Water source detection method and system based on unmanned aerial vehicle, electronic equipment and storage medium

Abstract

The invention provides a water source detection method and system based on an unmanned aerial vehicle, electronic equipment and a storage medium, and relates to the field of water source detection. The method comprises the following steps: collecting multi-source heterogeneous data; the method comprises the following steps: preprocessing multi-source heterogeneous data to obtain multi-scale feature data, and establishing a multi-dimensional hydrogeological feature space; and inputting the multi-dimensional hydrogeological feature space into a preset deep belief network, and generating a probabilistic distribution diagram of the hydrogeological elements in the detection area. And updating preset hydrogeological conceptual model parameters based on the hydrogeological element probability distribution map, inputting the multi-source heterogeneous data into the corrected hydrogeological conceptual model, outputting spatial and temporal distribution characteristic data, and generating a water source potential partition map through multi-criterion evaluation. And determining a high potential area according to the water source potential partition map, performing encryption detection on the high potential area to obtain encryption detection data, and determining an optimal water source point position coordinate based on the encryption detection data. According to the technical scheme, the accuracy of water source detection based on the unmanned aerial vehicle is improved.

Description

Technical Field

[0001] The present application relates to the field of water source detection, and in particular to a water source detection method, system, electronic device and storage medium based on an unmanned aerial vehicle. Background Art

[0002] In desert areas, the exploration of water resources is of great significance to local economic development and ecological protection. At present, desert water source detection mainly adopts remote sensing image interpretation, geophysical exploration and other technical means to determine the location of water sources by obtaining surface information and underground structure characteristics. With the development of drone technology, its application in the field of resource exploration is becoming more and more extensive. The existing drone water source detection method usually collects data on a pre-set fixed route, and the collected data includes optical remote sensing images, multispectral images, etc. After processing and analysis, these data are combined with existing hydrogeological data 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 adopts a fixed detection route and a single data analysis method, which leads to uncertainty in the judgment of the location of water sources. Summary of the invention

[0003] The present application provides a drone-based water source detection method, system, electronic device and storage medium to improve the accuracy of drone-based water source detection.

[0004] In a first aspect, the present application provides a water source detection method based on a drone, comprising: 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, wherein the multi-source heterogeneous data includes remote sensing image data and geophysical 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.

[0005] In the above technical scheme, the initial detection route is determined by obtaining the geographic data of the area to be detected, and based on the initial detection route, the drone is controlled to collect multi-source heterogeneous data including remote sensing image data and geophysical data. Since the use of multi-source heterogeneous data can reflect the distribution characteristics of groundwater from different dimensions, the information integrity of water source detection is improved. The pre-processed multi-scale feature data is used to establish a multi-dimensional hydrogeological feature space containing geological structure, hydrological characteristics and groundwater distribution, and the feature space is mapped 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 source conservation area, and then generate a probability distribution map of the hydrogeological elements of the detection area, thereby achieving accurate quantification of the hydrogeological elements. By using the probability distribution map of the 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. The multi-source heterogeneous data is input into the revised hydrogeological conceptual model, the spatiotemporal distribution characteristic data is output, and a multi-criteria evaluation is performed to obtain the potential zoning map of the water source, which provides a basis for the optimization of the detection route. Based on the water source potential zoning map, the initial detection route was adjusted and the high-potential areas were detected more densely. The location coordinates of the optimal water source were determined through dynamic inversion and parameter optimization, which achieved adaptive optimization of the detection process and significantly improved the accuracy and efficiency of water source detection.

[0006] In a second aspect of the present application, a water source detection system based on a drone is provided, the system comprising: 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.

[0007] In a third aspect of the present application, a computer storage medium is provided, wherein the computer storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the above method steps.

[0008] 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 executes the above method.

[0009] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. This application determines the initial detection route by obtaining geographic data of the area to be detected, and controls the drone to collect multi-source heterogeneous data including remote sensing image data and geophysical data based on the initial detection route. Since the use of multi-source heterogeneous data can reflect the distribution characteristics of groundwater from different dimensions, the information integrity of water source detection is improved. The pre-processed multi-scale feature data is used to establish a multi-dimensional hydrogeological feature space including geological structure, hydrological characteristics and groundwater distribution, and the feature space is mapped into a preset deep confidence network to obtain the spatial distribution probability of desert aquifers, the location probability and range probability of water conservation areas, and then generate a probability distribution map of hydrogeological elements in the detection area, realizing the accurate quantification of hydrogeological elements.

[0010] 2. This application uses the probability distribution map of hydrogeological elements 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. Multi-source heterogeneous data are input into the revised hydrogeological conceptual model, and the spatiotemporal distribution characteristic data are output and multi-criteria evaluation is performed to obtain the water source potential zoning map, which provides a basis for the optimization of the detection route. Based on the water source potential zoning map, the initial detection route is adjusted and the high potential area is encrypted. 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

[0011] Figure 1 A schematic diagram of a flow chart of a water source detection method based on a drone provided in an embodiment of the present application; Figure 2 An architecture diagram of a water source detection system based on a drone provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of an electronic device provided in this application. DETAILED DESCRIPTION

[0012] In order to enable technicians in this field 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 drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0013] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0014] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0015] In order to facilitate 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 is first introduced.

[0016] 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 advancement of science and technology, desert water source detection technology has gradually developed, mainly through remote sensing image interpretation and geophysical exploration, to obtain surface information and underground structural characteristics to infer the location of water sources. In recent years, drone technology has shown significant advantages in the field of resource exploration, providing new technical means for water source detection. At present, the drone water source detection method mainly flies along a pre-set fixed route, collects optical remote sensing images and multispectral images and other data, and combines these data with existing hydrogeological data to analyze 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, and it is impossible to dynamically optimize and adjust the detection process, resulting in the accuracy and reliability of water source location judgment being difficult to guarantee.

[0017] After the background introduction of the above content, those skilled in the art can understand the problems existing in the prior art. The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments.

[0018] Based on the above background technology, please refer to Figure 1 , Figure 1 A flow chart of a water source detection method based on a drone provided in an embodiment of the present application. The system can be implemented by a computer program or can be run as an independent tool application. Specifically, in an embodiment of the present application, the method can be applied on a server, but can also be applied to electronic devices such as servers. A water source detection method based on a drone includes the following steps: S101, obtaining geographic data of the area to be detected, and determining an initial detection route according to the geographic data; Specifically, during implementation, the geographic data of the area to be detected are first obtained, including terrain elevation data, surface cover type data and geological structure data. Among them, terrain elevation data is used to characterize the characteristics of surface undulation, surface cover type data reflects the spatial distribution of different covers such as surface vegetation and bare soil, and geological structure data reflects the characteristics of regional geological structures such as faults and folds. By analyzing and processing these geographic data, a comprehensive geographic information layer is generated, which integrates multi-dimensional information such as terrain, surface cover and geological structure. Based on the comprehensive geographic information layer, the grid division method is used to divide the area to be detected into several regular detection grids, and the size of each detection grid is determined according to the complexity of the terrain and the detection accuracy requirements. On the basis of the detection grid, the initial detection route is designed by connecting the center points of each grid. The initial detection route fully considers the impact of terrain conditions on the flight of the UAV, avoids the dangerous terrain that is not conducive to the flight of the UAV, and ensures that the detection route effectively covers the entire area to be detected. 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 the UAV flight.

[0019] Based on the above embodiment, as an optional embodiment, determining the initial detection route according to the geographic data includes: S201, analyzing and processing the geographic data to generate a comprehensive geographic information layer; Specifically, geographic data includes digital elevation model data, remote sensing image data and geological structure data. The digital elevation model data is used to extract terrain characteristic parameters such as slope and aspect, and the remote sensing image data is used to identify surface features such as vegetation coverage and land use type. The geological structure information such as faults and folds is extracted from the geological structure data. The extracted terrain characteristic parameters, surface features and geological structure information are spatially registered, and the various types of information are integrated using spatial overlay analysis methods to generate a comprehensive geographic information layer containing multiple layers of geographic information. The comprehensive geographic information layer is stored in a raster data structure, and each raster unit contains attribute information such as terrain, surface and geology, realizing the effective integration of multi-source geographic information. The generated comprehensive geographic information layer provides complete geographic spatial information support for subsequent detection grid division and route planning, and improves the rationality of the initial detection route design.

[0020] S202, dividing the detection grids according to the comprehensive geographic information layer, and performing route design based on the detection grids to obtain the initial detection route.

[0021] Specifically, according to the terrain complexity and detection accuracy requirements in the comprehensive geographic information layer, an adaptive grid division algorithm is used to divide the detection area into grids. The algorithm divides smaller detection grids in areas with complex terrain and larger detection grids in areas with flat terrain by calculating the terrain change gradient of each area. The size of the detection grid ranges from 50 meters to 200 meters. After the division is completed, the improved ant colony algorithm is used for route design. The algorithm uses the center point of the detection grid as the path node and determines the optimal node connection order by calculating factors such as the terrain resistance value, flight distance and detection coverage efficiency between adjacent nodes. In the route design process, the endurance of the UAV and the working characteristics of the detection equipment are comprehensively considered, and the detection area is divided into multiple sub-areas. The detection route length of each sub-area does not exceed the maximum range of the UAV. 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 and improves the detection efficiency.

[0022] S102, generating UAV route planning data according to the initial detection route, and controlling the UAV to fly along the detection route according to the route planning data to collect multi-source heterogeneous data, wherein the multi-source heterogeneous data includes remote sensing image data and geophysical exploration data; Specifically, based on the initial detection route, the route planning algorithm is used to generate the UAV route planning data, which contains flight parameter information such as flight altitude, speed, and heading angle. In the route planning process, considering that the remote sensing image data acquisition needs to maintain a certain altitude to obtain a larger ground coverage, while the geophysical data acquisition requires a lower flight altitude to improve the detection sensitivity, a segmented variable altitude flight mode is adopted, and the altitude is set to 300 meters in the remote sensing image acquisition section and reduced to 100 meters in the geophysical data acquisition section. The route planning data is converted into flight control instructions through the UAV control system to control the UAV to fly according to the predetermined route. During the flight, the multispectral camera carried collects remote sensing image data including visible light and near-infrared bands, while the airborne magnetometer and electromagnetic detection equipment collect geomagnetic field intensity, georesistivity and other geophysical data. This multi-source heterogeneous data acquisition method enables the detection data to contain 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.

[0023] S103, 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; Specifically, the collected multi-source heterogeneous data are first preprocessed, and the deformation error of remote sensing image data is eliminated by geometric correction. The multispectral data is atmospherically corrected and reflectivity converted by radiometric calibration method, and the geophysical data is noise filtered and data smoothed. Based on the preprocessing, the multi-scale analysis method is used to extract features. The texture features and surface cover features at different scales are extracted by wavelet transform for remote sensing image data, and the geological structure features in different frequency domains are extracted by Fourier transform for geophysical data to form multi-scale feature data. Based on the multi-scale feature data, a multi-dimensional hydrogeological feature space is constructed by deep learning algorithm. The feature space contains three dimensions: the geological structure dimension reflects the distribution characteristics of geological structures such as faults and folds, the hydrological feature dimension reflects hydrological indicators such as surface water system and vegetation coverage, and the groundwater distribution dimension represents groundwater characteristics such as aquifer location and burial depth. The information of the three dimensions is integrated through the feature fusion algorithm to establish a unified multi-dimensional hydrogeological feature space. The feature space realizes the organic combination of surface information and underground information, and provides a complete feature expression for the subsequent water source location judgment.

[0024] Based on the above embodiment, as an optional embodiment, the preprocessing of the multi-source heterogeneous data to obtain multi-scale feature data includes: S301, geometrically correcting 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; Specifically, for the collected multi-source heterogeneous data, geometric correction processing is first performed. This process uses ground control points to perform spatial registration and coordinate conversion on the original data, eliminates geometric deformation caused by factors such as terrain undulation, satellite attitude and sensor distortion, and makes the data have a unified geographic coordinate system to obtain the first multi-source heterogeneous data. The first multi-source heterogeneous data is subjected to radiation correction. This process eliminates the influence of factors such as atmospheric scattering and absorption through the atmospheric correction model, and uses the sensor calibration parameters to convert digital quantities into physical quantities. At the same time, radiation normalization processing is performed on data of different phases to make the data comparable, and the second multi-source heterogeneous data is obtained. This data preprocessing method ensures the consistency of multi-source heterogeneous data in spatial position and radiation characteristics, laying the foundation for subsequent multi-scale feature extraction. Through these two correction steps, the geometric accuracy and radiation accuracy of the data are significantly improved, ensuring the reliability of subsequent analysis results.

[0025] S302, performing filtering and noise reduction processing on the second multi-source heterogeneous data to obtain target multi-source heterogeneous data; Specifically, the second multi-source heterogeneous data is filtered and denoised, and the wavelet transform method is used to perform multi-scale decomposition on the data, and the signal is decomposed into different frequency components. In the wavelet domain, the noise coefficient is processed using the threshold method to retain the low-frequency coefficients that characterize the geological information and suppress the high-frequency noise components. At the same time, an adaptive median filter is used to remove the impulse noise in the data. The filter dynamically adjusts the filter window size according to the local data characteristics, effectively suppressing random noise while maintaining the geological boundary characteristics. After filtering and denoising, the target multi-source heterogeneous data is obtained, which has a higher signal-to-noise ratio and clearer geological structure characteristics. This denoising method based on wavelet transform and adaptive filtering can effectively remove noise while maintaining the effective information in the original data to the greatest extent, thereby improving the accuracy and reliability of subsequent analysis.

[0026] S303, performing multi-scale decomposition on the target multi-source heterogeneous data to obtain the multi-scale feature data.

[0027] Specifically, the pyramid multi-resolution analysis method is used to perform multi-scale decomposition of the target multi-source heterogeneous data, and 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 group is used to extract the directional characteristics of the geological structure, including linear structure, circular structure, etc. At the same time, the Gabor wavelet transform is used to decompose the data in the frequency domain to extract the texture features under different frequency components. The information of these different scales and different features is integrated to form multi-scale feature data. The multi-scale feature data contains complete geological information from local details to regional macro, and can comprehensively characterize the geological structure characteristics of the study area. Through this multi-scale decomposition method, the multi-level characterization of the geological body is realized, providing rich feature information for subsequent geological interpretation and hydrogeological modeling.

[0028] S104, 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; Specifically, the constructed multidimensional hydrogeological feature space is used as input data and mapped to a pre-trained deep belief network for probabilistic reasoning. The deep belief network is composed of multiple layers of restricted Boltzmann machines, each layer of which contains hundreds of neuron nodes for feature extraction and probability calculation. The first layer of the network receives the input data of the multidimensional hydrogeological feature space and extracts deep feature representation through feature transformation and nonlinear mapping. Feature combination and probabilistic reasoning 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 groundwater bodies in three-dimensional space, the location probability of the water source conservation area reflects the location of surface water recharging groundwater, and the range probability describes the spatial range of the water source conservation area. Based on these three probability indicators, the geographic information system technology is used to generate the probability distribution map of the hydrogeological elements in the detection area. The distribution map stores the probability values ​​in the form of a raster, and the probability size is represented by different color depths, realizing the visual expression of the distribution of hydrogeological elements. This probabilistic reasoning method based on the deep belief network makes full use of the information of the multidimensional feature space and improves the accuracy of hydrogeological element identification.

[0029] S105, updating parameters of a preset hydrogeological conceptual model based on the hydrogeological element probability distribution map to obtain a revised hydrogeological conceptual model; Specifically, the generated probability distribution map of hydrogeological elements is compared and analyzed with the preset hydrogeological conceptual model, which contains information such as stratigraphic structure, hydrogeological parameters and groundwater flow field. The Bayesian update method is used to correct the model parameters. First, the probability distribution map of hydrogeological elements is converted into a likelihood function, which is combined with the prior distribution of model parameters to calculate the posterior distribution of parameters. The specific updated parameters include hydrogeological parameters such as aquifer permeability coefficient, water storage coefficient, and recharge coefficient. At the same time, the hydrodynamic characteristics such as groundwater flow direction and flow velocity are adjusted. Through iterative calculation, when the model response change caused by parameter update is less than the set threshold, the parameter update process is completed. The revised hydrogeological conceptual model not only contains the original geological structure framework, but also incorporates the hydrogeological characteristics reflected by the measured data, which improves the model's ability to express actual hydrogeological conditions. This model parameter update method based on measured data effectively improves the accuracy and reliability of the hydrogeological conceptual model and provides a more accurate model basis for subsequent groundwater resource evaluation.

[0030] Based on the above embodiment, as an optional embodiment, the parameters of the preset hydrogeological conceptual model are updated based on the hydrogeological element probability distribution map to obtain a revised hydrogeological conceptual model, including: S401, extracting key feature points in the hydrogeological element probability distribution map; Specifically, key feature points are extracted from the probability distribution map of hydrogeological elements, and the corner detection algorithm is used to identify the intersection points and inflection points of geological structures. These points usually represent important hydrogeological significance. At the same time, the regional growing algorithm is used to extract the boundary points of aquifer distribution. These boundary points characterize the spatial distribution characteristics of aquifers. In areas where hydrogeological elements change significantly, such as fault zones and lithological contact zones, the gradient operator is used to calculate the rate of change of probability values, and probability value mutation points are extracted as key feature points. Cluster analysis is performed on the probability values ​​of hydrogeological elements to identify the center points of high-value areas and the dividing points of low-value areas. The extraction process of these key feature points comprehensively considers the characteristics of geological structures, aquifer distribution characteristics, and probability value distribution characteristics, providing control point information for the subsequent parameter update of the hydrogeological conceptual model, and improving the accuracy and pertinence of model correction.

[0031] S402, correcting the structural parameters of the hydrogeological conceptual model based on the key feature points to obtain a preliminary hydrogeological conceptual model; Specifically, the structural parameters of the hydrogeological conceptual model are corrected based on the extracted key feature points. First, the discrete key feature points are converted into a continuous parameter distribution field using the Kriging interpolation method. For structural parameters such as aquifer thickness and burial depth, the objective function is established using the variational method. The key feature points are used as constraints, and the original structural parameters are optimized and adjusted by the least squares method. In areas with obvious features such as fault zones and lithology boundaries, the local weighted regression method is used to finely correct the structural parameters. The model grid is adjusted by elastic grid deformation technology so that the grid nodes are adapted to the positions of key feature points, thereby improving the spatial expression accuracy of the structural parameters. After correction, a preliminary hydrogeological conceptual model is obtained. The distribution of the structural parameters of the model is more in line with the actual geological conditions, which improves the structural accuracy of the model. This structural parameter correction method based on key feature points realizes the quantitative optimization of the model structure and lays the foundation for the subsequent fine expression of hydrogeological parameters.

[0032] S403, dynamically adjusting the hydrological parameters of the preliminary hydrogeological conceptual model using the probability distribution information to obtain the revised hydrogeological conceptual model.

[0033] Specifically, the hydrological parameters of the preliminary hydrogeological conceptual model are dynamically adjusted using the probability distribution information of hydrogeological elements. First, the conversion relationship between probability values ​​and hydrological parameters is established. The parameter conversion function is constructed through the correlation analysis between hydrological parameters such as permeability coefficient and water storage coefficient and probability values. The Bayesian framework is used to update the parameters, and the probability distribution is used as prior information. Combined with the field pumping test data as conditional information, the hydrological parameters are iteratively optimized through the Markov chain Monte Carlo algorithm. In the parameter optimization process, the adaptive weight method is used to dynamically adjust the parameter correction amplitude according to the probability value of different regions to ensure the rationality of parameter update. At the same time, the validity of the parameters is verified by the water balance constraint condition to ensure that the revised hydrological parameters meet the regional hydrogeological conditions. After dynamic adjustment, the revised hydrogeological conceptual model is obtained. The hydrological parameter distribution of the 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.

[0034] S106, 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; Specifically, the collected multi-source heterogeneous data are used as the input data of the revised hydrogeological conceptual model, and the spatiotemporal distribution characteristic data of groundwater occurrence conditions are obtained through model calculation. The data contains characteristic information of groundwater level, water quality parameters, water volume distribution, etc. that change with time and space. Based on the spatiotemporal 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 coefficient of each indicator is determined by 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, to generate a water source potential zoning map. The zoning map uses different colors to identify areas of different potential levels, and marks the location and range of the high potential area that is the focus of attention. Through this multi-criteria evaluation method, a comprehensive evaluation of the potential of groundwater resources is achieved, which provides a scientific basis for water source site selection decisions and improves the efficiency and accuracy of water source exploration.

[0035] Based on the above embodiment, as an optional embodiment, the multi-criteria evaluation is performed according to the spatiotemporal distribution characteristic data to obtain a water source potential zoning map, including: S501, establishing an evaluation index system, and standardizing various indicators in the evaluation index system to obtain a preliminary evaluation index system; Specifically, an evaluation index system is established based on the temporal and spatial distribution characteristic data. The index system includes hydrogeological conditions, topography, recharge conditions, mining conditions and other aspects. In terms of hydrogeological conditions, aquifer thickness, permeability coefficient and water 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 and groundwater runoff modulus are selected as evaluation indicators; in terms of mining conditions, burial depth and water quality type are selected as evaluation indicators. The extreme value standardization method is used to non-dimensionalize indicators of different dimensions, and the values ​​of each indicator are uniformly converted to the range of 0-1. For positive indicators, the minimum-maximum value standardization formula is used for conversion; for negative indicators, the maximum-minimum value standardization formula is used for conversion. The preliminary evaluation index system is obtained through standardization, which makes different indicators comparable and provides a basis for the subsequent indicator weight determination and comprehensive evaluation. This multi-level and multi-angle evaluation index system establishment method ensures the comprehensiveness and scientificity of water source potential evaluation.

[0036] S502, using the analytic hierarchy process to determine the weight of each indicator in the preliminary evaluation indicator system to obtain a comprehensive evaluation indicator system; Specifically, the analytic hierarchy process was used to determine the weight of each indicator in the preliminary evaluation index system. First, the index hierarchy structure was constructed, and the evaluation indicators were divided into three levels: target layer, criterion layer, and indicator layer. The expert scoring method was used to establish a pairwise comparison judgment matrix between indicators, and the 1-9 ratio scaling method was used to quantify the importance of indicators. The eigenvalue method was used to calculate the maximum eigenvalue and corresponding eigenvector of the judgment matrix, and the weight value of each layer of indicators was obtained after the eigenvector was normalized. The judgment matrix was tested for consistency, and the consistency index and consistency ratio were calculated. When the consistency ratio was less than 0.1, it indicated that the weight distribution was reasonable. The hierarchical comprehensive method was used to combine the weights of each level to obtain the comprehensive weight value of all indicators relative to the overall goal. Finally, a comprehensive evaluation index system including an indicator system and a weight system was formed. The system fully considered the contribution of each indicator to the evaluation of water source potential, and provided a scientific quantitative basis for the subsequent multi-criteria comprehensive evaluation.

[0037] S503, calculating the individual indicator score 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; Specifically, the individual scores of each evaluation index in the spatiotemporal distribution characteristic data are calculated according to the comprehensive evaluation index system, and the standardized index values ​​are converted into evaluation scores using the fuzzy membership function. The continuous index is converted using the piecewise linear membership function, the optimal interval and critical interval of the index value are set, and the membership scores corresponding to different index values ​​are calculated. The expert scoring method is used to directly assign evaluation scores to discrete indicators. The individual scores of each evaluation index are multiplied by the corresponding weight value, and the comprehensive evaluation score of each evaluation unit is obtained by weighted summation. The Kriging spatial interpolation method is used to convert the discrete evaluation unit scores into a continuous distribution evaluation score distribution map, which shows the development potential of water sources 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 water source potential. The evaluation score distribution map intuitively reflects the spatial differentiation characteristics of water source suitability, providing a scientific basis for water source site selection decisions.

[0038] S504, performing grade division according to the evaluation score distribution map and the preset zoning threshold standard, determining potential zoning boundaries, and generating the water source potential zoning map containing zoning grade attributes according to the potential zoning boundaries.

[0039] Specifically, the potential zoning of water sources is divided according to the evaluation score distribution map. First, the zoning threshold standard is set based on the suitability of water source development, and the evaluation score is divided into three levels: high potential area, medium potential area and low potential area. The natural breakpoint method is used to determine the grading threshold of the evaluation score. This method achieves optimal grading by minimizing the intra-level variance and maximizing the inter-level variance. The vectorization tool in the geographic information system is used to extract contour lines, and the evaluation score distribution map is converted into potential zones with clear boundaries. The fragmentation of the zone boundaries is eliminated through topological processing to ensure the continuity and integrity of the zone boundaries. Each potential zone is assigned a corresponding level attribute, and a water source potential zoning map containing attribute information such as zone code, zone level, and area statistics is generated. The zoning map clearly shows the spatial distribution pattern of the development potential of the water source in the study area. The demarcation of the zone boundaries not only takes into account the continuous change characteristics of the evaluation scores, but also ensures the practicality and operability of the zones, providing an intuitive spatial decision-making basis for water source planning and management.

[0040] S107, adjusting the initial detection route based on the water source potential zoning map to obtain a target detection route, and performing 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; Specifically, according to the generated water source potential zoning map, the initial detection route is optimized and adjusted, the detection density is increased in high potential areas, and the detection routes in low potential areas are reduced to form a target detection route. The design of the target detection route adopts an adaptive grid encryption method. In the high potential area, the detection line spacing is reduced from the initial 500 meters to 100 meters. At the same time, the connecting survey line perpendicular to the main survey line is increased to form a grid detection system. Based on the target detection route, the detection is encrypted, and a variety of detection methods are used in the high potential area: the transient electromagnetic method is used to obtain underground electrical structure data, the seismic exploration method is used to collect stratigraphic structure information, and the density distribution characteristics are obtained through gravity measurement. These encrypted detection data have higher spatial resolution and detection accuracy, and can describe the geological structure and aquifer characteristics of the high potential area in detail. Through the optimization design of the target detection route and the implementation of encrypted detection, the detection accuracy of the hydrogeological conditions in the high potential area is improved, providing more detailed data support for the subsequent determination of the water source.

[0041] Based on the above embodiment, as an optional embodiment, the adjusting the initial detection route based on the water source potential zoning map to obtain the target detection route includes: S601, identifying the boundary of the high potential area in the water source potential zoning map; Specifically, the boundary of the high potential area is identified based on the potential zoning map of the water source. First, the spatial range of the high potential area is extracted by vector data processing. The boundary tracking algorithm is used to extract the contour of the high potential area, and the boundary line of the area with the highest evaluation score in the zoning map is vectorized. The boundary line is smoothed and simplified by morphological processing methods to eliminate subtle bumps and retain the main boundary features. The connectivity and adjacency relationship of the high potential area are determined by topological analysis, and the transition zone position of adjacent partitions is identified. The identified boundaries are attributed and the spatial coordinates and length information of the boundary line are recorded. The identification results of the high potential area boundary are saved in the form of vector boundary lines for subsequent optimization design of the detection route. This boundary recognition method accurately extracts the spatial distribution range of the high potential area and provides a spatial reference basis for the reasonable layout of the detection route.

[0042] S602, designing an encrypted detection grid according to the spatial distribution characteristics of the high potential area, and adjusting the initial detection route based on the encrypted detection grid to obtain the target detection route.

[0043] Specifically, based on the spatial distribution characteristics of high-potential areas, the design of encrypted detection grids is carried out, and smaller grid spacing is used for encrypted layout in high-potential areas, and the grid spacing is reduced from 100 meters of the original detection grid to 50 meters. A square grid division scheme is adopted to ensure the regularity of the grid and the uniformity of detection coverage. A gradient grid design is adopted in the boundary zone of the high-potential area, and the grid spacing gradually transitions from the high-potential area to the outside to avoid sudden changes in the grid scale. The initial detection route is adjusted according to the encrypted detection grid, the detection point position is adjusted to the grid node, and the detection line is laid along the grid boundary. The shortest path algorithm is used to optimize the detection route direction, and the total length of the route is reduced while meeting the detection accuracy requirements. The design of the target detection route not only ensures the detailed detection of the high-potential area, but also realizes the reasonable allocation of detection resources. The adjusted target detection route is saved in the form of a vector line, containing attribute information such as detection point coordinates, route length, and grid number, which provides specific technical guidance for subsequent field detection work.

[0044] Based on the above embodiment, as an optional embodiment, determining the initial detection route according to the geographic data includes: S701, analyzing and processing the geographic data to generate a comprehensive geographic information layer; Specifically, the geographic data is analyzed and processed. First, the geographic data from different sources are unified into vector data format through data format conversion. The geographic data is converted into a unified coordinate system using projection transformation to ensure accurate correspondence of spatial positions. The spatial overlay analysis method is used to synthesize the layers of geographical elements such as terrain, landforms, water systems, and roads to form a multi-level geographic information expression. The landform features such as slope and slope aspect are extracted through terrain analysis and digitized. The water system data is extracted and graded to identify the spatial distribution pattern of major rivers and tributaries. The traffic accessibility analysis layer is constructed using road network data, and the grade attributes of the main roads and secondary roads are marked. The layer management technology is used to organize various geographic elements in layers to generate a comprehensive geographic information layer containing multi-dimensional information such as terrain, water systems, and transportation. This layer is saved in the form of layered vector data, which realizes the systematic management and visual expression of geographic information and provides a complete geographic spatial reference for the planning and design of the detection route.

[0045] S702, dividing the detection grid according to the comprehensive geographic information layer, and designing a route based on the detection grid to obtain the initial detection route.

[0046] Specifically, the detection grid is divided based on the comprehensive geographic information layer, and the study area is divided into square grid units of 100 meters × 100 meters using the regular grid method. When performing grid division, the terrain undulation and road distribution characteristics are taken into consideration, and the grid is adjusted for steep terrain areas and areas with inconvenient transportation. The grid division tool is used to generate grid codes, and a grid attribute table is established to record the geographic feature information of each grid unit. Route design is performed based on the detection grid. First, the locations of the detection start and end points are determined, and an area with convenient transportation and flat terrain is selected as the detection starting point. The detection route direction is designed using a serpentine traversal method so that the detection route passes through each grid node in turn. In the route design process, the detection route is optimized in combination with the road distribution, and it is laid out along the existing roads as much as possible to reduce the construction of new channels. The optimal connection method between grid nodes is determined by 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 location, and grid number, which provides basic data for subsequent detection route optimization.

[0047] S108, performing dynamic inversion based on the encrypted detection data to obtain a dynamic inversion result, and performing parameter optimization based on the dynamic inversion result to obtain the location coordinates of the optimal water source.

[0048] Specifically, dynamic inversion is performed using encrypted detection data. The inversion process uses the conjugate gradient method to iteratively calculate the detection data, optimizes the model parameters through the least squares principle, and realizes the dynamic update of underground medium parameters. During the dynamic inversion process, data from multiple geophysical 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, genetic algorithms are used for parameter optimization. Parameters such as aquifer thickness, burial depth, permeability, and recharge conditions are used as optimization targets, and the suitability of water sources at different locations is evaluated through fitness functions. In the iterative optimization process, population parameters and crossover 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.

[0049] Based on the above embodiment, as an optional embodiment, 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: S801, spatially registering the spatial distribution probability of the desert aquifer, the location probability of the water conservation area, and the range probability, respectively, to obtain a registered spatial distribution probability, a registered location probability, and a registered range probability; Specifically, the probability data of hydrogeological elements are spatially registered. First, a unified geographic coordinate reference system is established, and the UTM projection method is used to ensure the accurate correspondence of spatial positions. The spatial distribution probability data of desert aquifers are geometrically corrected using spatial registration tools and converted to the target coordinate system. The location probability data of water conservation areas are registered and transformed, and the accurate correspondence of spatial positions is achieved through control point matching. The range probability data is processed by the resampling method 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 the probability value. The registration results are evaluated for accuracy, and the registration error is calculated to ensure that the registration accuracy meets the requirements of subsequent analysis. The registered spatial distribution probability, registered location probability, and registered range probability are all converted into a unified raster data format with the same spatial resolution and coordinate reference. Spatial registration processing realizes the spatial unification of different probability data and provides basic data support for subsequent probability overlay analysis.

[0050] S802, constructing a probability superposition model 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; Specifically, when constructing the probability superposition model based on Bayesian theory, the spatial distribution probability after registration is used as the prior probability reflecting the distribution law of desert aquifers, which represents the initial understanding of the spatial distribution of aquifers before obtaining other information. The location probability after registration is used as the conditional probability to represent the probability of aquifers appearing when the location of the water conservation area is known, reflecting the correlation between the water conservation area and the distribution of aquifers. The range probability after registration is used as the marginal probability to characterize the overall distribution characteristics of aquifers in the study area. The Bayesian formula is used to establish a probability superposition calculation model, and the posterior probability of each grid unit in the study area is calculated through the mathematical combination of prior probability, conditional probability and marginal probability. In the process of model construction, the log-likelihood function is used to process the probability multiplication operation to avoid numerical truncation caused by decimal multiplication. 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 mathematical formulas, which is convenient for subsequent program implementation and calculation processing.

[0051] S803, performing probability space interpolation using the probability superposition model to generate a continuous probability distribution field; Specifically, when using the probability superposition model for probability spatial interpolation, the Kriging interpolation method is used to process discrete probability data. This method takes into account spatial autocorrelation and can reflect the spatial variation characteristics of probability values. Before interpolation calculation, the spatial correlation structure of the probability field is determined by variogram analysis, and a semivariogram model is established to describe the spatial variation law of probability values. The spherical model is selected as the theoretical semivariogram, and the experimental semivariogram is fitted by the least squares method to obtain spatial structural parameters such as range and sill value. The ordinary Kriging interpolation algorithm is used to grid the study area to generate regular raster data. In 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 results are 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 raster data with a spatial resolution of 10 meters, which realizes the continuous expression of the probability field and provides complete spatial probability information for subsequent hydrogeological element analysis.

[0052] S804, performing probability threshold analysis on the continuous probability distribution field to determine a probability threshold analysis result; Specifically, the probability threshold analysis of the continuous probability distribution field is carried out. First, the probability statistics method is used to calculate the frequency distribution characteristics of the probability value, and the probability value statistical histogram is established. The distribution law of the probability value is determined by cumulative frequency analysis, and the cumulative frequency at different probability levels is calculated. The probability value is graded using the natural breakpoint method, and the probability value is divided into three level intervals: high, medium, and low. In the process of probability threshold division, the variance minimization criterion is used to determine the optimal classification breakpoint, so that the intra-class variance is minimized and the inter-class variance is maximized. Spatial statistical analysis is performed on each level interval to calculate the area proportion of different probability level areas. Combined with the known hydrogeological conditions, the rationality of the probability threshold is verified, and the final probability threshold analysis results are determined. The probability threshold analysis results are expressed in the form of graded raster data, which clearly shows the spatial differentiation characteristics of the hydrogeological elements in the study area, and provides a quantitative basis for the optimization of the detection area.

[0053] S805: Generate a probability distribution map of hydrogeological elements in the detection area based on the probability threshold analysis result.

[0054] Specifically, the probability distribution map of hydrogeological elements in the detection area is generated based on the results of probability threshold analysis, and the map is compiled using the geographic information system mapping method. First, a unified map projection and coordinate system is established, and an appropriate map scale is set to ensure the accuracy of map expression. The results of probability threshold analysis are converted into vector data format, and a spatial database of hydrogeological elements in the detection area is established. The legend is designed using a graded color expression scheme, with red for high-probability areas, yellow for medium-probability areas, and blue for low-probability areas, highlighting the spatial differences in probability distribution. In the process of map making, basic geographic information such as topographic base maps and administrative boundaries are superimposed to improve the configuration of map elements. Essential map elements such as compasses, scales, and legends are added to improve the readability of the map. The resulting probability distribution map of hydrogeological elements in the detection area intuitively shows the spatial distribution law of hydrogeological elements in the study area, providing a spatial decision-making basis for subsequent detection work.

[0055] On the other hand, the present application also provides a water source detection system based on a drone, such as Figure 2 The system comprises: Route planning module 1, 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 2, used for generating UAV route planning data according to the initial detection route, and controlling 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 3 is used to preprocess the multi-source heterogeneous data to obtain multi-scale feature data, and to 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; Data processing module 4 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 and the range probability of the water conservation area; A parameter updating module 5 is used to update 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 6 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; The encrypted detection module 7 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 8 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.

[0056] Please refer to Figure 3 The application also discloses an electronic device. Figure 3 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 .

[0057] The communication bus 302 is used to realize the connection and communication between these components.

[0058] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0059] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0060] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field~Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0061] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read~Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally be at least one storage system located away 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.

[0062] exist Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the application program storing the road assessment method in the memory 305. When executed by one or more processors 301, the electronic device 300 executes one or more methods in the above-mentioned embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited to the described order of actions, because according to the present application, certain steps can be performed in other orders 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 required for the present application. In the above embodiments, the description of each embodiment has its own emphasis. For the parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0063] In the several implementations provided in this application, it should be understood that the disclosed system can be implemented in other ways. For example, the system embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as 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 mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of the system or unit can be electrical or other forms.

[0064] 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 may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0065] The present application also provides a computer storage medium that can store multiple instructions, which are suitable for being loaded and executed by a processor as described above. Figure 1 The road assessment method of the embodiment shown in the figure can be found in the specific implementation process. Figure 1 The specific description of the illustrated embodiment will not be repeated here.

[0066] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0067] If 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, 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. The computer software product is stored in a memory, including a number of instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps 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 drives, magnetic disks or optical disks.

[0068] The above are only exemplary embodiments of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0069] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not described in the present disclosure. The description and examples are to be regarded as exemplary only, 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 for grade division, the potential zoning boundaries are determined, and the potential zoning map of the water source area containing zoning grade attributes is generated 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