KR102275531B1 - Leaf wetness duration predicition system and operating method thereof - Google Patents

Abstract

A foliar wetting duration prediction system is disclosed. An embodiment predicts whether dew will occur at each of a plurality of locations by time based on a plurality of weather prediction information and a dew determination model, and predicts whether dew occurs at each of the plurality of locations by time. Based on the leaf wetting duration information of each of the plurality of positions is generated, and leaf wetting duration spatial distribution information is generated based on the generated leaf wetting duration information of each of the plurality of positions.

Description

LEAF WETNESS DURATION PREDICITION SYSTEM AND OPERATING METHOD THEREOF

The following examples relate to a system for predicting leaf wetting duration.

The Korea Meteorological Administration operates more than 500 automatic meteorological observation equipment nationwide, and observes four basic variables (temperature, relative humidity, wind direction, wind speed) and additional factors of interest every minute. The Korea Meteorological Administration operates 11 meteorological observation points related to agriculture, and the expanded branches express meteorological data related to agriculture in connection with the Rural Development Administration.

However, the weather observation elements necessary for agricultural workers are still lacking. In particular, it is not easy to observe the leaf wetness duration (or leaf wetness duration, LWD), which studies agricultural production and has an important effect on the pest and pest environment, and it is not easy to observe because there is no standard observation standard. producing material. Therefore, spatial and temporal expansion of LWD data has many difficulties in reality, and many researchers have developed physical and empirical LWD prediction models to solve these problems.

There are two typical empirical models: Classification And Regression Tree/Stepwise Linear Discriminant (CART/SLD) and Number of Hours of Relative Humidity (NHRH). CART/SLD is a method that uses a hierarchical decision tree by empirically setting threshold values of relative humidity, dew point temperature, and wind speed. . NHRH is a method to determine whether there is dew based on a specific threshold of 90% relative humidity. It is the simplest of the prediction models and it is difficult to expect high accuracy.

A representative physical model is the Penman-Monteith (PM) method, which is a method for determining dew by calculating the latent heat flux using the energy balance. The PM physical model can compensate for the large deviation of the prediction accuracy according to the region suggested as a disadvantage of the empirical model. On the other hand, the use of the PM method is limited because the radiation that has the greatest effect on performance is difficult to observe.

The AI technique, which has been actively researched recently, has superior accuracy than the previous model, can be used in various regions, and has the advantage of easy model construction because it uses weather factors that are relatively easy to observe. If an LWD prediction system is built using artificial intelligence like this, it is possible to provide high-accuracy LWD information at any point.

A method of operating a foliar wetting duration prediction system according to one side includes: predicting for each time whether dew will occur at each of a plurality of locations based on a plurality of weather prediction information and a dew determination model; generating information on foliar wetting duration of each of the plurality of locations based on a prediction result of whether or not dew occurs at each of the plurality of locations; and generating leaf wetting duration spatial distribution information based on the generated leaf wetting duration information of each of the plurality of locations.

The plurality of weather prediction information may include time-specific prediction values of one or more weather variables of each of the plurality of locations.

The one or more weather variables may correspond to one or more of temperature, relative humidity, wind speed, insolation, and rainfall.

The step of generating the leaf wetting duration information of each of the plurality of locations is counting the time period in which the occurrence of dew at each of the plurality of locations is predicted, and based on the counting result, the leaf surface of each of the plurality of locations per day It may include the step of generating the wet duration information.

The dew determination model may predict whether or not dew will occur in the specific time zone at the specific location when the predicted values for each of a plurality of weather variables in the specific time zone of the specific location are received.

The dew determination model may include an Extreme Learning Machine (ELM) model.

In the step of generating the leaf wetting duration spatial distribution information, the topographic information including the plurality of locations and the generated leaf wetting duration information of each of the plurality of locations are integrated to generate the leaf wetting duration spatial distribution information. may include the step of

The operating method may further include displaying the generated foliar wetting duration spatial distribution information on a display.

A foliar wetting duration prediction system according to one side includes a memory for storing a dew determination model; and predicting whether dew will occur at each of a plurality of locations by time based on a plurality of weather prediction information and the dew determination model, and based on the prediction result of whether dew occurs at each of the plurality of locations by time and a controller for generating leaf wetting duration information of each of the plurality of locations, and generating spatial distribution information of leaf wetting duration based on the generated leaf wetting duration information of each of the plurality of locations.

The plurality of weather prediction information may include time-specific prediction values of one or more weather variables of each of the plurality of locations.

The one or more weather variables may correspond to one or more of temperature, relative humidity, wind speed, insolation, and rainfall.

The controller may count a time period in which the occurrence of dew at each of the plurality of locations is predicted, and generate information on the daily foliar wetting duration of each of the plurality of locations based on the counting result.

The dew determination model may predict whether or not dew will occur in the specific time zone at the specific location when the predicted values for each of a plurality of weather variables in the specific time zone of the specific location are received.

The dew determination model may include an ELM model.

The controller may generate the leaf wetting duration spatial distribution information by integrating the topographic information including the plurality of locations and the generated leaf wetting duration information of each of the plurality of locations.

The controller may display the generated foliar wetting duration spatial distribution information on a display.

1 is a diagram for explaining a system for predicting leaf wetting duration according to an embodiment.
2 is a flowchart illustrating a method of generating a dew determination model according to an exemplary embodiment.
3 to 4 are diagrams for explaining the operation of the dew determination model according to an embodiment.
5 is a view for explaining the execution time of the foliar wetting duration prediction system according to an embodiment.
6 is a view for explaining a spatial distribution map of leaf wetting duration according to an embodiment.
7 is a flowchart illustrating an operating method of a system for predicting leaf wetting duration according to an embodiment.
8 is a block diagram illustrating a system for predicting leaf wetting duration according to an embodiment.
9 is a view for explaining the operation of the foliar wetting duration prediction system and a plurality of user terminals according to an embodiment.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. However, since various changes may be made to the embodiments, the scope of the patent application is not limited or limited by these embodiments. It should be understood that all modifications, equivalents and substitutes for the embodiments are included in the scope of the rights.

Terms used in the examples are used for the purpose of description only, and should not be construed as limiting. The singular expression includes the plural expression unless the context clearly dictates otherwise. In the present specification, terms such as “comprise” or “have” are intended to designate that a feature, number, step, operation, component, part, or combination thereof described in the specification exists, but one or more other features It should be understood that this does not preclude the existence or addition of numbers, steps, operations, components, parts, or combinations thereof.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the embodiment belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and should not be interpreted in an ideal or excessively formal meaning unless explicitly defined in the present application. does not

In addition, in the description with reference to the accompanying drawings, the same components are given the same reference numerals regardless of the reference numerals, and the overlapping description thereof will be omitted. In the description of the embodiment, if it is determined that a detailed description of a related known technology may unnecessarily obscure the gist of the embodiment, the detailed description thereof will be omitted.

1 is a diagram for explaining a system for predicting leaf wetting duration according to an embodiment.

Referring to FIG. 1 , a leaf wetness duration (LWD) prediction system 110 includes an input data processing unit 110 , a dew determination unit 120 , and a spatial distribution information generation unit 130 .

The input data processing unit 110 pre-processes weather prediction data. For example, the input data processing unit 110 may convert the weather forecast data into weather forecast data for each location and/or time according to an input format of a dew determination model to be described later. In other words, the input data processing unit 110 may extract weather prediction data for each location and/or time from the weather prediction data. Here, the location may indicate a location where an Automatic Weather System (AWS) managed by the Korea Meteorological Administration is installed.

The dew determination unit 120 determines whether dew is generated based on the pre-processed weather prediction data and the dew determination model. In other words, the dew determination unit 120 determines whether dew is generated for each location and for each time based on the pre-processed weather prediction data and the dew determination model. As an example, the dew determination model of the dew determination unit 120 may predict whether dew will occur at a specific location for each time when receiving weather forecast data for each time at a specific location. The generation of the dew determination model will be described later with reference to FIG. 2, and the specific operation of the dew determination model will be described later with reference to FIGS. 3 to 4 .

The dew determination unit 120 generates LWD information for each location based on a result of determining whether dew is generated for each location and for each time.

The spatial distribution information generating unit 130 generates LWD spatial distribution information based on LWD information for each location. For example, the spatial distribution information generating unit 130 may generate a nationwide LWD spatial distribution map by performing linear interpolation on the LWD information for each location.

The LWD prediction system 100 according to an embodiment may generate daily LWD spatial distribution information based on weather prediction data, so that LWD information of a desired location may be provided to the user. In addition, the LWD prediction system 100 according to an embodiment may provide LWD information of a location without weather observation to a user (eg, an agricultural worker), and may assist the user in determining agricultural work.

2 is a flowchart illustrating a method of generating a dew determination model according to an exemplary embodiment.

The dew determination model according to an embodiment may be generated by the model generating apparatus, but is not limited thereto and may be generated by the LWD prediction system 100 .

Referring to FIG. 2 , the model generating device collects ground observation data ( 210 ). Ground observation data may include, but is not limited to, one or more of, for example, temperature, relative humidity, wind speed, insolation, and dew duration.

The model generating device sets the Extreme Learning Machine (ELM) (220). For example, the model generating apparatus sets the number of nodes of the ELM model to 900 and sets a regulation factor of the ELM model to 0.9.

The model generating device performs ELM model optimization and verification (230). In other words, the model generating device may train the ELM model based on the collected ground observation data.

The model generating apparatus extracts weights from the optimized ELM model ( 240 ). The extracted weights are applied to the LWD prediction system 100 . In other words, since the extracted weights are applied to the LWD prediction system 100 , the dew determination model of the dew determination unit 120 may be implemented in the LWD prediction system 100 .

3 to 4 are diagrams for explaining the operation of the dew determination model according to an embodiment.

Referring to FIG. 3 , the dew determination model may receive weather prediction data for each location/time, and predict whether or not dew will occur for each location/time. The weather forecast data may include predicted values of each of the weather variables (eg, temperature, relative humidity, wind speed, solar radiation, and rainfall).

Referring to FIG. 4 , the dew determination model may predict whether dew will occur in each time zone at each location when receiving weather forecast data for each time at each location. As an example, the dew determination model is the hourly predicted value of the temperature of the location A on the map shown in FIG. 4, the hourly predicted value of the relative humidity of the location A, the hourly predicted value of the wind speed at the location A, the hourly predicted value of the insolation of the location A, and the location A It is possible to receive an input of an hourly predicted value of the rainfall amount, and it is possible to predict whether or not dew will occur for each time period at the location A, as in the example shown in FIG. 4 . In the example shown in FIG. 4 , the dew determination model may predict that dew will occur at 3 to 4 o'clock the next day at location A and dew will occur at 4 to 5 o'clock the next day. Similarly, the dew determination model may predict whether dew is generated for each time zone at each of locations B to F.

The dew determination unit 120 may count a time period in which the occurrence of dew at each of the plurality of locations is predicted, and may generate LWD information of each location based on the counting result. In the example shown in FIG. 4, the dew determination unit 120 predicted that dew would occur at 3-4 o'clock and 4-5 o'clock the next day at each of positions A to E, and dew at positions F at 3 to 4 o'clock the next day, 4 It was predicted to occur at ~5 o'clock and at 5-6 o'clock. In this case, the dew determination unit 120 may count two time periods in which the occurrence of dew is predicted at each of positions A to E, and may count three time periods in which the occurrence of dew at the position F is predicted. Accordingly, the dew determination unit 120 may predict the LWD at each of positions A to E as 2 hours and the LWD at the position F as 3 hours. In other words, the dew determination unit 120 may determine the LWD information of the next day at each of the positions A to E as 2 hours and the next day LWD information at the position F as 3 hours.

The positions A to F described with reference to FIG. 4 are merely examples for convenience of description, and the positions are not limited to the positions A to F described with reference to FIG. 4 . In addition, the time period in which the occurrence of dew is predicted described with reference to FIG. 4 is also given as an example for convenience of explanation, and the time period in which the occurrence of dew is predicted is not limited to that described with reference to FIG. 4 .

5 is a view for explaining the execution time of the foliar wetting duration prediction system according to an embodiment.

Referring to FIG. 5 , the analysis of the Local Data Assimilation and Prediction System (LDAPS) starts at 00 UTC. The local forecast model is a model that predicts the weather on the Korean Peninsula, and it can predict the weather on the Korean Peninsula up to 36 hours (or 48 hours) later.

Scale refinement execution time is 05 UTC. Scale refinement can represent the work of expanding the prediction data of the local forecasting model to a resolution of up to 100 m. The result of performing scale detailing on the prediction data of the local forecast model may be input to the above-described input data processing unit 110 . In other words, the scale detailed result may correspond to weather forecast data input to the input data processing unit 110 .

The prediction model execution time is 08 UTC. The prediction model may predict whether dew occurs at each location described above for each time after 8 hours have elapsed from 00 UTC.

6 is a view for explaining a spatial distribution map of leaf wetting duration according to an embodiment.

Referring to FIG. 6 , examples of LWD spatial distribution charts for each day are shown.

The spatial distribution information generating unit 130 may generate a daily LWD spatial distribution map based on the daily LWD information of each location. For example, the spatial distribution information generating unit 130 may generate a daily LWD spatial distribution map by integrating the daily LWD information and topographic information of each location. In an embodiment, the spatial distribution information generating unit 130 may utilize an NCAR Command Language (NCL) program to generate a daily LWD spatial distribution map.

7 is a flowchart illustrating an operating method of a system for predicting leaf wetting duration according to an embodiment.

Referring to FIG. 7 , the LWD prediction system 100 predicts for each time whether dew will occur at each of a plurality of locations based on a plurality of weather prediction information and a dew determination model ( 710 ). In other words, the LWD prediction system 100 may generate prediction information on whether or not dew is generated by time at each of a plurality of locations based on a plurality of weather prediction information and a dew determination model. The plurality of locations may indicate points where AWS managed by the Korea Meteorological Administration is installed, but is not limited thereto. The plurality of weather forecast information may correspond to the pre-processed weather forecast data described above. The plurality of weather prediction information may include, for example, time-wise prediction values of one or more weather variables of each of the plurality of locations.

In an embodiment, the dew determination model may predict whether dew will occur in a specific time zone of a specific location when a predicted value for each of a plurality of weather variables in a specific time zone of a specific location is received. Since the operation of the dew determination model has been described in detail with reference to FIG. 4 , a detailed description thereof will be omitted.

The LWD prediction system 100 generates LWD information of each of the plurality of locations based on the prediction result of whether or not dew is generated for each time of the plurality of locations ( 720 ). For example, the LWD prediction system 100 may count a time period in which the occurrence of dew at each of the plurality of locations is predicted, and may generate daily LWD information of each of the plurality of locations based on the counting result.

The LWD prediction system 100 generates LWD spatial distribution information based on the generated LWD information of each of the plurality of positions ( 730 ). For example, the LWD prediction system 100 may generate LWD spatial distribution information by integrating topographic information including a plurality of locations and LWD information for each of the plurality of locations.

A new location may be added or one or more of existing locations may be removed according to a user's request. Due to the flexibility of the system 100, the user may be provided with LWD information of a desired location. In addition, the user may be provided with LWD information of a desired time zone.

Since the matters described with reference to FIGS. 1 to 6 may be applied to the matters described with reference to FIG. 7 , a detailed description thereof will be omitted.

8 is a block diagram illustrating a system for predicting leaf wetting duration according to an embodiment.

Referring to FIG. 8 , the LWD prediction system 100 includes a controller 810 and a memory 820 .

The memory 820 stores the dew determination model 310 . In other words, the memory 820 stores the weights described with reference to FIG. 2 .

The controller 810 may implement the above-described input data processing unit 110 , the dew determination unit 120 , and the spatial distribution information generation unit 130 . The controller 810 predicts for each time whether dew will occur at each of a plurality of locations based on the plurality of weather prediction information and the dew determination model 310 . The controller 810 generates LWD information of each of the plurality of locations based on the prediction result of whether or not dew is generated at each of the plurality of locations. The controller 810 generates LWD spatial distribution information based on LWD information of each of the plurality of locations.

Since the matters described with reference to FIGS. 1 to 7 may be applied to the matters described with reference to FIG. 8 , a detailed description thereof will be omitted.

9 is a view for explaining the operation of the foliar wetting duration prediction system and a plurality of user terminals according to an embodiment.

Referring to FIG. 9 , a plurality of user terminals 910 - 1 to 910 - n may access the LWD prediction system 100 .

Each of the plurality of user terminals 910-1 to 910-n may correspond to a mobile terminal (eg, a smart phone, a tablet) or a fixed terminal (eg, a PC).

The LWD spatial distribution may be displayed on the display of each of the plurality of user terminals 910 - 1 to 910 - n according to a user request. Accordingly, each user may check LWD information of a desired location and/or a desired time zone.

Although not shown in FIG. 9 , the daily LWD information generated by the LWD prediction system 100 may be transmitted to the pest prevention system, thereby contributing to the generation of a crop management risk level alert.

LWD prediction system 100 according to an embodiment may provide agricultural workers with information required for agricultural decision making, and may provide LWD information that anyone can use. In addition, the LWD prediction system 100 may determine whether dew is generated by using the ELM model and the prediction system for LWD information at a point where there is no weather observation, and may generate LWD information for the next day. Such LWD information can help agricultural workers make agricultural work judgments. In addition, LWD information can be provided to consumers of agricultural information and can be used as an input to the pest prevention system, contributing to the generation of a crop management risk level warning.

The device described above may be implemented as a hardware component, a software component, and/or a combination of the hardware component and the software component. For example, devices and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA). , a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions, may be implemented using one or more general purpose or special purpose computers. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For convenience of understanding, although one processing device is sometimes described as being used, one of ordinary skill in the art will recognize that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that can include For example, the processing device may include a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as parallel processors.

The software may comprise a computer program, code, instructions, or a combination of one or more thereof, which configures a processing device to operate as desired or is independently or collectively processed You can command the device. The software and/or data may be any kind of machine, component, physical device, virtual equipment, computer storage medium or device, to be interpreted by or to provide instructions or data to the processing device. , or may be permanently or temporarily embody in a transmitted signal wave. The software may be distributed over networked computer systems, and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic such as floppy disks. - includes magneto-optical media, and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

As described above, although the embodiments have been described with reference to the limited embodiments and drawings, various modifications and variations are possible from the above description by those skilled in the art. For example, the described techniques are performed in a different order than the described method, and/or the described components of the system, structure, apparatus, circuit, etc. are combined or combined in a different form than the described method, or other components Or substituted or substituted by equivalents may achieve an appropriate result.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

Claims (16)

In the operating method of the foliar wetting duration prediction system,
Predicting whether dew will occur at each of a plurality of locations based on a plurality of weather prediction information and a dew determination model for each time period;
generating information on foliar wetting duration of each of the plurality of locations based on a prediction result of whether or not dew is generated for each time zone at each of the plurality of locations; and
generating leaf wetting duration spatial distribution information based on the generated leaf wetting duration information of each of the plurality of locations;
containing,
Operation method of foliar wetting duration prediction system.
According to claim 1,
The plurality of weather forecast information includes a forecast value for each time period of one or more weather variables of each of the plurality of locations,
Operation method of foliar wetting duration prediction system.
3. The method of claim 2,
wherein the one or more weather variables correspond to one or more of temperature, relative humidity, wind speed, insolation, and rainfall;
Operation method of foliar wetting duration prediction system.
According to claim 1,
The step of generating leaf wetting duration information of each of the plurality of positions comprises:
Counting the time period in which the occurrence of dew at each of the plurality of locations is predicted, and generating information on the daily foliar wetting duration of each of the plurality of locations based on the counting result
containing,
Operation method of foliar wetting duration prediction system.
According to claim 1,
The dew determination model predicts whether or not dew will occur in the specific time zone of the specific location when a predicted value for each of a plurality of weather variables of a specific time zone of a specific location is received,
Operation method of foliar wetting duration prediction system.
According to claim 1,
The dew determination model comprises an Extreme Learning Machine (ELM) model,
Operation method of foliar wetting duration prediction system.
According to claim 1,
The step of generating the foliar wetting duration spatial distribution information comprises:
Generating the leaf wetting duration spatial distribution information by integrating the topographic information including the plurality of locations and the generated leaf wetting duration information of each of the plurality of locations
containing,
Operation method of foliar wetting duration prediction system.
According to claim 1,
Displaying the generated foliar wetting duration spatial distribution information on a display
further comprising,
Operation method of foliar wetting duration prediction system.
In the foliar wetting duration prediction system,
a memory for storing the dew judgment model; and
Based on a plurality of weather prediction information and the dew determination model, it is predicted for each time whether dew will occur at each of a plurality of locations, and based on the prediction result of whether or not dew occurs at each of the plurality of locations for each time period A controller that generates leaf wetting duration information of each of the plurality of locations, and generates leaf wetting duration spatial distribution information based on the generated leaf wetting duration information of each of the plurality of locations
containing,
Foliar wetting duration prediction system.
10. The method of claim 9,
The plurality of weather forecast information includes a forecast value for each time period of one or more weather variables of each of the plurality of locations,
Foliar wetting duration prediction system.
11. The method of claim 10,
wherein the one or more weather variables correspond to one or more of temperature, relative humidity, wind speed, insolation, and rainfall;
Foliar wetting duration prediction system.
10. The method of claim 9,
The controller is
Counting the time period in which the occurrence of dew at each of the plurality of locations is predicted, and generating information on the daily foliar wetting duration of each of the plurality of locations based on the counting result,
Foliar wetting duration prediction system.
10. The method of claim 9,
The dew determination model predicts whether or not dew will occur in the specific time zone of the specific location when a predicted value for each of a plurality of weather variables of a specific time zone of a specific location is received,
Foliar wetting duration prediction system.
10. The method of claim 9,
The dew determination model comprises an Extreme Learning Machine (ELM) model,
Foliar wetting duration prediction system.
10. The method of claim 9,
The controller is
Generating the leaf wetting duration spatial distribution information by integrating the topographic information including the plurality of locations and the generated leaf wetting duration information of each of the plurality of locations,
Foliar wetting duration prediction system.
10. The method of claim 9,
The controller is
Displaying the generated foliar wetting duration spatial distribution information on a display,
Foliar wetting duration prediction system.

Images