which can better describe the change in fruit weight of apple growth and development over time. The calculation formula for the weight of each apple is as follows:

[0049]

[0050] Among them, x represents the number of growing days, Weight endis the weight of each apple; K is the cumulative growth saturation value; a0 is the initial growth parameter; b0 is the growth rate parameter; c0 is the allometric growth parameter. To simplify the calculation, this model takes c0 as 2.

[0051] The above Richards theoretical growth equation is transformed into the Logistic growth equation as shown below:

[0052]

[0053] Among them, b 0i , K i and Weight i are the apple fruit growth rate parameter, cumulative growth saturation value and apple weight on the i-th day respectively.

[0054] Among them, in the early stage of the expansion period of apple fruit growth, the apple growth rate is relatively fast, which is the critical period of apple fruit growth. The soil moisture content during this period plays a decisive role in the size of apple fruit. The cumulative precipitation during the fruit expansion period directly determines the size of the apple fruit diameter. If the precipitation is insufficient during this period, the soil moisture content is too low, and the apple orchard suffers from drought, the fruit will be too small and the fruit weight will be affected; if there is too much precipitation, it will cause vigorous growth of new shoots and serious canopy shading, which will affect the coloring of the fruit in the later stage, thereby affecting the quality of the apple fruit. In this stage, only the impact of insufficient precipitation on the weight of apple fruit is considered. Among them, insufficient precipitation mainly affects the cumulative growth saturation value and growth rate parameters. The relationship between the daily growth rate parameter, the cumulative growth saturation value and the daily precipitation is shown in the following formulas:

[0055]

[0056] Among them, b 0i and K i are the apple fruit growth rate parameter and cumulative growth saturation value on day i; apcp i is the cumulative precipitation on the i-th day and the past 7 days; apcp base It is the lower limit of precipitation in 7 days. When it is lower than this lower limit, the growth rate of apple weight will be hindered.

[0057] Furthermore, the data to be predicted is input into the yield prediction model to obtain the apple yield prediction result within the time period to be predicted, including: inputting the disaster sample data and the meteorological sample data of each day, the number of apple trees and the year within the time period to be predicted into the yield prediction model to obtain the apple yield prediction result within the time period to be predicted. It should be noted that in the yield prediction model provided in the present application, if the impact of hail disasters on apple yield is not considered and only scenario simulation is used to predict apple yield, the apple yield for many years in the future can be estimated.

[0058] Exemplarily, if the apple production in September 2021 is to be predicted, the data to be predicted from January to August are obtained, and the data to be predicted include the disaster sample data from January to August and the meteorological sample data of each day. Among them, the disaster sample data include: the number of frost disasters during the apple flowering period, the number of hail disasters during the apple flowering period, and the amount of fruit on each apple tree after experiencing frost disasters and hail disasters. The meteorological sample data include: the lowest temperature of each day, the total time that the temperature is lower than the preset threshold every day, and the precipitation every day. When the apples are in the red-revealing stage-young fruit stage, the lowest temperature of each day, the total time that the temperature is lower than the preset threshold every day, and the number of hail occurrences are obtained. The frost mortality rate is obtained based on the above data, and the hail mortality rate is obtained based on the frost mortality rate. Combined with the initial flowering amount, the flower and fruit thinning rate is obtained, and the fruit thinning rate of each apple tree is calculated based on the frost mortality rate, hail mortality rate, flower and fruit thinning rate, and initial flowering amount. When apples are in the expansion period, the growth rate and cumulative growth saturation value of apple fruits are calculated based on the daily precipitation, so as to obtain the weight of apple fruits that increases every day. The daily weight increase is accumulated day by day to finally obtain the weight of each apple. If the yield of apples per acre is to be calculated, the calculated fruit amount of each apple tree, the weight of each apple, the number of apple trees per acre and the year are input into the apple yield prediction model to finally obtain the apple yield prediction result of that year.

[0059] The apple yield prediction method provided in the present application comprehensively considers the effects of hail disasters, frost disasters and flower and fruit thinning on the amount of apple fruit, and the effect of precipitation on the weight of single apple fruit, and uses the historical apple yield data and corresponding meteorological data in the required area to construct an apple yield prediction model for the area, and combines the meteorological data and disaster data of the predicted year to predict the apple yield of that year. The apple yield prediction method provided in the present application solves the problem that the current apple yield prediction method is not universal and cannot accurately predict apple yield.

[0060] Please refer to Figure 2 As shown, Figure 2 : is a flow chart of another apple yield prediction method provided in an embodiment of the present application, the method comprising:

[0061] S201. Obtain multiple sample data.

[0062] Specifically, the electronic device obtains multiple sample data, including disaster sample data within the target time period and meteorological sample data for each day. Among them, the disaster sample data includes: the number of frost disasters during the apple flowering period, the number of hail disasters during the apple flowering period, and the amount of fruit on each apple tree after experiencing frost disasters and hail disasters. The meteorological sample data includes: the lowest temperature of each day, the total duration of the temperature below the preset threshold on each day, and the precipitation of each day.

[0063] S202: using a box plot to remove outliers from multiple sample data.

[0064] Specifically, after the electronic device obtains multiple sample data, it uses a box plot to eliminate outliers in the apple yield sample data of the multiple sample data. Outliers include values ​​where the annual apple yield is less than a preset minimum value or greater than a preset maximum value. Among them, the specific method of using a box plot to eliminate outliers may include: after obtaining multiple sample data, analyzing and sorting the sample data, for example, associating the data corresponding to a certain year, a certain time period and a certain location, and obtaining a spatiotemporal mixed sample of apple yield at the location within a certain time period of the year, analyzing the spatiotemporal mixed sample, and using a box plot to eliminate outliers in apple yield, that is, pre-setting a preset minimum value and a preset maximum value of the yield value. When the annual apple yield in a certain year is less than the preset minimum value or greater than the preset maximum value, the annual yield value is an outlier, and the outlier is then eliminated. Among them, the calculation formulas for the preset minimum value and the preset maximum value of the annual yield are as follows:

[0065] Outlier_below=Q1–1.5×(Q3-Q1)

[0066] Outlier_up=Q3+1.5×(Q3-Q1)

[0067] Among them, Outlier_below is the lower inner limit; Outlier_up is the upper inner limit; Q1 is the lower quartile; Q3 is the upper quartile.

[0068] S203, training the multiple sample data after removing outliers to obtain a yield prediction model.

[0069] Specifically, the electronic device trains multiple sample data after removing outliers, and obtains the relationship between the disaster sample data and the daily meteorological sample data and the apple yield data based on the training, and finally obtains the yield prediction model.

[0070] S204, obtaining disaster sample data and meteorological sample data of each day within the time period to be predicted, and inputting the disaster sample data and meteorological sample data of each day into the production prediction model.

[0071] Specifically, if you want to predict the apple production in a certain area from September to October of a certain year, obtain the disaster sample data and daily meteorological sample data of the area from January to August of the same year, and input the above data into the production prediction model. This application is an embodiment of the production prediction model using a progressive coefficient.

[0072] S205. Determine the frost mortality rate, hail mortality rate, flower and fruit thinning rate, and fruit growth rate based on the disaster sample data and the daily meteorological sample data.

[0073] Specifically, the freezing mortality rate, hail mortality rate, flower and fruit thinning rate and fruit growth rate are determined according to the disaster sample data and the meteorological sample data of each day. Wherein, due to the weak cold resistance of apple during the flowering period and young fruit stage, the low temperature tolerance is poor, which easily causes the falling of flowers and fruits. Therefore, in the embodiment of the present application, the freezing mortality rate can be calculated according to the disaster sample data from January to August, and the flower and fruit thinning rate is determined according to the freezing mortality rate and the hail mortality rate. The specific formula for calculating the freezing mortality rate, the hail mortality rate and the flower and fruit thinning rate is referred to the above embodiment, and the present embodiment will not repeat them. In the early stage of the apple fruit expansion period, the fruit growth rate is faster, which is the critical period of apple growth and development. The soil moisture content during this period plays a decisive role in the fruit size. Therefore, the apple fruit growth rate is determined according to the daily precipitation during the fruit expansion period. The specific calculation formula is referred to the above embodiment, and the present embodiment will not repeat them.

[0074] S206. Determine the amount of fruit on each apple tree based on the frost-related mortality rate, hail-related mortality rate, and flower and fruit thinning rate, and determine the weight of each apple based on the fruit growth rate.

[0075] Specifically, the amount of fruit on each apple tree is determined based on the obtained frost mortality rate, hail mortality rate, and flower and fruit thinning rate, and the weight of each apple is determined based on the fruit growth rate. Please refer to the above embodiment for the specific calculation formula, which will not be repeated in this embodiment.

[0076] Wherein, the frost-injury fatality rate is the probability that the frost-injury disaster causes apple necrosis. Since the apple flowering period and young fruit period have weak cold resistance and poor tolerance to low temperature, it is easy to cause falling flowers and fruits. In the embodiment of the present application, the apple flower and fruit drop rate caused by the frost-injury disaster is set to depend on the frost-injury fatality rate. The hail fatality rate is the probability that the hail disaster causes apple necrosis. Late spring hail mostly occurs from mid-April to mid-May. During this period of time, hail will fall on the petals or young fruits that are opening, which has a certain impact on apple yield. Therefore, the yield prediction model provided by the present application concretizes the impact of hail disaster on apple yield in this time period into the hail fatality rate. The flower and fruit thinning rate is the impact of the agricultural operation of artificial flower and fruit thinning on apples on the amount of apple fruit. The fruit growth rate is the growth rate of apple fruit every day during the young fruit period and the expansion period. Wherein, as the apple fruit diameter increases, the apple weight also increases therewith, and there is a positive correlation between the two. The apple fruit weight can be described using the change in the apple fruit diameter. The growth process of apple fruit diameter presents an "S" curve. The young fruit stage is within 30 days after fruit setting, and the apple grows faster. Then it enters the early stage of fruit expansion. This stage is mainly about the increase of cell number. The fruit mainly grows vertically. It is the critical period of apple moisture. At the same time, the apple growth rate generally reaches the maximum around the 60th day after fruit setting; 75 days after fruit setting, it enters the late stage of fruit expansion. This stage is mainly about the increase of the overall volume of cells. The fruit mainly expands horizontally, the growth rate is slow, and it enters the slow growth stage. Therefore, in the embodiment of the present application, the growth rate of apple fruit every day during the young fruit stage and the expansion stage is counted.

[0077] S207, input the amount of fruit on each apple tree, the weight of each apple, the number of apple trees and the predicted year into the yield prediction model to obtain the apple yield prediction result.

[0078] Specifically, the calculated amount of fruit on each apple tree, the weight of each apple, the number of apple trees and the predicted year are input into a yield prediction model to obtain the predicted apple yield in that year and that region.

[0079] In an embodiment of the present application, disaster sample data and daily meteorological data are introduced into a yield prediction model, wherein the disaster sample data simultaneously considers frost damage and hail disasters, and the meteorological sample data considers not only conventional environmental factors such as temperature and precipitation, but also the impact of flower and fruit thinning on apple yield. A plurality of sample data carrying the above data are simulated to establish a yield prediction model covering the entire apple growth process. In the process of predicting yield, the apple yield of the same year can be predicted based on the disaster data and meteorological data of the time period to be predicted. The apple yield prediction method provided by the present application solves the problem that the current apple yield prediction method is not universal and cannot accurately predict apple yield.

[0080] Please refer to Figure 3As shown in the figure, based on the prediction method of apple production, Figure 3 Schematic diagram of an apple yield prediction device provided in an embodiment of the present application, comprising:

[0081] The first acquisition module 301 is used to acquire data to be predicted; the data to be predicted includes disaster sample data within a target time period and meteorological sample data of each day;

[0082] The prediction module 302 is used to input the data to be predicted into the yield prediction model to obtain the apple yield prediction result within the time period to be predicted; the disaster sample data within the target time period and the meteorological sample data of each day are used to predict the apple yield within the time period to be predicted in the same year; the yield prediction model is trained by multiple sample data, each of the sample data includes the disaster sample data within the preset time period and the meteorological sample data of each day and the apple yield sample data of the same year as the preset time period.

[0083] In some embodiments, the apparatus further comprises:

[0084] A second acquisition module, used for acquiring a plurality of sample data before the first acquisition module 301 acquires the data to be predicted;

[0085] The training module is used to train the plurality of sample data to obtain the yield prediction model.

[0086] In some embodiments, the apparatus further comprises:

[0087] The elimination module is used to eliminate abnormal values ​​from the sample data after the second acquisition module acquires the multiple sample data and before the training module trains the multiple sample data; the abnormal values ​​include values ​​where the annual apple production is less than a preset minimum value or greater than a preset maximum value.

[0088] In some embodiments, the rejection module is specifically used to:

[0089] The box plot is used to remove outliers from the sample data.

[0090] In some embodiments, the prediction module 302 includes:

[0091] The third acquisition module is used to input the disaster sample data within the time period to be predicted and the meteorological sample data of each day into the yield prediction model to obtain the frost mortality rate, hail mortality rate, flower and fruit thinning rate and fruit growth rate;

[0092] A determination module, used to determine the amount of fruit on each apple tree according to the frost-related mortality rate, the hail-related mortality rate and the flower and fruit thinning rate; and to determine the weight of each apple according to the fruit growth rate;

[0093] The fourth acquisition module is used to obtain the apple yield prediction result within the time period to be predicted based on the fruit quantity of each apple tree, the weight of each apple and the number of apple trees.

[0094] In some embodiments, the meteorological sample data includes at least one of the following: the lowest temperature of each day, the total duration of each day when the temperature is below a preset threshold, and the precipitation of each day; the disaster sample data includes at least one of the following: the number of frost disasters during the apple blossom period, the number of hail disasters during the apple blossom period, and the amount of fruit on each apple tree after experiencing frost disasters and hail disasters;

[0095] The third acquisition module is specifically used for:

[0096] The frost damage mortality rate is obtained based on the daily minimum temperature, the total duration of each day when the temperature is below the preset threshold, and the number of frost damage disasters occurring during the apple flowering period; the hail mortality rate is obtained based on the number of hail disasters occurring during the apple flowering period; the flower and fruit thinning rate is obtained based on the amount of fruit on each apple tree after experiencing frost damage and hail disasters; and the fruit growth rate is obtained based on the daily precipitation.

[0097] In some embodiments, the yield prediction model includes an improvement coefficient and a prediction year; the improvement coefficient combined with the prediction year represents the impact of non-environmental factors on apple yield;

[0098] The prediction module 302 is specifically used for:

[0099] The disaster sample data within the time period to be predicted, the meteorological sample data of each day, the number of apple trees and the year are input into the yield prediction model to obtain the apple yield prediction result within the time period to be predicted.

[0100] Please refer to Figure 4 As shown, a schematic diagram of the structure of an electronic device 400 provided in an embodiment of the present application. The electronic device 400 may include at least: at least one processor 401, such as a CPU, at least one network interface 404, a user interface 403, a memory 405, and at least one communication bus 402. Among them, the communication bus 402 is used to realize the connection and communication between these components. The user interface 403 may include but is not limited to a display, a touch screen, a keyboard, a mouse, a joystick, etc. The network interface 404 may optionally include a standard wired interface, a wireless interface (such as a WIFI interface), and a communication connection can be established with a server through the network interface 404. The memory 402 may be a high-speed RAM memory, or it may be a non-volatile memory (non-volatile memory), such as at least one disk storage. As Figure 4As shown, the memory 405 as a computer storage medium may include an operating system, a network communication module, a user interface module, and program instructions.

[0101] It should be noted that the network interface 404 can be connected to an acquirer, a transmitter or other communication modules. Other communication modules may include but are not limited to WiFi modules, operator network communication modules, etc. It can be understood that the electronic device in the embodiment of the present application may also include an acquirer, a transmitter and other communication modules.

[0102] The processor 401 may be used to call the program instructions stored in the memory 405, and may execute the following method:

[0103] Acquire the data to be predicted; the data to be predicted includes disaster sample data within the target time period and meteorological sample data for each day;

[0104] The data to be predicted is input into the yield prediction model to obtain the apple yield prediction result within the time period to be predicted; the disaster sample data within the target time period and the meteorological sample data of each day are used to predict the apple yield within the time period to be predicted in the same year; the yield prediction model is trained by multiple sample data, each of the sample data includes the disaster sample data within the preset time period and the meteorological sample data of each day and the apple yield sample data of the same year as the preset time period.

[0105] Possibly, before obtaining the data to be predicted, the processor 401 is further configured to execute:

[0106] Acquire a plurality of the sample data;

[0107] A plurality of the sample data are trained to obtain the yield prediction model.

[0108] Possibly, after the processor 401 acquires the plurality of sample data and before the processor 401 trains the plurality of sample data, the processor 401 is further configured to execute:

[0109] Outliers are removed from the sample data; the outliers include values ​​where the annual apple production is less than a preset minimum value or greater than a preset maximum value.

[0110] Possibly, the processor 401 removes outliers from the sample data by specifically performing:

[0111] The box plot is used to remove outliers from the sample data.

[0112] Possibly, the processor 401 inputs the data to be predicted into a yield prediction model to obtain the apple yield prediction result within the time period to be predicted, and specifically executes:

[0113] Input the disaster sample data within the time period to be predicted and the meteorological sample data of each day into the yield prediction model to obtain the frost damage mortality rate, hail mortality rate, flower and fruit thinning rate and fruit growth rate;

[0114] The amount of fruit on each apple tree is determined according to the frost-related mortality rate, the hail-related mortality rate and the flower and fruit thinning rate; and the weight of each apple is determined according to the fruit growth rate;

[0115] The apple yield forecast result within the forecast time period is obtained based on the amount of fruit on each apple tree, the weight of each apple and the number of apple trees.

[0116] Possibly, the meteorological sample data includes at least one of the following: the lowest temperature of each day, the total duration of each day when the temperature is below a preset threshold, and the daily precipitation; the disaster sample data includes at least one of the following: the number of frost disasters during the apple blossom period, the number of hail disasters during the apple blossom period, and the amount of fruit on each apple tree after experiencing frost disasters and hail disasters;

[0117] The processor 401 inputs the disaster sample data within the time period to be predicted and the meteorological sample data of each day into the yield prediction model to obtain the frost mortality rate, hail mortality rate, flower and fruit thinning rate and fruit growth rate, and specifically performs:

[0118] The frost damage mortality rate is obtained based on the daily minimum temperature, the total duration of each day when the temperature is below the preset threshold, and the number of frost damage disasters occurring during the apple flowering period; the hail mortality rate is obtained based on the number of hail disasters occurring during the apple flowering period; the flower and fruit thinning rate is obtained based on the amount of fruit on each apple tree after experiencing frost damage and hail disasters; and the fruit growth rate is obtained based on the daily precipitation.

[0119] Possibly, the yield prediction model includes an improvement coefficient and a prediction year; the improvement coefficient combined with the prediction year characterizes the impact of non-environmental factors on apple yield;

[0120] The processor 401 inputs the data to be predicted into the yield prediction model to obtain the apple yield prediction result within the time period to be predicted, and specifically performs:

[0121] The disaster sample data within the time period to be predicted, the meteorological sample data of each day, the number of apple trees and the year are input into the yield prediction model to obtain the apple yield prediction result within the time period to be predicted.

[0122] The embodiment of the present application also provides a computer-readable storage medium, which stores instructions, and when the instructions are executed on a computer or a processor, the computer or the processor executes one or more steps in any of the above methods. If the above-mentioned apple production prediction device and each component module of the electronic device are implemented in the form of software functional units and sold or used as independent products, they can be stored in the computer-readable storage medium.

[0123] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted by the computer-readable storage medium. The computer instructions can be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (Digital Subscriber Line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server, a data center, etc. that contains one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a digital versatile disk (DVD), or a semiconductor medium (e.g., a solid state disk (SSD)), etc.).

[0124] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The aforementioned storage medium includes: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes. In the absence of conflict, the technical features in this embodiment and the implementation scheme can be combined arbitrarily.

[0125] The embodiments described above are merely preferred embodiments of the present application and are not intended to limit the scope of the present application. Without departing from the design spirit of the present application, various modifications and improvements made to the technical solutions of the present application by ordinary technicians in this field should fall within the protection scope determined by the claims of the present application.

Claims

1. A method for predicting apple yield, characterized in that: The method comprises: Acquire the data to be predicted; the data to be predicted includes disaster sample data within the target time period and meteorological sample data for each day; The data to be predicted is input into the yield prediction model to obtain the apple yield prediction result within the time period to be predicted; the disaster sample data within the target time period and the meteorological sample data of each day are used to predict the apple yield within the time period to be predicted in the same year; the yield prediction model is trained by a plurality of sample data, each of which includes the disaster sample data within a preset time period and the meteorological sample data of each day and the apple yield sample data of the same year as the preset time period; The step of inputting the data to be predicted into a yield prediction model to obtain an apple yield prediction result within a time period to be predicted includes: Input the disaster sample data within the time period to be predicted and the meteorological sample data of each day into the yield prediction model to obtain the frost damage mortality rate, hail mortality rate, flower and fruit thinning rate and fruit growth rate; Determine the amount of fruit on each apple tree according to the initial flower amount, the frost injury mortality rate, the hail mortality rate and the flower and fruit thinning rate; Combining Richards theoretical growth equation and Logistic growth equation, determining the weight of each apple according to the fruit growth rate; The apple yield forecast result within the forecast time period is obtained based on the amount of fruit on each apple tree, the weight of each apple and the number of apple trees.

2. The method according to claim 1, characterized in that Before obtaining the data to be predicted, the method further includes: Acquire a plurality of the sample data; A plurality of the sample data are trained to obtain the yield prediction model.

3. The method according to claim 2, characterized in that After acquiring the plurality of sample data and before training the plurality of sample data, the method further includes: Outliers are removed from the sample data; the outliers include values ​​where the annual apple production is less than a preset minimum value or greater than a preset maximum value.

4. The method according to claim 3, characterized in that The step of removing outliers from the sample data includes: The box plot is used to remove outliers from the sample data.

5. The method according to claim 4, characterized in that The meteorological sample data includes at least one of the following: the lowest temperature of each day, the total duration of each day when the temperature is below the preset threshold, and the daily precipitation; the disaster sample data includes at least one of the following: the number of frost disasters during the apple flowering period, the number of hail disasters during the apple flowering period, and the amount of fruit on each apple tree after experiencing frost disasters and hail disasters; The disaster sample data within the time period to be predicted and the meteorological sample data of each day are input into the yield prediction model to obtain the frost mortality rate, hail mortality rate, flower and fruit thinning rate and fruit growth rate, including: The frost damage mortality rate is obtained based on the daily minimum temperature, the total duration of each day when the temperature is below the preset threshold, and the number of frost damage disasters occurring during the apple flowering period; the hail mortality rate is obtained based on the number of hail disasters occurring during the apple flowering period; the flower and fruit thinning rate is obtained based on the amount of fruit on each apple tree after experiencing frost damage and hail disasters; and the fruit growth rate is obtained based on the daily precipitation.

6. The method according to claim 1, characterized in that The yield prediction model includes an improvement coefficient and a prediction year; the improvement coefficient combined with the prediction year represents the impact of non-environmental factors on apple yield; The step of inputting the data to be predicted into a yield prediction model to obtain an apple yield prediction result within a time period to be predicted includes: The disaster sample data within the time period to be predicted, the meteorological sample data of each day, the number of apple trees and the year are input into the yield prediction model to obtain the apple yield prediction result within the time period to be predicted.

7. A device for predicting apple yield, characterized in that: The device comprises: The first acquisition module is used to acquire the data to be predicted; the data to be predicted includes disaster sample data within the target time period and meteorological sample data of each day; A prediction module is used to input the data to be predicted into a yield prediction model to obtain the apple yield prediction result within the time period to be predicted; the disaster sample data within the target time period and the meteorological sample data of each day are used to predict the apple yield within the time period to be predicted in the same year; the yield prediction model is trained by a plurality of sample data, each of which includes the disaster sample data within a preset time period and the meteorological sample data of each day and the apple yield sample data of the same year as the preset time period; The prediction module is specifically used to input the disaster sample data within the predicted time period and the meteorological sample data of each day into the yield prediction model to obtain the frost mortality rate, hail mortality rate, flower and fruit thinning rate and fruit growth rate; Determine the amount of fruit on each apple tree according to the initial flower amount, the frost injury mortality rate, the hail mortality rate and the flower and fruit thinning rate; Combining Richards theoretical growth equation and Logistic growth equation, the weight of each apple is determined according to the fruit growth rate; The apple yield forecast result within the forecast time period is obtained based on the amount of fruit on each apple tree, the weight of each apple and the number of apple trees.

8. An electronic device, characterized in that: Including processor, memory and communication interface: The processor is connected to the memory and the communication interface; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the apple yield prediction method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for predicting apple yield as described in any one of claims 1 to 6 is implemented.

Images