Efficient monitoring of radar precipitation data and intelligent irrigation management platform

Abstract

The application relates to the technical field of data processing, in particular to a radar precipitation data efficient monitoring and intelligent irrigation management platform; first abnormal point positions and non-initial abnormal point positions are obtained according to the data quantity characteristics of intensity data clusters of echo intensity and the data difference characteristics of the intensity data clusters; point position connected domains are obtained according to the intensity data clusters of the non-initial abnormal point positions; spatial noise characteristic values are obtained according to the position distribution characteristics between the point position connected domains and the data difference characteristics in the point position connected domains; time noise characteristic values are obtained according to the echo intensity history of the non-initial abnormal point positions; second abnormal point positions are obtained according to the spatial noise characteristic values and the time noise characteristic values; the corresponding echo intensity is corrected according to the position characteristics of the first abnormal point positions and the second abnormal point positions; the precipitation amount is determined according to the corrected echo intensity, and the irrigation rule is adjusted, so that the accuracy of rainfall amount judgment and irrigation amount adjustment is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a radar precipitation data efficient monitoring and intelligent irrigation management platform. BACKGROUND

[0002] The intelligent irrigation management platform refers to intelligently managing the irrigation area through data analysis and water quantity control, so as to improve the automation and accuracy of irrigation. The existing intelligent irrigation technology can combine the monitoring of radar precipitation data, monitor the rainfall in the subsequent precipitation area through radar, and thus control the irrigation amount to avoid the over-flooding or insufficient irrigation amount in the irrigation area. Radar measures precipitation by detecting the scattering effect of precipitation particles on electromagnetic waves, and calculates the precipitation intensity and distribution. However, in the actual monitoring process, the radar monitoring of precipitation is easily disturbed by complex environment, resulting in inaccurate precipitation data monitored by some areas, reducing the accuracy of the intelligent irrigation management platform in adjusting the regional irrigation amount, and finally having a negative impact on the growth of crops. SUMMARY

[0003] In order to solve the above technical problems, the purpose of the present application is to provide a radar precipitation data efficient monitoring and intelligent irrigation management platform, and the technical solution adopted is as follows:

[0004] The data acquisition module is used to acquire the echo intensity of different point positions monitored by the weather radar.

[0005] The first rainfall analysis module is used to obtain different intensity data clusters according to the difference characteristics of the echo intensity of all point positions; obtain the initial abnormal degree according to the data amount characteristics in the intensity data cluster and the data difference characteristics between the intensity data cluster and other intensity data clusters; obtain the first abnormal point position and the non-initial abnormal point position according to the initial abnormal degree.

[0006] The second rainfall analysis module is used to obtain different point position connected domains according to the intensity data cluster of the non-initial abnormal point position; obtain the spatial noise characteristic value of the point position connected domain according to the position distribution characteristics between the point position connected domains and the data difference characteristics within the point position connected domain; obtain the time noise characteristic value according to the change characteristics of the historical echo intensity of the non-initial abnormal point position; obtain the noise degree according to the spatial noise characteristic value and the time noise characteristic value; obtain the second abnormal point position according to the noise degree.

[0007] The data adjustment module is used to correct the corresponding echo intensity according to the position characteristics of the first abnormal point position and the second abnormal point position; determine the precipitation amount and adjust the irrigation rules according to the corrected echo intensity.

[0008] Further, the step of obtaining different intensity data clusters according to the difference features of echo intensity of all point positions comprises:

[0009] The echo intensity of all point positions is clustered by a K-means clustering algorithm to obtain different intensity data clusters.

[0010] Further, the step of obtaining an initial abnormality degree according to the data quantity feature in the intensity data cluster and the data difference feature between the intensity data cluster and other intensity data clusters comprises:

[0011] The reciprocal of the echo intensity quantity value in the intensity data cluster is calculated and normalized to obtain a sparsity degree; the average value of the absolute value of the difference between the cluster center of the intensity data cluster and the cluster center of all other intensity data clusters is calculated and normalized to obtain a data difference degree; and the average value of the sparsity degree and the data difference degree is calculated to obtain the initial abnormality degree of the intensity data cluster.

[0012] Further, the step of obtaining a first abnormal point position and a non-initial abnormal point position according to the initial abnormality degree comprises:

[0013] When the initial abnormality degree of the intensity data cluster exceeds a preset first threshold value, the point position corresponding to the echo intensity in the intensity data cluster is a first abnormal point position, otherwise it is a non-initial abnormal point position.

[0014] Further, the step of obtaining different point position connected domains according to the intensity data cluster of the non-initial abnormal point position comprises:

[0015] Adjacent non-initial abnormal point positions belonging to the same intensity data cluster are connected to obtain a point position connected domain.

[0016] Further, the step of obtaining a spatial noise feature value of the point position connected domain according to the position distribution feature between the point position connected domains and the data difference feature in the point position connected domain comprises:

[0017] The sum value of the nearest distance between the point position connected domain and each other point position connected domain in the same intensity data cluster is calculated and normalized to obtain a distribution interval degree; the average value of the absolute value of the difference between the echo intensity of all point positions in the point position connected domain and the average value of the echo intensity is calculated and normalized to obtain a data dispersion degree; and the average value of the distribution interval degree and the data dispersion degree is calculated to obtain the spatial noise feature value of the point position connected domain.

[0018] Further, the step of obtaining a time noise feature value according to the change feature of the historical echo intensity of the non-initial abnormal point position comprises:

[0019] calculate the standard deviation of the echo intensity of the non-initial abnormal point position in the preset historical period and normalize it to obtain the dispersion degree; calculate the sum of the absolute values of the difference of the echo intensity of each adjacent time in the non-initial abnormal point position in the preset historical period and normalize it to obtain the fluctuation degree; calculate the average of the dispersion degree and the fluctuation degree to obtain the time noise characteristic value.

[0020] Further, the step of obtaining the noise degree according to the spatial noise characteristic value and the time noise characteristic value comprises:

[0021] calculate the average of the time noise characteristic value and the spatial noise characteristic value of the point position connected domain where the non-initial abnormal point position is located to obtain the noise degree of the non-initial abnormal point position.

[0022] Further, the step of obtaining the second abnormal point position according to the noise degree comprises:

[0023] the non-initial abnormal point position whose noise degree exceeds the preset second threshold value is taken as the second abnormal point position.

[0024] Further, the step of correcting the corresponding echo intensity according to the position characteristics of the first abnormal point position and the second abnormal point position comprises:

[0025] the point position connected domain without the second abnormal point position is taken as a normal connected domain; the echo intensity of the first abnormal point position or the second abnormal point position is replaced by the average of the echo intensity of the nearest normal connected domain.

[0026] The present application has the following beneficial effects:

[0027] In the present application, the intensity data cluster can distinguish different echo intensities and preliminarily determine the obvious noise data in the echo intensity; the initial abnormal degree can represent the possibility of the intensity data cluster being noise data; the first abnormal point position and the non-initial abnormal point position can distinguish the obvious noise data; the point position connected domain can further distinguish the noise data possibly existing in the non-initial point position; since the point position connected domain characteristics of the normal rainfall area and the environmental interference area are different, the spatial noise characteristic value can represent the possibility of the noise data existing in the point position connected domain; since the change characteristics of the echo intensity of the normal rainfall area and the environmental interference area are different, the time noise characteristic value can represent the possibility of the noise data existing in the non-initial abnormal point position; the noise degree can further accurately represent the possibility of the non-initial abnormal point being noise data. Finally, the corresponding echo intensity can be corrected according to the position characteristics of the first abnormal point position and the second abnormal point position, which can improve the accuracy of the irrigation area rainfall intensity judgment and make the irrigation amount adjustment more accurate. BRIEF DESCRIPTION OF DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, and the advantages thereof, below will briefly introduce the drawings needed in the embodiments or prior art description. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative effort.

[0029] Figure 1 A block diagram of a radar precipitation data efficient monitoring and intelligent irrigation management platform provided by an embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined purpose, the specific embodiments, structure, features and effects of a radar precipitation data efficient monitoring and intelligent irrigation management platform according to the present application will be described in detail below in combination with the drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0031] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0032] The specific scheme of the radar precipitation data efficient monitoring and intelligent irrigation management platform provided by the present application will be described in detail below in combination with the drawings.

[0033] Please refer to Figure 1 which shows a block diagram of a radar precipitation data efficient monitoring and intelligent irrigation management platform provided by an embodiment of the present application. The platform includes the following modules:

[0034] The data acquisition module S1 is used to acquire the echo intensity of different point positions monitored by the weather radar.

[0035] In the embodiment of the present application, the implementation scenario is that the intelligent irrigation management platform adjusts the irrigation amount according to the precipitation condition in the future period monitored by the weather radar, so as to avoid the problem of too large or too small irrigation amount. First, the precipitation data in the irrigation area for a period of time is collected by using the weather radar monitoring. The radar monitoring is a multi-point monitoring, and the echo intensity of a part of the region is collected by each point position monitoring. In the radar mosaic in the two-dimensional plane, each point position corresponds to an echo intensity, and the precipitation degree can be calculated through the echo intensity.

[0036] The first rainfall analysis module S2 is configured to obtain different intensity data clusters according to the difference characteristics of the echo intensities of all the point positions; obtain an initial abnormality degree according to the data quantity characteristics of the intensity data clusters and the data difference characteristics between the intensity data clusters and other intensity data clusters; and obtain first abnormal point positions and non-initial abnormal point positions according to the initial abnormality degree.

[0037] During radar monitoring of the precipitation process, complex environmental interference is likely to occur, resulting in noise data in the echo intensity, which usually includes ground clutter and thermal noise of the radar system; the ground clutter such as buildings, towers and artificial activity generated dust smoke groups and the like can reflect radar waves, generating false strong echoes at some positions; the thermal noise of the radar system such as random signals of electronic devices themselves can form scattered points in the weak echo area. The noise data in the echo intensity can interfere with the judgment of the precipitation intensity, thereby affecting the accuracy of the irrigation quantity adjustment and having a negative impact on the growth of crops. Therefore, it is necessary to correct the echo intensity of part of the point positions and improve the accuracy of the precipitation intensity analysis; first, different intensity data clusters are obtained according to the difference characteristics of the echo intensities of all the point positions; preferably, in the embodiments of the present application, the step of obtaining the intensity data clusters includes: clustering the echo intensities of all the point positions by a K-means clustering algorithm to obtain different intensity data clusters; it should be noted that the K-means clustering algorithm belongs to the prior art, and the specific steps will not be described here, and the number of clustering clusters is obtained by the elbow method. The intensity data clusters can divide data with similar echo intensities into a cluster; since the precipitation has a range, when the precipitation is about to occur in a certain area, the echo intensities of a large number of point positions will be affected similarly, and the influence range is larger than that of the ground clutter and the thermal noise; and the echo intensity affected by the precipitation is quite different from that of the ground clutter and the thermal noise; therefore, an initial abnormality degree can be obtained according to the data quantity characteristics of the intensity data clusters and the data difference characteristics between the intensity data clusters and other intensity data clusters.

[0038] Preferably, in the embodiments of the present application, the step of obtaining the initial abnormality degree comprises: calculating the reciprocal of the quantity value of the echo intensity in the intensity data cluster and normalizing to obtain the sparsity degree; in the embodiments of the present application, the normalization method is linear normalization. When the data quantity in the intensity data cluster is smaller, the sparsity degree is larger, which means that the echo intensity in the cluster is more likely to be noise data generated by environmental interference. The average value of the absolute value of the difference between the cluster class center of the intensity data cluster and the cluster class center of all other intensity data clusters is calculated and normalized to obtain the data difference degree; the noise data caused by ground clutter or thermal noise has a larger difference in echo intensity with the normal monitoring echo in other regions, while the echo intensities of different points in the normal rainfall area are relatively close, so when the echo intensity difference between the intensity data cluster and other intensity data clusters is larger, the data difference degree is larger, which means that the intensity data cluster is more likely to be generated by environmental interference. The average value of the sparsity degree and the data difference degree is calculated to obtain the initial abnormality degree of the intensity data cluster; when the initial abnormality degree is larger, it means that the echo intensity in the intensity data cluster is more likely to be noise data rather than real echo intensity.

[0039] Further, the first abnormal point and the non-initial abnormal point can be obtained according to the initial abnormality degree; preferably, in the embodiments of the present application, when the initial abnormality degree of the intensity data cluster exceeds a preset first threshold, the point corresponding to the echo intensity in the intensity data cluster is the first abnormal point, otherwise it is the non-initial abnormal point. Since the value range of the initial abnormality degree in the embodiments of the present application is 0 to 1, the initial abnormality degree with noise data characteristics tends to 1, and the initial abnormality degree of normal echo intensity tends to 0, which are distributed at both ends of the value range, so the preset first threshold in the embodiments of the present application is 0.5, which can be determined by the implementer according to the implementation scene. The first abnormal point means that the echo intensity of the point is obviously abnormal, and the credibility of the echo intensity of the non-initial abnormal point needs to be further judged.

[0040] The second rainfall analysis module S3 is configured to obtain different point connected domains according to the intensity data cluster of the non-initial abnormal point; obtain a spatial noise feature value of the point connected domain according to the position distribution characteristics between the point connected domains and the data difference characteristics in the point connected domain; obtain a time noise feature value according to the change characteristics of the historical echo intensity of the non-initial abnormal point; obtain a noise degree according to the spatial noise feature value and the time noise feature value; and obtain a second abnormal point according to the noise degree.

[0041] Since the first abnormal point is obtained based on the echo intensity value screening, only the obvious noise data can be distinguished. However, part of the noise data has similar echo intensity value with the normal rainfall area, which leads to the point being mistaken for a rainfall area. For example, the dense insect group often seen in farmland irrigation area. The distribution range of the insect group is large due to the characteristics of insect aggregation habitat, and the weak echo of the insect group is easy to be confused with light rain, forming noise data which is not easy to distinguish directly. Therefore, further analysis is needed for the non-initial abnormal point. First, different point connected domains are obtained according to the intensity data cluster of the non-initial abnormal point. Specifically, the non-initial abnormal points belonging to the same intensity data cluster are connected to obtain a point connected domain. Different point connected domains are formed in the two-dimensional radar mosaic. Because the distribution of the insect group is dense or sparse, the distribution shape and area are not fixed, so the distribution of the corresponding noise data in the two-dimensional plane will show the characteristics of discrete gaps. The point connected domain corresponding to the rainfall area is relatively dense. Moreover, the density of the insect group is different, leading to a large difference in reflected echo intensity, while the rainfall intensity in the same rainfall area is similar, and the corresponding echo intensity is similar. Therefore, the spatial noise feature value of the point connected domain can be obtained according to the position distribution characteristics between the point connected domains and the data difference characteristics in the point connected domain.

[0042] Preferably, in the embodiments of the present application, the step of obtaining the spatial noise feature value comprises: calculating the sum value of the nearest distance of the point connected domain and each other point connected domain in the same intensity data cluster and normalizing to obtain the distribution interval degree; the farther the distance between the point connected domains, the greater the distribution interval degree, which means that the point connected domain is more likely to be formed by the influence of the insect group. Calculate the average value of the absolute value of the difference between the echo intensity of all points in the point connected domain and the average value of the echo intensity and normalize to obtain the data dispersion degree; the greater the difference between the echo intensity of the point in the point connected domain and the average value of the echo intensity, the greater the data dispersion degree, which means that the echo intensity distribution is more inconsistent, and it is more likely that the insect group has different density. The smaller the data dispersion degree, the more similar the echo intensity, which is more likely to be the echo intensity corresponding to the rainfall area. Calculate the average value of the distribution interval degree and the data dispersion degree to obtain the spatial noise feature value of the point connected domain; the greater the spatial noise feature value, the more likely the point connected domain is caused by the distribution of the insect group. The formula for obtaining the spatial noise feature value comprises:

[0043]

[0044] In the formula, R represents the spatial noise feature value of the point connected domain, N represents the number of other point connected domains in the same intensity data cluster of the point connected domain, Dn represents the nearest distance between the point connected domain and the nth other point connected domain. represents the distribution interval, M represents the number of point positions in the point position connected domain, represents the echo intensity of the mth point position, represents the echo intensity mean value of the point position connected domain, represents the data dispersion degree.

[0045] Further, the rainfall intensity changes less or more slowly in the same point position in a period of time, and the free speed of the insect group is fast, and it is difficult to be stationary for a long time in the same point position; therefore, when the echo intensity of the same point position in the history of multiple monitoring appears a large change, it is more likely to be caused by the insect group. Therefore, the time noise feature value is obtained according to the change characteristics of the echo intensity in the history of the non-initial abnormal point position; preferably, in the embodiment of the present application, the step of obtaining the time noise feature value comprises: calculating the standard deviation of the echo intensity of the preset history period of the non-initial abnormal point position and normalizing to obtain the dispersion degree; the greater the dispersion degree, the greater the difference in echo intensity, and the less likely it is that the echo intensity is affected by the rainfall area; in the embodiment of the present application, the preset history period is a period of time including the latest ten monitoring time points of the current monitoring time point, and the implementer can determine it according to the implementation scene. The sum value of the absolute value of the difference of the echo intensity of each adjacent time point in the preset history period of the non-initial abnormal point position is calculated and normalized to obtain the fluctuation degree; the greater the fluctuation degree, the faster the change in echo intensity, and the less likely it is that the echo intensity is affected by the rainfall area. The average value of the dispersion degree and the fluctuation degree is calculated to obtain the time noise feature value of the non-initial abnormal point position; the greater the time noise feature value, the more likely it is that the echo intensity of the non-initial abnormal point position is affected by the insect group.

[0046] After obtaining the spatial noise feature value and the time noise feature value, the noise degree can be obtained according to the spatial noise feature value and the time noise feature value, preferably, in the embodiment of the present application, the step of obtaining the noise degree comprises: calculating the average value of the time noise feature value and the spatial noise feature value of the point position connected domain where the non-initial abnormal point position is located to obtain the noise degree of the non-initial abnormal point position; the greater the noise degree, the more likely it is that the echo intensity of the non-initial abnormal point is noise data, and it is difficult to reflect the true rainfall intensity. Further, the second abnormal point position can be obtained according to the noise degree, specifically comprising: taking the non-initial abnormal point position with a noise degree exceeding a preset second threshold as the second abnormal point position; since the value range of the noise degree is 0 to 1, and the noise degree of the noise data and the normal echo data is distributed at both ends of the value range, in the embodiment of the present application, the preset second threshold is 0.5, and the implementer can determine it according to the implementation scene. The second abnormal point position represents the point position with echo intensity similar to that of other regional point positions but belonging to noise data.

[0047] The data adjustment module S4 is configured to correct the corresponding echo intensity according to the position characteristics of the first abnormal point and the second abnormal point, and determine the precipitation and adjust the irrigation rules according to the corrected echo intensity.

[0048] After the first abnormal point and the second abnormal point are obtained in all points, in order to improve the accuracy of the rainfall intensity judgment, the echo intensity of such points needs to be adjusted, so the corresponding echo intensity is corrected according to the position characteristics of the first abnormal point and the second abnormal point. In the embodiment of the present application, the step of correcting the echo intensity preferably includes: regarding the point connected domain without the second abnormal point as a normal connected domain; because the rainfall conditions of the adjacent regions are close, the echo intensity of the adjacent points is close; therefore, the echo intensity of the first abnormal point or the second abnormal point is replaced by the mean value of the echo intensity of the nearest normal connected domain. After the echo intensity is corrected, the precipitation can be determined according to the corrected echo intensity and the irrigation rules can be adjusted. The radar echo intensity is converted into rainfall intensity by the existing precipitation estimation QPE method, and the irrigation rules are adjusted by the intelligent irrigation management platform according to the rainfall intensity of the future period; for example, if there is heavy rainfall in the future, the regional irrigation amount is reduced; or if there is no rainfall in the future, the regional irrigation amount is increased. The implementer can determine the irrigation amount adjustment rules according to the implementation scene, so as to protect the growth environment of crops sensitive to water amount. Thus, by adjusting the echo intensity of the noise data that may appear in the weather radar, the accuracy of the rainfall intensity judgment of the irrigation area is improved, and the irrigation amount adjustment is more accurate.

[0049] In summary, the embodiment of the present application provides an efficient monitoring and intelligent irrigation management platform for radar precipitation data. The first abnormal point and the non-initial abnormal point are obtained according to the data amount characteristics in the intensity data cluster of the echo intensity and the data difference characteristics of the intensity data cluster. The point connected domain is obtained according to the intensity data cluster of the non-initial abnormal point. The spatial noise characteristic value is obtained according to the position distribution characteristics between the point connected domains and the data difference characteristics in the point connected domain. The time noise characteristic value is obtained according to the historical echo intensity of the non-initial abnormal point. The second abnormal point is obtained according to the spatial noise characteristic value and the time noise characteristic value. The corresponding echo intensity is corrected according to the position characteristics of the first abnormal point and the second abnormal point. The precipitation is determined according to the corrected echo intensity, and the irrigation rules are adjusted, thereby improving the accuracy of the rainfall amount judgment and the irrigation amount adjustment.

[0050] It should be noted that the above-mentioned embodiment sequence of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0051] The various embodiments described in this specification are presented by way of example, and each embodiment is not inherently more important than any other embodiment.

Claims

1. A platform for efficient monitoring of radar precipitation data and intelligent irrigation management, characterized in that, The platform comprises the following modules: a data acquisition module, configured to acquire echo intensity of different point positions monitored by a weather radar; a first rainfall analysis module, configured to obtain different intensity data clusters according to difference features of echo intensity of all point positions; obtain an initial abnormality degree according to data quantity features in the intensity data cluster and data difference features between the intensity data cluster and other intensity data clusters; obtain a first abnormal point position and a non-initial abnormal point position according to the initial abnormality degree; a second rainfall analysis module, configured to obtain different point position connected domains according to intensity data clusters of the non-initial abnormal point positions; obtain a spatial noise feature value of the point position connected domain according to position distribution features between the point position connected domains and data difference features within the point position connected domain; obtain a time noise feature value according to change features of historical echo intensity of the non-initial abnormal point positions; obtain a noise degree according to the spatial noise feature value and the time noise feature value; obtain a second abnormal point position according to the noise degree; a data adjustment module, configured to correct corresponding echo intensity according to position features of the first abnormal point position and the second abnormal point position; determine rainfall and adjust irrigation rules according to the corrected echo intensity.

2. The platform for efficient monitoring of radar precipitation data and intelligent irrigation management as claimed in claim 1, wherein, The step of obtaining different intensity data clusters according to difference features of echo intensity of all point positions comprises: perform clustering on echo intensity of all point positions by a K-means clustering algorithm to obtain different intensity data clusters.

3. The platform for efficient monitoring of radar precipitation data and intelligent irrigation management as claimed in claim 1, wherein, The step of obtaining an initial abnormality degree according to data quantity features in the intensity data cluster and data difference features between the intensity data cluster and other intensity data clusters comprises: calculate a reciprocal of echo intensity quantity value in the intensity data cluster and normalize to obtain a sparsity degree; calculate an average value of absolute values of differences between cluster centers of the intensity data cluster and all other intensity data clusters and normalize to obtain a data difference degree; calculate an average value of the sparsity degree and the data difference degree to obtain the initial abnormality degree of the intensity data cluster.

4. The platform for efficient monitoring of radar precipitation data and intelligent irrigation management as claimed in claim 1, wherein, The step of obtaining a first abnormal point position and a non-initial abnormal point position according to the initial abnormality degree comprises: when the initial abnormality degree of the intensity data cluster exceeds a preset first threshold value, the point position corresponding to the echo intensity in the intensity data cluster is a first abnormal point position, otherwise, it is a non-initial abnormal point position.

5. The platform for efficient monitoring of radar rainfall data and intelligent irrigation management as claimed in claim 1, wherein, The step of obtaining different point position connected domains according to intensity data clusters of the non-initial abnormal point positions comprises: connect adjacent non-initial abnormal point positions belonging to the same intensity data cluster to obtain a point position connected domain.

6. The platform for efficient monitoring of radar rainfall data and intelligent irrigation management as claimed in claim 1, wherein, The step of obtaining a spatial noise feature value of the point position connected domain according to position distribution features between the point position connected domains and data difference features within the point position connected domain comprises: calculate a sum value of nearest distances of the point position connected domain and each other point position connected domain in the same intensity data cluster and normalize to obtain a distribution interval degree; calculate an average value of absolute values of differences between echo intensity of all point positions in the point position connected domain and an average value of echo intensity and normalize to obtain a data dispersion degree; calculate an average value of the distribution interval degree and the data dispersion degree to obtain the spatial noise feature value of the point position connected domain.

7. The platform for efficient monitoring of radar precipitation data and intelligent irrigation management as claimed in claim 1, wherein, The step of obtaining a time noise characteristic value according to the change characteristic of the echo intensity of the non-initial abnormal point position history comprises: calculating the standard deviation of the echo intensity of the non-initial abnormal point position in a preset historical period and normalizing to obtain a dispersion degree; calculating the sum value of the absolute value of the difference of the echo intensity of each adjacent time of the non-initial abnormal point position in a preset historical period and normalizing to obtain a fluctuation degree; and calculating the average of the dispersion degree and the fluctuation degree to obtain the time noise characteristic value.

8. The platform for efficient monitoring of radar rainfall data and intelligent irrigation management as claimed in claim 1, wherein, The step of obtaining a noise degree according to the spatial noise characteristic value and the time noise characteristic value comprises: calculating the average of the time noise characteristic value and the spatial noise characteristic value of the point position connected domain where the non-initial abnormal point position is located to obtain the noise degree of the non-initial abnormal point position.

9. The platform for efficient monitoring of radar rainfall data and intelligent irrigation management as claimed in claim 1, wherein, The step of obtaining a second abnormal point position according to the noise degree comprises: the non-initial abnormal point position whose noise degree exceeds a preset second threshold is taken as the second abnormal point position.

10. The platform for efficient monitoring of radar precipitation data and intelligent irrigation management as claimed in claim 1, wherein, The step of correcting the corresponding echo intensity according to the position characteristic of the first abnormal point position and the second abnormal point position comprises: a point position connected domain without a second abnormal point position is taken as a normal connected domain; and the echo intensity of the first abnormal point position or the second abnormal point position is replaced by the average of the echo intensity of the nearest normal connected domain.

Images