Water source detection method, system, electronic device and storage medium based on drone

Abstract

The present application provides a water source detection method, system, electronic device and storage medium based on drones, and relates to the field of water source detection. The method includes: collecting multi-source heterogeneous data. Preprocessing the multi-source heterogeneous data to obtain multi-scale feature data, and establishing a multi-dimensional hydrogeological feature space. Inputting the multi-dimensional hydrogeological feature space into a preset deep belief network to generate a probability distribution map of hydrogeological elements in the detection area. Based on the probability distribution map of hydrogeological elements, the preset hydrogeological conceptual model parameters are updated, and the multi-source heterogeneous data are input into the revised hydrogeological conceptual model, and the spatiotemporal distribution characteristic data is output, and a water source potential zoning map is generated through multi-criteria evaluation. According to the water source potential zoning map, high potential areas are determined, and encrypted detection is performed on the high potential areas to obtain encrypted detection data, and the location coordinates of the optimal water source are determined based on the encrypted detection data. The accuracy of water source detection based on drones is improved by the above technical solution.

Description

Technical Field

[0001] This application relates to the field of water source detection, and particularly to a water source detection method, system, electronic device and storage medium based on an unmanned aerial vehicle (UAV). Background Art

[0002] In desert areas, the exploration of water resources is of great significance for local economic development and ecological protection. At present, the detection of desert water sources mainly uses technical means such as remote sensing image interpretation and geophysical exploration, and judges the location of water sources by obtaining surface information and underground structure characteristics. With the development of UAV technology, its application in the field of resource exploration is becoming increasingly widespread. The existing UAV water source detection methods usually collect data on a pre-set fixed route, and the collected data includes optical remote sensing images, multi-spectral images, etc. After these data are processed and analyzed, combined with the existing hydrogeological data, they are used to infer the possible location of water sources. However, the existing technology has the problem of low detection accuracy. This is mainly because the existing technology uses a fixed detection route and a single data analysis method, resulting in uncertainty in the judgment of the water source location. Summary of the Invention

[0003] This application provides a water source detection method, system, electronic device and storage medium based on an unmanned aerial vehicle to improve the accuracy of water source detection based on an unmanned aerial vehicle.

[0004] In a first aspect, this application provides a water source detection method based on an unmanned aerial vehicle, including:

[0005] Obtain the geographical data of the area to be detected, and determine the initial detection route according to the geographical data;

[0006] Generate UAV route planning data according to the initial detection route, and control the UAV to fly along the detection route according to the route planning data to collect multi-source heterogeneous data, where the multi-source heterogeneous data includes remote sensing image data and geophysical exploration data;

[0007] Preprocess the multi-source heterogeneous data to obtain multi-scale feature data, and establish a multi-dimensional hydrogeological feature space according to the multi-scale feature data, where the multi-dimensional hydrogeological feature space includes geological structure features, hydrogeological features and groundwater distribution features;

[0008] Map the multi-dimensional hydrogeological feature space into a preset deep belief network to obtain the spatial distribution probability of the desert aquifer, the location probability and the range probability of the water conservation area, and generate a probability distribution map of hydrogeological elements in the detection area according to the spatial distribution probability of the desert aquifer, the location probability and the range probability of the water conservation area;

[0009] Update the parameters of the preset hydrogeological conceptual model based on the probability distribution map of the hydrogeological elements to obtain a corrected hydrogeological conceptual model;

[0010] Input the multi-source heterogeneous data into the corrected hydrogeological conceptual model, output the spatio-temporal distribution characteristic data of the groundwater occurrence conditions, and perform multi-criteria evaluation based on the spatio-temporal distribution characteristic data to obtain a water source potential zoning map;

[0011] Adjust the initial detection route based on the water source potential zoning map to obtain a target detection route, and perform encrypted detection on the high-potential areas in the water source potential zoning map based on the target detection route to obtain encrypted detection data;

[0012] Perform dynamic inversion based on the encrypted detection data to obtain a dynamic inversion result, and perform parameter optimization based on the dynamic inversion result to obtain the coordinate of the optimal water source location.

[0013] In the above technical solution, the initial detection route is determined by obtaining the geographical data of the area to be detected, and the multi-source heterogeneous data including remote sensing image data and geophysical exploration data is collected by controlling the unmanned aerial vehicle based on the initial detection route. Since the multi-source heterogeneous data can reflect the groundwater distribution characteristics from different dimensions, the information integrity of water source detection is improved. The preprocessed multi-scale feature data is used to establish a multi-dimensional hydrogeological feature space including geological structures, hydrogeological features and groundwater distribution, and the feature space is mapped into a preset deep belief network, so as to obtain the spatial distribution probability of the desert aquifer, the location probability and range probability of the water conservation area, and then generate the probability distribution map of hydrogeological elements in the detection area, realizing the accurate quantification of hydrogeological elements. By using the probability distribution map of hydrogeological elements to update the parameters of the hydrogeological conceptual model, the model is more in line with the actual situation and the accuracy of subsequent analysis is improved. Input the multi-source heterogeneous data into the corrected hydrogeological conceptual model, output the spatio-temporal distribution characteristic data and perform multi-criteria evaluation to obtain the water source potential zoning map, providing a basis for the optimization of the detection route. Adjust the initial detection route based on the water source potential zoning map and perform encrypted detection on the high-potential areas. Determine the coordinate of the optimal water source location through dynamic inversion and parameter optimization, realizing the adaptive optimization of the detection process and significantly improving the accuracy and efficiency of water source detection.

[0014] In the second aspect of the present application, a water source detection system based on an unmanned aerial vehicle is provided. The system includes:

[0015] A route planning module, configured to obtain geographical data of the area to be detected and determine an initial detection route according to the geographical data;

[0016] Multi-source heterogeneous data collection is used to generate UAV route planning data according to the initial detection route, and control the UAV to fly along the detection route for multi-source heterogeneous data collection according to the route planning data, where the multi-source heterogeneous data includes remote sensing image data and geophysical exploration data;

[0017] A preprocessing module is used to preprocess the multi-source heterogeneous data to obtain multi-scale feature data, and establish a multi-dimensional hydrogeological feature space according to the multi-scale feature data. The multi-dimensional hydrogeological feature space includes geological structure features, hydrogeological features, and groundwater distribution features;

[0018] A data processing module is used to map the multi-dimensional hydrogeological feature space into a preset deep belief network to obtain the spatial distribution probability of the desert aquifer, the location probability and range probability of the water conservation area, and generate a hydrogeological element probability distribution map of the detection area according to the spatial distribution probability of the desert aquifer, the location probability of the water conservation area, and the range probability;

[0019] A parameter update module is used to update the parameters of a preset hydrogeological conceptual model based on the hydrogeological element probability distribution map to obtain a corrected hydrogeological conceptual model;

[0020] A multi-criteria evaluation module is used to input the multi-source heterogeneous data into the corrected hydrogeological conceptual model, output spatio-temporal distribution characteristic data including groundwater occurrence conditions, and perform multi-criteria evaluation according to the spatio-temporal distribution characteristic data to obtain a water source potential zoning map;

[0021] An encrypted detection module is used to adjust the initial detection route based on the water source potential zoning map to obtain a target detection route, and perform encrypted detection on the high-potential areas in the water source potential zoning map based on the target detection route to obtain encrypted detection data;

[0022] An optimal water source location determination module is used to perform dynamic inversion based on the encrypted detection data to obtain a dynamic inversion result, and perform parameter optimization based on the dynamic inversion result to obtain the position coordinates of the optimal water source location.

[0023] In the third aspect of the present application, a computer storage medium is provided. The computer storage medium stores multiple instructions, and the instructions are suitable for being loaded and executed by a processor to perform the above method steps.

[0024] In the fourth aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device performs the above method.

[0025] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0026] 1. In the present application, the initial detection route is determined by obtaining the geographical data of the area to be detected, and the multi-source heterogeneous data including remote sensing image data and geophysical exploration data is collected by controlling the drone based on the initial detection route. Since the multi-source heterogeneous data can reflect the distribution characteristics of groundwater from different dimensions, the information integrity of water source detection is improved. The preprocessed multi-scale feature data is used to establish a multi-dimensional hydrogeological feature space including geological structures, hydrogeological features and groundwater distribution, and the feature space is mapped into a preset deep belief network, so as to obtain the spatial distribution probability of the desert aquifer, the location probability and range probability of the water conservation area, and then generate the probability distribution map of hydrogeological elements in the detection area, realizing the accurate quantification of hydrogeological elements.

[0027] 2. In the present application, the probability distribution map of hydrogeological elements is used to update the parameters of the hydrogeological conceptual model, making the model more in line with the actual situation and improving the accuracy of subsequent analysis. The multi-source heterogeneous data is input into the corrected hydrogeological conceptual model, and the spatio-temporal distribution characteristic data is output and multi-criterion evaluation is carried out to obtain the potential zoning map of the water source area, providing a basis for the optimization of the detection route. The initial detection route is adjusted based on the potential zoning map of the water source area and the high-potential area is densely detected, and the optimal water source location coordinates are determined through dynamic inversion and parameter optimization, realizing the adaptive optimization of the detection process and significantly improving the accuracy and efficiency of water source detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 is a schematic flow chart of a water source detection method based on a drone provided by an embodiment of the present application;

[0029] Figure 2 is an architecture diagram of a water source detection system based on a drone provided by an embodiment of the present application;

[0030] Figure 3 is a schematic structural diagram of an electronic device provided by the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0031] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments.

[0032] In the description of the embodiments of the present application, words such as "for example" or "for illustration" are used to give examples, illustrations or explanations. Any embodiment or design solution described as "for example" or "for illustration" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "for example" or "for illustration" is intended to present related concepts in a specific manner.

[0033] In the description of the embodiments of the present application, the term "a plurality of" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. In addition, the terms "first" and "second" are used only for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the technical features indicated. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. The terms "comprise", "include", "have" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0034] To facilitate the understanding of the method and system provided by the embodiments of the present application, before introducing the embodiments of the present application, the background of the embodiments of the present application will be introduced first.

[0035] In desert areas, the exploration of groundwater resources is of great significance for promoting local economic development and maintaining the balance of the ecosystem. With the progress of technology, desert water source detection technology has gradually developed. Mainly through means such as remote sensing image interpretation and geophysical exploration, surface information and underground structural characteristics are obtained to infer the location of water sources. In recent years, unmanned aerial vehicle (UAV) technology has shown significant advantages in the field of resource exploration, providing a new technical means for water source detection. Currently, the UAV water source detection method mainly flies along a pre-set fixed route, collects data such as optical remote sensing images and multispectral images, and combines these data with existing hydrogeological data for analyzing the possible location of water sources. However, this detection method has the technical problem of low accuracy. This is mainly because the existing technology uses a fixed detection route for data collection, and the data analysis method is relatively single, unable to dynamically optimize and adjust the detection process, resulting in the accuracy and reliability of the judgment of the water source location being difficult to guarantee.

[0036] After the above background introduction, those skilled in the art can understand the problems existing in the prior art. Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments.

[0037] On the basis of the above background technology, further, please refer to Figure 1 , Figure 1The flowchart of a water source detection method based on an unmanned aerial vehicle (UAV) provided by an embodiment of the present application. This system can be implemented relying on a computer program or run as an independent tool application. Specifically, in the embodiment of the present application, this method can be applied to a server, but can also be applied to electronic devices such as a server. A water source detection method based on an unmanned aerial vehicle includes the following steps:

[0038] S101, obtain geographical data of the area to be detected, and determine an initial detection route according to the geographical data;

[0039] Specifically, in implementation, first obtain the geographical data of the area to be detected. These geographical data include terrain elevation data, surface cover type data, and geological structure data. Among them, the terrain elevation data is used to characterize the surface undulation change characteristics, the surface cover type data reflects the spatial distribution of different covers such as surface vegetation and bare soil, and the geological structure data reflects the geological structure characteristics such as regional faults and folds. By analyzing and processing these geographical data, a comprehensive geographical information layer is generated. This layer integrates multi-dimensional information such as terrain, surface cover, and geological structure. Based on the comprehensive geographical information layer, the area to be detected is divided into several regular detection grids by using a grid division method. The size of each detection grid is determined according to the terrain complexity and detection accuracy requirements. On the basis of the detection grids, an initial detection route is designed by connecting the center points of each grid. This initial detection route fully considers the influence of terrain conditions on UAV flight, avoids dangerous terrains that are not conducive to UAV flight, and at the same time ensures the effective coverage of the entire area to be detected by the detection route. The initial detection route determined in this way not only ensures the integrity of the detection data, but also improves the safety and reliability of UAV flight.

[0040] Based on the above embodiment, as an alternative embodiment, the determining an initial detection route according to the geographical data includes:

[0041] S201, analyze and process the geographical data to generate a comprehensive geographical information layer;

[0042] Specifically, the geographical data includes digital elevation model data, remote sensing image data, and geological structure data. Topographic feature parameters such as slope and aspect are extracted from the digital elevation model data, surface features such as vegetation coverage and land use types are identified using the remote sensing image data, and geological structure information such as faults and folds is extracted from the geological structure data. The extracted topographic feature parameters, surface features, and geological structure information are spatially registered, and various types of information are integrated using the spatial overlay analysis method to generate a comprehensive geographical information layer containing multiple layers of geographical information. This comprehensive geographical information layer is stored in a raster data structure, and each raster cell contains attribute information such as topography, surface, and geology, realizing the effective integration of multi-source geographical information. The generated comprehensive geographical information layer provides complete geographical spatial information support for subsequent detection grid division and route planning, improving the rationality of the initial detection route design.

[0043] S202, divide the detection grid according to the comprehensive geographical information layer, and design a route based on the detection grid to obtain the initial detection route.

[0044] Specifically, according to the topographic complexity in the comprehensive geographical information layer and the detection accuracy requirements, an adaptive grid division algorithm is used to divide the area to be detected. This algorithm calculates the topographic change gradient of each area, divides smaller detection grids in areas with complex topography, and divides larger detection grids in areas with gentle topography. The size range of the detection grids is between 50 meters and 200 meters. After the division, an improved ant colony algorithm is used for route design. This algorithm takes the center points of the detection grids as path nodes, and determines the optimal node connection sequence by calculating factors such as the topographic resistance value, flight distance, and detection coverage efficiency between adjacent nodes. During the route design process, the endurance of the unmanned aerial vehicle and the working characteristics of the detection equipment are comprehensively considered, and the detection area is divided into multiple sub-areas. The length of the detection route in each sub-area does not exceed the maximum flight range of the unmanned aerial vehicle. The initial detection route designed in this way not only ensures the spatial continuity of the detection data but also realizes the reasonable allocation of detection resources, improving the detection efficiency.

[0045] S102, generate unmanned aerial vehicle route planning data according to the initial detection route, and control the unmanned aerial vehicle to fly along the detection route according to the route planning data to collect multi-source heterogeneous data, where the multi-source heterogeneous data includes remote sensing image data and geophysical exploration data;

[0046] Specifically, based on the initial detection route, an aircraft route planning algorithm is used to generate UAV route planning data, which includes flight parameters such as flight altitude, speed, and heading angle. During the route planning process, considering that remote sensing image data collection requires maintaining a certain flight altitude to obtain a large ground coverage area, while geophysical exploration data collection requires a lower flight altitude to improve detection sensitivity. Therefore, a segmented variable altitude flight method is adopted. The flight altitude is set to 300 meters in the remote sensing image collection section and reduced to 100 meters in the geophysical exploration data collection section. The route planning data is converted into flight control instructions through the UAV control system to control the UAV to fly along the predetermined route. During the flight, the carried multispectral camera collects remote sensing image data including visible light and near-infrared bands, and at the same time, the airborne magnetometer and electromagnetic detection equipment collect geophysical exploration data such as geomagnetic field intensity and ground resistivity. This multi-source heterogeneous data collection method enables the detection data to include both surface feature information and underground structure information, providing rich data support for subsequent hydrogeological analysis. Through the precise control of the route planning data, the spatial registration accuracy and data quality of the collected data are ensured, and the reliability of the detection data is improved.

[0047] S103. Preprocess the multi-source heterogeneous data to obtain multi-scale feature data, and based on the multi-scale feature data, establish a multi-dimensional hydrogeological feature space, where the multi-dimensional hydrogeological feature space includes geological structure features, hydrogeological features, and groundwater distribution features;

[0048] Specifically, the collected multi-source heterogeneous data is first preprocessed. The deformation error of the remote sensing image data is eliminated through geometric correction, the atmospheric correction and reflectance conversion of the multispectral data are carried out by using the radiometric calibration method, and noise filtering and data smoothing processing are carried out on the geophysical exploration data. On the basis of the preprocessing, a multi-scale analysis method is used to extract features. Wavelet transform is used to extract texture features and surface coverage features at different scales for the remote sensing image data, and Fourier transform is used to extract geological structure features in different frequency domains for the geophysical exploration data to form multi-scale feature data. Based on the multi-scale feature data, a deep learning algorithm is used to construct a multi-dimensional hydrogeological feature space. This feature space includes three dimensions: the geological structure dimension reflects the distribution characteristics of geological structures such as faults and folds, the hydrogeological feature dimension reflects hydrogeological indicators such as surface water systems and vegetation coverage, and the groundwater distribution dimension characterizes groundwater features such as the location and burial depth of aquifers. The information of the three dimensions is integrated through a feature fusion algorithm to establish a unified multi-dimensional hydrogeological feature space, which realizes the organic combination of surface information and underground information and provides a complete feature expression for subsequent water source location judgment.

[0049] Based on the above embodiments, as an alternative embodiment, the preprocessing of the multi-source heterogeneous data to obtain multi-scale feature data includes:

[0050] S301. Geometrically correct the multi-source heterogeneous data to obtain the first multi-source heterogeneous data, and radiometrically correct the first multi-source heterogeneous data to obtain the second multi-source heterogeneous data;

[0051] Specifically, for the collected multi-source heterogeneous data, geometric correction processing is first performed. In this process, the original data is spatially registered and coordinate-transformed through ground control points to eliminate geometric deformations caused by factors such as terrain undulation, satellite attitude, and sensor distortion, so that the data has a unified geographic coordinate system, obtaining the first multi-source heterogeneous data. Then, radiometric correction is performed on the first multi-source heterogeneous data. In this process, the influence of factors such as atmospheric scattering and absorption is eliminated through an atmospheric correction model, and the digital quantity is converted into a physical quantity using sensor calibration parameters. At the same time, radiometric normalization processing is performed on data of different time phases to make the data comparable, obtaining the second multi-source heterogeneous data. This data preprocessing method ensures the consistency of the multi-source heterogeneous data in terms of spatial position and radiometric characteristics, laying a foundation for subsequent multi-scale feature extraction. Through these two-step corrections, the geometric accuracy and radiometric accuracy of the data are significantly improved, ensuring the reliability of subsequent analysis results.

[0052] S302. Perform filtering and noise reduction processing on the second multi-source heterogeneous data to obtain the target multi-source heterogeneous data;

[0053] Specifically, for filtering and noise reduction processing of the second multi-source heterogeneous data, wavelet transform method is used to perform multi-scale decomposition on the data, decomposing the signal into different frequency components. In the wavelet domain, the threshold method is used to process the noise coefficients, retaining the low-frequency coefficients representing geological information and suppressing the high-frequency noise components. At the same time, an adaptive median filter is used to remove the impulse noise in the data. This filter dynamically adjusts the filter window size according to local data characteristics, effectively suppressing random noise while maintaining the geological boundary characteristics. After filtering and noise reduction processing, the target multi-source heterogeneous data is obtained, which has a higher signal-to-noise ratio and clearer geological structure characteristics. This noise reduction method based on wavelet transform and adaptive filtering maximally preserves the effective information in the original data while effectively removing noise, improving the accuracy and reliability of subsequent analysis.

[0054] S303. Perform multi-scale decomposition on the target multi-source heterogeneous data to obtain the multi-scale feature data.

[0055] Specifically, the pyramid multi-resolution analysis method is used to perform multi-scale decomposition on the target multi-source heterogeneous data. An image pyramid is constructed through Gaussian filtering and downsampling operations to obtain data levels with different spatial resolutions. At each scale level, a directional filter bank is used to extract the directional features of geological structures, including linear structures, circular structures, etc. At the same time, the Gabor wavelet transform is used to decompose the data in the frequency domain to extract texture features under different frequency components. The information with different scales and different features is comprehensively integrated to form multi-scale feature data. This multi-scale feature data contains complete geological information from local details to regional macro, and can comprehensively depict the geological structure features of the study area. Through this multi-scale decomposition method, multi-level characterization of geological bodies is achieved, providing rich feature information for subsequent geological interpretation and hydrogeological modeling.

[0056] S104, map the multi-dimensional hydrogeological feature space into a preset deep belief network to obtain the spatial distribution probability of the desert aquifer, the location probability and the range probability of the water conservation area, and generate a probability distribution map of hydrogeological elements in the exploration area according to the spatial distribution probability of the desert aquifer, the location probability of the water conservation area and the range probability;

[0057] Specifically, the constructed multi-dimensional hydrogeological feature space is used as input data and mapped into a pre-trained deep belief network for probability inference. This deep belief network is composed of multiple layers of restricted Boltzmann machines, and each layer contains hundreds of neuron nodes for feature extraction and probability calculation. The first layer of the network receives the input data of the multi-dimensional hydrogeological feature space, and through feature transformation and non-linear mapping, deep feature representations are extracted. Feature combination and probability inference are performed in the middle layer of the network, and finally three probability indicators are generated in the output layer: the spatial distribution probability of the desert aquifer represents the distribution possibility of the underground water body in the three-dimensional space, the location probability of the water conservation area reflects the location where surface water recharges groundwater, and the range probability describes the spatial range of the water conservation area. Based on these three probability indicators, a probability distribution map of hydrogeological elements in the exploration area is generated using geographic information system technology. This distribution map stores probability values in a raster form and represents the probability magnitude through different shades of color, realizing the visual expression of the distribution of hydrogeological elements. This probability inference method based on the deep belief network makes full use of the information in the multi-dimensional feature space and improves the accuracy of hydrogeological element identification.

[0058] S105, update the parameters of the preset hydrogeological conceptual model based on the probability distribution map of hydrogeological elements to obtain a revised hydrogeological conceptual model;

[0059] Specifically, the generated probability distribution map of hydrogeological elements is compared and analyzed with a preset hydrogeological conceptual model, which includes information such as stratigraphic structure, hydrogeological parameters, and groundwater flow field. The Bayesian updating method is used to correct the model parameters. First, the probability distribution map of hydrogeological elements is converted into a likelihood function, combined with the prior distribution of the model parameters, and the posterior distribution of the parameters is calculated. The specific updated parameters include hydrogeological parameters such as aquifer permeability coefficient, storage coefficient, and recharge coefficient. At the same time, hydrodynamic characteristics such as groundwater flow direction and velocity are adjusted. Through iterative calculation, when the change in the model response caused by parameter update is less than the set threshold, the parameter update process is completed. The corrected hydrogeological conceptual model not only includes the original geological structure framework but also incorporates the hydrogeological characteristics reflected by the measured data, improving the model's ability to represent the actual hydrogeological conditions. This method of updating model parameters based on measured data effectively improves the accuracy and reliability of the hydrogeological conceptual model, providing a more accurate model basis for subsequent groundwater resource evaluation.

[0060] Based on the above embodiments, as an alternative embodiment, parameter updating of the preset hydrogeological conceptual model is performed based on the probability distribution map of hydrogeological elements to obtain a corrected hydrogeological conceptual model, including:

[0061] S401, extracting key feature points from the probability distribution map of hydrogeological elements;

[0062] Specifically, key feature points are extracted from the probability distribution map of hydrogeological elements. The corner detection algorithm is used to identify the intersection points and inflection points of geological structures, which usually represent important hydrogeological significance. At the same time, the region growing algorithm is used to extract the boundary points of the aquifer distribution, which depict the spatial distribution characteristics of the aquifer. In areas where hydrogeological elements change significantly, such as fault zones and lithological contact zones, the gradient operator is used to calculate the change rate of probability values, and the mutation points of probability values are extracted as key feature points. Cluster analysis is performed on the hydrogeological element probability values to identify the center points of high-value areas and the demarcation points of low-value areas. The extraction process of these key feature points comprehensively considers geological structure characteristics, aquifer distribution characteristics, and probability value distribution characteristics, providing control point information for subsequent parameter updating of the hydrogeological conceptual model and improving the accuracy and pertinence of model correction.

[0063] S402, correcting the structural parameters of the hydrogeological conceptual model based on the key feature points to obtain a preliminary hydrogeological conceptual model;

[0064] Specifically, based on the extracted key feature points, the structural parameters of the hydrogeological conceptual model are corrected. First, the Kriging interpolation method is used to convert the discrete key feature points into a continuous parameter distribution field. For structural parameters such as aquifer thickness and burial depth, the variational method is used to establish an objective function, with the key feature points as constraint conditions, and the original structural parameters are optimized and adjusted by the least squares method. In areas with obvious features such as fault zones and lithological boundaries, the locally weighted regression method is used to refine the correction of the structural parameters. The model grid is adjusted through the elastic grid deformation technology to make the grid nodes adapt to the positions of the key feature points, improving the spatial expression accuracy of the structural parameters. After correction, a preliminary hydrogeological conceptual model is obtained, and the distribution of the structural parameters of this model is more in line with the actual geological conditions, improving the structural accuracy of the model. This method for correcting structural parameters based on key feature points realizes the quantitative optimization of the model structure and lays a foundation for the refined expression of subsequent hydrogeological parameters.

[0065] S403. Dynamically adjust the hydrogeological parameters of the preliminary hydrogeological conceptual model by using probability distribution information to obtain the corrected hydrogeological conceptual model.

[0066] Specifically, the hydrogeological parameters of the preliminary hydrogeological conceptual model are dynamically adjusted by using the probability distribution information of hydrogeological elements. First, a conversion relationship between probability values and hydrogeological parameters is established. Through the correlation analysis between hydrogeological parameters such as hydraulic conductivity and storage coefficient and probability values, a parameter conversion function is constructed. The Bayesian framework is used for parameter updating, with the probability distribution as prior information and combined with on-site pumping test data as conditional information, and the hydrogeological parameters are iteratively optimized by the Markov chain Monte Carlo algorithm. In the process of parameter optimization, an adaptive weight method is adopted to dynamically adjust the parameter correction amplitude according to the probability value sizes in different regions to ensure the rationality of parameter updating. At the same time, the effectiveness of the parameters is verified through the water balance constraint conditions to ensure that the corrected hydrogeological parameters meet the regional hydrogeological conditions. After dynamic adjustment, a corrected hydrogeological conceptual model is obtained, and the distribution of the hydrogeological parameters of this model is more reasonable, which can better reflect the hydrogeological characteristics of the study area and improve the prediction accuracy and reliability of the model.

[0067] S106. Input the multi-source heterogeneous data into the corrected hydrogeological conceptual model, output the spatio-temporal distribution characteristic data including the groundwater occurrence conditions, and conduct multi-criteria evaluation based on the spatio-temporal distribution characteristic data to obtain the potential zoning map of the water source area;

[0068] Specifically, the collected multi-source heterogeneous data is used as the input data for the revised hydrogeological conceptual model. Through model calculation, the spatio-temporal distribution characteristic data of groundwater occurrence conditions is obtained. This data includes characteristic information such as the water table, water quality parameters, and water volume distribution that change over time and space. Based on the spatio-temporal distribution characteristic data, a multi-criteria evaluation system is established using the analytic hierarchy process. The evaluation indicators include aquifer thickness, groundwater depth, recharge conditions, water quality conditions, etc., and the weight coefficients of each indicator are determined through expert scoring. The fuzzy comprehensive evaluation method is used to quantitatively calculate and comprehensively integrate each evaluation indicator, and the evaluation results are divided into three levels: high-potential area, medium-potential area, and low-potential area, generating a potential zoning map of the water source area. Different colors are used in this zoning map to identify areas with different potential levels, and the locations and ranges of high-potential areas that require key attention are marked. Through this multi-criteria evaluation method, the comprehensive evaluation of the potential of groundwater resources is realized, providing a scientific basis for the decision-making of water source site selection and improving the efficiency and accuracy of water source exploration.

[0069] Based on the above embodiments, as an alternative embodiment, the multi-criteria evaluation according to the spatio-temporal distribution characteristic data to obtain the potential zoning map of the water source area includes:

[0070] S501, establish an evaluation index system and standardize each index in the evaluation index system to obtain a preliminary evaluation index system;

[0071] Specifically, an evaluation index system is established based on the spatio-temporal distribution characteristic data. This index system includes multiple aspects such as hydrogeological conditions, topography, recharge conditions, and exploitation conditions. In terms of hydrogeological conditions, aquifer thickness, permeability coefficient, and storage coefficient are selected as evaluation indicators; in terms of topography, terrain slope and elevation change are selected as evaluation indicators; in terms of recharge conditions, precipitation infiltration amount and groundwater runoff modulus are selected as evaluation indicators; in terms of exploitation conditions, burial depth and water quality type are selected as evaluation indicators. The extreme value standardization method is used to dimensionlessize indicators with different dimensions, and each indicator value is uniformly converted into the 0-1 interval. For positive indicators, the minimum-maximum standardization formula is used for conversion; for negative indicators, the maximum-minimum standardization formula is used for conversion. Through standardization, a preliminary evaluation index system is obtained, making different indicators comparable and providing a basis for subsequent determination of indicator weights and comprehensive evaluation. This method of establishing a multi-level and multi-angle evaluation index system ensures the comprehensiveness and scientific nature of the water source potential evaluation.

[0072] S502, use the analytic hierarchy process to determine the weights of each index in the preliminary evaluation index system to obtain a comprehensive evaluation index system;

[0073] Specifically, the analytic hierarchy process is used to determine the weights of the indicators in the preliminary evaluation index system. First, an indicator hierarchy structure is constructed, and the evaluation indicators are divided into three levels: the target level, the criterion level, and the indicator level. The pairwise comparison judgment matrix between indicators is established through the expert scoring method, and the importance of indicators is quantitatively assigned using the 1-9 ratio scale method. The maximum eigenvalue and the corresponding eigenvector of the judgment matrix are calculated using the eigenvalue method, and the eigenvector is normalized to obtain the weight values of the indicators at each level. The consistency of the judgment matrix is tested, and the consistency index and the consistency ratio are calculated. When the consistency ratio is less than 0.1, it indicates that the weight distribution is reasonable. The comprehensive method of hierarchy is used to combine the weights at each level to obtain the comprehensive weight value of all indicators relative to the total target. Finally, a comprehensive evaluation index system including the index system and the weight system is formed. This system fully considers the contribution degree of each indicator to the evaluation of the water source potential, providing a scientific quantitative basis for the subsequent multi-criteria comprehensive evaluation.

[0074] S503. Calculate the single-index scores of each evaluation indicator in the spatio-temporal distribution characteristic data according to the comprehensive evaluation index system, and perform weighted summation on the single-index scores to obtain the evaluation score distribution map.

[0075] Specifically, calculate the single scores of each evaluation indicator in the spatio-temporal distribution characteristic data according to the comprehensive evaluation index system, and use the fuzzy membership function to convert the standardized index value into an evaluation score. For continuous indicators, a piecewise linear membership function is used for conversion, setting the optimal interval and critical interval of the indicator value, and calculating the membership scores corresponding to different indicator values. For discrete indicators, the expert scoring method is directly used to assign evaluation scores. Multiply the single scores of each evaluation indicator by the corresponding weight values, and obtain the comprehensive evaluation score of each evaluation unit through weighted summation. Use the Kriging spatial interpolation method to convert the discrete evaluation unit scores into a continuously distributed evaluation score distribution map. This map shows the size of the water source development potential at different locations in the study area in the form of contour lines. This method based on fuzzy comprehensive evaluation realizes the quantitative evaluation of the water source potential, and the evaluation score distribution map intuitively reflects the spatial differentiation characteristics of the water source suitability, providing a scientific basis for the water source site selection decision.

[0076] S504. Perform grade division according to the evaluation score distribution map and the preset partition threshold standard, determine the potential partition boundary, and generate the water source potential partition map including the partition grade attribute according to the potential partition boundary.

[0077] Specifically, for the potential zoning of water source areas based on the evaluation score distribution map, first, set the zoning threshold standard based on the development suitability degree of water source areas, and divide the evaluation scores into three levels: high-potential area, medium-potential area, and low-potential area. The natural break method is used to determine the grading threshold of the evaluation scores. This method achieves optimal grading by minimizing the variance within levels and maximizing the variance between levels. Use the vectorization tool in the geographic information system to extract contour lines, and convert the evaluation score distribution map into a potential zoning map with clear boundaries. Eliminate the fragmentation of the zoning boundaries through topological processing to ensure the continuity and integrity of the zoning boundaries. Assign corresponding grade attributes to each potential zoning area, and generate a water source area potential zoning map containing attribute information such as zoning codes, zoning grades, and area statistics. This zoning map clearly shows the spatial distribution pattern of the development potential of water source areas in the study area. The delineation of the zoning boundaries not only considers the continuous change characteristics of the evaluation scores but also ensures the practicality and operability of the zoning, providing an intuitive spatial decision-making basis for water source area planning and management.

[0078] S107. Adjust the initial detection route based on the water source area potential zoning map to obtain a target detection route, and conduct encrypted detection on the high-potential areas in the water source area potential zoning map based on the target detection route to obtain encrypted detection data.

[0079] Specifically, according to the generated water source area potential zoning map, optimize and adjust the initial detection route, increase the detection density in high-potential areas, and reduce the detection routes in low-potential areas to form a target detection route. The design of the target detection route adopts the adaptive grid encryption method. In high-potential areas, the spacing between detection lines is reduced from the initial 500 meters to 100 meters, and at the same time, connecting lines perpendicular to the main detection line are added to form a grid-like detection system. Conduct encrypted detection based on the target detection route. In high-potential areas, multiple detection methods are jointly used: the transient electromagnetic method is used to obtain underground electrical structure data, the seismic exploration method is used to collect formation structure information, and gravity measurement is used to obtain density distribution characteristics. These encrypted detection data have higher spatial resolution and detection accuracy, and can detail the geological structure and aquifer characteristics of high-potential areas. Through the optimized design of the target detection route and the implementation of encrypted detection, the detection accuracy of the hydrogeological conditions in high-potential areas is improved, providing more detailed data support for the subsequent determination of water source areas.

[0080] Based on the above embodiments, as an optional embodiment, the adjusting the initial detection route based on the water source area potential zoning map to obtain a target detection route includes:

[0081] S601. Identify the boundaries of high-potential areas in the water source area potential zoning map.

[0082] Specifically, for the identification of the boundaries of high-potential areas based on the potential zoning map of water sources, first, the spatial scope of high-potential areas is extracted through vector data processing. The boundary tracking algorithm is used to extract the contours of high-potential areas, and the boundary lines of the areas with the highest evaluation scores in the zoning map are vectorized. The morphological processing method is used to smooth and simplify the boundary lines, eliminating minor undulations and retaining the main boundary features. The connectivity and adjacency relationships of high-potential areas are determined through topological analysis, and the positions of the transition zones between adjacent partitions are identified. Attribute annotations are made for the identified boundaries, recording the spatial coordinates and length information of the boundary lines. The identification results of the boundaries of high-potential areas are saved in the form of vector boundary lines for the subsequent optimization design of exploration routes. This boundary identification method accurately extracts the spatial distribution scope of high-potential areas, providing a spatial reference basis for the rational layout of exploration routes.

[0083] S602. Design an encrypted exploration grid based on the spatial distribution characteristics of the high-potential areas, and adjust the initial exploration route based on the encrypted exploration grid to obtain the target exploration route.

[0084] Specifically, for the design of an encrypted exploration grid based on the spatial distribution characteristics of high-potential areas, a smaller grid spacing is used for encrypted layout within high-potential areas, and the grid spacing is reduced from 100 meters of the original exploration grid to 50 meters. The square grid division scheme is adopted to ensure the regularity of the grid and the uniformity of exploration coverage. A gradient grid design is adopted in the boundary zone of high-potential areas, and the grid spacing gradually transitions outward from the high-potential areas to avoid sudden changes in grid scale. The initial exploration route is adjusted according to the encrypted exploration grid, and the exploration point positions are adjusted to the grid nodes, and the exploration routes are arranged along the grid boundaries. The shortest path algorithm is used to optimize the direction of the exploration routes, reducing the total route length while meeting the requirements of exploration accuracy. The design of the target exploration route not only ensures the detailed exploration of high-potential areas but also realizes the rational allocation of exploration resources. The adjusted target exploration route is saved in the form of vector lines, including attribute information such as exploration point coordinates, route length, and grid numbers, providing specific technical guidance for subsequent on-site exploration work.

[0085] Based on the above embodiments, as an alternative embodiment, the determination of the initial exploration route according to the geographical data includes:

[0086] S701. Analyze and process the geographical data to generate a comprehensive geographical information layer;

[0087] Specifically, for the analysis and processing of geographical data, first, the geographical data from different sources are unified into the vector data format through data format conversion. Projection transformation is used to convert the geographical data into a unified coordinate system to ensure the precise correspondence of spatial positions. The spatial overlay analysis method is utilized to synthesize layers of geographical elements such as terrain, landform, water system, and roads to form a multi-level geographical information expression. Geomorphic features such as slope and aspect are extracted through terrain analysis and digitized. The water system data are extracted and classified to identify the spatial distribution pattern of main rivers and tributaries. The traffic accessibility analysis layer is constructed using the road network data, and the grade attributes of arterial roads and secondary arterial roads are marked. The layer management technology is adopted to hierarchically organize various geographical elements to generate a comprehensive geographical information layer containing multi-dimensional information such as terrain, water system, and traffic. This layer is saved in the form of hierarchical vector data, realizing the systematic management and visual expression of geographical information and providing a complete geographical space reference for the planning and design of the detection route.

[0088] S702, divide the detection grid according to the comprehensive geographical information layer, and design the route based on the detection grid to obtain the initial detection route.

[0089] Specifically, for the detection grid division based on the comprehensive geographical information layer, the regular grid method is adopted to divide the study area into square grid units of 100 meters × 100 meters. When dividing the grid, the terrain undulation and road distribution characteristics are considered, and the grid is adjusted for steep terrain areas and areas with inconvenient transportation. The grid coding is generated using the grid division tool, and the grid attribute table is established to record the geographical feature information of each grid unit. For the route design based on the detection grid, first, the positions of the detection start and end points are determined, and an area with convenient transportation and gentle terrain is selected as the detection starting point. The snake-like traversal method is adopted to design the detection route direction, so that the detection route passes through each grid node in turn. During the route design process, the detection route is optimized in combination with the road distribution, and it is arranged along the existing roads as much as possible to reduce the construction of new channels. The optimal connection method between grid nodes is determined through the minimum resistance path analysis to avoid terrain obstacle areas. The design of the initial detection route not only meets the coverage requirements of the detection grid but also ensures the feasibility of the detection operation. The generated initial detection route contains spatial attribute information such as route direction, detection point position, and grid number, providing basic data for the subsequent optimization of the detection route.

[0090] S108, perform dynamic inversion based on the encrypted detection data to obtain the dynamic inversion result, and perform parameter optimization based on the dynamic inversion result to obtain the coordinate of the optimal water source location.

[0091] Specifically, dynamic inversion is carried out using encrypted detection data. In this inversion process, the conjugate gradient method is used to iteratively calculate the detection data, and the model parameters are optimized through the least square principle to achieve dynamic update of the underground medium parameters. During the dynamic inversion process, data from multiple geophysical exploration methods are processed simultaneously, including the resistivity distribution reflected by transient electromagnetic data, the velocity structure reflected by seismic data, and the density distribution reflected by gravity data. The comprehensive geophysical characteristics of the underground medium are obtained through joint inversion. Based on the dynamic inversion results, the genetic algorithm is used for parameter optimization. Parameters such as the thickness, burial depth, permeability, and recharge conditions of the aquifer are taken as optimization objectives, and the suitability of water source areas at different locations is evaluated through a fitness function. During the iterative optimization process, the population parameters and the crossover and mutation probabilities are continuously adjusted until the optimal solution is found, and the coordinates of the optimal water source location are output. This method based on dynamic inversion and parameter optimization makes full use of high-precision detection data, determines the optimal water source location through quantitative calculation, and improves the scientificity and reliability of water source site selection.

[0092] Based on the above embodiments, as an alternative embodiment, the generating a probability distribution map of hydrogeological elements in the detection area according to the spatial distribution probability of the desert aquifer, the location probability of the water conservation area, and the range probability includes:

[0093] S801, perform spatial registration on the spatial distribution probability of the desert aquifer, the location probability of the water conservation area, and the range probability respectively to obtain the registered spatial distribution probability, the registered location probability, and the registered range probability;

[0094] Specifically, for the spatial registration process of hydrogeological element probability data, first establish a unified geographic coordinate reference system, and use the UTM projection method to ensure the accurate correspondence of spatial positions. Use the spatial registration tool to geometrically correct the spatial distribution probability data of the desert aquifer and convert it to the target coordinate system. Perform registration transformation on the location probability data of the water conservation area to achieve precise correspondence of spatial positions through control point matching. Use the resampling method to process the range probability data to make its spatial resolution consistent with other data layers. In the registration process, the bilinear interpolation algorithm is used for data resampling to maintain the continuous change characteristics of probability values. Evaluate the accuracy of the registration results, calculate the registration error, and ensure that the registration accuracy meets the requirements of subsequent analysis. The registered spatial distribution probability, the registered location probability, and the registered range probability are all converted into a unified raster data format, with the same spatial resolution and coordinate reference. The spatial registration process realizes the spatial unification of different probability data and provides basic data support for subsequent probability superposition analysis.

[0095] S802. Construct a probability superposition model based on the Bayesian theory. Among them, the registered spatial distribution probability is used as the prior probability of the probability superposition model, the registered position probability is used as the conditional probability of the probability superposition model, and the registered range probability is used as the marginal probability of the probability superposition model;

[0096] Specifically, when constructing a probability superposition model based on the Bayesian theory, the registered spatial distribution probability is used as the prior probability reflecting the distribution law of the desert aquifer. This probability represents the initial understanding of the spatial distribution of the aquifer before obtaining other information. The registered position probability is used as the conditional probability, which represents the probability of the aquifer appearing under the condition that the location of the water conservation area is known, reflecting the correlation between the water conservation area and the aquifer distribution. The registered range probability is used as the marginal probability to characterize the overall distribution characteristics of the aquifer in the study area. The Bayesian formula is used to establish a probability superposition calculation model, and the posterior probability of each grid cell in the study area is calculated through the mathematical combination of the prior probability, conditional probability, and marginal probability. During the model construction process, the logarithmic likelihood function is used to process the probability multiplication operation to avoid numerical truncation caused by consecutive multiplication of decimals. The establishment of the probability superposition model realizes the organic integration of multi-source probability information, makes full use of the known hydrogeological information, and improves the reliability of aquifer distribution prediction. The model is expressed in the form of a mathematical formula, which is convenient for subsequent program implementation and calculation processing.

[0097] S803. Use the probability superposition model to perform probability spatial interpolation to generate a continuous probability distribution field;

[0098] Specifically, when using the probability superposition model to perform probability spatial interpolation, the Kriging interpolation method is used to process the discrete probability data. This method considers spatial autocorrelation and can reflect the spatial variation characteristics of probability values. Before the interpolation calculation, the spatial correlation structure of the probability field is determined through variogram analysis, and a semi-variogram model is established to describe the spatial variation law of probability values. The spherical model is selected as the theoretical semi-variogram, and the experimental semi-variogram is fitted by the least squares method to obtain spatial structure parameters such as the range and sill value. The ordinary Kriging interpolation algorithm is used to perform grid calculation on the study area to generate regular grid data. During the interpolation process, the search radius is set to 2 / 3 of the range, and 16 nearest neighbor points are used to participate in the interpolation calculation to ensure the smoothness of the interpolation result. The interpolation result is cross-validated, and the root mean square error is calculated to evaluate the interpolation accuracy. The generated continuous probability distribution field is stored in the form of grid data with a spatial resolution of 10 meters, realizing the continuous expression of the probability field and providing complete spatial probability information for subsequent hydrogeological element analysis.

[0099] S804. Perform probability threshold analysis on the continuous probability distribution field to determine the probability threshold analysis result;

[0100] Specifically, for the probability threshold analysis of the continuous probability distribution field, first, the frequency distribution characteristics of probability values are calculated using probability statistics methods, and a probability value statistical histogram is established. The distribution law of probability values is determined through cumulative frequency analysis, and the cumulative frequencies at different probability levels are calculated. The natural break point method is used to classify the probability values, which are divided into three grade intervals: high, medium, and low. During the probability threshold division process, the variance minimization criterion is adopted to determine the optimal classification break point, minimizing the within-class variance and maximizing the between-class variance. Spatial statistical analysis is carried out for each grade interval to calculate the area proportion of different probability grade regions. Combining the known hydrogeological conditions, the rationality of the probability threshold is verified, and the final probability threshold analysis result is determined. The probability threshold analysis result is expressed in the form of classified raster data, clearly showing the spatial differentiation characteristics of hydrogeological elements in the study area and providing a quantitative basis for the optimization of the exploration area.

[0101] S805, generate a probability distribution map of hydrogeological elements in the exploration area based on the probability threshold analysis result.

[0102] Specifically, to generate a probability distribution map of hydrogeological elements in the exploration area based on the probability threshold analysis result, a geographic information system mapping method is used for map compilation. First, a unified map projection and coordinate system are established, and an appropriate map scale is set to ensure the accuracy requirements of map expression. The probability threshold analysis result is converted into a vector data format, and a spatial database of hydrogeological elements in the exploration area is established. A classified color expression scheme is used to design the legend. The high-probability area uses the red color system, the medium-probability area uses the yellow color system, and the low-probability area uses the blue color system to highlight the spatial differences in probability distribution. During the map production process, basic geographic information such as topographic base maps and administrative boundaries is overlaid to improve the map element configuration. Essential map elements such as a north arrow, scale, and legend are added to improve the readability of the map. The finally generated probability distribution map of hydrogeological elements in the exploration area intuitively shows the spatial distribution law of hydrogeological elements in the study area and provides a spatial decision-making basis for subsequent exploration work.

[0103] On the other hand, the present application also provides an unmanned aerial vehicle-based water source detection system, as Figure 2 , the system includes:

[0104] A route planning module 1, configured to obtain geographic data of the area to be detected and determine an initial detection route according to the geographic data;

[0105] A multi-source heterogeneous data acquisition 2, configured to generate unmanned aerial vehicle route planning data according to the initial detection route and control the unmanned aerial vehicle to fly along the detection route for multi-source heterogeneous data acquisition according to the route planning data, wherein the multi-source heterogeneous data includes remote sensing image data and geophysical exploration data;

[0106] A preprocessing module 3 is configured to preprocess the multi-source heterogeneous data to obtain multi-scale feature data, and establish a multi-dimensional hydrogeological feature space according to the multi-scale feature data. The multi-dimensional hydrogeological feature space includes geological structure features, hydrogeological features, and groundwater distribution features.

[0107] A data processing module 4 is configured to map the multi-dimensional hydrogeological feature space into a preset deep belief network to obtain the spatial distribution probability of the desert aquifer, the location probability and range probability of the water conservation area, and generate a probability distribution map of hydrogeological elements in the detection area according to the spatial distribution probability of the desert aquifer, the location probability of the water conservation area, and the range probability.

[0108] A parameter update module 5 is configured to update the parameters of a preset hydrogeological conceptual model based on the probability distribution map of hydrogeological elements to obtain a corrected hydrogeological conceptual model.

[0109] A multi-criteria evaluation module 6 is configured to input the multi-source heterogeneous data into the corrected hydrogeological conceptual model, output data on the spatio-temporal distribution characteristics of groundwater occurrence conditions, and perform multi-criteria evaluation according to the spatio-temporal distribution characteristics data to obtain a potential zoning map of water sources.

[0110] An encrypted detection module 7 is configured to adjust the initial detection route based on the potential zoning map of water sources to obtain a target detection route, and perform encrypted detection on high-potential areas in the potential zoning map of water sources based on the target detection route to obtain encrypted detection data.

[0111] An optimal water source location determination module 8 is configured to perform dynamic inversion based on the encrypted detection data to obtain a dynamic inversion result, and perform parameter optimization based on the dynamic inversion result to obtain the position coordinates of the optimal water source location.

[0112] Please refer to Figure 3 This application also discloses an electronic device. Figure 3 FIG. is a schematic structural diagram of an electronic device disclosed in an embodiment of this application. The electronic device 300 may include: at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302.

[0113] Among them, the communication bus 302 is used to realize the connection and communication between these components.

[0114] Among them, the user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may further include a standard wired interface and a wireless interface.

[0115] Among them, the network interface 304 may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface).

[0116] Among them, the processor 301 may include one or more processing cores. The processor 301 connects various parts within the entire server through various interfaces and lines. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and by calling data stored in the memory 305, it performs various functions of the server and processes data. Optionally, the processor 301 may be implemented in at least one of the following hardware forms: digital signal processing (DSP), field-programmable gate array (FPGA), and programmable logic array (PLA). The processor 301 may integrate a combination of one or more of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interface, application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communication. It can be understood that the above-mentioned modem may not be integrated into the processor 301 and may be implemented separately by a single chip.

[0117] Among them, the memory 305 may include random access memory (RAM) and may also include read-only memory. Optionally, the memory 305 includes a non-transitory computer-readable medium. The memory 305 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store data involved in the above-mentioned method embodiments. Optionally, the memory 305 may also be at least one storage system located far from the aforementioned processor 301. Refer to Figure 3 , the memory 305, as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for a flocculant addition analysis method.

[0118] In Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an interface for the user to input and obtain the data input by the user; while the processor 301 can be used to call the application program for the road evaluation method stored in the memory 305. When executed by one or more processors 301, the electronic device 300 is caused to execute the method of one or more of the above embodiments. It should be noted that, for the foregoing method embodiments, for simplicity of description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present application. In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0119] In several implementation manners provided by the present application, it should be understood that the disclosed system can be implemented in other ways. For example, the system embodiments described above are only illustrative. For example, the division of units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the couplings or direct couplings or communication connections shown or discussed with each other can be through some service interfaces. The indirect couplings or communication connections of systems or units can be in electrical or other forms.

[0120] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0121] The embodiments of the present application also provide a computer storage medium. The computer storage medium can store multiple instructions, and the instructions are suitable for being loaded and executed by a processor to perform the road evaluation method of the embodiment shown above Figure 1 The specific execution process can be referred to the specific description of the embodiment shown Figure 1 and will not be elaborated here.

[0122] In addition, in each embodiment of the present application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0123] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present application. The aforementioned memory includes various media that can store program codes, such as USB flash drives, mobile hard disks, magnetic disks, or optical discs.

[0124] The above are only exemplary embodiments of the present disclosure, and the scope of the present disclosure cannot be limited thereby. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure still fall within the scope covered by the present disclosure. After considering the specification and the practice of the present disclosure, those skilled in the art will readily think of other implementation manners of the present disclosure.

[0125] The present application aims to cover any variations, uses, or adaptive changes of the present disclosure that follow the general principles of the present disclosure and include the common general knowledge or conventional technical means in the technical field not recorded in the present disclosure. The specification and the embodiments are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A water source detection method based on drone, characterized in that: The method comprises: Acquire geographic data of the area to be detected, and determine an initial detection route based on the geographic data; Generate UAV route planning data according to the initial detection route, and control the UAV to fly along the detection route according to the route planning data to collect multi-source heterogeneous data to obtain multi-source heterogeneous data, wherein the multi-source heterogeneous data includes remote sensing image data and geophysical exploration data; Preprocessing the multi-source heterogeneous data to obtain multi-scale feature data, and establishing a multi-dimensional hydrogeological feature space based on the multi-scale feature data, wherein the multi-dimensional hydrogeological feature space includes geological structure features, hydrological features, and groundwater distribution features; Mapping the multidimensional hydrogeological feature space into a preset deep belief network to obtain the spatial distribution probability of the desert aquifer, the location probability and range probability of the water conservation area, and generating a probability distribution map of the hydrogeological elements of the detection area according to the spatial distribution probability of the desert aquifer, the location probability and the range probability of the water conservation area; Based on the probability distribution map of the hydrogeological elements, the parameters of the preset hydrogeological conceptual model are updated to obtain a revised hydrogeological conceptual model; Inputting the multi-source heterogeneous data into the modified hydrogeological conceptual model, outputting spatiotemporal distribution characteristic data including groundwater storage conditions, and performing multi-criteria evaluation based on the spatiotemporal distribution characteristic data to obtain a water source potential zoning map; Adjust the initial detection route based on the water source potential zoning map to obtain a target detection route, and perform encrypted detection on the high potential area in the water source potential zoning map based on the target detection route to obtain encrypted detection data; Dynamic inversion is performed based on the encrypted detection data to obtain dynamic inversion results, and parameter optimization is performed based on the dynamic inversion results to obtain the optimal water source location coordinates.

2. The method according to claim 1, characterized in that: The preprocessing of the multi-source heterogeneous data to obtain multi-scale feature data includes: Performing geometric correction on the multi-source heterogeneous data to obtain first multi-source heterogeneous data, and performing radiation correction on the first multi-source heterogeneous data to obtain second multi-source heterogeneous data; Performing filtering and noise reduction processing on the second multi-source heterogeneous data to obtain target multi-source heterogeneous data; The target multi-source heterogeneous data is decomposed at multiple scales to obtain the multi-scale feature data.

3. The method according to claim 1, characterized in that The method of updating the parameters of the preset hydrogeological conceptual model based on the hydrogeological element probability distribution map to obtain a revised hydrogeological conceptual model includes: Extract key feature points from the probability distribution map of the hydrogeological elements; Correcting the structural parameters of the hydrogeological conceptual model based on the key characteristic points to obtain a preliminary hydrogeological conceptual model; The hydrological parameters of the preliminary hydrogeological conceptual model are dynamically adjusted using the probability distribution information to obtain the revised hydrogeological conceptual model.

4. The method according to claim 1, characterized in that The multi-criteria evaluation is performed according to the spatiotemporal distribution characteristic data to obtain a water source potential zoning map, including: Establishing an evaluation index system, and standardizing various indicators in the evaluation index system to obtain a preliminary evaluation index system; The analytic hierarchy process is used to determine the weight of each indicator in the preliminary evaluation indicator system to obtain a comprehensive evaluation indicator system; Calculating the individual indicator scores of each evaluation indicator in the spatiotemporal distribution characteristic data according to the comprehensive evaluation indicator system, and performing weighted summation on the individual indicator scores to obtain the evaluation score distribution map; The evaluation score distribution map and the preset zoning threshold standard are used to perform grade division, determine the potential zoning boundaries, and generate the water source potential zoning map containing zoning grade attributes based on the potential zoning boundaries.

5. The method according to claim 1, characterized in that The step of adjusting the initial detection route based on the water source potential zoning map to obtain a target detection route includes: Identify the boundaries of high potential areas in the water source potential zoning map; An encrypted detection grid is designed according to the spatial distribution characteristics of the high potential area, and the initial detection route is adjusted based on the encrypted detection grid to obtain the target detection route.

6. The method according to claim 1, characterized in that The step of determining an initial detection route according to the geographic data comprises: Analyzing and processing the geographic data to generate a comprehensive geographic information layer; The detection grid is divided according to the comprehensive geographic information layer, and the route design is performed based on the detection grid to obtain the initial detection route.

7. The method according to claim 1, characterized in that The generating of the probability distribution map of hydrogeological elements in the detection area according to the spatial distribution probability of the desert aquifer, the location probability of the water conservation area and the range probability comprises: Performing spatial registration on the spatial distribution probability of the desert aquifer, the location probability of the water conservation area, and the range probability respectively to obtain the registered spatial distribution probability, the registered location probability, and the registered range probability; A probability superposition model is constructed based on Bayesian theory, wherein the spatial distribution probability after registration is used as the prior probability of the probability superposition model, the position probability after registration is used as the conditional probability of the probability superposition model, and the range probability after registration is used as the edge probability of the probability superposition model; Using the probability superposition model to perform probability space interpolation to generate a continuous probability distribution field; Performing probability threshold analysis on the continuous probability distribution field to determine a probability threshold analysis result; A probability distribution map of hydrogeological elements in the detection area is generated based on the probability threshold analysis results.

8. A water source detection system based on drone, characterized in that: The system comprises: A route planning module, used to obtain geographic data of the area to be detected and determine an initial detection route based on the geographic data; Multi-source heterogeneous data acquisition, used to generate UAV route planning data according to the initial detection route, and control the UAV to fly along the detection route according to the route planning data to perform multi-source heterogeneous data acquisition, wherein the multi-source heterogeneous data includes remote sensing image data and geophysical data; A preprocessing module, used to preprocess the multi-source heterogeneous data to obtain multi-scale feature data, and establish a multi-dimensional hydrogeological feature space based on the multi-scale feature data, wherein the multi-dimensional hydrogeological feature space includes geological structure features, hydrological features and groundwater distribution features; A data processing module is used to map the multidimensional hydrogeological feature space into a preset deep belief network to obtain the spatial distribution probability of the desert aquifer, the location probability and range probability of the water conservation area, and generate a probability distribution map of the hydrogeological elements of the detection area according to the spatial distribution probability of the desert aquifer, the location probability of the water conservation area and the range probability; A parameter updating module, used for updating the parameters of the preset hydrogeological conceptual model based on the hydrogeological element probability distribution map to obtain a revised hydrogeological conceptual model; A multi-criteria evaluation module is used to input the multi-source heterogeneous data into the modified hydrogeological conceptual model, output the spatiotemporal distribution characteristic data including groundwater storage conditions, and perform multi-criteria evaluation based on the spatiotemporal distribution characteristic data to obtain a water source potential zoning map; An encrypted detection module is used to adjust the initial detection route based on the water source potential zoning map to obtain a target detection route, and perform encrypted detection on the high potential area in the water source potential zoning map based on the target detection route to obtain encrypted detection data; The optimal water source location determination module is used to perform dynamic inversion based on the encrypted detection data to obtain dynamic inversion results, and perform parameter optimization based on the dynamic inversion results to obtain the location coordinates of the optimal water source location.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: It includes a processor, a memory and a transceiver, the memory is used to store instructions, the transceiver is used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method according to any one of claims 1 to 7.

Images