Water conservancy infrastructure risk early warning method, system and equipment and storage medium

Abstract

The invention discloses a water conservancy infrastructure risk early warning method, system and device and a storage medium, and the method comprises the steps: obtaining the optical remote sensing data, single-view complex product data, ground distance product data and pixel distance of a target region, and the marking value of a water conservancy infrastructure; determining a first time sequence deformation sequence of the target area based on the single-view complex product data and the pixel distance; determining a first soil water content sequence of the target area based on the optical remote sensing data and the ground distance product data; calculating a correlation coefficient of the first time sequence deformation sequence and the first soil water content sequence; and inputting the labeled value of the water conservancy infrastructure, the first time sequence deformation sequence, the first soil water content sequence and the correlation coefficient into a disaster monitoring model to obtain a disaster occurrence probability value output by the disaster monitoring model, and performing early warning based on the disaster occurrence probability value. And the early warning accuracy of the disaster of the water conservancy infrastructure of the river and lake in the target area is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of water conservancy infrastructure risk early warning, in particular to a water conservancy infrastructure risk early warning method, system, device and storage medium. BACKGROUND

[0002] As the core facilities of the flood and tide prevention engineering system, the structural safety of water conservancy infrastructure (such as dams, embankments and dykes) is directly related to the safety of the coastal cities, farmland and people's life and property. With the increase of service time and the long-term effect of external environment (such as rainfall, water flow erosion and groundwater change), water conservancy infrastructure is prone to seepage, piping, settlement and landslide hazards. If these hazards are not identified in time, they may cause major disasters such as dam break, so it is crucial to accurately and efficiently detect the risk of water conservancy infrastructure.

[0003] At present, the risk detection methods of water conservancy infrastructure mostly rely on manual inspection, point sensor (such as osmometer, displacement meter) monitoring or empirical evaluation based on the inherent properties of embankments (such as soil type, construction grade and service life), which leads to a lack of comprehensiveness in risk judgment and is difficult to meet the needs of water conservancy infrastructure safety management in complex environments. SUMMARY

[0004] The present application aims to at least solve the technical problems existing in the prior art. To this end, the present application provides a water conservancy infrastructure risk early warning method, system, device and storage medium, which can integrate a first time sequence rainfall sequence, a second time sequence rainfall sequence, optical remote sensing data, single-view complex product data and geodetic product data to improve the accuracy of water conservancy infrastructure risk early warning.

[0005] In a first aspect, the present application provides a water conservancy infrastructure risk early warning method, comprising the following steps: obtaining optical remote sensing data, single-view complex product data, geodetic product data, pixel distance and labeled value of water conservancy infrastructure of a target area, wherein the single-view complex product data and the geodetic product data are data of a satellite revisit period at a to-be-predicted time obtained by a heavy rail time sequence synthetic aperture radar, and the pixel distance is a pixel distance of synthetic aperture radar data obtained by a heavy rail time sequence synthetic aperture radar; determining a first time sequence deformation sequence of the target area based on the single-view complex product data and the pixel distance; determining a first soil moisture content sequence of the target area based on the optical remote sensing data and the geodetic product data; calculating the correlation coefficient of the first time sequence deformation sequence and the first soil moisture content sequence; Input the labeled value of the water conservancy infrastructure, the first time sequence deformation sequence, the first soil moisture sequence and the correlation coefficient into a disaster monitoring model to obtain a disaster occurrence probability value output by the disaster monitoring model, and perform early warning based on the disaster occurrence probability value.

[0006] The water conservancy infrastructure risk early warning method according to the embodiments of the present application has at least the following beneficial effects: The method comprises the following steps: obtaining optical remote sensing data, single-view complex product data, ground distance product data, pixel distance and a labeled value of a water conservancy infrastructure of a target region, wherein the single-view complex product data and the ground distance product data are data of a satellite revisit period at a to-be-predicted moment obtained by a repeat-pass time sequence synthetic aperture radar, and the pixel distance is a pixel distance of synthetic aperture radar data obtained by the repeat-pass time sequence synthetic aperture radar; determining a first time sequence deformation sequence of the target region based on the single-view complex product data and the pixel distance; determining a first soil moisture sequence of the target region based on the optical remote sensing data and the ground distance product data; calculating a correlation coefficient of the first time sequence deformation sequence and the first soil moisture sequence; inputting the labeled value of the water conservancy infrastructure, the first time sequence deformation sequence, the first soil moisture sequence and the correlation coefficient into a disaster monitoring model to obtain a disaster occurrence probability value output by the disaster monitoring model, and performing early warning based on the disaster occurrence probability value. The present application integrates the optical remote sensing data, the single-view complex product data, the ground distance product data, the pixel distance and the labeled value of the water conservancy infrastructure to construct a disaster monitoring model, thereby breaking through the data island and mechanism deficiency of traditional technologies and improving the early warning accuracy of disasters of the water conservancy infrastructure in the target region.

[0007] According to some embodiments of the present application, the first time sequence deformation sequence of the target region is determined based on the single-view complex product data and the pixel distance, which comprises the following steps: A second time sequence deformation sequence of the single-view complex product data is calculated by a small-baseline set interferometric synthetic aperture radar method, wherein the time sequence deformation sequence comprises a plurality of time sequence deformation values and longitude and latitude corresponding to each time sequence deformation value; A third time sequence deformation sequence of the single-view complex product data is calculated by a permanent scatterer synthetic aperture radar interferometry method; The distance between a first type of point and a second type of point in a preset coordinate system is calculated as a first point distance, wherein the first type of point is any point in the second time sequence deformation sequence, the second type of point is any point in the third time sequence deformation sequence, and the points in the time sequence deformation sequence are obtained by projecting the longitude and latitude corresponding to each time sequence deformation value into the preset coordinate system; The first time sequence deformation sequence is determined based on the second time sequence deformation sequence, the third time sequence deformation sequence, the first point distance and the pixel distance.

[0008] According to some embodiments of the present application, the first time sequence of deformation is determined based on the second time sequence of deformation, the third time sequence of deformation, the first inter-point distance and the pixel distance, including: All points in the second time sequence of deformation whose distance to any point in the third time sequence of deformation is less than a first preset distance threshold are filtered out as homonymic points in the second time sequence of deformation, wherein the first preset distance threshold is one-tenth of the pixel distance; A fourth time sequence of deformation is determined, wherein the fourth time sequence of deformation is a sequence composed of all points in the second time sequence of deformation except the homonymic points in the second time sequence of deformation; A first trend item of the third time sequence of deformation is calculated by a time sequence decomposition algorithm, and a second trend item of the fourth time sequence of deformation is calculated by the time sequence decomposition algorithm, wherein the first trend item belongs to the third time sequence of deformation, and the second trend item belongs to the fourth time sequence of deformation; A distance between the second type of points and a third type of points in the preset coordinate system is calculated as a second inter-point distance, wherein the third type of points are any one of the points in the fourth time sequence of deformation; Points whose second inter-point distance is less than a second preset distance threshold are filtered out from the points in the third time sequence of deformation and the fourth time sequence of deformation, wherein the point pair is composed of the point in the third time sequence of deformation and the point in the fourth time sequence of deformation corresponding to the second inter-point distance less than the second preset distance threshold; A third trend item corresponding to all points in the third time sequence of deformation in the point pair is determined, and a fourth trend item corresponding to all points in the fourth time sequence of deformation in the point pair is determined, wherein the third trend item belongs to the first trend item, and the fourth trend item belongs to the second trend item; The third trend item is substituted for the fourth trend item in the fourth time sequence of deformation to obtain a fifth time sequence of deformation; The third time sequence of deformation and the fifth time sequence of deformation are combined to obtain the first time sequence of deformation.

[0009] According to some embodiments of the present application, the first soil water content sequence of the target area is determined based on the optical remote sensing data and the land product data, including: Polarization data and cross-polarization data of the land product data are extracted; The polarization data is filtered to obtain filtered polarization data, and the cross-polarization data is filtered to obtain filtered cross-polarization data; geocode the filtered co-polarization data to obtain coded co-polarization data, and geocode the filtered cross-polarization data to obtain coded cross-polarization data; radiometrically calibrate the coded co-polarization data to obtain a co-polarization backscatter coefficient, and radiometrically calibrate the coded cross-polarization data to obtain a cross-polarization backscatter coefficient; determine a joint backscatter coefficient based on the co-polarization backscatter coefficient, the cross-polarization backscatter coefficient, and a preset backscatter coefficient parameter value; calculate a normalized vegetation index and a normalized water index of the optical remote sensing data; input the joint backscatter coefficient, the normalized vegetation index, and the normalized water index into a soil moisture prediction model to obtain the first soil moisture sequence output by the soil moisture prediction model.

[0010] According to some embodiments of the present application, the preset backscatter coefficient parameter value includes a first parameter value and a second parameter value, and the determination of the joint backscatter coefficient based on the co-polarization backscatter coefficient, the cross-polarization backscatter coefficient, and the preset backscatter coefficient parameter value includes: multiplying the co-polarization backscatter coefficient by the first parameter value to obtain a first coefficient; multiplying the cross-polarization backscatter coefficient by the second parameter value to obtain a second coefficient; adding the first coefficient and the second coefficient to obtain the joint backscatter coefficient.

[0011] According to some embodiments of the present application, the calculation of the correlation coefficient of the first time-series deformation sequence and the first soil moisture sequence includes: extracting the first time-series deformation sequence in a preset time window as a second time-series deformation sequence, and extracting the first soil moisture sequence in a preset time window as a second soil moisture sequence; calculating a time-series deformation mean of the second time-series deformation sequence, and calculating a soil moisture mean of the second soil moisture sequence; determining the correlation coefficient based on the second time-series deformation sequence, the second soil moisture sequence, the time-series deformation mean, and the soil moisture mean.

[0012] According to some embodiments of the present application, before obtaining the labeled value of the water conservancy infrastructure in the target area, the method further includes: In the case that the soil type, the process type, the geological condition type, the construction level and the used years of the water conservancy infrastructure in the target area are obtained, the soil type, the process type, the geological condition type and the construction level of the water conservancy infrastructure are encoded by a one-hot encoding method respectively, to obtain a soil type encoding value, a process type encoding value, a geological condition type encoding value and a construction level encoding value; The used years are rounded to an integer, and the integer is taken as a used years label value; The label value of the water conservancy infrastructure in the target area is obtained, including: The soil type encoding value, the process type encoding value, the geological condition type encoding value, the construction level encoding value and the used years label value of the water conservancy infrastructure are taken as the label value of the water conservancy infrastructure.

[0013] In a second aspect of the present application, a water conservancy infrastructure risk early warning system is provided, which comprises: A data acquisition module is configured to acquire optical remote sensing data, single-view complex product data, ground distance product data, pixel distance and label value of water conservancy infrastructure in a target area, wherein the single-view complex product data and the ground distance product data are data of a satellite revisit cycle to which a to-be-predicted moment belongs, obtained by a repeat-pass time series synthetic aperture radar, and the pixel distance is a pixel distance of synthetic aperture radar data obtained by a repeat-pass time series synthetic aperture radar; A first time sequence deformation sequence determination module is configured to determine a first time sequence deformation sequence of the target area based on the single-view complex product data and the pixel distance; A first soil moisture content sequence determination module is configured to determine a first soil moisture content sequence of the target area based on the optical remote sensing data and the ground distance product data; A correlation coefficient calculation module is configured to calculate a correlation coefficient of the first time sequence deformation sequence and the first soil moisture content sequence; An early warning module is configured to input the label value of the water conservancy infrastructure, the first time sequence deformation sequence, the first soil moisture content sequence and the correlation coefficient into a disaster monitoring model, to obtain a disaster occurrence probability value output by the disaster monitoring model, and to perform early warning based on the disaster occurrence probability value.

[0014] The system obtains optical remote sensing data of a target region, single-view complex product data, ground distance product data, pixel distance and labeled values of water conservancy infrastructure, wherein the single-view complex product data and the ground distance product data are data of a satellite revisit period of a to-be-predicted moment obtained through a re-rail time sequence synthetic aperture radar, and the pixel distance is a pixel distance of synthetic aperture radar data obtained through the re-rail time sequence synthetic aperture radar; a first time sequence deformation sequence of the target region is determined based on the single-view complex product data and the pixel distance; a first soil moisture content sequence of the target region is determined based on the optical remote sensing data and the ground distance product data; a correlation coefficient of the first time sequence deformation sequence and the first soil moisture content sequence is calculated; the labeled values of the water conservancy infrastructure, the first time sequence deformation sequence, the first soil moisture content sequence and the correlation coefficient are input into a disaster monitoring model to obtain a disaster occurrence probability value output by the disaster monitoring model, and early warning is performed based on the disaster occurrence probability value. The present application integrates optical remote sensing data, single-view complex product data, ground distance product data, pixel distance and labeled values of water conservancy infrastructure to construct a disaster monitoring model, thereby breaking through the data island and mechanism deficiency of traditional technologies and improving the early warning accuracy of disasters of water conservancy infrastructure in the target region.

[0015] In a third aspect, the present application provides a water conservancy infrastructure risk early warning electronic device, comprising at least one control processor and a memory in communication connection with the at least one control processor; the memory stores instructions executable by the at least one control processor, and the instructions are executed by the at least one control processor to enable the at least one control processor to execute the water conservancy infrastructure risk early warning method described above.

[0016] In a fourth aspect, the present application provides a computer readable storage medium, which stores computer executable instructions for causing a computer to execute the water conservancy infrastructure risk early warning method described above.

[0017] It should be noted that the beneficial effects between the second aspect to the fourth aspect of the present application and the prior art are the same as the beneficial effects between the water conservancy infrastructure risk early warning system described above and the prior art, which will not be described here in detail.

[0018] Additional aspects and advantages of the present application will be in part apparent and in part pointed out hereinafter. BRIEF DESCRIPTION OF DRAWINGS

[0019] The above and / or additional aspects and advantages of the present application will become apparent and be readily appreciated from the following description, including the appended drawings, wherein: Figure 1 is a flowchart of the water conservancy infrastructure risk early warning method provided by the present application; Figure 2 is a structural schematic diagram of an embodiment of a water conservancy infrastructure risk early warning system provided by the present application; Figure 3 is a structural schematic diagram of an embodiment of an electronic device provided by the present application. DETAILED DESCRIPTION

[0020] Embodiments of the present application are described in detail below, examples of the embodiments being shown in the accompanying drawings, in which the same or similar reference numerals represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by reference to the accompanying drawings are exemplary and are only used to explain the present application and cannot be understood as limiting the present application.

[0021] In the description of the present application, if there is a description of first, second, etc., it is only for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features or implicitly indicating the order of the indicated technical features.

[0022] In the description of the present application, it should be understood that the orientation description, such as up, down, etc., indicates the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, which is only for the convenience of describing the present application and simplifying the description, and therefore cannot be understood as indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present application.

[0023] In the description of the present application, it should be noted that, unless otherwise explicitly limited, the words such as setting, mounting, connecting, etc. should be broadly understood, and those skilled in the art can reasonably determine the specific meaning of the above words in the present application in combination with the specific content of the technical solution.

[0024] Water conservancy infrastructure (such as dams, embankments and embankments) is the core facility of the flood control and moisture prevention engineering system, and its structural safety is directly related to the safety of the coastal city, farmland and people's life and property. With the increase of service time and the long-term effect of external environment (such as rainfall, water flow erosion and groundwater change, etc.), water conservancy infrastructure is prone to leakage, piping, settlement and landslide hazards, and if not identified in time, it may cause dam break and other major disasters, so it is very important to accurately and efficiently detect the risk of water conservancy infrastructure.

[0025] At present, the risk detection method of water conservancy infrastructure mainly relies on manual inspection, point sensor (such as osmometer, displacement meter) monitoring or empirical evaluation based on the inherent properties of embankment (such as soil type, construction grade and service life), which leads to lack of comprehensiveness in risk judgment and difficulty in meeting the needs of water conservancy infrastructure safety management in complex environment.

[0026] To solve the above technical defects, the embodiment of the present application provides a water conservancy infrastructure risk early warning method, system, device and storage medium.

[0027] Please refer to Figure 1 , which is a flowchart of a water conservancy infrastructure risk early warning method provided by the embodiment of the present application. The method is applied to an electronic device, which can be a server or the like. As shown in Figure 1 , the water conservancy infrastructure risk early warning method comprises: Step S101, optical remote sensing data, single-view complex product data, ground distance product data, pixel distance and annotation value of the water conservancy infrastructure of a target area are acquired, wherein the single-view complex product data and the ground distance product data are data of a satellite revisit period to which a to-be-predicted moment belongs, obtained by a re-rail time sequence synthetic aperture radar, and the pixel distance is a pixel distance of synthetic aperture radar data obtained by the re-rail time sequence synthetic aperture radar; Step S102, a first time sequence deformation sequence of the target area is determined based on the single-view complex product data and the pixel distance; Step S103, a first soil moisture content sequence of the target area is determined based on the optical remote sensing data and the ground distance product data; Step S104, a correlation coefficient of the first time sequence deformation sequence and the first soil moisture content sequence is calculated; Step S105, the annotation value of the water conservancy infrastructure, the first time sequence deformation sequence, the first soil moisture content sequence and the correlation coefficient are input into a disaster monitoring model, a disaster occurrence probability value output by the disaster monitoring model is obtained, and early warning is performed based on the disaster occurrence probability value.

[0028] The above water conservancy infrastructure can include but is not limited to dams, embankments and embankments.

[0029] The soil material type code value, the process type code value, the geological condition type code value, the construction grade code value and the used time annotation value.

[0030] The above first time sequence deformation sequence can include but is not limited to a first time sequence deformation variable sequence and a first time sequence deformation rate sequence, and the above first time sequence deformation sequence can be a time sequence deformation sequence arranged in chronological order.

[0031] The above first soil moisture content sequence can be a soil moisture content sequence arranged in chronological order.

[0032] In the above step S104, early warning can be performed based on the disaster occurrence probability value, which can be performed by reminding the user by short message when the disaster occurrence probability value is greater than a preset early warning threshold value, wherein the preset early warning threshold value can be a constant value set in advance according to actual needs.

[0033] The method comprises the following steps: acquiring optical remote sensing data, single-view complex product data, ground distance product data, pixel distance and labeled values of water conservancy infrastructure of a target area, wherein the single-view complex product data and the ground distance product data are data of a satellite revisit period to which a to-be-predicted moment belongs and are obtained by a re-radar time series synthetic aperture radar, and the pixel distance is a pixel distance of synthetic aperture radar data obtained by the re-radar time series synthetic aperture radar; determining a first time series deformation sequence of the target area based on the single-view complex product data and the pixel distance; determining a first soil moisture content sequence of the target area based on the optical remote sensing data and the ground distance product data; calculating a correlation coefficient of the first time series deformation sequence and the first soil moisture content sequence; inputting the labeled values of the water conservancy infrastructure, the first time series deformation sequence, the first soil moisture content sequence and the correlation coefficient into a disaster monitoring model to obtain a disaster occurrence probability value output by the disaster monitoring model, and performing early warning based on the disaster occurrence probability value. The present application integrates the optical remote sensing data, the single-view complex product data, the ground distance product data, the pixel distance and the labeled values of the water conservancy infrastructure, constructs the disaster monitoring model, breaks through the data island and mechanism deficiency of the traditional technology, and improves the early warning accuracy of disasters of the water conservancy infrastructure in the target area. In some embodiments, step S102 can include, but is not limited to, steps S201 to S204: Step S201, calculating a second time series deformation sequence of the single-view complex product data by a small-baseline set interferometric synthetic aperture radar method, wherein the time series deformation sequence comprises a plurality of time series deformation values and longitude and latitude corresponding to each time series deformation value; Step S202, calculating a third time series deformation sequence of the single-view complex product data by a permanent scatterer synthetic aperture radar interferometry method; Step S203, calculating a distance between a first type of point and a second type of point in a preset coordinate system as a first inter-point distance, wherein the first type of point is any one point in the second time series deformation sequence, the second type of point is any one point in the third time series deformation sequence, and the points in the time series deformation sequence are obtained by projecting the longitude and latitude corresponding to each time series deformation value into the preset coordinate system; Step S204, determining a first time series deformation sequence based on the second time series deformation sequence, the third time series deformation sequence, the first inter-point distance and the pixel distance.

[0034] The second time series deformation sequence can be a time series deformation sequence arranged in chronological order.

[0035] The third time series deformation sequence can be a time series deformation sequence arranged in chronological order.

[0036] The preset coordinate system can be a geodetic coordinate system.

[0037] The first time sequence of deformation is determined by a small baseline set interferometric synthetic aperture radar method and a permanent scatterer synthetic aperture radar interferometry method, and the accuracy of the first time sequence of deformation is improved.

[0038] In some embodiments, step S204 can include, but is not limited to, steps S301-S308: Step S301, points in the second time sequence of deformation are traversed, all points in the second time sequence of deformation with a distance less than a first preset distance threshold from any point in the third time sequence of deformation are screened out as homonymous points in the second time sequence of deformation, and the first preset distance threshold is one-tenth of a pixel distance; Step S302, a fourth time sequence of deformation is determined, wherein the fourth time sequence of deformation is a sequence composed of all points in the second time sequence of deformation except the homonymous points in the second time sequence of deformation; Step S303, a first trend item of the third time sequence of deformation is calculated by a time series decomposition algorithm, and a second trend item of the fourth time sequence of deformation is calculated by the time series decomposition algorithm, wherein the first trend item belongs to the third time sequence of deformation, and the second trend item belongs to the fourth time sequence of deformation; Step S304, a distance between the second type of points and the third type of points in a preset coordinate system is calculated as a second inter-point distance, wherein the third type of points are any points in the fourth time sequence of deformation; Step S305, points in the third time sequence of deformation and the fourth time sequence of deformation are traversed, and a point pair with a second inter-point distance less than a second preset distance threshold is screened out, wherein the point pair is composed of a point in the third time sequence of deformation and a point in the fourth time sequence of deformation corresponding to the second inter-point distance less than the second preset distance threshold; Step S306, a third trend item corresponding to all points in the third time sequence of deformation in the point pair is determined, and a fourth trend item corresponding to all points in the fourth time sequence of deformation in the point pair is determined, wherein the third trend item belongs to the first trend item, and the fourth trend item belongs to the second trend item; Step S307, the third trend item is replaced with the fourth trend item in the fourth time sequence of deformation to obtain a fifth time sequence of deformation; Step S308, the third time sequence of deformation and the fifth time sequence of deformation are combined to obtain the first time sequence of deformation.

[0039] The third trend item and the fourth trend item are determined based on a time series decomposition algorithm, the third trend item is substituted into the fourth time sequence deformation sequence to obtain a fifth time sequence deformation sequence, the third time sequence deformation sequence and the fifth time sequence deformation sequence are combined to obtain the first time sequence deformation sequence, and the trend item can reflect the core component of the long-term evolution direction of data, thereby improving the accuracy of the first time sequence deformation sequence and providing more accurate data basis for subsequent disaster occurrence probability value prediction.

[0040] In some embodiments, step S103 can include but is not limited to steps S401 to S407: Step S401, extracting co-polarization data and cross-polarization data of the ground distance product data; Step S402, filtering the co-polarization data to obtain filtered co-polarization data, and filtering the cross-polarization data to obtain filtered cross-polarization data; Step S403, geocoding the filtered co-polarization data to obtain encoded co-polarization data, and geocoding the filtered cross-polarization data to obtain encoded cross-polarization data; Step S404, radiometrically scaling the encoded co-polarization data to obtain co-polarization backscatter coefficients, and radiometrically scaling the encoded cross-polarization data to obtain cross-polarization backscatter coefficients; Step S405, determining joint backscatter coefficients based on the co-polarization backscatter coefficients, the cross-polarization backscatter coefficients, and preset backscatter coefficient parameter values; Step S406, calculating normalized vegetation indices and normalized water indices of the optical remote sensing data; Step S407, inputting the joint backscatter coefficients, the normalized vegetation indices, and the normalized water indices into a soil moisture prediction model to obtain a first soil moisture sequence output by the soil moisture prediction model.

[0041] The preset backscatter coefficient parameter values include a first parameter value and a second parameter value, the first parameter value can be 0.6, and the second parameter value can be 0.4.

[0042] The soil moisture is predicted by the joint backscatter coefficients, the normalized vegetation indices, and the normalized water indices, the accuracy of the first soil moisture sequence is improved, and more accurate data basis is provided for subsequent disaster occurrence probability value prediction.

[0043] In some embodiments, step S405 can include but is not limited to steps S501 to S503: Step S501, multiplying the co-polarization backscatter coefficients by the first parameter value to obtain first coefficients; Step S502: Multiply the cross-polarization backscattering coefficient by the second parameter value to obtain the second coefficient; Step S503: Add the first coefficient and the second coefficient to obtain the joint backscattering coefficient.

[0044] This application improves the accuracy of joint backscattering coefficient calculation by giving different parameter values ​​for the co-polarized backscattering coefficient and the cross-polarized backscattering coefficient.

[0045] In some embodiments, step S104 may include, but is not limited to, steps S601 to S603: Step S601: Extract the first temporal deformation sequence within the preset time window as the second temporal deformation sequence; extract the first soil moisture content sequence within the preset time window as the second soil moisture content sequence. Step S602: Calculate the mean temporal deformation of the second temporal deformation sequence; calculate the mean soil moisture content of the second soil moisture content sequence; Step S603: Determine the correlation coefficient based on the second time-series deformation sequence, the second soil moisture content sequence, the time-series deformation mean, and the soil moisture content mean.

[0046] The aforementioned preset time window can be a value that can be preset according to actual needs. The time length of the preset time window is less than or equal to the time length of the first time-series deformation sequence, and the time length of the preset time window is less than or equal to the time length of the second soil moisture content sequence.

[0047] In step S603, the correlation coefficient is calculated based on the second time-series deformation sequence, the second soil moisture content sequence, the time-series deformation mean, and the soil moisture content mean using the following formula: ; in, The correlation coefficient, The mean of time-series deformation, This represents the average soil moisture content. The starting point within the preset time window. This is the end time point of the first temporal deformation sequence. The first in the second temporal deformation sequence The second time-series deformation value. The first in the second soil moisture content sequence The second soil moisture content value.

[0048] This application introduces a correlation coefficient to provide more accurate data for predicting the probability of subsequent disasters.

[0049] In some embodiments, before obtaining the labeled values ​​of the water infrastructure in the target area, the method further includes: Step S701, under the condition of obtaining the soil type, process type, geological condition type, construction level and service life of the water conservancy infrastructure in the target area, the soil type, process type, geological condition type and construction level of the water conservancy infrastructure are encoded respectively by one-hot encoding method, and the soil type encoding value, process type encoding value, geological condition type encoding value and construction level encoding value are obtained; Step S702, rounding the service life to an integer, and taking the integer as the service life label value; Obtaining the label value of the water conservancy infrastructure in the target area, comprising: Step S703, taking the soil type encoding value, process type encoding value, geological condition type encoding value, construction level encoding value and service life label value of the water conservancy infrastructure as the label value of the water conservancy infrastructure.

[0050] The soil type can include but is not limited to clay, loam and bentonite.

[0051] The process type can include but is not limited to earth-rock dam, concrete dam and masonry embankment.

[0052] The geological condition type can include but is not limited to soft foundation and rock foundation.

[0053] The construction level can include but is not limited to level 1, level 2, level 3, level 4 and level 5.

[0054] The service life is the historical use time of the water conservancy infrastructure in the target area.

[0055] The rounding of the service life can be rounding up the historical use time of the water conservancy infrastructure in the target area.

[0056] The present application calculates the possibility of disaster of river and lake embankment in the target area, and warns the possible risk hidden danger. The risk area is quickly located by the embankment inspection personnel, the inspection workload of the inspection personnel is reduced, and the work efficiency of the inspection personnel is improved.

[0057] In addition, referring to Figure 2 An embodiment of the present application provides a water conservancy infrastructure risk warning system, comprising a data acquisition module 1100, a first time sequence deformation sequence determination module 1200, a first soil water content sequence determination module 1300, a correlation coefficient calculation module 1400 and a warning module 1500, wherein: The data acquisition module 1100 is configured to acquire optical remote sensing data, single-view complex product data, ground distance product data, pixel distance, and labeled values of water conservancy infrastructure of a target region, wherein the single-view complex product data and the ground distance product data are data of a satellite revisit period to which a to-be-predicted moment belongs and which is obtained by a re-radar time sequence synthetic aperture radar, and the pixel distance is a pixel distance of synthetic aperture radar data obtained by the re-radar time sequence synthetic aperture radar. The first time sequence deformation sequence determination module 1200 is configured to determine a first time sequence deformation sequence of the target region based on the single-view complex product data and the pixel distance. The first soil moisture content sequence determination module 1300 is configured to determine a first soil moisture content sequence of the target region based on the optical remote sensing data and the ground distance product data. The correlation coefficient calculation module 1400 is configured to calculate a correlation coefficient of the first time sequence deformation sequence and the first soil moisture content sequence. The early warning module 1500 is configured to input the labeled values of the water conservancy infrastructure, the first time sequence deformation sequence, the first soil moisture content sequence, and the correlation coefficient into a disaster monitoring model, obtain a disaster occurrence probability value output by the disaster monitoring model, and perform early warning based on the disaster occurrence probability value.

[0058] The system acquires optical remote sensing data, single-view complex product data, ground distance product data, pixel distance, and labeled values of water conservancy infrastructure of a target region, wherein the single-view complex product data and the ground distance product data are data of a satellite revisit period to which a to-be-predicted moment belongs and which is obtained by a re-radar time sequence synthetic aperture radar, and the pixel distance is a pixel distance of synthetic aperture radar data obtained by the re-radar time sequence synthetic aperture radar; a first time sequence deformation sequence of the target region is determined based on the single-view complex product data and the pixel distance; a first soil moisture content sequence of the target region is determined based on the optical remote sensing data and the ground distance product data; a correlation coefficient of the first time sequence deformation sequence and the first soil moisture content sequence is calculated; the labeled values of the water conservancy infrastructure, the first time sequence deformation sequence, the first soil moisture content sequence, and the correlation coefficient are input into a disaster monitoring model, a disaster occurrence probability value output by the disaster monitoring model is obtained, and early warning is performed based on the disaster occurrence probability value. The present application integrates optical remote sensing data, single-view complex product data, ground distance product data, pixel distance, and labeled values of water conservancy infrastructure, constructs a disaster monitoring model, breaks through the data island and mechanism defects of traditional technologies, and improves the early warning accuracy of disasters of water conservancy infrastructure in a target region.

[0059] It should be noted that the system embodiment and the method embodiment described above are based on the same inventive concept, and therefore the related content of the method embodiment described above is also applicable to the system embodiment, which will not be described here in detail.

[0060] Figure 3A hardware structure schematic diagram of water conservancy infrastructure risk early warning provided by an embodiment of the present application is shown.

[0061] The water conservancy infrastructure risk early warning device can include a processor 301 and a memory 302 storing computer program instructions.

[0062] Specifically, the processor 301 can include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement one or more embodiments of the present application.

[0063] The memory 302 can include a mass storage for data or instructions. By way of example and not limitation, the memory 302 can include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. Where appropriate, the memory 302 can include removable or non-removable (or fixed) media. Where appropriate, the memory 302 can be internal or external to the integrated gateway disaster recovery device. In some embodiments, the memory 302 is a non-volatile solid-state memory.

[0064] In some embodiments, the memory 302 can include read-only memory (ROM), random access memory (RAM), a disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical, or other physical / tangible memory storage device. Thus, generally, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software that, when executed (e.g., by one or more processors), is operable to perform operations described with reference to the methods according to an aspect of the present disclosure.

[0065] The processor 301 implements any one of the water conservancy infrastructure risk early warning methods in the above embodiments by reading and executing the computer program instructions stored in the memory 302.

[0066] In one example, the water conservancy infrastructure risk early warning device can further include a communication interface 303 and a bus 310. As shown, the processor 301, the memory 302, and the communication interface 303 are connected through the bus 310 and complete communication with each other. Figure 3

[0067] The communication interface 303 is mainly used to realize the communication between the modules, devices, units and / or equipment in the embodiments of the present application.​

[0068] Bus 310 includes hardware, software, or both, to couple components of the water infrastructure risk early warning device to each other and to couple components of the water infrastructure risk early warning device to other devices. While bus 310 is shown for the sake of clarity as a single bus, it can comprise one or more buses operating together. Bus 310 can be implemented using any suitable type, unidirectional and / or bidirectional, of connection including an address bus, a data bus, a control bus, a graphics bus, a video bus, a signaling bus, a digital

[0069] The water infrastructure risk early warning device can perform the water infrastructure risk early warning method in the embodiments of the present application based on the three-dimensional design model, thereby realizing the water infrastructure risk early warning method and system described in combination with Figure 1 and Figure 2 the above embodiments.

[0070] In addition, in combination with the water infrastructure risk early warning method in the above embodiments, the embodiments of the present application can provide a computer storage medium to realize. The computer storage medium has computer program instructions stored thereon; the computer program instructions are executed by a processor to realize any one of the water infrastructure risk early warning methods in the above embodiments.

[0071] It needs to be made clear that the present application is not limited to the specific configurations and processes described above and shown in the drawings. For the sake of brevity, detailed descriptions of well-known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present application are not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between steps, after understanding the spirit of the present application.

[0072] The functional blocks shown in the structural block diagrams above can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, and the like. When implemented in software, the elements of the present application are program or code segments that are used to perform the required tasks. The program or code segments can be stored in a machine-readable medium, or transmitted through a data signal carried in a carrier wave over a transmission medium or communication link. A "machine-readable medium" includes any medium that can store or transport information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memories, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, and the like. The code segments can be downloaded via computer networks such as the Internet, intranets, and the like.

[0073] It is also important to note that the examples mentioned in the present application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the examples, or in an order different from the examples, or several steps can be performed simultaneously.

[0074] The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other processing device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other processing device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer program instructions can also be stored in a computer readable medium that can direct a computer, other programmable data processing apparatus, or other processing device to operate in a particular manner, such that the instructions stored in the computer readable medium produce an article of manufacture including instructions which implement the function / act specified in the flowchart and / or block diagram block or blocks. The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other processing device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other processing device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer program instructions can also be stored in a computer readable medium that can direct a computer, other programmable data processing apparatus, or other processing device to operate in a particular manner, such that the instructions stored in the computer readable medium produce an article of manufacture including instructions which implement the function / act specified in the flowchart and / or block diagram block or blocks.

[0075] The above merely describes a specific implementation of the present application. Those skilled in the art can clearly understand the specific working processes of the system, modules and units described above for the convenience and brevity of description, and can refer to the corresponding processes in the foregoing method embodiments, which will not be described herein again. It should be understood that the protection scope of the present application is not limited to this, and any person skilled in the art can easily think of various equivalent modifications or replacements within the technical range disclosed by the present application, and these modifications or replacements should be covered within the protection scope of the present application.

Claims

1. A water conservancy infrastructure risk early warning method, characterized in that, The water conservancy infrastructure risk early warning method comprises: Obtaining optical remote sensing data, single-view complex product data, ground distance product data, pixel distance and labeled value of water conservancy infrastructure of a target area, wherein the single-view complex product data and the ground distance product data are data of a satellite revisit period of a to-be-predicted time obtained by a heavy rail time sequence synthetic aperture radar, and the pixel distance is a pixel distance of synthetic aperture radar data obtained by the heavy rail time sequence synthetic aperture radar; Determine a first time sequence deformation sequence of the target area based on the single-view complex product data and the pixel distance; Determine a first soil moisture content sequence of the target area based on the optical remote sensing data and the ground distance product data; Calculate a correlation coefficient of the first time sequence deformation sequence and the first soil moisture content sequence; Input the labeled value of the water conservancy infrastructure, the first time sequence deformation sequence, the first soil moisture content sequence and the correlation coefficient into a disaster monitoring model to obtain a disaster occurrence probability value output by the disaster monitoring model, and perform early warning based on the disaster occurrence probability value.

2. The water infrastructure risk early warning method of claim 1, wherein, The method comprises the following steps: Calculate a second time sequence deformation sequence of the single-view complex product data by a small-baseline set interferometric synthetic aperture radar method, wherein the time sequence deformation sequence comprises a plurality of time sequence deformation values and corresponding longitude and latitude of each time sequence deformation value; Calculate a third time sequence deformation sequence of the single-view complex product data by a permanent scatterer synthetic aperture radar interferometry method; Calculate a distance between a first type of point and a second type of point in a preset coordinate system as a first point distance, wherein the first type of point is any point in the second time sequence deformation sequence, the second type of point is any point in the third time sequence deformation sequence, and the point in the time sequence deformation sequence is obtained by projecting the corresponding longitude and latitude of each time sequence deformation value into the preset coordinate system; Determine the first time sequence deformation sequence based on the second time sequence deformation sequence, the third time sequence deformation sequence, the first point distance and the pixel distance.

3. The water infrastructure risk early warning method of claim 2, wherein, The method comprises the following steps: Traverse the points in the second time sequence deformation sequence, and filter out all points in the second time sequence deformation sequence whose distance from any point in the third time sequence deformation sequence is less than a first preset distance threshold as homonymous points in the second time sequence deformation sequence, wherein the first preset distance threshold is one tenth of the pixel distance; Determine a fourth time sequence deformation sequence, wherein the fourth time sequence deformation sequence is a sequence composed of all points in the second time sequence deformation sequence except the homonymous points in the second time sequence deformation sequence; calculating a first trend item of the third time sequence of deformations by a time series decomposition algorithm, and calculating a second trend item of the fourth time sequence of deformations by the time series decomposition algorithm, wherein the first trend item belongs to the third time sequence of deformations, and the second trend item belongs to the fourth time sequence of deformations; calculating a distance between the second type of points and third type of points in the preset coordinate system as a second inter-point distance, wherein the third type of points are any points in the fourth time sequence of deformations; traversing points in the third time sequence of deformations and the fourth time sequence of deformations, and screening out a point pair with a second inter-point distance less than a second preset distance threshold, wherein the point pair is composed of a point in the third time sequence of deformations and a point in the fourth time sequence of deformations corresponding to the second inter-point distance less than the second preset distance threshold; determining a third trend item corresponding to all points in the third time sequence of deformations in the point pair, and determining a fourth trend item corresponding to all points in the fourth time sequence of deformations in the point pair, wherein the third trend item belongs to the first trend item, and the fourth trend item belongs to the second trend item; replacing the fourth trend item in the fourth time sequence of deformations with the third trend item to obtain a fifth time sequence of deformations; combining the third time sequence of deformations and the fifth time sequence of deformations to obtain the first time sequence of deformations.

4. The water infrastructure risk early warning method of claim 1, wherein, The first soil water content sequence of the target area is determined based on the optical remote sensing data and the land product data, including: extracting co-polarization data and cross-polarization data of the land product data; filtering the co-polarization data to obtain filtered co-polarization data, and filtering the cross-polarization data to obtain filtered cross-polarization data; geocoding the filtered co-polarization data to obtain encoded co-polarization data, and geocoding the filtered cross-polarization data to obtain encoded cross-polarization data; radiometrically calibrating the encoded co-polarization data to obtain co-polarization backscatter coefficients, and radiometrically calibrating the encoded cross-polarization data to obtain cross-polarization backscatter coefficients; determining joint backscatter coefficients based on the co-polarization backscatter coefficients, the cross-polarization backscatter coefficients, and preset backscatter coefficient parameter values; calculating normalized vegetation indices and normalized water indices of the optical remote sensing data; inputting the joint backscatter coefficients, the normalized vegetation indices, and the normalized water indices into a soil water content prediction model to obtain the first soil water content sequence output by the soil water content prediction model.

5. The water infrastructure risk early warning method of claim 4, wherein, The preset backscatter coefficient parameter values include first parameter values and second parameter values, and the joint backscatter coefficients are determined based on the co-polarization backscatter coefficients, the cross-polarization backscatter coefficients, and the preset backscatter coefficient parameter values, including: multiplying the co-polarization backscatter coefficients by the first parameter values to obtain first coefficients; multiplying the cross-polarization backscatter coefficients by the second parameter values to obtain second coefficients; Adding the first coefficient and the second coefficient obtains the joint backscattering coefficient.

6. The water infrastructure risk early warning method of claim 1, wherein, The method further comprises: extracting the first time-series deformation sequence within a preset time window as a second time-series deformation sequence; and extracting the first soil moisture content sequence within the preset time window as a second soil moisture content sequence; calculating a time-series deformation mean value of the second time-series deformation sequence; and calculating a soil moisture content mean value of the second soil moisture content sequence; determining the correlation coefficient based on the second time-series deformation sequence, the second soil moisture content sequence, the time-series deformation mean value, and the soil moisture content mean value.

7. The water infrastructure risk early warning method of claim 6, wherein, Before acquiring the labeled value of the water conservancy infrastructure in the target region, the method further comprises: under the condition that the soil material type, the process type, the geological condition type, the construction level, and the used age of the water conservancy infrastructure in the target region are acquired, the soil material type, the process type, the geological condition type, and the construction level of the water conservancy infrastructure are encoded by a one-hot encoding method to obtain a soil material type encoding value, a process type encoding value, a geological condition type encoding value, and a construction level encoding value; the used age is rounded to an integer, and the integer is taken as a used age labeled value; the labeled value of the water conservancy infrastructure in the target region comprises: the soil material type encoding value, the process type encoding value, the geological condition type encoding value, the construction level encoding value, and the used age labeled value of the water conservancy infrastructure are taken as the labeled value of the water conservancy infrastructure.

8. A water infrastructure risk early warning system characterized in that, The water conservancy infrastructure risk early warning system comprises: a data acquisition module configured to acquire optical remote sensing data, single-view complex product data, ground distance product data, pixel distance, and a labeled value of a water conservancy infrastructure in a target region, wherein the single-view complex product data and the ground distance product data are data of a satellite revisit period to which a to-be-predicted moment belongs, which are obtained by a re-radar time-series synthetic aperture radar, and the pixel distance is a pixel distance of synthetic aperture radar data obtained by the re-radar time-series synthetic aperture radar; a first time-series deformation sequence determination module configured to determine a first time-series deformation sequence of the target region based on the single-view complex product data and the pixel distance; a first soil moisture content sequence determination module configured to determine a first soil moisture content sequence of the target region based on the optical remote sensing data and the ground distance product data; a correlation coefficient calculation module configured to calculate a correlation coefficient of the first time-series deformation sequence and the first soil moisture content sequence; an early warning module configured to input the labeled value of the water conservancy infrastructure, the first time-series deformation sequence, the first soil moisture content sequence, and the correlation coefficient into a disaster monitoring model to obtain a disaster occurrence probability value output by the disaster monitoring model, and perform early warning based on the disaster occurrence probability value.

9. A water infrastructure risk early warning device, characterized by, comprises at least one control processor and a memory connected in communication with the at least one control processor; The memory stores instructions executable by the at least one control processor, the instructions being executed by the at least one control processor to enable the at least one control processor to perform a water infrastructure risk early warning method as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer readable storage medium stores computer executable instructions for causing a computer to perform a water infrastructure risk early warning method as claimed in any one of claims 1 to 7.

Images