Ecological protection and restoration monitoring method and system based on spatiotemporal big data

Abstract

The present application relates to the technical field of water leakage monitoring, and particularly relates to an ecological protection and restoration monitoring method and system based on space-time big data. According to the surface hydrological path characteristics and underground space position characteristics of a space unit, the present application determines the surface runoff time consumption and underground water leakage time consumption, and generates a theoretical simulation flow by time lag calculation of rainfall, obtains the underground water leakage tendency probability value of the space unit by combining the deviation of the outlet measured flow, and combines the vegetation recession characteristics of the space unit in the drought monitoring period and the terrain undulation characteristics of adjacent space units to screen and merge the leakage units, thereby obtaining the underground leakage connected body. According to the underground water leakage tendency probability value of the space unit in the overlapping area between the underground leakage connected body and the preset legal construction boundary, the present application obtains the estimated amount of anti-seepage grouting material. The present application is based on the hydrological time lag backstepping bottom leakage probability, and fuses the vegetation recession and terrain clustering to accurately locate the false ecological restoration area, thereby improving the accuracy of ecological protection monitoring.

Description

Technical Field

[0001] This invention relates to the field of water leakage monitoring technology, specifically to an ecological protection and restoration monitoring method and system based on spatiotemporal big data. Background Technology

[0002] Territorial space ecological protection and restoration projects are important strategic measures to improve the regional ecological environment and curb soil erosion. In conventional ecological restoration projects, construction companies typically use methods such as shallow soil covering and surface seeding to rapidly increase the vegetation coverage rate in a short period of time, thereby meeting the project acceptance standards.

[0003] Currently, conventional ecological monitoring methods mainly rely on optical satellite remote sensing images to extract surface vegetation cover, using this as the core indicator for judging the effectiveness of ecological restoration. However, karst landforms generally possess two different hydrological structures: one on the surface and one underground. During rainfall events, large amounts of water cannot be effectively retained by the shallow root systems of herbaceous plants, but instead quickly penetrate the shallow soil layer and drain away through unsealed underground karst fissures and sinkholes. This phenomenon of surface greening and continuous leakage at the bottom leads to unsustainable soil and water conservation effects, with vegetation rapidly withering during droughts, resulting in typical pseudo-ecological restoration. Furthermore, optical remote sensing can only observe the greening status of the surface and cannot penetrate the surface to detect leakage in deep underground channels, easily leading to erroneous conclusions about whether ecological restoration has met standards. Summary of the Invention

[0004] To address the technical problem of inaccurate ecological protection monitoring caused by the disconnect between surface vegetation cover and subsurface loss in karst landforms, resulting in false ecological restoration, this invention aims to provide an ecological protection and restoration monitoring method and system based on spatiotemporal big data. The specific technical solution adopted is as follows: In a first aspect, one embodiment of the present invention provides an ecological protection and restoration monitoring method based on spatiotemporal big data, the method comprising: Acquire the rainfall at each spatial unit within the target watershed at each moment during the hydrological monitoring period, as well as the measured outflow at the watershed outlet at the corresponding moment; Based on the surface hydrological path characteristics and underground spatial location characteristics of each spatial unit, the surface runoff time and underground leakage time of each spatial unit to the watershed outlet are determined respectively. By utilizing the surface runoff time and underground leakage time of each spatial unit, the rainfall at each moment is calculated using time-delay calculation to generate the theoretical simulated flow rate at the corresponding moment. By combining the deviation between the theoretical simulated flow rate and the measured flow rate at the outlet, the underground leakage tendency probability value of each spatial unit is obtained. Based on the vegetation decline characteristics and groundwater leakage tendency probability values ​​of each spatial unit during the drought monitoring period following the hydrological monitoring period, as well as the topographic relief characteristics between adjacent spatial units, leakage units in each spatial unit are screened; and the leakage units are connected and merged to obtain a groundwater leakage interconnection. Based on the probability value of underground water leakage tendency of spatial units within the overlapping area of ​​each underground leakage interconnection and the preset legal construction boundary, the estimated amount of anti-seepage grouting material is obtained.

[0005] Furthermore, obtaining the probability value of underground water leakage tendency for each spatial unit includes: For each spatial unit within the target watershed, a probability variable for groundwater leakage tendency to be solved is set with a value range of 0 to 1. Select any moment within the hydrological monitoring period as the example moment. Based on the surface runoff time and the groundwater leakage time of each spatial unit, use the groundwater leakage tendency probability variable to allocate the rainfall with time lag, and determine the surface flow contribution value and groundwater flow contribution value of the spatial unit at the example moment respectively. The theoretical simulated flow at the example time is obtained by summing the surface flow contribution and subsurface flow contribution values ​​of all spatial units within the target watershed at the example time. Based on the sum of squares of the differences between the theoretical simulated flow and the measured outlet flow at the same moment during the hydrological monitoring period, an objective optimization function is constructed. Under the constraint of the range of values, the value of the groundwater leakage tendency probability variable of each spatial unit when the objective optimization function takes the minimum value is taken as the groundwater leakage tendency probability value of the corresponding spatial unit.

[0006] Further, determining the surface flow contribution value and groundwater flow contribution value of the spatial unit at the example time includes: For each spatial unit, the difference between the example time and the surface runoff time and the groundwater leakage time of the spatial unit is calculated and recorded as the surface runoff time and the groundwater runoff time, respectively. If the surface runoff time is greater than zero, the product of constant 1 and the difference between the probability variable of the underground leakage tendency of the spatial unit, the rainfall of the spatial unit at the surface runoff time, and the preset volume conversion constant is used as the surface flow contribution value of the spatial unit at the example time; otherwise, the surface flow contribution value is zero. If the underground runoff time is greater than zero, the product of the rainfall, the probability variable of underground water leakage tendency, and the preset volume conversion constant of the spatial unit at the underground runoff time is taken as the underground flow contribution value of the spatial unit at the example time; otherwise, the underground flow contribution value is zero.

[0007] Furthermore, the filtering of missing units in each spatial unit includes: Obtain the vegetation degradation gradient of each spatial unit during the drought monitoring period following the hydrological monitoring period; The mean groundwater leakage tendency probability and the mean vegetation degradation gradient of all spatial units within the target watershed are calculated respectively. The groundwater leakage tendency probability and vegetation degradation gradient of each spatial unit are standardized, and the product of the two standardized results is used as the composite anomaly index of the spatial unit. An undirected graph is constructed with each spatial unit as a physical node and includes virtual leakage sources and normal sinks, denoted as the spatial feature adjacency graph. The weight of the edge connecting each physical node to the leakage source is set to the power of the composite anomaly index of the physical node with the natural constant as the base. The weight of the edge connecting each physical node to the normal sink is set to the power of the composite anomaly index of the physical node with the inverse of the natural constant as the base. The weight of the edge connecting two physical nodes is set to the reciprocal of the sum of the absolute difference of the elevation values ​​of the corresponding spatial units of the two physical nodes and a preset minimum positive number. Using the maximum flow minimum cut algorithm, with the constraint of minimizing the sum of the weights of the cut edges, the entity nodes in the spatial feature adjacency graph are divided into leakage nodes connected to the leakage source and normal nodes connected to the normal sink; the spatial unit corresponding to the leakage node is denoted as the leakage unit.

[0008] Furthermore, obtaining the vegetation degradation gradient of each spatial unit during the drought monitoring period following the hydrological monitoring period includes: Acquire the initial and final multispectral satellite images of the target watershed during the drought monitoring period; Calculate the difference in normalized vegetation index (NDI) of the corresponding region in the initial and final multispectral satellite images for each spatial unit. Select the maximum value between the ratio of the difference to the time interval between the two images and zero as the vegetation degradation gradient of that spatial unit.

[0009] Furthermore, the process of connecting and merging the leakage units to obtain an underground leakage network includes: The connected component labeling algorithm merges spatially adjacent missing units into at least one bounded polygonal connected body. The total number of spatial units contained in each polygonal connected body is counted. Polygonal connected bodies with a total number of spatial units greater than or equal to a preset threshold for the number of access units are identified as underground leakage connected bodies.

[0010] Furthermore, obtaining the estimated quantity of anti-seepage grouting material includes: Determine the center point of each underground leakage interconnection, and record all spatial units in the overlapping area between each underground leakage interconnection whose center point is located inside the preset legal construction boundary and the preset legal construction boundary as the unit to be calculated; The product of the underground water leakage tendency probability value, horizontal projected area, and preset static geological pore volume constant of the same unit to be calculated is used as the static fracture volume estimate of each unit to be calculated; and the sum of the static fracture volume estimates of all units to be calculated is calculated to obtain the total theoretical leakage cavity volume. The product of the theoretical total volume of the leakage cavity and the preset conversion constant per unit volume of the grout is used as the estimated amount of the seepage-proof grouting material.

[0011] Furthermore, determining the time for surface runoff and groundwater leakage from each spatial unit to the watershed outlet includes: Obtain the path length and surface velocity of each spatial unit along the surface water flow path to the watershed outlet; take the rounded result of the ratio of the path length to the surface velocity of the same spatial unit as the surface runoff time of each spatial unit. Obtain the straight-line distance and elevation difference from the center point of each spatial unit to the watershed outlet. Use the ratio of the elevation difference to the straight-line distance as the hydraulic gradient. Calculate the square root of the ratio of the hydraulic gradient to the preset benchmark hydraulic gradient. Multiply the underground river velocity by the square root and record it as the ideal underground flow velocity for each spatial unit. Use the rounded result of the ratio of the straight-line distance to the ideal underground flow velocity for the same spatial unit as the underground leakage time for each spatial unit.

[0012] Furthermore, the objective optimization function is expressed by the following formula: In the formula, Let X be the objective function; X be the set of probability variables of groundwater leakage tendency for all spatial units to be solved; H be the total number of time points during the hydrological monitoring period; and t be the time step index during the hydrological monitoring period. Let be the theoretical simulated flow rate at time t during the hydrological monitoring period; is the measured outflow at time t during the hydrological monitoring period; i is the index of the spatial unit; N is the total number of spatial units in the target watershed; Let be the probability variable of groundwater leakage tendency in the i-th spatial unit within the target watershed; This is the preset weight decay coefficient.

[0013] Secondly, another embodiment of the present invention provides an ecological protection and restoration monitoring system based on spatiotemporal big data, the system comprising: The data acquisition module is used to obtain the rainfall of each spatial unit within the target watershed at each moment during the hydrological monitoring period, as well as the measured outflow at the watershed outlet at the corresponding moment. The confluence time delay analysis module is used to determine the surface confluence time and underground leakage time of each spatial unit to the watershed outlet based on the surface hydrological path characteristics and underground spatial location characteristics of each spatial unit. The leakage probability inversion module is used to calculate the rainfall at each time by using the surface runoff time and underground leakage time of each spatial unit to generate the theoretical simulated flow rate at the corresponding time. Combined with the deviation between the theoretical simulated flow rate and the measured flow rate at the outlet, the underground leakage tendency probability value of each spatial unit is obtained. The leakage area identification module is used to filter out leakage units in each spatial unit based on the vegetation decline characteristics of each spatial unit during the drought monitoring period after the hydrological monitoring period and the probability value of the groundwater leakage tendency, as well as the topographic relief characteristics between adjacent spatial units; and to connect and merge the leakage units to obtain the groundwater leakage connected body. The repair module is used to obtain the estimated amount of anti-seepage grouting material based on the probability value of underground water leakage tendency of spatial units in the overlapping area of ​​underground leakage interconnections and preset legal construction boundaries.

[0014] The present invention has the following beneficial effects: Firstly, by utilizing the time taken for surface runoff and underground river drainage in complex karst landforms, and the time taken for underground water leakage, historical rainfall data is used to generate theoretical simulated flow rates through time-delay calculations. By comparing the simulated flow rates with the measured flow rates at the outlet, the probability value of underground water leakage tendency for each spatial unit is deconstructed. This approach overcomes the limitations of traditional optical remote sensing, which can only observe the superficial appearance of whether the surface is covered with vegetation, and effectively reveals the true situation of leakage in the underlying layers hidden beneath the vegetation cover.

[0015] Secondly, by combining the vegetation decline characteristics and the probability value of groundwater leakage tendency during the drought monitoring period, the external manifestations of vegetation decline and the internal probability of groundwater leakage tendency are cross-verified to eliminate misjudgments caused by the disconnect between surface greening and groundwater leakage; and by combining the topographic undulation characteristics between adjacent spatial units to screen and connect and merge leakage units, abnormal defective units are transformed into topographically continuous groundwater leakage interconnections, so as to achieve accurate spatial positioning of pseudo-ecological restoration areas.

[0016] Thirdly, based on the overlapping areas of underground leakage interconnections and the pre-set legal construction boundaries, the scope of responsibility for project jurisdiction is accurately identified; and the estimated amount of anti-seepage grouting material is determined by using the underground water leakage tendency probability value of spatial units within the overlapping area, so that the amount of hidden engineering under karst landforms can be quantified, providing practical and feasible data support for subsequent targeted anti-seepage repair projects. Attached Figure Description

[0017] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart illustrating the steps of an ecological protection and restoration monitoring method based on spatiotemporal big data, provided in one embodiment of the present invention; Figure 2 A flowchart illustrating a method for obtaining the probability value of underground water leakage tendency according to an embodiment of the present invention; Figure 3 This is a flowchart illustrating a method for obtaining a leaky cell according to an embodiment of the present invention. Figure 4 The diagram shows the system structure of an ecological protection and restoration monitoring system based on spatiotemporal big data, as provided in one embodiment of the present invention. Figure 5 This is a schematic diagram of a computer device for monitoring ecological protection and restoration based on spatiotemporal big data, provided as an embodiment of the present invention. Detailed Implementation

[0019] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of an ecological protection and restoration monitoring method and system based on spatiotemporal big data proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0020] 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 this invention pertains.

[0021] The following description, in conjunction with the accompanying drawings, details the specific scheme of the ecological protection and restoration monitoring method and system based on spatiotemporal big data provided by this invention.

[0022] Example 1:

[0023] This invention proposes a monitoring method for ecological protection and restoration based on spatiotemporal big data. Please refer to [link / reference]. Figure 1 The diagram illustrates a flowchart of a monitoring method for ecological protection and restoration based on spatiotemporal big data, provided by an embodiment of the present invention. The method includes: Step S1: Obtain the rainfall at each spatial unit within the target watershed during the hydrological monitoring period, and the measured outflow at the watershed outlet at the corresponding time.

[0024] Based on a Geographic Information System (GIS), a digital elevation model (DEM) is extracted for the target watershed. The DEM is essentially a raster image containing geographic coordinate system metadata, where each pixel records an elevation value. The target watershed refers to a catchment area enclosed by a topographic watershed, where all surface and groundwater runoff ultimately converges at a single hydrological flow outlet. The target watershed is uniformly divided into multiple square grids on a horizontal plane formed by the X and Y axes of the 2000 National Geodetic Coordinate System, with each grid representing a spatial unit. In this embodiment, the size of a single spatial unit is 20 meters × 20 meters, i.e., the horizontal projected area of ​​the spatial unit is 400 square meters. Implementers can set this size according to specific circumstances.

[0025] The coordinates of the center point of each spatial unit on the horizontal plane are used as the horizontal position coordinates. Using the sampling tools of the geographic information system, the pixel points that overlap with the horizontal position coordinates are found in the digital elevation model, and the height value of the pixel points is used as the elevation value of the spatial unit.

[0026] Due to the pseudo-recovery characteristic of karst landforms—"surface greening but underlying loss"—this phenomenon only becomes apparent through the entire process of rapid water loss during rainfall and rapid vegetation withering during dry periods. Therefore, it is necessary to determine the hydrological monitoring period and the drought monitoring period. Using meteorological stations or IoT rain gauges distributed within and around the target watershed, the measured rainfall in the target watershed is collected in real time at each moment during a rainfall event. The product of the preset runoff coefficient and the measured rainfall is taken as the final rainfall at that moment after deducting losses due to vegetation interception, depression storage, daily evapotranspiration, and soil vadose. The difference between the rainfall at each moment and the previous moment is taken as the cumulative rainfall, and the duration of continuous dry periods following the rainfall event is also obtained. If the cumulative rainfall at any point during a rainfall event exceeds the preset rainstorm threshold, and the duration of no rainfall after the end of the rainfall event reaches the preset number of drought days, then the time period from the start of the rainfall event to the point when the water flow at the watershed outlet drops back to the average water flow at least one day before the rainfall event shall be designated as the hydrological monitoring period; the time period between the hydrological monitoring period and the next rainfall event shall be designated as the drought monitoring period.

[0027] Spatial kriging interpolation is used to map the cumulative rainfall at each moment during the hydrological monitoring period onto each spatial unit, thereby obtaining the rainfall at the corresponding moment in each spatial unit within the target watershed during the hydrological monitoring period. The total amount of water actually flowing out of the target watershed at each moment during the hydrological monitoring period is collected in real time by a hydrological monitoring station deployed at the downstream end of the target watershed, and recorded as the measured outflow at that moment.

[0028] In this embodiment of the invention, the preset rainfall threshold is 50 mm, the preset drought days are 7 days, and the time interval between any two adjacent moments is set to 1 hour. Implementers can set these values ​​according to specific circumstances. The preset runoff coefficient represents the proportion of runoff generated after deducting plant interception, surface depression storage, evapotranspiration, and soil vadose infiltration: for strongly karst areas with thin soil layers and a rock exposure rate higher than 70%, the value is 0.8; for moderately karst areas with relatively continuous soil layers and high vegetation cover, the value is 0.7; and under conditions of extreme drought or pre-dry conditions with more than 15 consecutive days without rain, the value is 0.75.

[0029] Multispectral satellite imagery data covering the target watershed was acquired using publicly available satellite imagery sources such as Landsat. Multispectral satellite images were extracted for the start and end dates of the drought monitoring period, and denoted as the start and end multispectral satellite images, respectively. The projected coordinate system of the multispectral satellite images was kept consistent with the horizontal plane of the 2000 National Geodetic Coordinate System used to divide the spatial units. Using spatial overlay analysis tools from a Geographic Information System (GIS), the horizontal boundaries of each spatial unit were spatially overlaid and aligned with the multispectral satellite images. The region comprised of all pixels in the multispectral satellite images whose geometric centers fall within the horizontal boundary of each spatial unit was taken as the corresponding region of that spatial unit in the multispectral satellite image.

[0030] Step S2: Based on the surface hydrological path characteristics and underground spatial location characteristics of each spatial unit, determine the surface runoff time and underground leakage time of each spatial unit to the watershed outlet.

[0031] Karst landforms possess two hydrological structures: surface and underground. Water flows along the surface slope to the outlet, while water that leaks into deep underground fissures or sinkholes is quickly discharged along the underground river system. There is a time lag difference in water transport between the surface and underground paths. Determining the surface runoff time and the underground leakage time provides a spatiotemporal physical benchmark for subsequent time lag inversion.

[0032] Step S3: Using the surface runoff time and underground leakage time of each spatial unit, the rainfall at each moment is calculated by time delay to generate the theoretical simulated flow rate at the corresponding moment. Combining the deviation between the theoretical simulated flow rate and the measured flow rate at the outlet, the underground leakage tendency probability value of each spatial unit is obtained.

[0033] By shifting the historical rainfall data of each spatial unit along the time axis according to the surface runoff time and the underground leakage time, the theoretical simulated flow rate at the watershed outlet conforms to the objective physical lag process is simulated. By using the deviation between the theoretical simulated flow rate and the measured flow rate at the outlet, the probability value of underground leakage tendency of each spatial unit is obtained, revealing the degree of permeability development of the rock layer fissures at the bottom of the spatial unit. This allows for the precise quantification of deep geological leakage defects, providing data support for identifying areas of pseudo-ecological restoration.

[0034] Step S4: Based on the vegetation decline characteristics and groundwater leakage tendency probability values ​​of each spatial unit during the drought monitoring period after the hydrological monitoring period, as well as the topographic relief characteristics between adjacent spatial units, the leakage units in each spatial unit are screened; and the leakage units are connected and merged to obtain the groundwater leakage connected body.

[0035] Because geological defects identified solely by the probability value of groundwater leakage tendencies tend to appear as isolated, scattered points, and deep leakage causes surface vegetation to rapidly yellow and wither due to lack of water, the characteristics of vegetation decline during drought periods are introduced for dual anomaly verification along with the probability of groundwater leakage tendencies, significantly improving the confidence level of defect identification. Simultaneously, by utilizing the topographic undulation characteristics of adjacent spatial units, leakage units with obvious geological defects and continuous topography are screened out, completely eliminating misjudgments caused by single optical remote sensing monitoring. Furthermore, leakage units are connected and merged to obtain underground leakage contiguous bodies, transforming discrete anomalous defect units into physical working surfaces that conform to engineering practical dimensions, accurately identifying pseudo-ecological restoration areas.

[0036] Step S5: Based on the probability value of underground water leakage tendency of spatial units in the overlapping area of ​​each underground leakage interconnection and the preset legal construction boundary, obtain the estimated amount of anti-seepage grouting material.

[0037] Naturally formed underground leakage networks often cross pre-defined legal construction boundaries. By extracting spatial units within the overlapping area, effective work locations can be precisely located. Based on the probability values ​​of underground water leakage tendency of these spatial units, the estimated amount of anti-seepage grouting material can be obtained, which allows the amount of hidden engineering work under karst landforms to be objectively quantified, providing practical data support for subsequent accurate assignment of construction tasks and cost auditing.

[0038] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the surface runoff time and the underground leakage time includes: obtaining the path length and surface velocity of each spatial unit along the surface water flow path to the watershed outlet; taking the rounded result of the ratio of the path length to the surface velocity of the same spatial unit as the surface runoff time of each spatial unit; obtaining the straight-line distance and elevation difference from the center point of each spatial unit to the watershed outlet, and taking the ratio of the elevation difference to the straight-line distance as the hydraulic gradient; calculating the square root of the ratio of the hydraulic gradient to the preset benchmark hydraulic gradient, and taking the product of the underground underground river velocity and the square root as the ideal underground flow velocity of each spatial unit; taking the rounded result of the ratio of the straight-line distance to the ideal underground flow velocity of the same spatial unit as the underground leakage time of each spatial unit.

[0039] It should be noted that water flow on the surface is affected by topographic gravity and flows along the fastest descending path of the terrain. Therefore, the length of the water catchment trajectory is used to reflect the effect of topographic inflection on the extension of the surface runoff time. A high-precision digital elevation model of the target watershed is obtained; the D8 algorithm is used to trace the water catchment trajectory from the spatial unit to the watershed outlet, and the length of this trajectory is recorded as the path length. Based on a high-precision digital elevation model, the elevation values ​​of each spatial unit and its adjacent spatial units are fitted using a spatial surface analysis algorithm to obtain the tangent plane of the spatial unit. The tangent of the angle between the tangent plane and the horizontal plane is used as the average slope factor. The surface cover type of the spatial unit (such as bare soil, grassland, or woodland) is identified, and the Manning roughness coefficient is determined by consulting the cover type-Manning value mapping table based on Chow (1959) (for example, 0.03 for bare soil and 0.15 for vegetation cover). The hydraulic radius is determined by field experiments or by the hydraulic radius value in the regional hydrological manual of the target watershed. The average slope factor, Manning roughness coefficient, and hydraulic radius of the spatial unit are substituted into the Manning formula to obtain the surface velocity.

[0040] Because karst landforms have efficient underground river systems, water transport tends to proceed rapidly along the shortest hydraulic gradient. Therefore, the analysis uses the straight-line distance from the center point of the spatial unit to the watershed outlet. The ratio of elevation difference to straight-line distance is calculated to obtain the hydraulic gradient, which reflects the driving force of groundwater flow in the spatial unit. According to the principles of groundwater mechanics, in karst conduits dominated by turbulent or transitional flow, the flow velocity is directly proportional to the square root of the hydraulic gradient. Reference parameters need to be established through tracer experiments: hydrological tracers are released at typical sinkholes or karst funnels upstream of the target watershed, and the elevation difference and straight-line distance between the tracer release point and the watershed outlet are measured. The ratio of elevation difference to the straight-line distance is used as the preset reference hydraulic gradient. Simultaneously, the time difference between the tracer release time and the first detection of the tracer at the watershed outlet is calculated, and the ratio of straight-line distance to time difference is used as the underground underground river velocity. Finally, the ideal underground flow velocity for each spatial unit is determined using the proportional relationship between the underground underground river velocity and the square root of the gradient. It is important to note that the watershed outlet is the final point of convergence and discharge of surface water and groundwater within the watershed. Topographically, it is usually located at the lowest elevation within the watershed, while the elevation of upstream sinkholes or karst funnels must be higher than that of the outlet; otherwise, water could not flow by gravity to the outlet. Therefore, the elevation difference between the center point of each spatial unit and the watershed outlet must be greater than zero.

[0041] Since the measured outflow and rainfall are based on time-series data with a fixed time step, in order to accurately map the rainfall to the flow contribution at a specific moment, the two ratios are rounded to the nearest integer to eliminate time axis misalignment caused by floating-point numbers.

[0042] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the probability value of underground water leakage tendency is described in [reference needed]. Figure 2 The diagram illustrates a flowchart of a method for obtaining the probability value of underground water leakage tendency according to an embodiment of the present invention. The method includes: Step S310: Set up a groundwater leakage tendency probability variable with a value range of 0 to 1 for each spatial unit in the target watershed; select any time during the hydrological monitoring period as the example time; based on the surface runoff time and groundwater leakage time of each spatial unit, use the groundwater leakage tendency probability variable to allocate the rainfall with time lag, and determine the surface flow contribution value and groundwater flow contribution value of the spatial unit at the example time respectively.

[0043] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the surface flow contribution value and the groundwater flow contribution value includes: for each spatial unit, calculating the difference between the example time and the surface runoff time and the groundwater leakage time of the spatial unit, respectively, and recording them as the surface runoff time and the groundwater runoff time; if the surface runoff time is greater than zero, the product of the difference between constant 1 and the groundwater leakage tendency probability variable of the spatial unit, the rainfall of the spatial unit at the surface runoff time, and the preset volume conversion constant is taken as the surface flow contribution value of the spatial unit at the example time; otherwise, the surface flow contribution value is zero; if the groundwater runoff time is greater than zero, the product of the rainfall of the spatial unit at the groundwater runoff time, the groundwater leakage tendency probability variable, and the preset volume conversion constant is taken as the groundwater flow contribution value of the spatial unit at the example time; otherwise, the groundwater flow contribution value is zero.

[0044] It should be noted that the groundwater leakage tendency probability variable is an unknown quantity, reflecting the proportion of water that, after receiving precipitation, fails to be intercepted and buffered by the root system of surface vegetation and directly penetrates the shallow soil layer into the deep karst underground river system. If the surface runoff time is greater than zero, it indicates that the precipitation of the spatial unit at historical times reaches the outlet at the example time. In this case, the difference between constant 1 and the groundwater leakage tendency probability variable of the spatial unit represents the proportion of water flowing along the surface channel after receiving precipitation in the spatial unit. The rainfall at the surface runoff time represents the amount of precipitation that flows to the watershed outlet at the example time. The preset volume conversion constant can convert the rainfall depth into flow volume. The product of the three quantifies the contribution of the spatial unit to the measured flow at the outlet at the example time. Otherwise, it indicates that no precipitation has reached the watershed outlet of the spatial unit at the example time, and the surface flow contribution value is directly determined to be zero.

[0045] Similarly, the contribution analysis of underground passages is similar to that of surface passages. The difference is that the probability variable of underground water leakage tendency represents the proportion of water that leaks into underground passages after a spatial unit receives precipitation due to the development of karst fissures in the strata. The contribution value of underground flow needs to be determined based on the probability variable of underground water leakage tendency.

[0046] In this embodiment of the invention, the horizontal projected area of ​​the spatial unit is multiplied by a unit conversion factor used to convert the unit of rainfall to the unit of length of the spatial unit to obtain a preset volume conversion constant.

[0047] Step S320: Sum the surface flow contribution and groundwater flow contribution of all spatial units within the target watershed at the example time to obtain the theoretical simulated flow at the example time; construct the objective optimization function based on the sum of squares of the differences between the theoretical simulated flow and the measured outlet flow at the same time during the hydrological monitoring period; under the constraint of the value range, take the value of the groundwater leakage tendency probability variable of each spatial unit when the objective optimization function reaches its minimum value as the groundwater leakage tendency probability value of the corresponding spatial unit.

[0048] In one specific implementation of this invention, the objective optimization function is expressed by the formula: In the formula, Let X be the objective function; X be the set of probability variables of groundwater leakage tendency for all spatial units to be solved; H be the total number of time points during the hydrological monitoring period; and t be the time step index during the hydrological monitoring period. Let be the theoretical simulated flow rate at time t during the hydrological monitoring period; is the measured outflow at time t during the hydrological monitoring period; i is the index of the spatial unit; N is the total number of spatial units in the target watershed; Let be the probability variable of groundwater leakage tendency in the i-th spatial unit within the target watershed; The preset weight decay coefficient can balance the accuracy of numerical fitting and the stability of spatial distribution. In this embodiment, it is set to 0.01.

[0049] It should be noted that, This is the data fitting error term; to prevent numerical oscillations where the probability values ​​of a few spatial units diverge extremely during the solution of underdetermined equations, a Tikhonov regularization penalty term is introduced. Under a forced boundary constraint of 0 to 1, the gradient descent algorithm is used to iteratively find the probability value of underground water leakage tendency that minimizes the objective optimization function. The probability value of underground water leakage tendency characterizes the maturity of underground karst fissures and the effective filling porosity of the spatial unit; the larger the value, the more developed and interconnected the karst caves, underground rivers, or large-sized fissures are inside the bedrock at the bottom of the spatial unit, and the more severe the leakage of water and soil into deep underground rivers during precipitation.

[0050] It is important to note that the stratigraphic and lithological distribution vector layer of the target watershed should be extracted from the local geological environment engineering database or regional geological survey ledger. A spatial intersection query tool should be used to overlay and compare the horizontal coordinates and elevation values ​​of the center point of each spatial unit with the stratigraphic and lithological distribution vector layer to determine the bedrock properties at that center point. If the bedrock properties do not belong to geological rock types characterized by strong karst development (such as exposed limestone, dolomite, or areas known to have sinkholes or underground streams), it indicates that the bottom strata of the spatial unit are dense and impermeable, and the probability value of underground water leakage tendency for such spatial units should be set to zero.

[0051] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the leakage unit is described in [reference needed]. Figure 3 The diagram illustrates a flowchart of a method for obtaining a leaky cell according to an embodiment of the present invention, the method comprising: Step S410: Obtain the vegetation degradation gradient of each spatial unit during the drought monitoring period following the hydrological monitoring period.

[0052] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the vegetation degradation gradient includes: acquiring the initial multispectral satellite image and the final multispectral satellite image of the target watershed during the drought monitoring period; calculating the difference of the normalized vegetation index of the corresponding region in the initial multispectral satellite image and the final multispectral satellite image for each spatial unit; and selecting the maximum value between the ratio of the difference to the shooting time interval of the two corresponding images and zero as the vegetation degradation gradient of the spatial unit.

[0053] It should be noted that the Normalized Difference Vegetation Index (NDVI) quantifies the chlorophyll content and growth vigor of vegetation; the ratio of the difference in NDVI to the time interval between the two images reflects the vegetation degradation rate of a spatial unit. To exclude local reverse vegetation growth caused by artificial irrigation or other disturbances, the maximum value between this ratio and zero is selected as the vegetation degradation gradient.

[0054] It is important to note that under natural ecological and geological conditions, soil moisture inevitably decreases due to continuous evapotranspiration. Simultaneously, spatial heterogeneity exists between different surface and subsurface conditions, leading to varying degrees of water stress responses in plants, manifested in different natural declines in the normalized difference vegetation index (NDI) in imagery. Therefore, the growth of all vegetation units will not remain absolutely constant during drought periods.

[0055] Step S420: Calculate the mean groundwater leakage tendency probability value and the mean vegetation degradation gradient of all spatial units in the target watershed, and standardize the groundwater leakage tendency probability value and vegetation degradation gradient of each spatial unit. The product of the two standardized results is used as the composite anomaly index of the spatial unit.

[0056] It should be noted that, considering the different dimensions of the groundwater leakage tendency probability and the vegetation degradation gradient, dimensionless standardization is required. Specifically, the ratio of the groundwater leakage tendency probability to the mean groundwater leakage tendency probability for each spatial unit, and the ratio of the vegetation degradation gradient to the mean vegetation degradation gradient for that spatial unit, are calculated. The product of these two ratios is used as the composite anomaly index for that spatial unit. A larger composite anomaly index indicates that the spatial unit has well-developed underground karst fissures leading to severe precipitation loss, and that the shallow surface soil layer has extremely poor water retention capacity. Therefore, the spatial unit is more likely to be identified as a pseudo-ecologically damaged area. It is important to note that spatial units with a certain leakage capacity or vegetation degradation characteristics exist within the target watershed; therefore, the mean groundwater leakage tendency probability and the mean vegetation degradation gradient for all spatial units within the target watershed cannot be zero.

[0057] Step S430: Construct an undirected graph with each spatial unit as a physical node and including virtual leakage sources and normal sinks, denoted as the spatial feature adjacency graph. The weight of the edge connecting each physical node to the leakage source is set to a power of the composite anomaly index of the physical node, with the natural constant as the base. The weight of the edge connecting each physical node to the normal sink is set to a power of the inverse of the composite anomaly index of the physical node, with the natural constant as the base. The weight of the edge connecting two physical nodes is set to the reciprocal of the sum of the absolute difference in elevation values ​​of the corresponding spatial units of the two physical nodes and a preset minimum positive number. The preset minimum positive number is used to prevent the weight of the corresponding edge from being meaningless due to the same elevation values ​​of adjacent spatial units. In this embodiment, it is set to 0.001 meters, but implementers can set it according to specific circumstances.

[0058] It should be noted that the core logic of the graph cut algorithm is to find the cut set with the minimum sum of weights in the graph to classify entity nodes. For the edges connecting entity nodes to two virtual points, a power function design combining the natural constant and the composite anomaly index is used, which produces a strong "Matthew effect" numerically: the higher the composite anomaly index of a spatial unit, the higher the probability that the spatial unit is identified as a pseudo-ecological damage area, the greater the weight of the edge connecting it to the leakage source, and the smaller the weight of the edge connecting it to the normal sink. This makes it difficult to cut the connection between the suspected leakage spatial unit and the leakage source, thus classifying the spatial unit as a geological defect leakage area. Adjacent spatial units with small elevation differences represent flat terrain in local areas. Assigning larger edge weights makes it difficult to cut the connection between flat adjacent grids, thus forcing adjacent units with flat terrain to be classified into the same category as a whole, thereby ensuring that the subsequent underground leakage interconnection has the terrain conditions for continuous passage of engineering machinery.

[0059] Step S440: Using the maximum flow minimum cut algorithm, with the constraint of minimizing the sum of the weights of the cut edges, divide the entity nodes in the spatial feature adjacency graph into leakage nodes connected to the leakage source and normal nodes connected to the normal sink; the spatial unit corresponding to the leakage node is denoted as the leakage unit.

[0060] It should be noted that the algorithm cuts off low-weighted edges in the spatial feature adjacency graph that have conflicting features (e.g., low composite anomaly index but are close to the leaking area) and significant elevation differences, while retaining high-weighted edges with consistent anomaly features and flat terrain. This divides all entity nodes in the graph into two disjoint sets. Entity nodes that maintain a path to the leaking source after the cut are called leaking nodes, while those that maintain a path to the normal sink are called normal nodes. The maximum flow minimum cut algorithm is well-known to those skilled in the art and will not be elaborated upon here.

[0061] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining underground lost connectivity includes: merging spatially adjacent lost units into at least one polygonal connectivity with closed boundaries using a connected component marking algorithm; counting the total number of spatial units contained in each polygonal connectivity, and identifying polygonal connectivity with a total number of spatial units greater than or equal to a preset threshold for the number of incoming units as underground lost connectivity. The connected component marking algorithm is a well-known technique to those skilled in the art and will not be described in detail here. Other spatial units on the horizontal plane that share a common boundary (shared edge) or a common vertex (shared angle) with each spatial unit are extracted as adjacent spatial units of that spatial unit.

[0062] It should be noted that, considering the need for sufficiently wide and flat sites for the entry, parking, and deployment of large-scale seepage grouting machinery in ecological restoration and seepage prevention projects, polygonal connected bodies with a total number of spatial units less than the threshold for the number of entry units cannot support mechanical construction operations and must be eliminated. Underground leakage connected bodies represent effective engineering operation areas that both possess underlying geological leakage defects and meet the operational conditions for large-scale seepage grouting machinery.

[0063] In this embodiment of the invention, the minimum footprint required for the entry, parking and deployment of large-scale anti-seepage grouting machinery is obtained, denoted as the minimum machinery operation footprint, preferably set to 400 square meters; the ratio of the minimum machinery operation footprint to the horizontal projection area of ​​a single spatial unit is rounded up to obtain the threshold for the number of entry restriction units.

[0064] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the estimated amount of anti-seepage grouting material includes: determining the center point of each underground leakage interconnection; recording all spatial units in the overlapping area of ​​each underground leakage interconnection with the preset legal construction boundary whose center point is located inside the preset legal construction boundary as units to be calculated; multiplying the underground water leakage tendency probability value, horizontal projected area, and preset static geological pore volume constant of the same unit to be calculated as the estimated static fracture volume of each unit to be calculated; calculating the sum of the estimated static fracture volume of all units to be calculated to obtain the total theoretical leakage cavity volume; and multiplying the total theoretical leakage cavity volume with the preset grout unit volume conversion constant as the estimated amount of anti-seepage grouting material.

[0065] It should be noted that the pre-defined legal construction boundary is a geographical jurisdictional red line or vector surface outline drawn based on bidding contracts or administrative jurisdictional responsibilities to clarify the jurisdiction of a specific construction unit for seepage prevention construction and project acceptance. Since naturally generated underground leakage polygons often cross artificially demarcated legal construction jurisdictional red lines, a central attribution method is used to determine the unit to be calculated, which has underground leakage defects and falls within the jurisdiction of the current project section, in order to clarify the project ownership interface. When calculating the project volume, the product of the horizontal projected area and the pre-defined static geological porosity constant represents the baseline of the natural cavity volume contained within the bedrock under the specific geomorphology of the unit to be calculated; the underground water leakage tendency probability value serves as an effective cavity development index, and the above product is proportionally reduced to obtain the estimated static fracture volume, representing the physical volume of the natural karst fractures to be filled below the surface of the unit to be calculated. The theoretical total leakage cavity volume reflects the total physical volume of natural geological cavities within the area to be repaired, i.e., the theoretical total leakage cavity volume. By utilizing the grout unit volume conversion constant, the theoretical total volume of leakage cavities is converted into the estimated amount of anti-seepage grouting materials required for actual procurement and mixing, thereby providing objective material basis for ecological restoration anti-seepage projects that can withstand cost audits.

[0066] In this embodiment of the invention, the preset static geological pore volume constant is an empirical constant pre-calibrated based on geological exploration records or historical grouting data. Specifically, the operation involves reading the karst development level attribute recorded in the geological record for the preset legal construction boundary. If it is determined to be a strongly karst developed area, the volume constant is assigned a value of 0.3 cubic meters per square meter; if it is determined to be a moderately karst developed area, the volume constant is assigned a value of 0.15 cubic meters per square meter; and if it is determined to be a weakly karst developed area, the volume constant is assigned a value of 0.075 cubic meters per square meter. A pilot hole grouting test is performed within the preset legal construction boundary. The cumulative volume of grout actually injected when the preset sealing pressure is reached is recorded, and the volume of the cavity corresponding to successful sealing is calculated using geophysical methods. The ratio of the cumulative grout volume to the cavity volume is used as the preset grout unit volume conversion constant.

[0067] This invention is now complete.

[0068] Example 2:

[0069] This invention proposes an ecological protection and restoration monitoring system based on spatiotemporal big data. Please refer to [link / reference]. Figure 4 The diagram illustrates the system architecture of an ecological protection and restoration monitoring system based on spatiotemporal big data, according to an embodiment of the present invention. The system includes: The data acquisition module 610 is used to acquire the rainfall of each spatial unit in the target watershed at each moment during the hydrological monitoring period, as well as the measured outflow of the watershed outlet at the corresponding moment. The confluence time delay analysis module 620 is used to determine the surface confluence time and underground leakage time of each spatial unit to the watershed outlet based on the surface hydrological path characteristics and underground spatial location characteristics of each spatial unit. The leakage probability inversion module 630 is used to calculate the rainfall at each time by using the surface runoff time and underground leakage time of each spatial unit to generate the theoretical simulated flow rate at the corresponding time. Combined with the deviation between the theoretical simulated flow rate and the measured flow rate at the outlet, the underground leakage tendency probability value of each spatial unit is obtained. The leakage area identification module 640 is used to filter out leakage units in each spatial unit based on the vegetation decline characteristics and groundwater leakage tendency probability values ​​of each spatial unit during the drought monitoring period after the hydrological monitoring period, as well as the topographic relief characteristics between adjacent spatial units; and to connect and merge the leakage units to obtain the underground leakage connected body. Repair module 650 is used to obtain the estimated amount of anti-seepage grouting material based on the probability value of underground water leakage tendency of spatial units in the overlapping area of ​​underground leakage interconnections and preset legal construction boundaries.

[0070] It should be noted that the devices provided in the above embodiments are only illustrative examples of the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above. Furthermore, the ecological protection and restoration monitoring system based on spatiotemporal big data and the ecological protection and restoration monitoring method based on spatiotemporal big data provided in the above embodiments belong to the same concept. For details of their implementation, please refer to the method embodiments, which will not be repeated here.

[0071] Example 3:

[0072] Figure 5 This is a schematic diagram of a computer device for an ecological protection and restoration monitoring system based on spatiotemporal big data, provided as an embodiment of the present invention. For example,... Figure 5 As shown, the computer device includes: a memory 701, a processor 702, and a computer program 703 stored in the memory 701 and running on the processor 702. When the processor 702 executes the computer program 703, the computer device can execute any of the aforementioned spatiotemporal big data-based ecological protection and restoration monitoring methods.

[0073] Furthermore, this application also protects an apparatus that may include a memory and a processor, wherein the memory stores executable program code, and the processor is used to call and execute the executable program code to execute the ecological protection and restoration monitoring method based on spatiotemporal big data provided in this application.

[0074] This embodiment can divide the device into functional modules based on the above method example. For example, each module can correspond to a separate function, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0075] It should be understood that the device provided in this embodiment is used to execute the above-described ecological protection and restoration monitoring method based on spatiotemporal big data, and therefore can achieve the same effect as the above-described implementation method.

[0076] When using integrated units, the device may include a processing module and a storage module. When applied to a workpiece, the processing module can be used to control and manage the workpiece's operations. The storage module can be used to support the execution of relevant program code by the workpiece.

[0077] The processing module may be a processor or a controller, which can implement or execute various exemplary logic blocks, modules, and circuits contained in conjunction with the disclosure of this application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a digital signal processor (DSP) and a microprocessor, etc., and the storage module may be a memory.

[0078] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0079] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0080] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A monitoring method for ecological protection and restoration based on spatiotemporal big data, characterized in that, The method includes: Acquire the rainfall at each spatial unit within the target watershed at each moment during the hydrological monitoring period, as well as the measured outflow at the watershed outlet at the corresponding moment; Based on the surface hydrological path characteristics and underground spatial location characteristics of each spatial unit, the surface runoff time and underground leakage time of each spatial unit to the watershed outlet are determined respectively. By utilizing the surface runoff time and groundwater leakage time of each spatial unit, the rainfall at each moment is time-delayed to generate the theoretical simulated flow rate for that moment. Combining the deviation between the theoretical simulated flow rate and the measured outlet flow rate, the groundwater leakage tendency probability value for each spatial unit is obtained. This includes: setting a groundwater leakage tendency probability variable with a value range of 0 to 1 for each spatial unit within the target watershed; selecting any moment within the hydrological monitoring period as an example moment; and using the groundwater leakage tendency probability variable to time-delay the rainfall based on the surface runoff time and groundwater leakage time of each spatial unit. The lag distribution is used to determine the surface flow contribution and groundwater flow contribution of each spatial unit at the example time. The sum of the surface flow contribution and groundwater flow contribution of all spatial units in the target watershed at the example time is accumulated to obtain the theoretical simulated flow at the example time. Based on the sum of the squares of the differences between the theoretical simulated flow and the measured outlet flow at the same time during the hydrological monitoring period, an objective optimization function is constructed. Under the constraint of the value range, the value of the groundwater leakage tendency probability variable of each spatial unit when the objective optimization function reaches its minimum value is taken as the groundwater leakage tendency probability value of the corresponding spatial unit. Based on the vegetation decline characteristics and groundwater leakage tendency probability values ​​of each spatial unit during the drought monitoring period following the hydrological monitoring period, as well as the topographic relief characteristics between adjacent spatial units, leakage units in each spatial unit are screened; and the leakage units are connected and merged to obtain a groundwater leakage interconnection. Based on the probability value of underground water leakage tendency of spatial units within the overlapping area of ​​each underground leakage interconnection and the preset legal construction boundary, the estimated quantity of anti-seepage grouting material is obtained, including: determining the center point of each underground leakage interconnection; recording all spatial units within the overlapping area of ​​each underground leakage interconnection and the preset legal construction boundary whose center point is located inside the preset legal construction boundary as units to be calculated; multiplying the probability value of underground water leakage tendency, the horizontal projected area, and the preset static geological pore volume constant of the same unit to be calculated as the estimated static fracture volume of each unit to be calculated; calculating the sum of the estimated static fracture volume of all units to be calculated to obtain the theoretical total volume of leakage cavity; and multiplying the theoretical total volume of leakage cavity and the preset grout unit volume conversion constant as the estimated quantity of anti-seepage grouting material.

2. The ecological protection and restoration monitoring method based on spatiotemporal big data according to claim 1, characterized in that, The determination of the surface flow contribution value and the groundwater flow contribution value of the spatial unit at the example time includes: For each spatial unit, the difference between the example time and the surface runoff time and the groundwater leakage time of the spatial unit is calculated and recorded as the surface runoff time and the groundwater runoff time, respectively. If the surface runoff time is greater than zero, the product of constant 1 and the difference between the probability variable of the underground leakage tendency of the spatial unit, the rainfall of the spatial unit at the surface runoff time, and the preset volume conversion constant is used as the surface flow contribution value of the spatial unit at the example time; otherwise, the surface flow contribution value is zero. If the underground runoff time is greater than zero, the product of the rainfall, the probability variable of underground water leakage tendency, and the preset volume conversion constant of the spatial unit at the underground runoff time is taken as the underground flow contribution value of the spatial unit at the example time; otherwise, the underground flow contribution value is zero.

3. The ecological protection and restoration monitoring method based on spatiotemporal big data according to claim 1, characterized in that, The process of filtering out missing units in each spatial unit based on vegetation decline characteristics during the drought monitoring period following the hydrological monitoring period, the probability value of groundwater leakage tendency, and the topographic relief characteristics between adjacent spatial units includes: Obtain the vegetation degradation gradient of each spatial unit during the drought monitoring period following the hydrological monitoring period; The mean groundwater leakage tendency probability and the mean vegetation degradation gradient of all spatial units within the target watershed are calculated respectively. The groundwater leakage tendency probability and vegetation degradation gradient of each spatial unit are standardized, and the product of the two standardized results is used as the composite anomaly index of the spatial unit. An undirected graph is constructed with each spatial unit as a physical node and includes virtual leakage sources and normal sinks, denoted as the spatial feature adjacency graph. The weight of the edge connecting each physical node to the leakage source is set to the power of the composite anomaly index of the physical node with the natural constant as the base. The weight of the edge connecting each physical node to the normal sink is set to the power of the composite anomaly index of the physical node with the inverse of the natural constant as the base. The weight of the edge connecting two physical nodes is set to the reciprocal of the sum of the absolute difference of the elevation values ​​of the corresponding spatial units of the two physical nodes and a preset minimum positive number. Using the maximum flow minimum cut algorithm, with the constraint of minimizing the sum of the weights of the cut edges, the entity nodes in the spatial feature adjacency graph are divided into leakage nodes connected to the leakage source and normal nodes connected to the normal sink; the spatial unit corresponding to the leakage node is denoted as the leakage unit.

4. The ecological protection and restoration monitoring method based on spatiotemporal big data according to claim 3, characterized in that, The acquisition of vegetation degradation gradients for each spatial unit during the drought monitoring period following the hydrological monitoring period includes: Acquire the initial and final multispectral satellite images of the target watershed during the drought monitoring period; Calculate the difference in normalized vegetation index (NDI) of the corresponding region in the initial and final multispectral satellite images for each spatial unit. Select the maximum value between the ratio of the difference to the time interval between the two images and zero as the vegetation degradation gradient of that spatial unit.

5. The ecological protection and restoration monitoring method based on spatiotemporal big data according to claim 1, characterized in that, The process of connecting and merging the leakage units to obtain an underground leakage network includes: The connected component labeling algorithm merges spatially adjacent missing units into at least one bounded polygonal connected body. The total number of spatial units contained in each polygonal connected body is counted. Polygonal connected bodies with a total number of spatial units greater than or equal to a preset threshold for the number of access units are identified as underground leakage connected bodies.

6. The ecological protection and restoration monitoring method based on spatiotemporal big data according to claim 1, characterized in that, The determination of the surface runoff time and groundwater leakage time from each spatial unit to the watershed outlet, based on the surface hydrological path characteristics and underground spatial location characteristics of each spatial unit, includes: Obtain the path length and surface velocity of each spatial unit along the surface water flow path to the watershed outlet; take the rounded result of the ratio of the path length to the surface velocity of the same spatial unit as the surface runoff time of each spatial unit. Obtain the straight-line distance and elevation difference from the center point of each spatial unit to the watershed outlet. Use the ratio of the elevation difference to the straight-line distance as the hydraulic gradient. Calculate the square root of the ratio of the hydraulic gradient to the preset benchmark hydraulic gradient. Multiply the underground river velocity by the square root and record it as the ideal underground flow velocity for each spatial unit. Use the rounded result of the ratio of the straight-line distance to the ideal underground flow velocity for the same spatial unit as the underground leakage time for each spatial unit.

7. The ecological protection and restoration monitoring method based on spatiotemporal big data according to claim 1, characterized in that, The objective optimization function is expressed by the following formula: In the formula, Let X be the objective function; X be the set of probability variables of groundwater leakage tendency for all spatial units to be solved; and H be the total number of time points during the hydrological monitoring period. t is the time step index within the hydrological monitoring period; Let be the theoretical simulated flow rate at time t during the hydrological monitoring period; is the measured outflow at time t during the hydrological monitoring period; i is the index of the spatial unit; N is the total number of spatial units in the target watershed; Let be the probability variable of groundwater leakage tendency in the i-th spatial unit within the target watershed; This is the preset weight decay coefficient.

8. An ecological protection and restoration monitoring system based on spatiotemporal big data, wherein the system is used to implement the method described in claim 1, characterized in that, The system includes: The data acquisition module is used to obtain the rainfall of each spatial unit within the target watershed at each moment during the hydrological monitoring period, as well as the measured outflow at the watershed outlet at the corresponding moment. The confluence time delay analysis module is used to determine the surface confluence time and underground leakage time of each spatial unit to the watershed outlet based on the surface hydrological path characteristics and underground spatial location characteristics of each spatial unit. The leakage probability inversion module is used to calculate the theoretical simulated flow rate for each moment by performing time-delay calculations on the rainfall at each spatial unit using the surface runoff time and groundwater leakage time of each spatial unit. Combining the deviation between the theoretical simulated flow rate and the measured outlet flow rate, the module obtains the groundwater leakage tendency probability value for each spatial unit. This includes: setting a groundwater leakage tendency probability variable with a value range of 0 to 1 for each spatial unit within the target watershed; selecting any moment within the hydrological monitoring period as an example moment; and using the groundwater leakage tendency probability variable to calculate the groundwater leakage tendency probability value for each spatial unit based on the surface runoff time and the groundwater leakage time of each spatial unit. Rainfall is time-delayed, and the surface flow contribution and groundwater flow contribution of each spatial unit at the example time are determined. The sum of the surface flow contribution and groundwater flow contribution of all spatial units in the target watershed at the example time is accumulated to obtain the theoretical simulated flow at the example time. Based on the sum of the squares of the differences between the theoretical simulated flow and the measured outlet flow at the same time during the hydrological monitoring period, an objective optimization function is constructed. Under the constraint of the value range, the value of the groundwater leakage tendency probability variable of each spatial unit when the objective optimization function reaches its minimum value is taken as the groundwater leakage tendency probability value of the corresponding spatial unit. The leakage area identification module is used to filter out leakage units in each spatial unit based on the vegetation decline characteristics of each spatial unit during the drought monitoring period after the hydrological monitoring period and the probability value of the groundwater leakage tendency, as well as the topographic relief characteristics between adjacent spatial units; and to connect and merge the leakage units to obtain the groundwater leakage connected body. The repair module is used to obtain an estimated amount of anti-seepage grouting material based on the probability value of underground water leakage tendency of spatial units in the overlapping area of ​​each underground leakage interconnection and the preset legal construction boundary. This includes: determining the center point of each underground leakage interconnection; designating all spatial units in the overlapping area of ​​each underground leakage interconnection and the preset legal construction boundary, where the center point is located within the preset legal construction boundary, as units to be calculated; multiplying the probability value of underground water leakage tendency, the horizontal projected area, and the preset static geological pore volume constant of the same unit to be calculated as the estimated static fracture volume of each unit to be calculated; calculating the sum of the estimated static fracture volume of all units to be calculated to obtain the theoretical total volume of the leakage cavity; and multiplying the theoretical total volume of the leakage cavity by the preset grout unit volume conversion constant as the estimated amount of anti-seepage grouting material.

Images