Multi-parameter Spatiotemporal Movement Comparison and Inspection Method for Operation Effect Region

Abstract

The present invention discloses a method for multi-parameter spatio-temporal moving contrast test in an operation effect area, which includes collecting working monitoring data of an artificial rainfall enhancement area and preprocessing the working monitoring data; obtaining a plurality of comparison parameters through the working monitoring data, selecting a catalyst diffusion and transmission scheme according to the operation mode to obtain an operation influence area; selecting an area not affected by the catalytic operation according to the operation influence area to obtain a comparison area, and performing a contrast test on the operation influence area and the comparison area according to the moving plurality of comparison parameters to obtain a contrast test formula; and using the rainfall amount to evaluate the post-operation effect according to the contrast test value to obtain the operation effect. This method can not only improve the accuracy of the multi-parameter spatio-temporal moving contrast test in the operation effect area, but also has good interpretability and can be directly applied to the multi-parameter spatio-temporal moving contrast test system in the operation effect area.

Description

Technical Field

[0001] The present invention relates to the field of comparative inspection, and particularly to a method for multi-parameter spatio-temporal movement comparative inspection of operation effect regions. Background Art

[0002] In recent years, with the continuous development of the national economy, society and industrialization, while bringing convenience to people, it has also brought some negative impacts. Meteorological disasters such as droughts, heavy rains and strong winds occur frequently. To solve these problems, the demand for artificial rain enhancement for drought resistance, artificial hail prevention and artificial rain reduction has been increasing, and artificial weather modification has received more extensive attention. With the increasing number of artificial catalysis operations, an inevitable problem is that we need to know whether there is an effect after the operation. However, the effect inspection after the operation is also a difficult point in artificial weather modification.

[0003] The effect inspection after the operation can be divided into physical inspection, statistical inspection and numerical simulation, etc. Statistical inspection is a basic effect inspection method, including randomized and non-randomized schemes. Well-known randomized experiments include the randomized cloud seeding experiment in Israel and the snow enhancement experiment in the United States. To evaluate the effect after the operation using statistical inspection, a randomized experiment should be carried out, and statistical data is used in the randomized trial. However, due to the long test period of the randomized trial, a large number of test samples are required, and it is difficult to exclude uncertain factors such as natural clouds. Therefore, the operation method in current actual operations is usually non-randomized; for numerical simulation inspection, the model inspection is to add a cloud seeding scheme in the model scheme to evaluate the effect after the operation, which depends on the accuracy of the numerical model; physical inspection is to study the changes in physical parameters during the cloud precipitation process after influencing the cloud to obtain the operation effect. For example, in some studies, a cloud groove or a stronger echo band formed by a large number of small ice crystals is observed on satellites and radars after cloud seeding. However, physical inspection cannot directly give a quantitative result, and it is not very applicable when a quantitative result is needed in many cases. Therefore, the present invention aims to invent a method for multi-parameter spatio-temporal movement comparative inspection of operation effect regions to improve the accuracy, timeliness and precision of effect inspection. Summary of the Invention

[0004] The object of the present invention is to provide a method for multi-parameter spatio-temporal movement comparative inspection of operation effect regions.

[0005] To achieve the above object, the present invention is implemented according to the following technical solution:

[0006] The present invention includes the following steps:

[0007] Collect the working monitoring data of the artificial rain enhancement region and preprocess the working monitoring data;

[0008] Multiple comparison parameters are obtained by selecting comparison parameters through the work monitoring data. According to the operation mode, a catalyst diffusion and transmission scheme is selected to obtain an operation influence area.

[0009] An area not affected by the catalytic operation is selected from the operation influence area to obtain a comparison area. The operation influence area and the comparison area are compared and tested according to the multiple moving comparison parameters to obtain a comparison test value.

[0010] The rainfall increment is used to evaluate the post-operation effect according to the comparison test value to obtain the operation effect.

[0011] Further, the method for obtaining multiple comparison parameters by selecting comparison parameters through the work monitoring data includes:

[0012] Parameters for the operation effect are obtained from the work monitoring data, and the correlation degree of the operation effect of the parameters is calculated:

[0013]

[0014] Where the b-th parameter is h b , and the correlation degree of the operation effect of parameter h b is The parameter h at the s-th moment b is h b (s), the parameter h at the s + 1-th moment b is h b (s + 1), the number of parameters is N, the probability of the parameter h b appearing is p(h b ), the sign function is sign(·), the actual operation effect after the change of the parameter h b is The predicted operation effect when the parameter h b is not changed is The weight of the parameter h b is η b , the error of the parameter h b is σ b , and the step function is δ|·|;

[0015] Parameters with an operation effect correlation degree greater than 0.3172 are used as candidate parameters, and the linear correlation degree between the candidate parameters is calculated:

[0016]

[0017] Where the average value of the b-th candidate parameter is The v-th candidate parameter is h v , and the average value of the v-th candidate parameter is The candidate parameter h b and the candidate parameter h vThe linear correlation degree is γ(h b ,h v ), the candidate parameter h b and the candidate parameter h v have a dissimilarity distance of The candidate parameter h b and the candidate parameter h v have a deviation of Δh b,v , and the similarity capacity parameter is ρ;

[0018] Calculate the change information degree between candidate parameters:

[0019]

[0020] Among them, the change information degree of the candidate parameter h b and the candidate parameter h v is ε b,v , the number of windows is p, and the probability of the deviation Δh b,v appearing is p(Δh b,v );

[0021] Calculate the change degree of candidate parameters:

[0022]

[0023] Among them, the importance of the candidate parameter h b is The scale factor is ζ, and the genetic coefficient is The error value is δ;

[0024] Output the candidate parameters with an importance greater than 0.137 as multiple comparison parameters.

[0025] Furthermore, the method for obtaining the operation influence area includes:

[0026] Obtain the operation area according to the catalyst diffusion transmission scheme, and calculate the change value of the multiple comparison parameters in the operation area;

[0027] Δu i,b = u io (s) - u i,b (s + j)

[0028] Among them, the b-th multiple comparison parameter of the i-th operation area is u i,b , the change value of the b-th multiple comparison parameter of the i-th operation area is Δu i,b , the initial value of the b-th multiple comparison parameter of the i-th operation area at the s-th moment is u io (s), and the b-th multiple comparison parameter of the i-th operation area at the s + j-th moment is u i,b (s + j);

[0029] The operation area where the change values of multiple comparison parameters are greater than 0.241 is used as the candidate impact area. According to the change values of multiple comparison parameters, primary division is carried out according to the criterion that the deviation is less than 0.216 to obtain the primary area;

[0030] Calculate the effect correlation degree of multiple comparison parameters:

[0031]

[0032] Among them, the external interference of the b-th multiple comparison parameter in the i-th primary area is B i,b , the number of multiple comparison parameters is N1, and the multiple comparison parameter u i,b The probability of occurrence is p(u i,b ), the importance weight of the b-th multiple comparison parameter in the i-th primary area is τ i,b , the multiple comparison parameter u i,b The effect correlation degree is

[0033] Construct an effect correlation matrix according to the effect correlation degree of multiple comparison parameters. Input the primary area into the convolutional neural network classification model and calculate the output of the convolutional layer:

[0034]

[0035] Among them, the output of the convolutional layer of the a-th area is D a , the activation function is θ, the output bias is M, the convolutional kernel size is Q, the classification boundary vector is d, the penalty coefficient is λ, and the numerical error of the z-th comparison parameter is ε b , the diagonal matrix is Σ, the effect correlation matrix of multiple comparison parameters in the a-th primary area is Z, the transpose is T, the effect correlation matrix of comparison parameters in different primary areas is R, and the first y columns of the effect correlation matrix of different primary areas are S y , the first y columns of the diagonal matrix are Σ y , the first y columns of the effect correlation matrix within the primary area are R y , the inverse matrix of the diagonal matrix is ∑ -1 , the number of primary areas is m;

[0036] Calculate the output category:

[0037]

[0038] Among them, the output of the fully connected layer of the a-th area is f a , the category of the a-th output is X a , the maximum pooling function value of the a-th area is W a , the moving length is ω, the pooling size is β, and the number of outputs is

[0039] Classify the output of the convolutional neural network classification model according to categories and output it as the operation impact area.

[0040] Furthermore, a method for obtaining a comparison area by selecting an area not affected by the catalytic operation according to the operation impact area includes:

[0041] Under the same weather influence system, select an area parallel to the operation impact area and perpendicular to the system moving direction, and not affected by the catalytic operation, and select an area with a location close to the impact area, the same shape and area as the comparison area.

[0042] Furthermore, a method for obtaining the comparison test formula includes:

[0043] Calculate the dynamic comparison values over time of multiple comparison parameters in the operation impact area and multiple comparison parameters in the comparison area:

[0044]

[0045] Where the operation impact area is c, the comparison area is c1, the b-th multiple comparison parameter at the s-th moment in the operation impact area is u c,b (s), the b-th multiple comparison parameter at the (s + j)-th moment in the operation impact area is u c,b (s + j), the b-th multiple comparison parameter at the s-th moment in the comparison area is The b-th multiple comparison parameter at the (s + j)-th moment in the comparison area is The dynamic comparison value over time of multiple comparison parameters in the operation impact area and multiple comparison parameters in the comparison area is The number of multiple comparison parameters in the operation impact area is n c , the number of multiple comparison parameters in the comparison area is

[0046] Use the dynamic comparison value over time of multiple comparison parameters in the operation impact area and multiple comparison parameters in the comparison area as the ratio test formula in a very short time.

[0047] Furthermore, a method for evaluating the post-operation effect according to the comparison test value using the rainfall increment includes:

[0048] Calculate the average rainfall values in the operation impact area and the comparison area:

[0049]

[0050] Where the average hourly rainfall in the area is The hourly rainfall observed by a certain automatic weather station in the area is P i , the number of stations where rainfall is observed at the current time The total number of automatic rainfall stations H;

[0051] Calculate the rainfall comparison test value between the operation impact area and the comparison area based on the rainfall value, and calculate the rainfall enhancement rate:

[0052]

[0053] Calculate the increased rainfall:

[0054]

[0055] Where the area of the impact area at a certain moment is V, and the increased rainfall is G;

[0056] When the comparison test value is greater than 1, analyze the effect after the operation by analyzing the change trends of the parameters in the impact area before and after the operation and the parameters in the comparison area.

[0057] In a second aspect, an embodiment of the present application further provides an electronic device, including:

[0058] A processor; and a memory arranged to store computer-executable instructions, and when the executable instructions are executed, the processor executes the method steps described in the first aspect.

[0059] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium, where the computer-readable storage medium stores one or more programs, and when the one or more programs are executed by an electronic device including multiple application programs, the electronic device executes the method steps described in the first aspect.

[0060] The beneficial effects of the present invention are:

[0061] The present invention is a method for spatio-temporal moving comparison test of multiple parameters in the operation effect area. Compared with the prior art, the present invention has the following technical effects:

[0062] Through steps such as preprocessing, comparison parameter selection, obtaining the operation impact area, obtaining the comparison area, obtaining the comparison test value, and post-operation effect evaluation, the present invention can improve the accuracy of the spatio-temporal moving comparison test of multiple parameters in the operation effect area, thereby improving the precision of the spatio-temporal moving comparison test of multiple parameters in the operation effect area. Optimizing the spatio-temporal moving comparison test of multiple parameters in the operation effect area can greatly save resources, improve work efficiency, can realize the automatic comparison test of the spatio-temporal moving of multiple parameters in the operation effect area, and conduct post-operation effect evaluation on the spatio-temporal moving comparison test of multiple parameters in the operation effect area in real time, which is of great significance for the automatic comparison test of the spatio-temporal moving of multiple parameters in the operation effect area, and can meet the automatic comparison test requirements of the spatio-temporal moving of multiple parameters in different standard operation effect areas and different operation effect areas, and has a certain universality. Description of the Drawings

[0063] Figure 1This is the step flow chart of a method for multi-parameter spatio-temporal movement contrast test in the operation effect area of the present invention;

[0064] Figure 2 This is the structural schematic diagram of an electronic device in the embodiment of the present specification. Specific embodiments

[0065] The present invention will be further described below through specific embodiments. The illustrative embodiments and descriptions of the present invention are used to explain the present invention, but not to limit the present invention.

[0066] A method for multi-parameter spatio-temporal movement contrast test in the operation effect area of the present invention includes the following steps:

[0067] As Figure 1 shown, in this embodiment, it includes the following steps:

[0068] Collect the working monitoring data of the artificial precipitation enhancement area and preprocess the working monitoring data;

[0069] In actual evaluation, taking an aircraft catalysis operation in a certain area on March 19, 2017 as an example, takeoff time: 10:25; landing time: 11:43; operation catalysis time: 10:41 - 11:14; operation catalysis height is about 3700 meters; operation catalysis concentration: a total of 750 g of silver iodide was sown. The horizontal moving wind speed and direction of the 3700 m dispersion layer on the same day were about 10 m / s, 233°;

[0070] Select the CAPPI at different heights of the radar and rainfall as parameters for calculation to see the effect after the cloud seeding operation;

[0071] Obtain multiple comparison parameters through the selection of comparison parameters from the working monitoring data, select the catalyst diffusion and transmission scheme according to the operation method, and obtain the operation influence area;

[0072] In actual evaluation, multiple comparison parameters include hourly ground precipitation, hourly radar composite reflectivity, CAPPI at different heights, echo top height, echo volume, maximum reflectivity, vertically integrated liquid water content, precipitation flux, optical thickness, cloud top height, cloud top temperature, cloud particles, ice crystal concentration; select 4 operation influence areas;

[0073] Select an area not affected by the catalysis operation according to the operation influence area to obtain a comparison area, and conduct a comparison test on the operation influence area and the comparison area according to the moving multiple comparison parameters to obtain a comparison test value;

[0074] In actual evaluation, select 4 comparison areas;

[0075] Adopt the increased rainfall to evaluate the effect after the operation according to the comparison test value to obtain the operation effect.

[0076] In this embodiment, the method for obtaining multiple comparison parameters by selecting comparison parameters through the work monitoring data includes:

[0077] Obtain the parameters of the operation effect according to the work monitoring data, and calculate the correlation degree of the operation effect of the parameters:

[0078]

[0079] Where the b-th parameter is h b , and the correlation degree of the operation effect of parameter h b is The parameter h at the s-th moment b is h b (s), the parameter h at the s+1-th moment b is h b (s+1), the number of parameters is N, the probability of parameter h b appearing is p(h b ), the sign function is sign(·), the actual operation effect after the change of parameter h b is The predicted operation effect when parameter h b remains unchanged is The weight of parameter h b is η b , the error of parameter h b is σ b , and the step function is δ|·|;

[0080] Take the parameters with an operation effect correlation degree greater than 0.3172 as candidate parameters, and calculate the linear correlation degree between the candidate parameters:

[0081]

[0082] Where the average value of the b-th candidate parameter is The v-th candidate parameter is h v , and the average value of the v-th candidate parameter is The linear correlation degree between candidate parameter h b and candidate parameter h v is γ(h b ,h v ), the dissimilarity distance between candidate parameter h b and candidate parameter h v is The deviation amount between candidate parameter h b and candidate parameter h v is Δh b,v , and the similarity capacity parameter is ρ;

[0083] Calculate the change information degree between the candidate parameters:

[0084]

[0085] Among them, the candidate parameter is h b and the candidate parameter h v The change information degree is ε b,v , the number of windows is p, and the deviation is Δh b,v The probability of occurrence is p(Δh b,v );

[0086] Calculate the change degree of the candidate parameter:

[0087]

[0088] Among them, the candidate parameter is h b The importance is The scale factor is ζ, and the genetic coefficient is The error value is δ;

[0089] Output the candidate parameters with an importance greater than 0.137 as multiple comparison parameters.

[0090] In this embodiment, the method for obtaining the operation influence area includes:

[0091] Obtain the operation area according to the catalyst diffusion transmission scheme, and calculate the change value of the multiple comparison parameters in the operation area;

[0092] Δu i,b = u io (s) - u i,b (s + j)

[0093] Among them, the b-th multiple comparison parameter of the i-th operation area is u i,b , the change value of the b-th multiple comparison parameter of the i-th operation area is Δu i,b , the initial value of the b-th multiple comparison parameter of the i-th operation area at the s-th moment is u io (s), and the b-th multiple comparison parameter of the i-th operation area at the s + j-th moment is u i,b (s + j);

[0094] The operation area with a change value of multiple comparison parameters greater than 0.241 is used as a candidate influence area, and the primary division is performed according to the criterion that the deviation is less than 0.216 based on the change value of multiple comparison parameters to obtain the primary area;

[0095] Calculate the effect correlation degree of the multiple comparison parameters:

[0096]

[0097] Among them, the external interference of the b-th multiple comparison parameter of the i-th primary area is Bi,b , the number of multiple comparison parameters is N1, and the multiple comparison parameter u i,b appears with a probability of p(u i,b ), and the importance weight of the b-th multiple comparison parameter in the i-th primary region is τ i,b , the multiple comparison parameter u i,b has an effect relevance of

[0098] Construct an effect correlation matrix based on the effect relevance of multiple comparison parameters, input the primary region into the convolutional neural network classification model, and calculate the output of the convolutional layer:

[0099]

[0100] where the output of the convolutional layer of the a-th region is D a , the activation function is θ, the output bias is M, the convolutional kernel size is Q, the classification boundary vector is d, the penalty coefficient is λ, and the numerical error of the z-th comparison parameter is ε b , the diagonal matrix is Σ, the effect correlation matrix of multiple comparison parameters within the a-th primary region is Z, the transpose is T, the effect correlation matrix of comparison parameters in different primary regions is R, and the first y columns of the effect correlation matrix of different primary regions are S y , the first y columns of the diagonal matrix are Σ y , the first y columns of the effect correlation matrix within the primary region are R y , the inverse matrix of the diagonal matrix is ∑ -1 , the number of primary regions is

[0101] Calculate the output category:

[0102]

[0103] where the output of the fully connected layer of the a-th region is f a , the category of the a-th output is χ a , the maximum pooling function value of the a-th region is W a , the moving length is ω, the pooling size is β, and the number of outputs is

[0104] Classify the output of the convolutional neural network classification model according to the category and output it as the job impact area.

[0105] In this embodiment, the method for obtaining a comparison area by selecting an area not affected by the catalytic operation according to the job impact area includes:

[0106] Under the same weather influence system, select an area with a range close to the influence area, the same shape and area as the influence area, and perpendicular to the system moving direction and parallel to the operation influence area, and not affected by the catalytic operation, as the comparison area.

[0107] In this embodiment, the method for obtaining the comparison test formula includes:

[0108] Calculate the dynamic comparison values over time of multiple comparison parameters in the operation influence area and multiple comparison parameters in the comparison area:

[0109]

[0110] Where the operation influence area is c, the comparison area is c1, the b-th multiple comparison parameter at the s-th moment in the operation influence area is u c,b (s), the b-th multiple comparison parameter at the (s + j)-th moment in the operation influence area is u c,b (s + j), the b-th multiple comparison parameter at the s-th moment in the comparison area is The b-th multiple comparison parameter at the (s + j)-th moment in the comparison area is The dynamic comparison value over time of multiple comparison parameters in the operation influence area and multiple comparison parameters in the comparison area is The number of multiple comparison parameters in the operation influence area is n c , the number of multiple comparison parameters in the comparison area is

[0111] In a very short time, use the dynamic comparison value over time of multiple comparison parameters in the operation influence area and multiple comparison parameters in the comparison area as the ratio test formula;

[0112] In the actual evaluation, the K value is significantly less than 1 before the operation; as the operation starts, the K value significantly increases, and at 11:41, the ratio K value of the rainfall in the operation influence area and the comparison area is greater than 1, and K is 1.2933; 2 hours after the operation, the K value reaches the maximum of 2.0565, and then the K value starts to decline, and at 13:41, the K value is still greater than 1; there are no rainfall stations in the influence area and the comparison area 4 hours after the operation, and the K value is 0; the above analysis of rainfall using the regional movement multi-parameter comparison analysis method shows that the catalytic operation in this operation has a certain rainfall enhancement effect in the operation influence area.

[0113] In this embodiment, the method for evaluating the post-operation effect of rainfall increase according to the comparison test value includes:

[0114] Calculate the average rainfall values in the operation influence area and the comparison area:

[0115]

[0116] Where the regional hourly average rainfall is The hourly rainfall observed by an automatic weather station in a certain area is P i , the number of stations where rainfall is observed at the current time The total number of automatic rainfall stations is H;

[0117] Calculate the rainfall comparison test value between the operation impact area and the comparison area based on the rainfall value, and calculate the rainfall enhancement rate:

[0118]

[0119] Calculate the increased rainfall:

[0120]

[0121] Among them, the area of the impact area at a certain moment is V, and the increased rainfall is G;

[0122] When the comparison test value is greater than 1, analyze the effect after the operation by analyzing the change trends of the parameters in the impact area before and after the operation and the parameters in the comparison area;

[0123] In the actual evaluation, the rainfall enhancement rates after the operation are approximately 0.520, 0.514, and 0.106 respectively; the average rainfall values in the impact area are approximately 0.056, 0.0473, 0.0422, and 0 respectively. The total precipitation in 1 hour after the catalytic operation is calculated to be 1.968×10^5 m 3 ; the total precipitation in 2 hours after the operation is 2.361×10^5 m 3 ; the total precipitation in 3 hours after the operation is 1.191×10^5 m 3 ; the total precipitation in 4 hours after the operation is 0 m 3 ;

[0124] The total increased rainfall in the impact area is 1.787×10^5 m 3 .

[0125] Figure 2 It is a schematic structural diagram of an electronic device according to an embodiment of the present application. Please refer to Figure 2 , at the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. Among them, the memory may include a memory, such as a high-speed random access memory (Random-Access Memory, RAM), and may also include a non-volatile memory, such as at least 1 disk memory, etc. Of course, the electronic device may also include other hardware required for other services.

[0126] The processor, network interface, and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 2 only a bidirectional arrow is used in Figure 2 , but it does not mean that there is only one bus or one type of bus.

[0127] Memory, which is used to store programs. Specifically, the program can include program code, and the program code includes computer operation instructions. The memory can include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0128] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a multi-parameter spatio-temporal movement contrast test device for the job effect area at the logical level. The processor executes the program stored in the memory and is specifically used to execute any of the aforementioned multi-parameter spatio-temporal movement contrast test methods for the job effect area.

[0129] As described above in this application Figure 1A method for multi-parameter spatio-temporal movement contrast test in an operation effect area disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in the processor or by instructions in the form of software. The above-mentioned processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed and completed by a hardware decoding processor, or executed and completed by a combination of hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the above method.

[0130] The electronic device can also execute Figure 1 a method for multi-parameter spatio-temporal movement contrast test in an operation effect area, and implement Figure 1 the functions of the illustrated embodiment. The embodiments of the present application will not be elaborated herein.

[0131] The embodiments of the present application also propose a computer-readable storage medium. The computer-readable storage medium stores one or more programs. The one or more programs include instructions that, when executed by an electronic device including a plurality of application programs, execute any of the foregoing methods for multi-parameter spatio-temporal movement contrast test in an operation effect area.

[0132] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0133] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0134] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implements the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0135] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0136] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and a memory.

[0137] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer-readable media.

[0138] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0139] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0140] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0141] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for multi-parameter spatio-temporal movement comparison and inspection of operation effect areas, characterized in that, It includes the following steps: Collect the working monitoring data of the artificial rainfall enhancement area and preprocess the working monitoring data; Obtain a number of comparison parameters by selecting comparison parameters through the working monitoring data, select a catalyst diffusion and transmission scheme according to the operation mode, and obtain an operation influence area, including: Obtain the parameters of the operation effect according to the working monitoring data, and calculate the operation effect correlation degree of the parameters: where the b-th parameter is , the relevance of parameter to the operation effect is , the parameter at the s-th moment is , the parameter at the (s + 1)-th moment is , the number of parameters is , the probability of parameter appearing is , the sign function is , the actual operation effect after parameter is changed to , the predicted operation effect without parameter being changed is , the weight of parameter is , the error of parameter is , the step function is ; Take the parameters with an operation effect correlation degree greater than 0.3172 as candidate parameters, and calculate the linear correlation degree between the candidate parameters: where the average value of the b-th candidate parameter is , the v-th candidate parameter is , the average value of the v-th candidate parameter is , the linear correlation degree between candidate parameter and candidate parameter is , the dissimilarity distance between candidate parameter and candidate parameter is , the deviation amount between candidate parameter and candidate parameter is , and the similarity capacity parameter is ; Calculate the change information degree between the candidate parameters: Among them, the candidate parameter and the candidate parameter The change information degree is , the number of windows is p, and the deviation amount is The probability of occurrence is ; Calculate the change degree of the candidate parameters: Among them, the candidate parameter has an importance of , a scale factor of , a genetic coefficient of , and an error value of ; Output the candidate parameters with an importance greater than 0.137 as a number of comparison parameters; Obtain the operation area according to the catalyst diffusion and transmission scheme, and calculate the change value of a number of comparison parameters in the operation area; where the -th multiple comparison parameter of the i-th operation area is , the change value of the -th multiple comparison parameter of the i-th operation area is , the initial value of the -th multiple comparison parameter of the i-th operation area at the s-th moment is , and the -th multiple comparison parameter of the i-th operation area at the (s + j)-th moment is ; The operation areas with a change value of a number of comparison parameters greater than 0.241 are used as candidate influence areas, and the candidate influence areas are initially divided according to the criterion that the deviation is less than 0.216 according to the change value of a number of comparison parameters to obtain primary areas; Calculate the effect correlation degree of a number of comparison parameters: Among them, the external interference of the th multi - item comparison parameter in the i - th primary region is , the number of multi - item comparison parameters is , the probability of the appearance of the multi - item comparison parameter is , the importance weight of the th multi - item comparison parameter in the i - th primary region is , the effect relevance of the multi - item comparison parameter is ; Construct an effect correlation matrix according to the effect correlation degree of a number of comparison parameters, input the primary area into a convolutional neural network classification model, and calculate the output of the convolutional layer: The output of the convolutional layer in the a-th region is , the activation function is , the output bias is M, the convolutional kernel size is Q, the classification boundary vector is , the penalty coefficient is , the numerical error of the z-th comparison parameter is , the diagonal matrix is , the effect correlation matrix of multiple comparison parameters in the a-th primary region is Z, the transpose is T, the effect correlation matrix of comparison parameters in different primary regions is R, and the first y columns of the effect correlation matrix of different primary regions are , the first y columns of the diagonal matrix are , the effect correlation matrix within the first y columns of the primary region is , the inverse matrix of the diagonal matrix is , the number of primary regions is ; Calculate the output category: The output of the fully connected layer in the a-th region is , the category of the a-th output is , the maximum pooling function value in the a-th region is , the moving length is , the pooling size is , the number of outputs is ; Classify the output of the convolutional neural network classification model according to the category and output it as an operation influence area; Select an area that is not affected by the catalytic operation according to the operation influence area to obtain a comparison area, and perform a comparison test on the operation influence area and the comparison area according to the moving a number of comparison parameters to obtain a comparison test value; Perform a post-operation effect evaluation on the comparison test value based on the rainfall amount to obtain an operation effect.

2. The multi-parameter spatio-temporal movement comparison and inspection method for an operation effect area according to claim 1, characterized in that The method for selecting an area that is not affected by the catalytic operation according to the operation influence area includes: Under the same weather influence system, select an area parallel to the operation influence area perpendicular to the system moving direction and not affected by the catalytic operation, and select an area with a similar location, shape and area to the influence area as the comparison area.

3. The multi-parameter spatio-temporal movement comparison and inspection method for the operation effect area according to claim 1, characterized in that The method for obtaining the comparison test formula includes: Calculate the dynamic comparison value over time of a number of comparison parameters in the operation influence area and a number of comparison parameters in the comparison area: where the operation influence area is c, and the comparison area is , the b-th multi-parameter comparison parameter at the s-th moment in the operation influence area is , the b-th multi-parameter comparison parameter at the (s + j)-th moment in the operation influence area is , the b-th multi-parameter comparison parameter at the s-th moment in the comparison area is , the b-th multi-parameter comparison parameter at the (s + j)-th moment in the comparison area is , the dynamic comparison value of the multi-parameter comparison parameters in the operation influence area and the multi-parameter comparison parameters in the comparison area over time is , the number of multi-parameter comparison parameters in the operation influence area is , the number of multi-parameter comparison parameters in the comparison area is ; Use the dynamic comparison value over time of a number of comparison parameters in the operation influence area and a number of comparison parameters in the comparison area as the comparison test formula in a very short time.

4. The multi-parameter spatio-temporal movement comparison and inspection method for an operation effect area according to claim 1, wherein The method for performing a post-operation effect evaluation on the comparison test value based on the rainfall amount includes: Calculate the average rainfall values in the operation influence area and the comparison area: Among them, the average hourly rainfall in the region is , and the hourly rainfall observed by an automatic station in the region is , the number of stations where rainfall is observed at the current time , and the total number of automatic rainfall stations is H; Calculate the rainfall comparison test value between the operation influence area and the comparison area according to the rainfall values, and calculate the rainfall enhancement rate: Calculate the rainfall enhancement amount: At a certain moment, the affected area is V, and the increased rainfall is ; When the comparison test value is greater than 1, analyze the post-operation effect by analyzing the change trends of the parameters in the influence area before and after the operation and the parameters in the comparison area.

5. An electronic device, comprising: A processor; And A memory arranged to store computer-executable instructions, and the executable instructions, when executed, cause the processor to execute the method according to any one of claims 1 to 4.

6. A computer-readable storage medium storing one or more programs which, when executed by an electronic device including a plurality of applications, cause the electronic device to perform the method according to any one of claims 1 to 4.

Images