KR20230100545A - Predicting method and system for eliminating birds using citizen science - Google Patents

Abstract

This is a technique for deriving vulnerable areas using citizen science, which can be the basis for deriving vulnerable areas for harmful bird species that appear in urban areas, and analyzing the eradication results based on the eradication prediction data of harmful birds. Therefore, it is possible to establish an optimal eradication frequency and a plan to eradicate harmful birds for the eradication area, thereby realizing the advantage of reducing the population and occurrence rate of harmful birds by region using citizen science data.

Description

Predicting system for eradication of harmful birds in urban areas using citizen science, and prediction method using the same {Predicting method and system for eliminating birds using citizen science}

It is about technology to derive vulnerable areas using citizen science, which can be the basis for deriving vulnerable areas for harmful bird species that appear in urban areas.

In general, birds cause human and economic damage due to collisions during takeoff and landing of airplanes at airports or airfields, cause crop damage in orchards, and avian influenza (Al) viruses in livestock, poultry, and poultry farms spreads and causes enormous damage, and recently, there is a demand for an eradication device to combat algae due to the wide and diverse types of damage, such as excrement damage to large factories such as industrial complexes and warehouse buildings.

Accordingly, various bird repellent devices have been disclosed in the prior art, and conventional bird repellent devices eradicate algae through smell using a repellent, exterminate algae with a loudspeaker, alarm sound, sound wave, etc., or lighting using a reflector, etc. It is to be able to eradicate algae through laser irradiation.

However, the reality is that conventional repellent devices are of a fixed type and cannot be a permanent countermeasure because the effect of repelling algae is halved or lost due to repeated learning of algae.

Accordingly, conventionally, as in the 'algae control device' of Publication No. 10-2016-0136899, when a bird is detected through a motion sensor, the laser light source is automatically irradiated while rotating horizontally to the detected area to repel the approaching bird. However, since this is to horizontally irradiate the laser light source with the laser launcher fixed to the support, the bird detection area by the motion sensor and the bird eradication area through the laser light source firing can only be used in an open area. However, it was impossible to eradicate algae at all in the detection shaded area due to obstacles such as buildings.

Conventional algae eradication technology has traditionally been approached to eradicate through the installation of devices for the area where the bird itself appears, and there is no systematic approach that can predict the area where a particular bird appears and eradicate it in advance.

Korean Patent Publication No. 10-2016-0136899 Korean Patent Registration No. 10-1113757

The present invention has been made to solve the above-mentioned problems, and an object of the present invention is to implement a technology for predicting and deriving vulnerable areas based on location data of harmful algae collected by citizens, and to implement efficient and effective areas based on the predicted areas. Its purpose is to provide a systemic technology that enables algae eradication.

As a means for solving the above problems, the present invention, as shown in FIGS. 1 to 4, captures images including harmful tides in a target area captured through a plurality of user terminals capable of wired/wireless communication and converts them into citizen image data. Citizen data providing module 100 to provide; Citizen image data transmitted from the citizen data providing module 100 is acquired, local self-spatial correlation analysis is performed based on the citizen image data, and the location of harmful tides is based on the information included in the citizen image data. a harmful algae eradication area prediction module 200 that calculates information, the number of individuals and the frequency of occurrence, analyzes a preferred habitat by reflecting environmental variables preferred by the harmful algae, and calculates information on an intensive eradication area; an eradication efficiency calculation module 300 that receives eradication result data performed based on the eradication area prediction information calculated in the harmful tide eradication area prediction module 200 and verifies reliability of the eradication area prediction information; An integrated management module that reflects the reliability of the eradication result data verified in the eradication efficiency calculation module 300, monitors the appearance rate of harmful birds before and after eradication, and calculates and provides information on the correlation between eradication frequency and eradication efficiency. (400); An eradication data providing module 500 for transmitting the result data of the eradication of harmful algae performed with respect to the eradication area prediction information calculated in the harmful algae eradication area prediction module 200 to the eradication efficiency calculation module 300; It is possible to provide a prediction system for the eradication of harmful tides that appear in urban areas using citizen science.

In addition, in another embodiment of the present invention, by using the above-described harmful tide elimination area prediction system, user terminals equipped with cameras and communication modules take images including harmful tides in the target area and receive citizen image data. step; A second step of classifying and storing data collected at the same location information point at the same set time interval with respect to the citizen image data transmitted in the first step in the eradication area prediction module 200; The eradication area prediction module 200 calculates the number of harmful birds included in the collected citizen image data, calculates the appearance time and latitude and longitude information of harmful birds included in the citizen image data, and self-spatial correlation Step 3 of calculating the location of a section where harmful tides are concentrated spatially by analyzing the relationship; Step 5 of analyzing preferred habitats by reflecting environmental variables preferred by the harmful birds in the eradication area prediction module 200 and deriving a species distribution model; Step 6 of calculating prediction data of the eradication area of harmful tides by reflecting the overlapping section of the location points using the preferred habitat, self-spatial correlation data and citizen image data in the eradication area prediction module 200; In addition, it is possible to provide a method for predicting areas for eradication of harmful tides that appear in urban areas using citizen science.

According to an embodiment of the present invention, there is an effect of realizing efficient eradication of harmful birds by analyzing the haunting area of harmful birds and predicting and providing an eradication area based on the location data of harmful birds collected by citizens. .

In addition, by analyzing the eradication results based on the eradication prediction data of harmful birds, it is possible to establish a plan to eradicate harmful birds for the optimal eradication frequency and eradication area, and to determine the number of harmful birds by region using citizen science data. And the advantage of reducing the appearance rate is realized.

1 and 2 are block diagrams of a system for predicting a harmful tide eradication area (hereinafter referred to as 'the present invention') appearing in an urban area using citizen science according to an embodiment of the present invention.
3 and 4 are flowcharts and conceptual diagrams illustrating a method of predicting an area to eradicate harmful tides appearing in an urban area using citizen science using FIGS. 1 and 2 .
5 to 17 are images illustrating an embodiment of a method for predicting a harmful tide eradication area appearing in an urban area using citizen science to which the configuration of the present invention is applied.

Advantages and features of the present invention, and methods of achieving them, will become clear with reference to the detailed description of the following embodiments taken in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments described herein and may be embodied in other forms. Rather, the embodiments introduced herein are provided so that the disclosed content will be thorough and complete and the spirit of the present invention will be sufficiently conveyed to those skilled in the art.

Terms used in this application are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, the terms "include" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that it does not preclude the possibility of the presence or addition of numbers, steps, operations, components, parts, or combinations thereof.

1 and 2 are block diagrams of a system for predicting a harmful tide eradication area (hereinafter referred to as 'the present invention') appearing in an urban area using citizen science according to an embodiment of the present invention. 3 and 4 are flowcharts and conceptual diagrams illustrating a method of predicting an area to eradicate harmful tides appearing in an urban area using citizen science using FIGS. 1 and 2 .

The present invention implements a technique for deriving vulnerable areas using citizen science, which can be the basis for deriving vulnerable areas for harmful bird species that appear in urban areas. In the case of existing harmful algae management, when a report of harmful algae comes in due to the characteristics of birds that migrate widely, a method of eradicating or inefficiently extensively processing is used, and this inefficient problem is solved by the present invention. Apply technology to implement information so that it can be solved.

As a configuration for implementing this, referring to FIGS. 1 and 2 , the present invention provides citizen data that is provided as citizen image data by taking an image including harmful tides in a target area photographed through a plurality of user terminals capable of wired and wireless communication. Obtain citizen image data transmitted from the module 100 and the citizen data providing module 100, perform regional self-spatial correlation analysis based on the citizen image data, and obtain information included in the citizen image data. A harmful tide elimination area prediction module 200 that calculates the location information, population and frequency of occurrence of harmful birds based on this, analyzes the preferred habitat by reflecting the environmental variables preferred by the harmful birds, and calculates information on the intensive eradication area and an eradication efficiency calculation module 300 receiving the eradication result data performed based on the eradication area prediction information calculated in the harmful tide eradication area prediction module 200 and verifying the reliability of the eradication area prediction information. Reflecting the reliability of the eradication result data verified in the eradication efficiency calculation module 300, the integrated management module ( 400) and an eradication data providing module 500 that transmits the result data of eradication of harmful algae performed with respect to the eradication area prediction information calculated in the harmful algae eradication area prediction module 200 to the eradication efficiency calculation module 300. can be configured.

The harmful bird eradication area prediction module 200 calculates the location information, number and frequency of occurrence of harmful birds based on the information included in the citizen image data, and determines the preferred habitat by reflecting environmental variables preferred by the harmful birds. It analyzes and enables the calculation of information on the intensive eradication area.

As a configuration to implement this, the harmful tide eradication area prediction module 200 classifies data collected at the same location information point at the same set time interval with respect to the citizen image data transmitted from the citizen data providing module 100. A data acquisition unit 210 that stores the data, a population derivation unit 220 that calculates the number of harmful birds included in the collected citizen image data, and the appearance time and latitude of harmful birds included in the collected citizen image data and an autocorrelation analysis unit 230 that calculates longitude information and analyzes self-spatial correlation to determine the location of a section where harmful birds are concentrated spatially. Preferred Habitat Calculation Unit 240 that analyzes and derives a species distribution model, and predictive data for the eradication area of harmful tides by reflecting the overlapping intervals of location points using the preferred habitat, self-spatial correlation data, and citizen image data It is configured to include an eradication area calculation unit 250 that calculates.

In addition, based on the data predicted by the above-mentioned harmful tide eradication area prediction module 200 as an area in need of intensive management and eradication of harmful tides, after eradication has been performed, in the present invention, the eradication efficiency calculation module ( 300), the reliability of the predicted data is evaluated and verified, and it is converted into big data so that it can be used to implement future prediction information. That is, the eradication efficiency calculation module 300 receives the eradication result data performed based on the eradication area prediction information calculated in the harmful tide eradication area prediction module 200, and verifies the reliability of the eradication area prediction information. .

To this end, the eradication efficiency calculation module 300 is an eradication area data acquisition unit that receives and stores the result data of eradication of harmful tides based on the prediction data of the eradication area of harmful tides derived from the eradication area calculation unit 250. 310, and an eradication performance data classification unit 320 that classifies the occurrence data of harmful tides in a specific section of the target area set in the eradication area prediction data and the appearance data of harmful tides after eradication; Based on the eradication performance data, It may be configured to include an eradication efficiency verification unit 330 that evaluates the reliability of the prediction data of the eradication area of harmful tides derived from the eradication area calculation unit 250.

Through the above configuration, in the present invention, the prediction of the harmful algae eradication area that appears in the urban area using citizen science, and the location data of harmful algae collected by citizens are analyzed, and the eradication By predicting and providing the area, it is possible to implement effective eradication of harmful tides.

Hereinafter, a process of predicting an area requiring intensive management (removal management) of harmful tides by applying the system for predicting areas for eradication of harmful tides according to the present invention described above will be described.

Referring to FIGS. 3 and 4, a method of predicting an area requiring intensive management (removal management) of harmful tides by applying the present invention described in FIGS. 1 and 2 is as follows.

First, a first step of receiving citizen image data by taking images including harmful tides in the target area from user terminals equipped with cameras and communication modules (hereinafter, referred to as 'citizen image data') is performed. The image data used in the present invention uses image data taken and provided by citizens, and the number of harmful birds included in the image data, location information, etc. are derived and used for analysis.

Thereafter, the eradication area prediction module 200 performs a second step of classifying and storing the data collected at the same location information point at the same set time interval with respect to the citizen image data transmitted in the first step. In the case of analysis methods based on data provided to citizens, which is usually referred to as citizen science, the quality of data produced through citizen science activities must be guaranteed in order to make practical contributions. If the quality of the data is not managed, it can be used for educational activities for participating citizens, but citizen science cannot actually contribute to research in the field of environmental science. Because there is a risk that it will increase. In the present invention, pictures of harmful algae and their location are collected based on citizen image data, and data collected at the same point at the same time interval (eg, 20 minute intervals) is applied to remove redundant data. make it possible

Thereafter, the eradication area prediction module 200 calculates the number of harmful birds included in the collected citizen image data, calculates the appearance time and latitude and longitude information of harmful birds included in the citizen image data, The third step is performed to calculate the location of the section where harmful tides are concentrated spatially by analyzing the spatial correlation. In addition, thereafter, in the eradication area prediction module 200, the fifth step of analyzing the preferred habitat by reflecting the environmental variables preferred by the harmful birds and deriving a species distribution model is performed.

In the eradication area prediction module 200, step 6 of calculating prediction data of the eradication area of harmful tides is performed by reflecting the overlapping interval between the preferred habitat and location points using self-spatial correlation data and citizen image data.

In the case of the preferred habitat of these harmful birds, the species distribution model is driven by considering the environmental variables preferred by the harmful birds. In addition, by analyzing the self-spatial correlation based on the data collected as citizen image data, the section where the most harmful tides are spatially concentrated is set. Afterwards, the section where the preferred habitat of the harmful tide and the location points using self-spatial correlation and citizen science data overlap the most is set as the eradication prediction point. After that, eradication is carried out periodically by grouping 4 sections by land use, and reliability can be verified based on the eradication results.

Afterwards, the number of short-term (weekly) and long-term (monthly) populations and the decrease in presence or absence are identified, and the most efficient type of eradication is extracted and analyzed.

Hereinafter, an embodiment in which the present invention described in FIGS. 1 to 4 and the method for predicting an eradication point using the same is applied to Suwon-si, Gyeonggi-do, Korea as a target area, and harmful tides are set as rooks will be described. do.

{Example: Target area_Suwon-si, Gyeonggi-do, harmful tide_Rook ( Corvus frugilegus )}

1. General information of target area and harmful birds (rook)

Suwon has an area of 121 km2 and consists of a large basin. The annual average temperature is 12.5℃, which is more temperate than Gyeonggi-do (11.2℃). In the case of annual precipitation, it is 1,367.8 mm, 62.6 mm less than the Gyeonggi-do average of 1,440 mm (Korea Meteorological Administration, 2017).

In the case of the target species, the rook, it lives in Amur, northeast and south China, and Mongolia from May to June, and winters in Korea, Japan, Taiwan, and China (east) from November to March. It is a common migratory bird that passes throughout Korea in spring and fall, and is a common winter bird in southern regions (Won Byeong-oh, 1981). Preferred habitats are plains, open lands, forests near farmlands, and rural dwellings and towns. They breed in groups on trees and prefer animal food, including insects, tree fruits, and seeds.

In Suwon-si, Gyeonggi-do, since 2016, rooks have been staying in the city center for a total of 5 months from November to March of the following year. The specific main haunting areas were identified as the densely populated Gwonseon-gu Office, Dongsuwon Intersection, Ajou University Intersection, Suwon City Hall, Gwonseon-gu Furniture Street, and the vicinity of Curve-dong.

Since rooks are mainly active in commercial or residential areas in urban areas, they cause various inconveniences to nearby residents due to the sanitary conditions caused by excreta falling on pedestrian paths and parked cars used by residents, and the noise of rooks in the evening, when they usually appear. Furthermore, out of the total population of 13.41 million in Gyeonggi-do, the population of Suwon-si is approximately 1.18 million, which is the largest in Gyeonggi-do, and also ranks third in the population density of Gyeonggi-do. is expected to be large.

It has a habit of staying together with hundreds or thousands of birds (Madge and Burn., 1994), leaving the nest and starting feeding activities at sunrise (Hubalek, 2017). Therefore, in this study, to analyze the preferred habitat of rooks, the sunrise and sunset times were selected based on the sunrise and sunset times of the sunrise and sunset times in Suwon from December 2020 to February 2021 provided by the Korea Meteorological Administration ( Table 1). Afterwards, considering the situation in which each sun completely rises and sets, it is set at 08:00 in the case of sunrise and 18:00 in the case of sunset.

{Table 1: Selected averages of sunrise and sunset times}

2. Apply citizen science data

(1) Acquisition and processing of data

The data used in the present invention was applied based on citizen science, that is, data transmitted by citizens with user terminals taking pictures of rooks found near Suwon-si. In the present invention, it is performed by receiving images from a plurality of terminals (FIG. 2, citizen data providing module 100).

In the harmful tide-repelling area prediction module 200 of the present invention, the location data of rooks collected through citizen science data in Suwon-si through the data acquisition unit 210 is a total of 6,314 pieces, and it is determined that there are no rooks in the picture or that they are inappropriate. 5,214 cases were extracted by inspecting the photos. Afterwards, the corresponding data located nationwide was clipped with Suwon City using ArcGIS, and finally, a total of 4,523 points where rooks appeared in Suwon City. This data was acquired from December 20 to March 21 (Fig. 6), and data acquired within 20 minutes at the same point were removed to minimize repetitive data at the same point.

Thereafter, the number of harmful birds included in the citizen image data collected by the population number derivation unit 220 is calculated, and the appearance time and latitude and longitude information of the harmful birds included in the citizen image data is calculated by the autocorrelation analysis unit 230. was calculated, and by analyzing the self-spatial correlation, the location of the section where harmful tides were concentrated spatially was calculated.

(2) Derivation and analysis process of preferred habitat

Then, in the preferred habitat calculation unit 240, the preferred habitat was analyzed by reflecting the environmental variables preferred by the harmful tide (rook), and a species distribution model was derived. The application of species distribution model (SDM) is a technique to predict species distribution by utilizing environmental covariates related to emergence records, field surveys, or animal tracking data for previously existing species.

In the present invention, the preferred habitat calculation unit 240 is an SDM model that uses only appearance data for cases where it is difficult to acquire precise distribution data due to human limitations in a wide range of ecological surveys or technical, temporal, and financial reasons, etc., using the MaxENT program. The analysis was performed by applying

In order to select environmental variables preferred by rooks inhabiting urban areas, major classifications of urban ecological status in Suwon, altitude, planting rate, distance from farmland, distance from telephone poles, distance from streetlights, and height of buildings were used for analysis of preferred habitats for rooks. It was used as an environmental variable factor (FIG. 7).

Among the factors of the above-mentioned environmental variables, in the case of the urban ecology status map, the data of Suwon city updated in 2019 was used, and in order to drive MaxENT, the geographical data and resolution of each variable must match, so all dependent variables are Suwon city ecology The current status map was produced in units of 5 × 5m, which is the resolution standard for major classifications.

In the case of the urban ecological status map, the data of Suwon City, which was updated in 2019, was used, and the number of building floors and vegetation coverage data of the urban ecological status map were used for the number of floors and vegetation coverage.

Euclidean distance was applied to the distance from arable land by extracting the arable land data of the major classifications of the urban ecology map.

For the distance from the streetlight, the Euclidean distance was applied after acquiring the streetlight location data in Suwon City provided in 2021 from the public data portal. The distance from the telephone pole was primarily obtained from the data of the area where the telephone pole was underground provided by the Korea Electric Power Corporation. Afterwards, transportation facilities were extracted from the urban ecological status map, excluding the underground areas in the major classification, and telephone poles were placed at equal intervals of 30m on top of them. The altitude was extracted at a resolution of 10 × 10 m using the digital topographic map provided by the National Geospatial Information Platform.

The MaxEnt model obtains the AUC (Area under the ROC curve) value through ROC (Receiver operating characteristics) verification, and the reliability of this ROC value determines that the potential explained by the model is a meaningful value when the AUC value is 0.7 or higher. . As shown in the analysis result shown in FIG. 8, the AUC value of the rook distribution probability prediction result is 0.86 or more, which is judged to be highly reliable.

The reliability value (AUC) of the distribution of rooks in the time zone after sunrise was more than 0.87, which was sufficiently explained and verified to have power. In the case of the time zone after sunset, the AUC value was higher than 0.85. In the case of cross-validation, a total of 10 trials were conducted.

{Table 2: Summary of explanatory power test of rook distribution model after sunset}

9 shows (a) prediction data for appearance of a rookery habitat after sunrise, and (b) shows prediction data for appearance of a rookery habitat after sunset.

After sunrise, a high probability of appearance was confirmed around the rook eating area. Specifically, it was possible to predict a high probability of appearance in the eastern part of Suwon City, in the arable land and around traffic facilities and streetlights around it (Figure 3). In the case of the time zone after sunset, the probability of appearance was high in the vicinity of Suwon City Hall in the southwest of the downtown area away from the eating area, and the high probability of appearance could be predicted in the vicinity of transportation facilities near farmland.

{Table 3: Summary of the Rook MaxENT model after sunrise }

2) Reflection of environmental variables

Among the predicted models evaluated for the probability of appearance of rooks after sunrise, in the case of the contribution of the result variable of the Jackknife Test, when only individual variables for the probability of appearance were considered, the distance from farmland showed the highest contribution, and all variables At the same time, when kept in mind, DEM showed the highest contribution (FIG. 10). In the case of the probability of occurrence of rooks according to the distance from farmland, the probability of occurrence was rapidly high between 0 and 100 m and 3,000 and 3,500 m adjacent to the farmland. In addition, in the case of DEM, the appearance probability was high within the low DEM unit between 25 and 30 m.

As shown in FIG. 10, the importance index for the model showed high contribution in the order of distance from farmland (39.2%), DEM (25.5%), and distance from streetlights (22.3%) in predicting the distribution of rooks in the time zone after sunrise. , the following variables contributed to predicting the distribution of rooks in the following order: distance from utility pole (7.1%), urban ecological status map (4.9%), and building number of floors (1%). In the case of the loss rate, no contribution appeared (see Table 3).

When the model for predicting the appearance of rooks in Suwon City after sunrise was run, the occurrence prediction rate was high in the vicinity of cultivated land among the major categories of the urban ecological status. It was confirmed that the occurrence rate of rooks after 8:00 am significantly decreased when they moved more than 500m away from the farmland. In the case of DEM, the probability of appearance decreased in areas above 40 m, and it was found that low altitudes were generally preferred. It was found that the cultivated land was far from the forests in the outskirts of Suwon and was generally located at a low altitude.

The probability of occurrence according to the number of floors in the building was high around high-rise apartments (over 20 floors), which confirmed that a large number of high-rise apartments were located around farmland. Therefore, it is judged that the results were derived from these environmental factors rather than relying on specific results for the number of floors in the building.

In the case of the distance from the street lamp, the probability of appearance decreased when the distance was more than 100m. This is because rooks have a habit of starting to move to feeding areas according to the intensity of illumination among various environmental factors, and according to previous studies, rooks have behavioral characteristics of moving to feeding areas usually 30 to 40 minutes before sunrise (Hubalek, 2017 ). Therefore, it is believed that this is because rooks move to feeding places before sunrise even in Suwon-si, and preferentially select cultivated areas with higher illumination than surrounding areas.

In the case of the number of floors of a building after sunset, the probability of appearing around a mid-story (6th floor or more) building was high. When the detailed contribution values of the major classifications of the urban ecological status map, which accounted for the highest contribution, were identified, it was found that the residential and residential mixed land and residential areas were high, and among the building types, it was found that the surroundings of mid-rise or higher buildings that can shield the wind were mainly preferred. I was able to confirm.

In the case of the distance from farmland, a high distribution probability was shown at a distance between 1 and 3.5 km, and in the habitat prediction after sunset, it can be seen that rooks prefer downtown areas within a radius of 1 to 3.5 km around farmland in Suwon (FIG. 11). ).

In the case of the contribution of the variables resulting from the Jackknife Test after sunset, when only individual variables for the probability of occurrence were considered, the urban ecological status map showed the highest contribution, and when all variables were taken into account at the same time, Distance showed the highest contribution (FIG. 11). Therefore, even if many environmental variables matched the habitat of the rook, the presence or absence of a whole body tree was found to have a significant effect on the probability of appearance. In the case of the major classifications of the urban ecological status map, high appearance values were derived around mixed-residential and residential areas. In the case of the distance from the telephone pole, the maximum value appeared between 0 and 10m close to the telephone pole, and the probability of appearance decreased rapidly when it was farther than 100m (Figure 9). Even in the importance index for the model, in predicting the distribution of rooks in the time zone after sunset, the urban ecological status also showed high contributions in the order of major classification (37.4%), distance from utility poles (25.8%), and DEM (13,4%). Variable contributions for predicting the distribution of rooks appeared in the following order: distance from (11.8%), distance from farmland (7.9%), number of building floors (1.4%), and coverage (1.3%) (Table 4).

Unlike the preferred habitat variables of rooks after sunrise, the distance from telephone poles was more important than the distance from streetlights after sunset. can judge Looking at previous studies, birds in urban areas often use telephone poles to use as hunting grounds (Dwyer et al,. 2014). Since trees are used as a resting space, telephone poles in downtown areas with similar heights are preferred.

{Table 4: Summary of the MaxENT model of the rook after sunset}

The location data of rooks infesting Suwon City was collected as citizen science data, and the habitat prediction of the time zone after sunset and sunrise was analyzed by driving the MaxENT model. It was confirmed that the AUC value of the model had sufficient explanatory power over 0.8 for each sunset and sunrise time zone. In the habitat emergence prediction map implemented through ArcGIS, the location of the rook's preferred area after sunset and sunrise also showed a clear difference.

Percentage contribution (Percent Contribution) is the highest contribution rate in the order of distance from farmland, DEM, and distance from streetlights in the case of sunrise through seven environmental variables, and in the order of distance from streetlights, DEM, and streetlights in the case of after sunset. I was able to figure out what it occupied.

In addition, through the Jackknife Test result of the model, in the case of the time zone after sunrise, when only individual variables for the probability of appearance were considered, the distance from the farmland showed the highest contribution, and when all variables were taken into account at the same time DEM showed the highest contribution. In the time zone after sunset, when only individual variables for the probability of appearance were considered, the urban ecological status map showed the highest contribution, and when all variables were considered simultaneously, the distance from the telephone pole showed the highest contribution. That is, in the case of sunrise, it is important to consider the distance from farmland where the DEM is low and there are many street lights around and the intensity of illumination is high. In the case of after sunset, it was found that it is important to focus on the areas where utility poles are located and the DEM is low among residential mixed-use lands and residential areas with a height of 6 or more floors (6th floor or higher).

In the present invention, environmental variables based on such data are reflected, so that preferred tasting sites can be calculated.

As shown in FIG. 12, through the eradication area calculation unit 250, (a) self-spatial correlation data, (b) species distribution model analysis result, the preferred habitat and citizen image data are used to reflect the overlapping section of location points. Therefore, (c) a prediction point for intensive eradication is selected (prediction data for the eradication area of harmful tides is calculated). Thereafter, eradication is performed to verify the efficiency, and, as in (d), an appropriate eradication frequency can be derived.

In this case, the analysis of the self-spatial correlation data of FIG. 12 (a) is, as shown in FIG. In Methane 1-dong and Uman 2-dong, the highest concentration of rooks was found, and the appearance rate of rooks was significantly lower in Jangan-gu. In conclusion, as a result of the autospatial correlation analysis, the areas adjacent to Methane Building 3 and Methane Building 4 were selected as target areas for intensive eradication of rooks.

Then, based on the data on the result of eradication performed based on the prediction data of the harmful tide eradication area derived from the harmful tide eradication area prediction module 200, the reliability of the data can be confirmed in the eradication efficiency calculation module 300. let it be

14 illustrates (a) eradication result data, and (b) shows eradication result data as image data.

After that, as shown in FIG. 15, the effect of increasing or decreasing the occurrence rate of rooks according to the eradication and the area with high eradication effect are calculated, so that they can be used to establish eradication information in the future. Furthermore, as shown in FIG. 16, the correlation with the eradication frequency and the change in the prevalence according to the eradication frequency can be analyzed in the eradication efficiency calculation module 300 to verify and reflect the accuracy and reliability of the prediction system and method of the present invention. let it be

In the present invention, as described above, by analyzing the eradication results based on the eradication prediction data of harmful birds, it is possible to establish an optimal eradication frequency and a plan for eradication of harmful birds for the eradication area, and thus, by region using citizen science data It is possible to reduce the population and appearance rate of harmful birds.

According to the present invention, the functional configuration and execution operation applied to the method for predicting the harmful tide eradication area appearing in the urban area using the above-mentioned citizen science can be represented by functional block configurations and various processing steps. These functional blocks may be implemented with any number of hardware or/and software components that perform specific functions. For example, the present invention relates to integrated circuit components, such as memory, processing, logic, look-up tables, etc., that can perform various functions by means of the control of one or more microprocessors or other control devices. can be hired

Similar to components of the present invention that may be implemented as software programming or software elements, the present invention may include various algorithms implemented as data structures, processes, routines, or combinations of other programming constructs, including Python ), C, C++, Java, assembler, and the like, programming or scripting languages may be implemented. Functional aspects may be implemented in an algorithm running on one or more processors. In addition, the present invention may employ conventional techniques for electronic environment setting, signal processing, and/or data processing.

As described above, the technical spirit of the present invention has been specifically described in the preferred embodiment, but the above preferred embodiment is for explanation and not for limitation. As such, those skilled in the art will understand that various embodiments are possible through the combination of the embodiments of the present invention within the scope of the technical spirit of the present invention.

100: citizen data provision module
200: Harmful tide elimination area prediction module
300: elimination efficiency calculation module
400: integrated management module
500: elimination data providing module

Claims (9)

A citizen data providing module 100 for photographing images including harmful tides in the target area captured through a plurality of user terminals capable of wired/wireless communication and providing them as citizen image data;
Obtaining citizen image data transmitted from the citizen data providing module 100, performing local self-spatial correlation analysis based on the citizen image data,
Based on the information included in the citizen image data, calculating the location information, number and frequency of occurrence of harmful birds, analyzing the preferred habitat by reflecting the environmental variables preferred by the harmful birds, and calculating information on the intensive eradication area Harmful tide elimination area prediction module 200;
an eradication efficiency calculation module 300 that receives eradication result data performed based on the eradication area prediction information calculated in the harmful tide eradication area prediction module 200 and verifies reliability of the eradication area prediction information;
An integrated management module that reflects the reliability of the eradication result data verified in the eradication efficiency calculation module 300, monitors the appearance rate of harmful birds before and after eradication, and calculates and provides information on the correlation between eradication frequency and eradication efficiency. (400);
An eradication data providing module 500 for transmitting the result data of the eradication of harmful algae performed with respect to the eradication area prediction information calculated in the harmful algae eradication area prediction module 200 to the eradication efficiency calculation module 300;
Prediction system for the eradication of harmful algae in urban areas using citizen science.
The method of claim 1,
The harmful tide elimination area prediction module 200,
With respect to the citizen image data transmitted from the citizen data providing module 100, a data acquisition unit 210 for classifying and storing data collected at the same location information point at the same set time interval;
a population number derivation unit 220 for calculating the number of harmful birds included in the collected citizen image data;
An autocorrelation analysis unit that calculates the appearance time and latitude and longitude information of harmful tides included in the collected citizen image data, and analyzes the self-spatial correlation to calculate the position of a section where harmful tides are spatially concentrated ( 230);
a preferred habitat calculation unit 240 for analyzing preferred habitats by reflecting environmental variables preferred by the harmful birds and deriving a species distribution model;
Containing,
A system for predicting areas to eliminate harmful birds that appear in urban areas using citizen science.
The method of claim 2,
The eradication efficiency calculation module 300,
an eradication area data acquisition unit 310 for receiving and storing result data obtained by eradicating harmful tides based on the prediction data of the eradication area of harmful tides derived from the eradication area calculation unit 250;
an eradication performance data classification unit 320 which classifies the occurrence data of harmful tides in a specific section of the target area set in the eradication area prediction data and the appearance data of harmful tides after eradication;
an elimination efficiency verification unit 330 that evaluates the reliability of the prediction data of the eradication area of harmful algae derived from the eradication area calculation unit 250 based on the eradication performance data;
including,
A system for predicting areas to eliminate harmful birds that appear in urban areas using citizen science.
The method of claim 3,
The preferred habitat calculation unit 240,
The harmful tide is set to a rook (Corvus frugilegus),
The points where the rooks are likely to appear are derived using MaxENT to derive results according to the environmental variables preferred by the rooks,
A system for predicting areas to eliminate harmful birds that appear in urban areas using citizen science.
The method of claim 4,
The environment variables preferred by the rooks are:
Reflecting at least two factors, such as major classification of urban ecological status, altitude, vegetation rate, distance from farmland, distance from telephone pole, distance from streetlight, and height of building,
A system for predicting areas to eliminate harmful birds that appear in urban areas using citizen science.
In the method of predicting the haunting area of harmful tides appearing in an urban area and predicting the eradication area by using the system according to claim 5,
Step 1 of receiving citizen image data by taking images including harmful tides in the target area from user terminals equipped with cameras and communication modules;
A second step of classifying and storing data collected at the same location information point at the same set time interval with respect to the citizen image data transmitted in the first step in the eradication area prediction module 200;
The eradication area prediction module 200 calculates the number of harmful birds included in the collected citizen image data, calculates the appearance time and latitude and longitude information of harmful birds included in the citizen image data, and self-spatial correlation Step 3 of calculating the location of a section where harmful tides are concentrated spatially by analyzing the relationship;
Step 5 of analyzing preferred habitats by reflecting environmental variables preferred by the harmful birds in the eradication area prediction module 200 and deriving a species distribution model;
Step 6 of calculating prediction data of the eradication area of harmful tides by reflecting the overlapping section of the location points using the preferred habitat, self-spatial correlation data and citizen image data in the eradication area prediction module 200; ,
A method for predicting harmful tide control areas in urban areas using citizen science.
The method of claim 6,
After step 6 above,
Based on the prediction data of the eradication area, the result data of eradication of harmful tides is received and stored,
Classifying the appearance data of harmful tides in a specific section of the target area set in the prediction data of the eradication area and the appearance data of harmful tides after eradication;
Based on the eradication performance data, a seventh step of evaluating the reliability of the prediction data of the eradication area of the harmful tide; further comprising,
A method for predicting harmful tide control areas in urban areas using citizen science.
The method of claim 7,
The 5 steps are
The harmful tide is set to a rook (Corvus frugilegus),
Using MaxENT at the point where the rooks are likely to appear, derive results according to the environmental variables preferred by the rooks,
The environmental variables are performed by reflecting at least two factors of the urban ecological status map, altitude, vegetation rate, distance from cultivated land, distance from telephone pole, distance from street light, and height of building,
A method for predicting harmful tide control areas that appear in urban areas using citizen science.
A recording medium containing a program that performs a method for predicting an area for eradication of harmful birds appearing in an urban area using citizen science according to claim 8.

Images