Orchard meteorological disaster monitoring and early warning method and system based on big data

Abstract

The invention discloses an orchard meteorological disaster monitoring and early warning method based on big data. The method comprises the steps of collecting data information; analyzing and processing the data information; predicting an orchard meteorological disaster model; according to the data early warning processing, an orchard meteorological disaster monitoring and early warning system based on big data comprises remote sensing equipment; internet of things; a processing unit; an edge cloud computer and a mobile terminal; data information of an orchard environment is collected through a remote sensing technology, and the trend of a cloud and rain layer is predicted in combination with predicted rainfall; calculating the prediction of the motion trail of the cloudy and rainy layer and the calculation prediction of the rainfall through a genetic algorithm, calculating and obtaining the possibility of the cloudy and rainy layer moving to the upper part of the orchard, and calculating whether the rainfall causes waterlogging and whether drought occurs or not according to disaster indexes; the collected data information is calculated and processed through the edge cloud computer, so that an orchard person in charge can obtain early warning of disasters in time, and safety protection processing is carried out.

Description

Technical Field

[0001] The present invention relates to the technical field of early warning technology for meteorological disasters in orchards, and in particular to a method and system for monitoring and early warning of meteorological disasters in orchards based on big data. Background Art

[0002] The fruit industry is an important source of income for the vast rural agricultural economy. It is of great significance to improve the living standards of local people and promote the development of local agricultural economy. In recent years, the agricultural industrial structure has changed rapidly. The most prominent point is that the planting area of ​​fruit trees with both edible value and economic value has increased significantly. With the expansion of the scale of economic forestry and fruit industry, the instability of the economic benefits of fruit trees caused by meteorological disasters has attracted more attention from the government, fruit farmers and related researchers, prompting the study of meteorological disasters for fruit trees to gradually become one of the hot issues in the study of agricultural meteorological disasters in recent years. Among them, the research on the indicators of meteorological disasters affecting fruit trees is particularly important. It is an inevitable link in the research of disaster monitoring, early warning, defense, planting planning, risk zoning, etc.

[0003] The monitoring and prediction of meteorological disasters are generally achieved by detecting various disaster indicators. The continuous development and progress of disaster detection and prediction technology has made great contributions to the prevention and response to meteorological disasters in orchards, and is of great significance to the stable production and development of orchards.

[0004] Drought and waterlogging refer to the phenomenon of persistent water shortage or water surplus caused by imbalance of water income and expenditure or supply and demand. The meteorological drought phenomenon is that the precipitation in a certain area in a certain period of time is significantly less than its multi-year average, while the excessive precipitation is waterlogging, which is the direct cause of drought and waterlogging disasters for fruit trees.

[0005] In the Chinese invention patent with application publication number CN115762062B, a kiwifruit orchard meteorological disaster monitoring and early warning method and device are disclosed, which obtains the predicted meteorological data in the future preset time period predicted by the meteorological observation station corresponding to the target area at each preset time interval, thereby obtaining the kiwifruit canopy temperature data in the future preset time period according to the predicted meteorological data and the kiwifruit canopy temperature prediction model, and then obtains the predicted temperature data of the target position on the kiwifruit tree in the future preset time period according to the kiwifruit canopy temperature data and the kiwifruit target position temperature prediction model, and determines the disaster information of the target position on the kiwifruit tree in the kiwifruit orchard in the target area in the future preset time period according to the predicted temperature data of the target position on the kiwifruit tree and the corresponding relationship between the disaster level and the temperature range of the target position on the kiwifruit tree. Timely and accurate prediction of kiwifruit meteorological disaster information is achieved.

[0006] However, in combination with the existing technology and the above application, there are still some problems in the existing technology. For example, it is impossible to predict the precipitation in the orchard based on various data information in the environment, which may easily lead to inaccurate precipitation prediction, prone to drought or waterlogging, and the processing of data information is relatively simple, unable to detect according to environmental factors, and the prediction results are relatively single.

[0007] To this end, the present invention provides an orchard meteorological disaster monitoring and early warning method and system based on big data. Summary of the invention

[0008] 1. Technical issues to be solved

[0009] In view of the deficiencies in the prior art, the present invention provides an orchard meteorological disaster monitoring and early warning method and system based on big data, which collects environmental data information of the orchard through remote sensing technology, classifies the collected data information according to the collected items, and combines the data information. After the combined processing, the rainfall amount is calculated and processed, and the movement trajectory of the cloud and rain layer is calculated and predicted to determine whether the cloud and rain layer will move above the orchard, and then the disaster is predicted and processed through a genetic algorithm to achieve early warning of the disaster, thereby solving the technical problems recorded in the background technology.

[0010] (II) Technical solution

[0011] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0012] A method for monitoring and early warning of meteorological disasters in orchards based on big data, comprising:

[0013] Collect data information, collect data information of the orchard environment through remote sensing technology, and construct a climate condition set with the collected data information, including temperature set X w , wind direction set X x , wind speed set X s , Cloud and Rain Layer Collection X y , air pressure set X q ;

[0014] Analyze and process the data information and combine it with the temperature set X w , Cloud and Rain Layer Collection X y , air pressure set X q Predict the amount of rain in the orchard, and the temperature and cloud layer composition data set (X w , X y ), and through the wind direction set X x , wind speed set X s Predict the direction of the cloud and rain layer, and the wind direction and wind speed constitute the data set (X x, X s );

[0015] And the calculation formula for the rainfall is as follows: Let the rainfall be C,

[0016] where n is the number of collected data information, i is the position of the collected data information, is the average value of the data information, and w1, w2, and w3 are the weight values of temperature, cloud and rain layer, and air pressure respectively;

[0017] The moving trajectory of the cloud and rain: The calculation formula is as follows, and let the trajectory path be S,

[0018] where n is the number of collected data information, i is the position of the collected data information, and θ is the moving trajectory angle between the cloud and rain layer and the orchard center on the horizontal plane;

[0019] The prediction of the orchard meteorological disaster model is to predict and process the orchard meteorological disaster through the genetic algorithm, that is, to predict the arrival of the cloud and rain layer through the trajectory path S, and to calculate and determine whether there will be a disaster of excessive rain through the rainfall C;

[0020] That is, through the genetic algorithm, calculate the prediction of the cloud and rain layer moving to the orchard under the action of the trajectory path;

[0021] Data warning processing, disaster index Z, In the formula: T is the continuous rain index, that is, the rainfall time; D is the drought degree of the orchard, and a disaster threshold K is set. If Z > K, an alarm is triggered to realize disaster warning. If Z < K, no alarm is triggered and it is normal rainfall.

[0022] Furthermore, set the initial population of the genetic algorithm:

[0023]

[0024] where X i,j (0) is the combined function of the i-th rainfall C and the j-th trajectory path S;

[0025]

[0026] where, and are the left and right boundaries of the trajectory path respectively, and rand(0,1) represents a random number in the interval [0,1];

[0027] The prediction calculation of the cloud and rain layer moving to the orchard under the action of the trajectory path to determine whether the cloud and rain layer will move above the orchard.

[0028] Furthermore, the orchard drought degree D is calculated as follows:

[0029] D = water requirement during the growing period / precipitation during the growing period × number of days without precipitation / number of days during the growing period ≈ number of days without precipitation / precipitation during the growing period × k;

[0030] In the formula: D is the drought index of different fruit areas; the two indicators "water requirement during the growing period" and "number of days in the growing period" are relatively stable and are regarded as constants. Therefore, k is used to represent the ratio of "water requirement during the growing period" and "number of days in the growing period", and the formula is simplified to the right part; obviously, the larger the D during the growing period, the more severe the drought.

[0031] Furthermore, remote sensing technology collects data information about the orchard environment and performs linear normalization processing, and maps the corresponding data values ​​to the interval [0,1] according to the following formula:

[0032]

[0033] Weight coefficient: 0≤ρ≤1, 0≤ζ≤1, and ρ+ζ=1;

[0034] Where X is the collected data information, and Y is the output value after normalization processing. The collected data information is reduced in dimension through linear normalization processing to improve the calculation efficiency of the data information and reduce the calculation pressure.

[0035] Furthermore, when calculating the trajectory path, the possibility of the travel path is calculated by Bayesian theorem to predict the trajectory path;

[0036]

[0037] P(c|x) is the probability of given trajectory synthetic data x, c is the trajectory path;

[0038] P(x|c) is the probability that x is the trajectory synthesis given the predicted trajectory path c;

[0039] S0 is the original trajectory path;

[0040] P(x) is the probability of the prediction calculation;

[0041] That is, through the calculation of the original trajectory path, the trajectory path and the trajectory synthesis, the probability of the cloud and rain layer's travel path is calculated, which facilitates the prediction and processing of disasters.

[0042] Furthermore, the weight values ​​of w1, w2, and w3 are assigned and calculated as follows:

[0043] Among them, n is the amount of each data collection, i is the data position, and m is the proportion of each data in the total data;

[0044] That is, the data information collected by temperature, cloud and rain layer and air pressure accounts for the total amount of data information, and the weight distribution is determined according to the distribution ratio;

[0045] And m is calculated as follows:

[0046] Among them, κ+κ+λ=0.1, and the proportion of each data in the total data is obtained by calculating the average value of temperature, cloud and rain layer and air pressure data.

[0047] An orchard meteorological disaster monitoring and early warning system based on big data, including:

[0048] Remote sensing equipment collects environmental data and obtains information about the earth's surface through satellites and drones. Remote sensing technology provides meteorological data to help analyze the occurrence, evolution and early warning of meteorological disasters, obtain data from meteorological disaster sites in real time, conduct data analysis and simulation, and improve disaster monitoring efficiency and accuracy.

[0049] Internet of Things: The collected data information can be transmitted through the Internet of Things or satellite communications, and the data information can be transmitted to the edge computer. The edge computer can calculate and process the data information, and obtain monitoring and early warning of meteorological disasters in the orchard through the calculation and processing of big data information.

[0050] The processing unit is used to process the data information collected by the remote sensing equipment to improve the accuracy of the data information. The processing module is used to receive, filter, convert, clean and amplify the data information;

[0051] Edge cloud computer: After receiving and processing the data information transmitted by the remote sensing equipment through the processing module, the edge cloud computer performs calculations and processing through the calculation formula of rainfall, the trajectory of cloud and rain, and the prediction model of orchard meteorological disasters, so as to realize data early warning processing of orchard disasters;

[0052] The mobile terminal receives the data warning calculation results processed by the edge cloud computer through the Internet of Things, and then the orchard manager takes preventive measures.

[0053] Furthermore, the processing module includes a receiving module for acquiring data information, a filtering module for filtering out clutter from the data information, a conversion module for performing analog-to-digital conversion on the data information, a cleaning module for removing abnormal data from the data information, and a gain module for amplifying the data information;

[0054] The calculation formula of the filter module is as follows:

[0055] Mean filter: The mean filter specifies a window with an odd length, uses the average value of all data in the window to replace the value in the middle, and then translates the window with a step size of 1. Repeat the above operation until it slides to the end of the time series data. The calculation formula of the mean filter is as follows:

[0056]

[0057] in, Represents the output data set after mean filtering, m represents the size of the window, v(n) j Represents the jth data information in the input data set.

[0058] Furthermore, the algorithm used by the cleaning module is a linear regression algorithm. In the linear regression algorithm, the data information is set to be Y and X, and X is the input value of each data, and the dependency relationship between Y and X is expressed as:

[0059] Y i =α+βX i +ε i ;

[0060] Among them, α and β are constants, ε i The random disturbance term is a random variable that cannot be directly observed. i represents the number of items of the i-th data information. α and β are collectively referred to as the parameters of the overall regression equation. α is the constant term of the overall regression equation, and the intercept of the overall regression line on the Y-axis. β is the overall regression coefficient. The data information far away from the regression line is listed as abnormal data through the linear regression algorithm, and the abnormal data is eliminated.

[0061] Furthermore, the cleaning module determines the distance away from the data by first determining the center value of the data information;

[0062] Among them, X is the collected data information, n is the number of collected data information, and z0 is the average value of all data;

[0063] For the distance away from the cluster center, it is Where X is the calculated data information, d is the distance between the data information and the average value, and if the distance between the data information is greater than 2d, the voltage peak signal is determined to be abnormal data information.

[0064] (III) Beneficial effects

[0065] The present invention provides a method and system for monitoring and early warning of meteorological disasters in orchards based on big data, which has the following beneficial effects:

[0066] When the present invention is used, data information of the orchard environment is collected by remote sensing technology, and the temperature set X is classified according to different collection directions.w , the wind direction set X x , the wind speed set X s , the cloud and rain layer set X y , the air pressure set X q , and by combining the temperature set X w , the cloud and rain layer set X y , the air pressure set X q to predict the rainfall, and the temperature and the cloud and rain layer form a data set (X w , X y ), and by the wind direction set X x , the wind speed set X s to predict the movement direction of the cloud and rain layer, and the wind direction and the wind speed form a data set (X x , X s );

[0067] And through the genetic algorithm to calculate the prediction of the movement trajectory of the cloud and rain layer and the calculation prediction of the rainfall, calculate the possibility that the cloud and rain layer moves above the orchard, and calculate according to the disaster index whether the rainfall will cause waterlogging and whether drought will occur, and set the disaster threshold K. If Z > K, then trigger an alarm to realize disaster early warning. If Z < K, then do not trigger an alarm and it is normal rainfall;

[0068] And through the edge cloud computer to calculate and process the collected data information, it can effectively reduce the resource construction of the orchard, that is, send the signal of the collected data information through the mobile terminal, and transmit the collected data information to the edge cloud computer for calculation and processing, and then transmit the calculated and processed prediction information to the mobile terminal, so that the orchard person in charge can timely obtain the disaster early warning and make safety protection treatment. Brief Description of the Drawings

[0069] Figure 1 is a schematic diagram of the steps of the orchard meteorological disaster monitoring and early warning method based on big data of the present invention;

[0070] Figure 2 is a schematic diagram of the structure of the orchard meteorological disaster monitoring and early warning system based on big data of the present invention. Detailed Embodiment

[0071] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0072] Please refer to Figure 1The present invention provides an orchard meteorological disaster monitoring and early warning method based on big data, comprising:

[0073] Collect data information, collect data information of the orchard environment through remote sensing technology, and construct a climate condition set with the collected data information, including temperature set X w , wind direction set X x , wind speed set X s , Cloud and Rain Layer Collection X y , air pressure set X q ;

[0074] Analyze and process the data information and combine it with the temperature set X w , Cloud and Rain Layer Collection X y , air pressure set X q Predict the amount of rain in the orchard, and the temperature and cloud layer composition data set (X w , X y ), and through the wind direction set X x , wind speed set X s Predict the direction of the cloud and rain layer, and the wind direction and wind speed constitute the data set (X x , X s );

[0075] The calculation formula for rainfall is as follows: Assuming the rainfall amount is C,

[0076] Where n is the number of collected data information, i is the location of the collected data information, is the average value of data information, w1, w2, w3 are the weight values ​​of temperature, cloud and rain layer, and air pressure respectively;

[0077] The trajectory of clouds and rain: The calculation formula is as follows, and the trajectory path is set to S.

[0078] Where n is the number of data information collected, i is the location of the collected data information, and θ is the angle between the moving trajectory of the cloud and rain layer and the center of the orchard on the horizontal plane;

[0079] Orchard meteorological disaster model prediction, through the genetic algorithm to achieve orchard meteorological disaster prediction processing, that is, through the trajectory path S, predict the arrival of the cloud and rain layer, and through the rainfall C, calculate and determine whether there will be excessive rainfall disasters;

[0080] That is, through genetic algorithm, the prediction calculation of the cloud and rain layer moving to the orchard under the action of the trajectory path is calculated;

[0081] Data warning processing, disaster index Z, Where: T is the continuous rain index, which is the rainfall time; D is the drought degree of the orchard, and a disaster threshold K is set. If Z > K, an alarm is triggered to achieve disaster early warning. If Z < K, no alarm is triggered, and it is normal rainfall.

[0082] In order to predict the movement trajectory of the cloud and rain layer and facilitate predicting the possibility of the cloud and rain layer moving above the orchard, in this embodiment, preferably, the initial population of the genetic algorithm is set:

[0083]

[0084] Among them, X i,j (0) is the combined function of the i-th rainfall amount C and the j-th trajectory path S;

[0085]

[0086] Among them, and are respectively the left and right boundaries of the trajectory path, and rand(0,1) represents a random number in the interval [0,1];

[0087] Under the action of the trajectory path of the cloud and rain layer, the prediction calculation of moving to the orchard is carried out to determine whether the cloud and rain layer will move above the orchard.

[0088] In order to calculate and detect the drought degree of the orchard and facilitate calculation and processing, in this embodiment, preferably, the calculation of the orchard drought degree D is as follows:

[0089] D = water requirement during the growth period / precipitation during the growth period × number of non-rainy days / number of days during the growth period ≈ number of non-rainy days / precipitation during the growth period × k;

[0090] Where: D is the drought index of different fruit-growing areas; in the formula, the two indicators of "water requirement during the growth period" and "number of days during the growth period" are relatively stable and regarded as constants. Therefore, k represents the ratio of "water requirement during the growth period" to "number of days during the growth period", and the formula is simplified to the right part; obviously, the larger the D during the growth period, the more serious the drought situation.

[0091] In order to perform linear normalization processing on the data information so that the data information can be mapped in [0,1], making the data information convenient for calculation and processing, improving the efficiency of data calculation and reducing the calculation pressure, in this embodiment, preferably, the data information collected by remote sensing technology for the orchard environment is subjected to linear normalization processing, and the corresponding data values are mapped into the interval [0,1] according to the following formula:

[0092]

[0093] Weight coefficients: 0 ≤ ρ ≤ 1, 0 ≤ ζ ≤ 1, and ρ + ζ = 1;

[0094] Where X is the collected data information, and Y is the output value after normalization processing. The collected data information is reduced in dimension through linear normalization processing to improve the calculation efficiency of the data information and reduce the calculation pressure.

[0095] In order to calculate the possibility of the movement trajectory of the cloud and rain layer, so as to facilitate the determination of the movement trajectory of the cloud and rain layer, in this embodiment, preferably, when calculating the trajectory path, the possibility of the travel path is calculated by Bayesian theorem to predict the trajectory path;

[0096]

[0097] P(c|x) is the probability of given trajectory synthetic data x, c is the trajectory path;

[0098] P(x|c) is the probability of x being the trajectory synthesis given the predicted trajectory path c;

[0099] S0 is the original trajectory path;

[0100] P(x) is the probability of the prediction calculation;

[0101] That is, through the calculation of the original trajectory path, the trajectory path and the trajectory synthesis, the probability of the cloud and rain layer's travel path is calculated, which facilitates the prediction and processing of disasters.

[0102] In order to achieve weight allocation for different temperatures, cloud and rain layers and air pressures, that is, to determine the importance of temperature, cloud and rain layers and air pressure through weight allocation, so as to facilitate the prediction and calculation of rainfall, in this embodiment, preferably, the weight values ​​of w1, w2 and w3 are allocated, and the calculation process is as follows:

[0103] Among them, n is the amount of each data collection, i is the data position, and m is the proportion of each data in the total data;

[0104] That is, the data information collected by temperature, cloud and rain layer and air pressure accounts for the total amount of data information, and the weight distribution is determined according to the distribution ratio;

[0105] And m is calculated as follows:

[0106] Among them, κ+κ+λ=0.1, and the proportion of each data in the total data is obtained by calculating the average value of temperature, cloud and rain layer and air pressure data.

[0107] See also Figure 2 , a big data-based orchard meteorological disaster monitoring and early warning system, including:

[0108] Remote sensing equipment collects environmental data and obtains information about the earth's surface through satellites and drones. Remote sensing technology provides meteorological data to help analyze the occurrence, evolution and early warning of meteorological disasters, obtain data from meteorological disaster sites in real time, conduct data analysis and simulation, and improve disaster monitoring efficiency and accuracy.

[0109] Internet of Things: The collected data information can be transmitted through the Internet of Things or satellite communications, and the data information can be transmitted to the edge computer. The edge computer can calculate and process the data information, and obtain monitoring and early warning of meteorological disasters in the orchard through the calculation and processing of big data information.

[0110] The processing unit is used to process the data information collected by the remote sensing equipment to improve the accuracy of the data information. The processing module is used to receive, filter, convert, clean and amplify the data information;

[0111] Edge cloud computer: After receiving and processing the data information transmitted by the remote sensing equipment through the processing module, the edge cloud computer performs calculations and processing through the calculation formula of rainfall, the trajectory of cloud and rain, and the prediction model of orchard meteorological disasters, so as to realize data early warning processing of orchard disasters;

[0112] The mobile terminal receives the data warning calculation results processed by the edge cloud computer through the Internet of Things, and then the orchard manager takes preventive measures.

[0113] In order to process the collected environmental data information, improve the accuracy of the data information, facilitate subsequent calculation and processing of the data information, and eliminate noise in the data information transmission process, in this embodiment, preferably, the processing module includes a receiving module for acquiring the data information, a filtering module for filtering out clutter from the data information, a conversion module for performing analog-to-digital conversion on the data information, a cleaning module for removing abnormal data from the data information, and a gain module for amplifying the data information;

[0114] The calculation formula of the filter module is as follows:

[0115] Mean filter: The mean filter specifies a window with an odd length, uses the average value of all data in the window to replace the value in the middle, and then translates the window with a step size of 1. Repeat the above operation until it slides to the end of the time series data. The calculation formula of the mean filter is as follows:

[0116]

[0117] in, Represents the output data set after mean filtering, m represents the size of the window, v(n)j Represents the jth data information in the input data set.

[0118] In order to eliminate abnormal error information in the data information, maintain the accuracy of the data information, and facilitate the accuracy of subsequent prediction calculations, in this embodiment, preferably, the algorithm used by the cleaning module is a linear regression algorithm. In the linear regression algorithm, the data information is Y and X, and X is the input value of each data, and the dependency relationship between Y and X is expressed as:

[0119] Y i =α+βX i +ε i ;

[0120] Among them, α and β are constants, ε i The random disturbance term is a random variable that cannot be directly observed. i represents the number of items of the i-th data information. α and β are collectively referred to as the parameters of the overall regression equation. α is the constant term of the overall regression equation, and the intercept of the overall regression line on the Y-axis. β is the overall regression coefficient. The data information far away from the regression line is listed as abnormal data through the linear regression algorithm, and the abnormal data is eliminated.

[0121] In order to determine the abnormal data information and to facilitate the elimination of the abnormal data information, in this embodiment, preferably, the cleaning module determines the distance away and first determines the center value of the data information;

[0122] Among them, X is the collected data information, n is the number of collected data information, and z0 is the average value of all data;

[0123] For the distance away from the cluster center, it is Where X is the calculated data information, d is the distance between the data information and the average value, and if the distance between the data information is greater than 2d, the voltage peak signal is determined to be abnormal data information.

[0124] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments 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 or computer programs. When the computer instructions or computer programs are loaded or 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 device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0125] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein 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.

[0126] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0127] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only some logical function divisions. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0128] 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, that is, they 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.

[0129] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0130] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0131] 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.

[0132] 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 monitoring and early warning of meteorological disasters in orchards based on big data, characterized in that: Included are: Collect data information, collect data information of the orchard environment through remote sensing technology, and construct a climate condition set with the collected data information, including temperature set X w , wind direction set X x , wind speed set X s , Cloud and Rain Layer Collection X y , air pressure set X q ; Analyze and process the data information and combine it with the temperature set X w , Cloud and Rain Layer Collection X y , air pressure set X q Predict the amount of rain in the orchard, and the temperature and cloud layer composition data set (X w , X y ), and through the wind direction set X x , wind speed set X s Predict the direction of the cloud and rain layer, and the wind direction and wind speed constitute the data set (X x , X s ); The calculation formula for rainfall is as follows: Assuming the rainfall amount is C, Where n is the number of collected data information, i is the location of the collected data information, is the average value of data information, w1, w2, w3 are the weight values ​​of temperature, cloud and rain layer, and air pressure respectively; The trajectory of clouds and rain: The calculation formula is as follows, and the trajectory path is set to S. Where n is the number of data information collected, i is the location of the collected data information, and θ is the angle between the moving trajectory of the cloud and rain layer and the center of the orchard on the horizontal plane; Orchard meteorological disaster model prediction, through the genetic algorithm to achieve orchard meteorological disaster prediction processing, that is, through the trajectory path S, predict the arrival of the cloud and rain layer, and through the rainfall C, calculate and determine whether there will be excessive rainfall disasters; That is, through genetic algorithm, the prediction calculation of the cloud and rain layer moving to the orchard under the action of the trajectory path is calculated; Data warning processing, disaster index Z Where: T is the continuous rainy day index, which is the rainfall time; D is the drought degree of the orchard, and a disaster threshold K is set. If Z > K, an alarm is triggered to achieve disaster warning. If Z < K, no alarm is triggered, and it is normal rainfall.

2. The method for monitoring and early warning of orchard meteorological disasters based on big data according to claim 1, characterized in that: Set the initial population of the genetic algorithm: Among them, X i,j (0) is the combined function of the i-th rainfall amount C and the j-th trajectory path S; in, and are the left and right boundaries of the trajectory path, respectively, and rand(0,1) represents a random number in the interval [0,1]; The cloud and rain layer moves to the orchard under the action of the trajectory path, and the prediction calculation determines whether the cloud and rain layer will move above the orchard.

3. The method for monitoring and early warning of meteorological disasters in orchards based on big data according to claim 1, characterized in that: The calculation of orchard drought degree D is as follows: D = water requirement during the growing period / precipitation during the growing period × number of days without precipitation / number of days during the growing period ≈ number of days without precipitation / precipitation during the growing period × k; In the formula: D is the drought index of different fruit areas; the two indicators "water requirement during the growing period" and "number of days in the growing period" are relatively stable and are regarded as constants. Therefore, k is used to represent the ratio of "water requirement during the growing period" and "number of days in the growing period", and the formula is simplified to the right part; obviously, the larger the D during the growing period, the more severe the drought.

4. The method for monitoring and early warning of meteorological disasters in orchards based on big data according to claim 1 is characterized in that: Remote sensing technology collects data information about the orchard environment, performs linear normalization, and maps the corresponding data values ​​to the interval [0,1] according to the following formula: Weight coefficient: 0≤ρ≤1, 0≤ζ≤1, and ρ+ζ=1; Where X is the collected data information, and Y is the output value after normalization processing. The collected data information is reduced in dimension through linear normalization processing to improve the calculation efficiency of the data information and reduce the calculation pressure.

5. The orchard meteorological disaster monitoring and early warning method based on big data according to claim 1 is characterized by: When calculating the trajectory path, the possibility of the travel path is calculated using the Bayesian theorem to predict the trajectory path; P(cx) is the probability of given trajectory synthetic data x, c is the trajectory path; P(xc) is the probability of x being the trajectory synthesis given the predicted trajectory path c; S0 is the original trajectory path; P(x) is the probability of the prediction calculation; That is, through the calculation of the original trajectory path, the trajectory path and the trajectory synthesis, the probability of the cloud and rain layer's travel path is calculated, which facilitates the prediction and processing of disasters.

6. The method for monitoring and early warning of meteorological disasters in orchards based on big data according to claim 1 is characterized by: The weight values ​​of w1, w2, and w3 are assigned and calculated as follows: Among them, n is the amount of each data collection, i is the data position, and m is the proportion of each data in the total data; That is, the data information collected by temperature, cloud and rain layer and air pressure accounts for the total amount of data information, and the weight distribution is determined according to the distribution ratio; And m is calculated as follows: Among them, κ+κ+λ=0.1, and the proportion of each data in the total data is obtained by calculating the average value of temperature, cloud and rain layer and air pressure data.

7. An orchard meteorological disaster monitoring and early warning system based on big data, characterized in that: Included are: Remote sensing equipment collects environmental data and obtains information about the earth's surface through satellites and drones. Remote sensing technology provides meteorological data to help analyze the occurrence, evolution and early warning of meteorological disasters, obtain data from meteorological disaster sites in real time, conduct data analysis and simulation, and improve disaster monitoring efficiency and accuracy. Internet of Things: The collected data information can be transmitted through the Internet of Things or satellite communications, and the data information can be transmitted to the edge computer. The edge computer can calculate and process the data information, and obtain monitoring and early warning of meteorological disasters in the orchard through the calculation and processing of big data information. The processing unit is used to process the data information collected by the remote sensing equipment to improve the accuracy of the data information. The processing module is used to receive, filter, convert, clean and amplify the data information; Edge cloud computer: After receiving and processing the data information transmitted by the remote sensing equipment through the processing module, the edge cloud computer performs calculations and processing through the calculation formula of rainfall, the trajectory of cloud and rain, and the prediction model of orchard meteorological disasters, so as to realize data early warning processing of orchard disasters; The mobile terminal receives the data warning calculation results processed by the edge cloud computer through the Internet of Things, and then the orchard manager takes preventive measures.

8. The orchard meteorological disaster monitoring and early warning system based on big data according to claim 7 is characterized by: The processing module includes a receiving module for acquiring data information, a filtering module for filtering out clutter from the data information, a conversion module for performing analog-to-digital conversion on the data information, a cleaning module for removing abnormal data from the data information, and a gain module for amplifying the data information; The calculation formula of the filter module is as follows: Mean filter: The mean filter specifies a window with an odd length, uses the average value of all data in the window to replace the value in the middle, and then translates the window with a step size of 1. Repeat the above operation until it slides to the end of the time series data. The calculation formula of the mean filter is as follows: in, Represents the output data set after mean filtering, m represents the size of the window, v(n) j Represents the jth data information in the input data set.

9. The orchard meteorological disaster monitoring and early warning system based on big data according to claim 8 is characterized by: The algorithm used by the cleaning module is a linear regression algorithm. In the linear regression algorithm, the data information is set as Y and X, and X is the input value of each data, and the dependency relationship between Y and X is expressed as: Y i =α+βX i +e i ; Among them, α and β are constants, ε i The random disturbance term is a random variable that cannot be directly observed. i represents the number of items of the i-th data information. α and β are collectively referred to as the parameters of the overall regression equation. α is the constant term of the overall regression equation, and the intercept of the overall regression line on the Y-axis. β is the overall regression coefficient. The data information far away from the regression line is listed as abnormal data through the linear regression algorithm, and the abnormal data is eliminated.

10. The orchard meteorological disaster monitoring and early warning system based on big data according to claim 9, characterized in that: Included are: The cleaning module determines the distance away and first determines the center value of the data information; Among them, X is the collected data information, n is the number of collected data information, and z0 is the average value of all data; For the distance away from the cluster center, it is Where X is the calculated data information, d is the distance between the data information and the average value, and if the distance between the data information is greater than 2d, the voltage peak signal is determined to be abnormal data information.

Images