Big data-based unmanned aerial vehicle airborne geophysical prospecting method and system

Abstract

The application discloses a kind of unmanned aerial vehicle aerological prospecting method and system based on big data, by obtaining the positioning data of global navigation satellite system and the measurement data of inertial measurement unit, correction and compensation are carried out in combination with differential positioning technology and terrain height model, accurate three-dimensional coordinate data set is obtained;According to three-dimensional coordinate data set, collect magnetic field signal and spectrum signal, using adaptive filtering algorithm to magnetic field signal and spectrum signal are denoising processing, obtain preprocessed signal data;It is judged whether the signal data amount of preprocessed signal data exceeds preset threshold, if signal data amount exceeds preset threshold, then through distributed computing framework to preprocessed signal data is fragmented processing, using convolutional neural network to extract the feature vector in each fragmented data, generates feature vector set.The application realizes the whole link optimization from data acquisition to ore body prediction, improves the precision and efficiency of geological exploration.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned aerial vehicle airborne geophysical prospecting, and particularly discloses an unmanned aerial vehicle airborne geophysical prospecting method and system based on big data. BACKGROUND

[0002] As an important means of modern mineral resource exploration, unmanned aerial vehicle airborne geophysical prospecting technology can efficiently obtain surface and underground resource information by integrating high-precision detection equipment and intelligent flight platforms, which has key significance for promoting the digital transformation and green exploration of the mining industry. This technology uses unmanned aerial vehicles to carry multiple sensors and combines intelligent data processing to significantly improve the efficiency and accuracy of exploration, and has been widely applied in resource exploration of iron ore, polymetallic ore, etc.

[0003] However, the existing exploration methods still have obvious limitations. Traditional ground exploration is limited by terrain, low in efficiency and high in cost, especially difficult to implement in complex environments such as deserts and high mountains; although conventional airborne geophysical prospecting has a wide coverage, the resolution is insufficient due to the high flight altitude, making it difficult to capture weak signals of deep ore bodies. These limitations reveal the core challenges in the field of unmanned aerial vehicle airborne geophysical prospecting.

[0004] Firstly, the high-precision positioning requirement under low-altitude flight becomes a technical bottleneck. The unmanned aerial vehicle needs to maintain ultra-low altitude flight of 50-150 meters in complex terrain while ensuring centimeter-level positioning accuracy to capture weak magnetic field or spectral signals, and any positioning deviation may lead to data distortion.

[0005] Secondly, the realization of high-precision positioning further deduces the problem of massive data processing. The data generated by ultra-low altitude flight is huge, and traditional processing methods are difficult to analyze and extract weak abnormal signals in real time, resulting in limited exploration efficiency.

[0006] In addition, the lack of data processing capacity also derives the urgent need for intelligent analysis, which needs to quickly filter out noise and build accurate geological models through advanced algorithms.

[0007] Therefore, how to realize centimeter-level positioning accuracy in ultra-low altitude flight, and develop efficient real-time data processing and intelligent analysis technology to ensure accurate capture of weak signals and rapid construction of geological models, has become a key problem to be solved in unmanned aerial vehicle airborne geophysical prospecting technology. SUMMARY

[0008] The present application provides an unmanned aerial vehicle airborne geophysical prospecting method and system based on big data, aiming to solve at least one of the defects in the prior art.

[0009] One aspect of the present application relates to an unmanned aerial vehicle airborne geophysical prospecting method based on big data, comprising the following steps:

[0010] Obtain positioning data of a global navigation satellite system and measurement data of an inertial measurement unit, correct the positioning data through a differential positioning technology, combine a terrain height model to compensate the height of the corrected data, and obtain a three-dimensional coordinate data set;

[0011] According to the three-dimensional coordinate data set, collect magnetic field signals and spectrum signals, and use an adaptive filtering algorithm to denoise the magnetic field signals and spectrum signals to obtain preprocessed signal data;

[0012] Determine whether the signal data quantity of the preprocessed signal data exceeds a preset threshold value, if the signal data quantity exceeds the preset threshold value, perform sharding processing on the preprocessed signal data through a distributed computing framework, extract feature vectors in each shard data using a convolutional neural network, and generate a feature vector set;

[0013] Input the feature vector set into a random forest classification model to obtain a geological anomaly classification result, combine pattern data in a ore body distribution knowledge base to determine a geological anomaly distribution atlas;

[0014] According to the geological anomaly distribution atlas, perform three-dimensional inversion calculation on the magnetic field signals and spectrum signals to establish a spatial distribution model of underground ore bodies and generate three-dimensional geological structure data;

[0015] Space register the three-dimensional geological structure data and the three-dimensional coordinate data set to output a three-dimensional geological model containing ore body distribution characteristics.

[0016] Further, the step of obtaining positioning data of a global navigation satellite system and measurement data of an inertial measurement unit, correcting the positioning data through a differential positioning technology, combining a terrain height model to compensate the height of the corrected data, and obtaining a three-dimensional coordinate data set includes:

[0017] Obtain positioning data of a global navigation satellite system and measurement data of an inertial measurement unit, align the time axis of the positioning data and the measurement data through a time synchronization algorithm, and use Kalman filtering to preprocess the measurement data to obtain preprocessed data;

[0018] Use a differential positioning technology to correct errors of the preprocessed data, generate correction data through differential calculation of a reference station and a mobile station, and combine a coordinate conversion algorithm to unify the correction data to a preset reference coordinate system to obtain corrected two-dimensional coordinate data;

[0019] According to the corrected two-dimensional coordinate data, obtain corresponding digital elevation information from a pre-established terrain height model, and adjust the height component of the corrected two-dimensional coordinate data through a height compensation algorithm to obtain a preliminary three-dimensional coordinate data set;

[0020] If the accuracy of the preliminary three-dimensional coordinate data set is lower than the preset threshold, the corrected positioning data and the measurement data are fused again by a data fusion algorithm, a weighted average method is used to optimize the preliminary three-dimensional coordinate data set, and a final three-dimensional coordinate data set is obtained.

[0021] Further, according to the three-dimensional coordinate data set, the magnetic field signal and the spectrum signal are collected, an adaptive filtering algorithm is used to denoise the magnetic field signal and the spectrum signal, and the step of obtaining the preprocessed signal data includes:

[0022] The magnetic field sensor and the spectrum sensor are calibrated by a sensor calibration algorithm, a preset calibration parameter is used to correct the deviation of the sensor output, and the calibrated magnetic field signal and the spectrum signal are obtained.

[0023] According to the calibrated magnetic field signal and the spectrum signal, a signal acquisition module is used to synchronously acquire data within a preset time interval, a time stamp alignment algorithm is used to ensure that the time axis is consistent with the three-dimensional coordinate data set, and an original signal data set is obtained.

[0024] For the original signal data set, an adaptive filtering algorithm is used to denoise the magnetic field signal and the spectrum signal, and the environmental interference is removed by dynamically adjusting the filtering parameters, and a preprocessed signal data set is obtained.

[0025] If the signal-to-noise ratio of the preprocessed signal data set is lower than the preset threshold, the preprocessed signal data set and the three-dimensional coordinate data set are associated by a data fusion algorithm, a weighted average method is used to optimize the correspondence between the signal and the coordinate, and the preprocessed signal data is obtained.

[0026] Further, it is judged whether the signal data amount of the preprocessed signal data exceeds a preset threshold, if the signal data amount exceeds the preset threshold, the preprocessed signal data is processed by a distributed computing framework, a convolutional neural network is used to extract feature vectors in each piece of data, and the step of generating a feature vector set includes:

[0027] If the signal data amount exceeds the preset threshold, the preprocessed signal data is processed by a distributed computing framework, and is distributed to a distributed node according to the data dimension by a hash mapping algorithm, and a piece of data set is obtained.

[0028] For the piece of data set, a convolutional neural network is used to extract features of each piece of data through a convolutional layer and a pooling layer, generate a feature vector of each piece of data, and obtain a feature vector set.

[0029] Further, the feature vector set is input into a random forest classification model to obtain a geological anomaly classification result, and the step of determining a geological anomaly distribution map in combination with the pattern data in the ore body distribution knowledge base includes:

[0030] Obtain the classification input data from the feature vector set, classify the feature vector by using the random forest classification model, vote for each feature vector by traversing the decision tree set, and obtain the classification result;

[0031] According to the classification result, obtain the mode data from the pre-established ore body distribution knowledge base, calculate the similarity value of the classification result and the mode data by using the cosine similarity algorithm, and determine the matched mode data;

[0032] If the similarity value of the matched mode data and the classification result exceeds the preset threshold value, the classification result is mapped to the two-dimensional space coordinates by using the grid division algorithm, and an initial geological anomaly distribution map is generated;

[0033] According to the initial geological anomaly distribution map, the two-dimensional space coordinates are smoothed by using the interpolation algorithm, and the final geological anomaly distribution map is generated in combination with the spatial distribution characteristics of the mode data.

[0034] Further, according to the geological anomaly distribution map, the magnetic field signal and the spectrum signal are calculated by three-dimensional inversion, and the spatial distribution model of the underground ore body is established, and the steps of generating three-dimensional geological structure data include:

[0035] Obtain the magnetic field signal and the spectrum signal data from the geological anomaly distribution map, and process the magnetic field signal and the spectrum signal by using the data fusion algorithm through the weighted average method to obtain the fusion signal data set;

[0036] According to the fusion signal data set, the fusion signal data set is calculated by using the three-dimensional inversion algorithm through the iterative least square method to determine the preliminary spatial distribution data;

[0037] If the inversion accuracy of the preliminary spatial distribution data is lower than the preset threshold value, the preliminary spatial distribution data is discretized in space by using the grid division algorithm, and the discretized data is enhanced by using the stereoscopic microscopy technology to obtain the optimized spatial distribution data;

[0038] According to the optimized spatial distribution data, the optimized spatial distribution data is smoothed by using the coordinate mapping algorithm through the interpolation algorithm to generate three-dimensional geological structure data.

[0039] Further, the three-dimensional geological structure data and the three-dimensional coordinate data set are spatially registered, and the steps of outputting the three-dimensional geological model containing the ore body distribution characteristics include:

[0040] Obtain the spatial position information from the three-dimensional geological structure data and the three-dimensional coordinate data set, and preliminarily align the three-dimensional geological structure data and the three-dimensional coordinate data set by using the coordinate mapping algorithm through the linear transformation method to obtain the preliminary registration data set;

[0041] According to the preliminary registration data set, the spatial discretization processing is carried out on the preliminary registration data set by using a meshing algorithm through a uniform mesh segmentation method, and a discretization registration data set is obtained;

[0042] If the registration error of the discretization registration data set is higher than the preset threshold, the feature enhancement is carried out on the discretization registration data set by using a support vector machine algorithm through a classification method, and an optimized registration data set is obtained;

[0043] According to the optimized registration data set, the smoothing processing is carried out on the optimized registration data set by using an interpolation smoothing algorithm through a spline interpolation method, and a three-dimensional geological model containing ore body distribution characteristics is generated.

[0044] Another aspect of the present application relates to a big data-based unmanned aerial vehicle airborne geophysical prospecting system for realizing the above-mentioned big data-based unmanned aerial vehicle airborne geophysical prospecting method, which comprises:

[0045] The first acquisition module is used for acquiring positioning data of a global navigation satellite system and measurement data of an inertial measurement unit, correcting the positioning data through differential positioning technology, and combining a terrain height model to perform height compensation on the corrected data to obtain a three-dimensional coordinate data set;

[0046] The second acquisition module is used for collecting magnetic field signals and spectrum signals according to the three-dimensional coordinate data set, and performing denoising processing on the magnetic field signals and spectrum signals by using an adaptive filtering algorithm to obtain preprocessed signal data;

[0047] The judgment module is used for judging whether the signal data amount of the preprocessed signal data exceeds a preset threshold, and if the signal data amount exceeds the preset threshold, performing sharding processing on the preprocessed signal data through a distributed computing framework, extracting feature vectors in each sharded data by using a convolutional neural network, and generating a feature vector set;

[0048] The determination module is used for inputting the feature vector set into a random forest classification model, acquiring a geological anomaly classification result, combining mode data in a ore body distribution knowledge base to determine a geological anomaly distribution atlas;

[0049] The generation module is used for performing three-dimensional inversion calculation on the magnetic field signals and spectrum signals according to the geological anomaly distribution atlas, establishing a spatial distribution model of underground ore bodies, and generating three-dimensional geological structure data;

[0050] The output module is used for performing spatial registration on the three-dimensional geological structure data and the three-dimensional coordinate data set, and outputting a three-dimensional geological model containing ore body distribution characteristics.

[0051] Further, the first acquisition module comprises:

[0052] The first acquisition unit is configured to acquire positioning data of a global navigation satellite system and measurement data of an inertial measurement unit, perform time axis alignment on the positioning data and the measurement data through a time synchronization algorithm, and perform preprocessing on the measurement data through Kalman filtering to obtain preprocessed data.

[0053] The second acquisition unit is configured to perform error correction on the preprocessed data through a differential positioning technology, generate correction data through differential calculation of a reference station and a mobile station, unify the correction data to a preset reference coordinate system through a coordinate conversion algorithm, and obtain corrected two-dimensional coordinate data.

[0054] The third acquisition unit is configured to acquire corresponding digital elevation information from a pre-established terrain height model according to the corrected two-dimensional coordinate data, adjust a height component of the corrected two-dimensional coordinate data through a height compensation algorithm, and obtain a preliminary three-dimensional coordinate data set.

[0055] The fourth acquisition unit is configured to, if the accuracy of the preliminary three-dimensional coordinate data set is lower than a preset threshold, perform secondary fusion on the corrected positioning data and the measurement data through a data fusion algorithm, optimize the preliminary three-dimensional coordinate data set through a weighted average method, and obtain a final three-dimensional coordinate data set.

[0056] Further, the second acquisition module comprises:

[0057] The fifth acquisition unit is configured to calibrate a magnetic field sensor and a spectrum sensor through a sensor calibration algorithm, correct deviations of sensor outputs through preset calibration parameters, and obtain calibrated magnetic field signals and spectrum signals.

[0058] The sixth acquisition unit is configured to acquire data within a preset time interval through a signal acquisition module according to the calibrated magnetic field signals and the spectrum signals, ensure time axis consistency with the three-dimensional coordinate data set through a time stamp alignment algorithm, and obtain an original signal data set.

[0059] The seventh acquisition unit is configured to, for the original signal data set, perform denoising processing on the magnetic field signals and the spectrum signals through an adaptive filtering algorithm, remove environmental interference through dynamic adjustment of filtering parameters, and obtain a preprocessed signal data set.

[0060] The eighth acquisition unit is configured to, if the signal-to-noise ratio of the preprocessed signal data set is lower than a preset threshold, perform coordinate correlation between the preprocessed signal data set and the three-dimensional coordinate data set through a data fusion algorithm, optimize the corresponding relationship between signals and coordinates through a weighted average method, and obtain preprocessed signals.

[0061] The beneficial effects achieved by the application are as follows:

[0062] The application provides a large data-based unmanned aerial vehicle airborne geophysical prospecting method and system. By acquiring data of a global navigation satellite system and an inertial measurement unit, correction and compensation are performed in combination with differential positioning technology and a terrain height model to obtain an accurate three-dimensional coordinate data set. On this basis, magnetic field and spectrum signals are collected and adaptive filtering denoising is performed. For large-scale data, distributed computing and a convolutional neural network are used to extract features, and a random forest classification model is used in combination with a knowledge base of ore body distribution to generate a geological anomaly distribution atlas. Finally, a three-dimensional inversion calculation is performed to establish a spatial distribution model of underground ore bodies, which is registered with the three-dimensional coordinate data set to output a three-dimensional geological model containing ore body distribution characteristics. BRIEF DESCRIPTION OF DRAWINGS

[0063] Figure 1 FIG. 1 is a flowchart of an embodiment of the large data-based unmanned aerial vehicle airborne geophysical prospecting method of the application. DETAILED DESCRIPTION

[0064] In order to better understand the above technical solutions, the above technical solutions will be described in detail below in combination with the drawings in the specification and specific embodiments.

[0065] As shown in FIG. 1, the first embodiment of the application proposes a large data-based unmanned aerial vehicle airborne geophysical prospecting method, which includes the following steps: Figure 1

[0066] Step S100: Acquire positioning data of a global navigation satellite system and measurement data of an inertial measurement unit, correct the positioning data by differential positioning technology, and combine a terrain height model to compensate the corrected data in height to obtain a three-dimensional coordinate data set.

[0067] Differential positioning technology is a satellite navigation technology that improves positioning accuracy by using real-time or post-processing error correction algorithms through the cooperative work of reference stations and mobile stations. Its core principle is to calculate satellite signal errors through reference stations (known accurate coordinates) and transmit error correction values to mobile stations (user end) to eliminate atmospheric delay, satellite clock error and other interference factors, thereby achieving centimeter-level positioning accuracy.

[0068] Height compensation of the corrected data is a technical process of secondary correction of measurement values by mathematical models or empirical parameters for systematic errors caused by spatial elevation differences on the premise of completed basic data calibration. Its core goal is to eliminate observation data deviations caused by terrain undulations or device installation height differences to ensure the accuracy and comparability of environmental parameters across regions and gradients.

[0069] ​A three-dimensional coordinate data set is a structured data set that records the position information of an object, point cloud, or environmental feature based on a three-dimensional coordinate system, usually containing numerical coordinates of X, Y, and Z dimensions, and can be attached with attribute labels (such as color, temperature, pressure, etc.) to realize multi-dimensional spatial analysis. Its essence is to construct a digital twin model of a physical or virtual scene through discrete or continuous spatial data mapping.

[0070] Step S200, according to the three-dimensional coordinate data set, collecting the magnetic field signal and the spectrum signal, using an adaptive filtering algorithm to denoise the magnetic field signal and the spectrum signal, and obtaining the preprocessed signal data.

[0071] An adaptive filtering algorithm is an intelligent computing method that can adjust filter parameters in real time according to the statistical characteristics of input signals to dynamically optimize signal processing effects (such as noise suppression, signal separation, or system modeling). Its core is to use feedback mechanisms and iterative optimization to enable the filter to maintain the best estimation or feature extraction capability of the target signal in a non-stationary environment.

[0072] Denoising refers to the process of identifying and eliminating noise interference from signals, data, or images while preserving as much original valid information as possible. Its core goal is to suppress or remove non-target components (such as random noise, environmental interference, device errors, etc.) to improve the signal-to-noise ratio (SNR) and usability of data, and is widely used in communication, medical imaging, speech processing, data science, and other fields.

[0073] Step S300, determining whether the signal data quantity of the preprocessed signal data exceeds a preset threshold, if the signal data quantity exceeds the preset threshold, performing sharding processing on the preprocessed signal data through a distributed computing framework, extracting feature vectors in each sharded data using a convolutional neural network, and generating a feature vector set.

[0074] A distributed computing framework is a software architecture and technical system that supports collaborative execution of computing tasks on multiple independent computers (nodes). Through task splitting, parallel processing, and data distribution mechanisms, it realizes a systematic solution for large-scale data processing, complex model training, or real-time resource scheduling. Its core is to provide high throughput, fault tolerance, and horizontal scalability through a network-connected node cluster to meet the computing needs of massive data or high-concurrency scenarios.

[0075] Sharding is a technique that divides large-scale data sets or system resources into multiple independent fragments (shards) for distributed storage, computation, or management. Its core goal is to alleviate single-point performance bottlenecks, improve system throughput, reduce latency, and enhance fault tolerance through horizontal expansion.

[0076] Convolutional Neural Network (CNN) is a deep learning model specialized in processing grid topology data such as images, audio, and video. Its core is through convolution operation, pooling operation and hierarchical feature extraction mechanism to realize the modeling of local correlation and efficient representation learning of input data. Convolutional Neural Network is a cornerstone model in the fields of computer vision and medical image analysis.

[0077] The feature vector set (feature space) is a linear subspace composed of all eigenvectors corresponding to a certain eigenvalue of the linear transformation or matrix and zero vectors.

[0078] Step S400, input the feature vector set into the random forest classification model, obtain the geological anomaly classification result, combine the pattern data in the ore body distribution knowledge base, and determine the geological anomaly distribution atlas.

[0079] Random Forest classification model is a supervised learning algorithm based on Ensemble Learning. It improves the classification accuracy and generalization ability by constructing multiple decision trees and voting (or averaging) their prediction results. Its core idea is to combine "Bootstrap resampling" and "feature random selection" strategy to generate a diverse decision tree group, reduce the overfitting risk of single decision tree, and output the final classification result through majority voting mechanism.

[0080] The geological anomaly classification result is a conclusion description based on specific classification criteria (such as genesis, size, and hosting medium) for systematically dividing and classifying geological bodies or geological processes with significant differences, aiming to reveal the genesis mechanism, spatial distribution law and resource and environmental effect of geological anomalies. Its core is to divide geological anomalies into categories with similar attributes through multi-dimensional feature analysis and threshold definition, providing scientific basis for mineral prediction, disaster prevention and control, and environmental evaluation.

[0081] The ore body distribution knowledge base is a structured data system integrating ore body spatial distribution characteristics, attribute parameters and geological correlation information, aiming to provide a standardized and interactive digital support platform for mineral resource exploration, development decision and geological research through multi-source data fusion and intelligent analysis technology. Its core is to convert key information such as ore body geometry, occurrence environment and genesis mechanism into quantifiable and searchable knowledge units through a unified data framework, realizing the visualization and dynamic updating of ore body distribution law.

[0082] Pattern Data is an abstract representation of regularity and repetition in complex datasets, often expressed as mathematical descriptions of specific rules, structures, or models that characterize the inherent relationships or behavioral trends within the data. Its essence is to compress and generalize raw data through algorithms or statistical methods, forming interpretable and reusable knowledge units to support classification, prediction, clustering, and other analysis tasks.

[0083] Geological anomaly distribution maps are systematic maps that express the spatial distribution, intensity levels, and genetic relationships of geological anomalies through visualization techniques, based on spatial geographic coordinates and integrated multi-source anomaly data such as geology, geophysics, and geochemistry. The core is to reveal the macroscopic distribution rules of geological anomalies and their internal relationships with mineralization, disaster risks, or environmental problems through layer stacking and comprehensive analysis.

[0084] Step S500, according to the geological anomaly distribution map, the magnetic field signal and the spectrum signal are calculated by three-dimensional inversion, the spatial distribution model of underground ore body is established, and three-dimensional geological structure data is generated.

[0085] Three-dimensional inversion calculation is a numerical simulation technology that inversely calculates the physical property parameter distribution (such as resistivity, magnetic susceptibility, density, etc.) of the target geological body in the underground three-dimensional space based on the physical field data observed on the ground or underground (such as electromagnetic, gravity, magnetic method, etc.), combined with geological models and mathematical optimization algorithms. Its core is to minimize the difference between measured data and theoretical forward response through nonlinear iterative optimization, and finally build a three-dimensional physical property model consistent with the true geological structure.

[0086] The spatial distribution model of underground ore body is a digital three-dimensional model constructed by integrating geological exploration data (such as drilling, geophysical prospecting, geochemical prospecting, etc.), geophysical parameters, and ore-forming geological conditions, used to quantitatively characterize the geometric shape, occurrence characteristics, physical and chemical property distribution of ore body in three-dimensional space, and its relationship with surrounding rock structure. The spatial distribution model of underground ore body uses computer as carrier, adopts mathematical algorithms and visualization technology, dynamically displays the spatial distribution law of ore body, and provides core basis for mineral exploration, reserve estimation and mining design.

[0087] Three-dimensional geological structure data is a digital information set that characterizes the geometric shape (such as rock layer interface, fault zone distribution), physical property parameters (such as density, resistivity, magnetic susceptibility) and topological relationship of underground geological bodies based on three-dimensional spatial coordinates (X, Y, Z). Its core is to construct a computer model that can describe the spatial distribution law and internal attribute variation of geological bodies through multi-source data fusion (such as drilling, geophysical prospecting, remote sensing, etc.), providing quantitative basis for geological analysis, resource exploration and engineering decision-making.

[0088] Step S600, spatially register the three-dimensional geological structure data with the three-dimensional coordinate data set, and output a three-dimensional geological model containing the distribution characteristics of the ore body.

[0089] Spatial registration is a technical process of unifying multi-source spatial data (such as remote sensing images, three-dimensional point clouds, geological models, etc.) from different sensors, different times, or different coordinate systems into the same spatial reference system through geometric transformation and algorithm optimization. The core is to realize the consistency and superposition of multi-source data in position, direction and scale through coordinate alignment, scale correction and geometric deformation elimination, supporting data fusion and comprehensive analysis.

[0090] The three-dimensional geological model containing the distribution characteristics of the ore body is a computer model that quantitatively represents the spatial distribution of the ore body and its relationship with the surrounding rock structure in a three-dimensional digital form by fusing geological exploration data (such as drilling, geophysical prospecting, geochemical prospecting), ore body geometric parameters (shape, occurrence), and mineralization attributes (grade, lithology). The three-dimensional geological model is a framework based on spatial coordinates (X, Y, Z), combined with geological laws and mathematical algorithms, dynamically revealing the ore body scale, extension direction, thickness variation and resource potential, providing visual decision support for mineral exploration, reserve estimation and mining design.

[0091] Further, the unmanned aerial vehicle airborne geophysical prospecting method based on big data provided by the embodiment comprises the following steps:

[0092] Step S110, obtain positioning data of a global navigation satellite system and measurement data of an inertial measurement unit, align the positioning data and the measurement data on the time axis through a time synchronization algorithm, and pre-process the measurement data by using Kalman filtering to obtain pre-processed data.

[0093] The data fusion of the global navigation satellite system (GNSS) and the inertial measurement unit (IMU) is a common technology for high-precision positioning, and is widely used in the fields of unmanned driving and unmanned aerial vehicle navigation. Taking the unmanned aerial vehicle navigation scene as an example, the technical theme of the above content is analyzed in detail, and the implementation method and beneficial effects are described through specific embodiments. For example, the GNSS receiver obtains the positioning data of the unmanned aerial vehicle, including latitude and longitude and time stamp, and the precision is about 2 meters. The IMU provides acceleration and angular velocity data, and the sampling frequency is 100 Hz.

[0094] The time synchronization algorithm ensures that the two sets of data are aligned on the time axis. In one possible implementation, the network time protocol (NTP) is used to calibrate the time stamps of the GNSS and the IMU, and the precision reaches the millisecond level.

[0095] Assuming the GNSS data timestamp is T1 = 10:00:00.000 and the IMU data is T2 = 10:00:00.005, align the IMU data to T1 time through linear interpolation, eliminate time deviation, and improve subsequent fusion accuracy. Kalman filter is used to preprocess IMU data to eliminate noise. For example, the acceleration data of IMU may have random drift due to vibration, and Kalman filter estimates the true state through prediction and update steps, outputs smooth acceleration value, and error is reduced from 0.5 m / s² to 0.1 m / s². This preprocessing enhances the reliability of the data and lays the foundation for subsequent correction.

[0096] Step S120, error correction of preprocessed data is carried out by using differential positioning technology, correction data is generated by differential calculation of reference station and mobile station, and coordinate conversion algorithm is combined to unify the correction data to the preset reference coordinate system, to obtain corrected two-dimensional coordinate data.

[0097] Differential positioning technology corrects GNSS error through cooperation of reference station and mobile station. In one embodiment, the reference station is located at a known coordinate (X0, Y0), receives the same satellite signal, and calculates the pseudo-range error.

[0098] The mobile station (drone) receives the correction value broadcast by the reference station and adjusts the GNSS data in real time. For example, the original positioning data is (X1, Y1) and the error is 2 meters, and after applying differential correction, the coordinate error is reduced to 0.2 meters.

[0099] The correction data is unified to the WGS84 reference coordinate system through the coordinate conversion algorithm, ensuring the consistency of coordinates of different data sources.

[0100] Step S130, according to the corrected two-dimensional coordinate data, the corresponding digital elevation information is obtained from the pre-established terrain height model, and the height component of the corrected two-dimensional coordinate data is adjusted through the height compensation algorithm to obtain a preliminary three-dimensional coordinate data set.

[0101] According to the corrected two-dimensional coordinate (X, Y), the elevation Z of the corresponding point is obtained from the digital elevation model (DEM). For example, the coordinate (X1, Y1) corresponds to the DEM elevation of 50 meters.

[0102] The height compensation algorithm adjusts the Z value, taking into account the terrain undulation and GNSS height error, to obtain the preliminary three-dimensional coordinate (X, Y, Z).

[0103] Step S140, if the accuracy of the preliminary three-dimensional coordinate data set is lower than the preset threshold, then the corrected positioning data and the measured data are fused again through the data fusion algorithm, the preliminary three-dimensional coordinate data set is optimized by using the weighted average method, and the final three-dimensional coordinate data set is obtained.

[0104] The accuracy of the preliminary three-dimensional coordinate data set is:

[0105] (1)

[0106] In formula (1), represents the accuracy evaluation value of the preliminary three-dimensional coordinate data set, represents the total number of coordinate points, , , represents the three-dimensional coordinate component of the mth measurement point, , , , represents the corresponding reference coordinate value, formula (1) is used to calculate the average deviation between the coordinate data set and the reference value to evaluate whether the accuracy is lower than the preset threshold.

[0107] The final three-dimensional coordinate vector obtained after data fusion is:

[0108] (2)

[0109] In formula (2), represents the final three-dimensional coordinate vector obtained after data fusion, represents the corrected positioning data coordinate vector, represents the measurement data coordinate vector, represents the weight coefficient of the corrected positioning data, represents the weight coefficient of the measurement data, formula (2) realizes the fusion and optimization of the corrected positioning data and the measurement data two data sources by using the weighted average method.

[0110] The normalized weight value of the data source is:

[0111] (3)

[0112] In formula (3), represents the normalized weight value of the kth data source, represents the measurement uncertainty or error standard deviation of the mth data source, represents the total number of data sources participating in fusion, represents the error standard deviation of the mth data source, formula (3) allocates corresponding weights according to the accuracy level of each data source, and the data source with higher accuracy obtains greater weight.

[0113] ​​Assuming the initial coordinate accuracy is 0.3 meters, which does not meet the preset threshold of 0.1 meters, the data fusion algorithm is started. Preferably, a weighted average method is used, with GNSS data weight of 0.7 and IMU data weight of 0.3, to generate the final three-dimensional coordinates (X', Y', Z') after fusion, with accuracy improved to 0.08 meters.

[0114] The above method significantly improves the positioning accuracy, especially in urban canyons or tunnels where GNSS signals are weak. IMU data compensates for the deficiency of GNSS. The final three-dimensional coordinate dataset provides reliable navigation basis for UAV aerial survey, ensuring the accuracy of path planning and obstacle avoidance, enhancing the safety and stability of the system.

[0115] Further, the UAV aerial geophysical prospecting method based on big data provided by the embodiment comprises the following steps:

[0116] In step S210, the magnetic field sensor and the spectrum sensor are calibrated by a sensor calibration algorithm. The preset calibration parameters are used to correct the deviation of the sensor output, and the calibrated magnetic field signal and spectrum signal are obtained.

[0117] In the UAV aerial navigation scenario, the sensor calibration algorithm is used to ensure the accuracy of the magnetic field sensor and the spectrum sensor data. The magnetic field sensor detects the geomagnetic field direction to assist the UAV attitude estimation; the spectrum sensor collects the environmental spectrum characteristics to assist the environmental perception. The calibration algorithm corrects the sensor deviation by using the preset parameters. For example, the magnetic field sensor may be disturbed by the metal structure of the UAV, and the output deviates from the true geomagnetic field direction by 5 degrees. During calibration, the known geomagnetic field data is used as a reference to adjust the sensor output, and the deviation is reduced to 0.5 degrees.

[0118] The spectrum sensor may have wavelength shift due to light changes. Through laboratory calibration of the spectrum curve, the wavelength error is reduced from 10 nanometers to 2 nanometers after correction. The calibrated signal is more reliable and provides high-quality data for subsequent processing.

[0119] In step S220, according to the calibrated magnetic field signal and spectrum signal, the signal acquisition module is used to synchronously acquire data within a preset time interval, and the time stamp alignment algorithm is used to ensure consistency with the time axis of the three-dimensional coordinate dataset, and the original signal dataset is obtained.

[0120] The signal acquisition module synchronously acquires the magnetic field signal and the spectrum signal at intervals of 10 milliseconds. A timestamp alignment algorithm ensures that the data is synchronized with the three-dimensional coordinate data set. For example, the coordinate data timestamp is 10:00:00.000, and the magnetic field signal timestamp is 10:00:00.002, which is aligned to 10:00:00.000 by linear interpolation, eliminating the time deviation. The synchronized original signal data set contains the magnetic field strength, direction and spectrum characteristics, forming a unified time axis with the coordinate data, facilitating subsequent fusion.

[0121] In step S230, for the original signal data set, an adaptive filtering algorithm is used to denoise the magnetic field signal and the spectrum signal, and by dynamically adjusting the filtering parameters, environmental interference is removed, and a preprocessed signal data set is obtained.

[0122] The adaptive filtering algorithm denoises the original signal data set. The magnetic field signal may be disturbed by power lines, producing high-frequency noise; the spectrum signal may be affected by cloud changes, introducing low-frequency drift. The adaptive filtering dynamically adjusts parameters such as bandwidth or cutoff frequency according to signal characteristics. For example, the magnetic field signal noise amplitude is reduced from 0.1 microtesla to 0.02 microtesla after filtering; the spectrum signal noise is reduced from 5% to 1%. The signal-to-noise ratio of the denoised signal data set is significantly improved, providing clear data for subsequent analysis.

[0123] In step S240, if the signal-to-noise ratio of the preprocessed signal data set is lower than a preset threshold, a data fusion algorithm is used to correlate the preprocessed signal data set with the three-dimensional coordinate data set, and a weighted average method is used to optimize the correspondence between the signal and the coordinate, obtaining the preprocessed signal data.

[0124] The signal-to-noise ratio of the preprocessed signal data set is:

[0125] (4)

[0126] In formula (4), represents the signal-to-noise ratio, represents the signal power, represents the noise power, represents the preset signal-to-noise ratio threshold, and when the calculated signal-to-noise ratio is lower than the preset threshold, the data fusion algorithm is triggered.

[0127] The fused coordinate correlation result is:

[0128] (5)

[0129] In formula (5), represents the fused coordinate correlation result, represents the total number of data points, represents the signal data, representing the first coordinate data, representing the first three-dimensional coordinate data, representing the regularization parameter, representing the coordinate correlation function.

[0130] The optimized signal data is:

[0131] (6)

[0132] In formula (6), representing the optimized signal data, representing the number of signals participating in the weighted average, representing the weight of the first signal, representing the first signal data, representing the first signal, representing the standard deviation of the first signal, the weight is proportional to the signal quality.

[0133] If the signal-to-noise ratio of the preprocessed signal data set is lower than the threshold value, such as lower than 20 decibels, the data fusion algorithm is started. The fusion algorithm associates the signal data set with the three-dimensional coordinate data set and optimizes the correspondence through weighted average. For example, the magnetic field signal indicates the direction of the unmanned aerial vehicle, and the weight is set to 0.6; the coordinate data provides the position, and the weight is 0.4.

[0134] After fusion, the signal and the coordinate are accurately matched to generate optimized signal data. For example, the magnetic field signal assists in correcting the coordinate deviation, and the spectral signal provides road material information, and the optimized data provides accurate basis for path planning. The fusion process considers the spatial relationship between signal characteristics and coordinates to ensure data consistency. It can be understood that the above method generates high-quality signal data through calibration, synchronization, denoising and fusion. Calibration improves sensor accuracy, synchronization ensures time consistency, denoising enhances signal clarity, and fusion optimizes data association. These steps support each other to form a complete data processing chain and provide reliable support for unmanned navigation.

[0135] Further, the unmanned aerial vehicle airborne geophysical prospecting method based on big data provided by the embodiment, step S300 includes:

[0136] Step S310, if the signal data amount exceeds the preset threshold value, the preprocessed signal data is processed by a distributed computing framework, and is distributed to a distributed node according to a hash mapping algorithm according to the data dimension, to obtain a sharded data set.

[0137] The triggering of the signal data volume is determined by the following formula:

[0138] (7)

[0139] In formula (7), represents a distributed processing trigger flag, represents a signal data set, represents a data volume size, represents a preset threshold. When the data volume exceeds the threshold, the distributed processing is triggered, otherwise the single-machine processing mode is adopted.

[0140] The hash value of the data point is calculated by the following formula:

[0141] (8)

[0142] In formula (8), represents a hash value of a data point, represents the i-th data point, represents the number of data dimensions, represents the hash coefficient of the i-th dimension, represents the feature value of the data point in the i-th dimension, represents a hash modulo parameter. The sharded data set is obtained by the following formula:

[0143]

[0144] (9)

[0145] In formula (9), represents the sharded data set allocated to the i-th node, represents the i-th data sample, represents the hash mapping value of the data, represents the total number of distributed nodes, represents the total number of data samples, represents the node number. In the unmanned aerial vehicle aviation navigation scene, the signal data volume may rapidly accumulate due to high-frequency collection, and needs to be efficiently processed through a distributed computing framework. The distributed computing framework shards and allocates data to multiple computing nodes, reducing the pressure on a single node.

[0146] In the unmanned aerial vehicle aviation navigation scene, the signal data volume may rapidly accumulate due to high-frequency collection, and needs to be efficiently processed through a distributed computing framework. The distributed computing framework shards and allocates data to multiple computing nodes, reducing the pressure on a single node.

[0147] ​​​​The hash mapping algorithm generates a unique identifier according to the data dimension, such as the intensity of the magnetic field signal or the wavelength of the spectral signal, and uniformly distributes the data. For example, the magnetic field signal data is divided into 10 subsets according to the intensity interval, and the spectral signal is divided into 8 subsets according to the wavelength range, and each subset is allocated to a different node to ensure load balancing. After sharding, each node processes the data in parallel to generate a set of shard data. This approach is suitable for large-scale data scenarios, such as when sensors on urban roads collect millions of records per second.

[0148] At step S320, for the shard data set, a convolutional neural network is used to extract features from each shard data through convolutional layers and pooling layers to generate a feature vector for each shard data, and a set of feature vectors is obtained.

[0149] Specifically, for the shard data set, the convolutional neural network is used for feature extraction. The convolutional layer scans the data through a sliding window to capture the local intensity variation of the magnetic field signal or the wavelength distribution feature of the spectral signal. For example, the convolution kernel of the magnetic field signal can be set to 3x3 to extract the directional variation pattern; the convolution kernel of the spectral signal can be set to 5x5 to extract the wavelength continuity feature. The pooling layer further compresses the data and retains key features, such as the maximum intensity of the magnetic field signal or the peak wavelength of the spectral signal. For example, the pooling operation reduces the spatial resolution of the magnetic field signal by 50% to retain the main directional information; the pooling of the spectral signal retains the main spectral peak and reduces redundant data. The generated set of feature vectors contains the core information of each shard, such as the directional feature vector of the magnetic field signal and the wavelength feature vector of the spectral signal.

[0150] The feature extraction process needs to consider the characteristics of the data. The magnetic field signal may exhibit nonlinear changes due to environmental interference, and the convolutional neural network captures these complex patterns through multiple convolutional layers. For example, in a tunnel scenario, the magnetic field signal is distorted due to metal structure interference, and the convolutional layer can extract distortion features to generate high-dimensional feature vectors.

[0151] The spectral signal may exhibit intermittent features due to light obstruction, and the pooling layer can retain key wavelength information to ensure the robustness of the feature vector. The set of feature vectors provides high-quality input for subsequent data fusion or path planning. For example, the feature vector can be used to identify the spectral features of road signs or correct the magnetic field direction of the UAV attitude. This method efficiently processes large-scale signal data through distributed computing and feature extraction, providing reliable support for unmanned driving navigation.

[0152] Further, the unmanned aerial vehicle airborne geophysical prospecting method based on big data provided by the embodiment, step S400 includes:

[0153] Step S410: Obtain classification input data from the feature vector set, use a random forest classification model to classify the feature vectors, and vote on each feature vector by traversing the decision tree set to obtain the classification result.

[0154] In geological exploration scenarios, the feature vector set consists of feature vectors from magnetic field signals or spectral signals, which need further classification to identify geological anomalies. Random forest classification models generate classification results by voting on feature vectors using multiple decision trees.

[0155] Specifically, each feature vector contains directional features of the magnetic field signal or wavelength features of the spectral signal. The random forest combines the classification results of each tree by traversing the set of decision trees. For example, if a feature vector represents an abnormal magnetic field direction, and 80 out of 100 decision trees classify it as "abnormal," the classification result is "geological anomaly." This voting mechanism ensures robustness of classification.

[0156] Step S420: Based on the classification results, obtain pattern data from the pre-established ore body distribution knowledge base, and use the cosine similarity algorithm to calculate the similarity value between the classification results and the pattern data to determine the matching pattern data.

[0157] The cosine similarity value between the classification result and the pattern data is calculated using the following formula:

[0158] (10)

[0159] In formula (10), The cosine similarity value represents the difference between the classification result and the pattern data. The first element of the classification result vector Each feature component The first element representing the pattern data vector Each feature component The number of dimensions of the feature vector is represented. Formula (10) measures the similarity between two vectors by calculating the cosine of the angle between them. The closer the value is to 1, the higher the similarity.

[0160] The final matched pattern data number is:

[0161] (11)

[0162] In formula (11), Indicates the pattern data number that was finally matched. This represents the total number of pattern data in the knowledge base. This indicates the first classification result. Each attribute value Indicates the first The first pattern data a property value, represents the total number of properties for matching. Formula (11) determines the best matching pattern data by finding the maximum similarity.

[0163] The complete structure of pattern data consists of:

[0164] (12)

[0165] In formula (12), represents the th set of pattern data of ore body distribution in the knowledge base, represents the th geometric feature parameter of the th pattern, represents the number of geometric feature parameters, represents the th property feature parameter of the th pattern, represents the number of property feature parameters.

[0166] The classification result is matched with the pattern data in the ore body distribution knowledge base. The pattern data stores known ore body distribution characteristics, such as the direction pattern of magnetic field anomalies or the peak pattern of spectral wavelengths.

[0167] The cosine similarity algorithm calculates the similarity between the classification result and the pattern data. For example, the similarity between the feature vector of the classification result and the pattern data of a certain iron ore in the knowledge base is 0.95, which exceeds the preset threshold value of 0.9, and it is determined as a match. Preferably, the knowledge base needs to be updated regularly to cover various ore body types, ensuring the accuracy of the match.

[0168] Step S430, if the similarity value between the matched pattern data and the classification result exceeds the preset threshold value, the classification result is mapped to the two-dimensional spatial coordinates through the grid division algorithm to generate an initial geological anomaly distribution map.

[0169] Determine a reasonable threshold range based on statistical distribution:

[0170] (13)

[0171] In formula (13), represents the preset threshold value for similarity determination, represents the mean of historical similarity data, represents the standard deviation of historical similarity data, represents the threshold adjustment coefficient.

[0172] The coordinate mapping of the classification result to the two-dimensional space is realized by the following formula:

[0173] (14)

[0174] In formula (14), represents the normalized coordinates of the grid point in two-dimensional space, and respectively represent the row and column indices of the grid, and represent the step size of the grid in the and directions, and represent the coordinate system origin offset, and represent the coordinate range in the and directions.

[0175] After the matching pattern data is confirmed, the classification result is mapped to the two-dimensional space coordinates to generate an initial geological anomaly distribution map. The grid division algorithm converts the spatial information of the feature vector into grid coordinates. For example, the magnetic field anomaly area is divided into 100x100 grids, and each grid corresponds to a classification result, marked as "abnormal" or "normal". This mapping method facilitates visualization of the anomaly distribution.

[0176] The grid size needs to be adjusted according to the exploration area. For example, a 50x50 grid can be used in a large mining area to improve resolution.

[0177] In step S440, according to the initial geological anomaly distribution map, an interpolation algorithm is used to smooth the two-dimensional space coordinates, and the spatial distribution characteristics of the pattern data are combined to generate a final geological anomaly distribution map.

[0178] The initial geological anomaly distribution map is smoothed by an interpolation algorithm to generate a final geological anomaly distribution map. The interpolation algorithm fills the gaps between grids, for example, using the Kriging interpolation method to estimate the anomaly strength of the intermediate area according to the anomaly values of adjacent grids. For example, the anomaly value of a certain grid is 0.8, and the adjacent grid is 0.6, and the value of the intermediate area after interpolation is 0.7.

[0179] Combined with the spatial distribution characteristics of the pattern data, such as the spatial gradient of the iron ore magnetic field anomaly, the map can clearly show the boundary and strength of the anomaly area. This smoothing process improves the readability of the map and provides accurate guidance for subsequent mineral development.

[0180] The above process needs to consider the complexity of the geological environment. For example, the magnetic field signal may present a non-uniform distribution due to rock layer interference, and the random forest classification can effectively identify the interference mode through multi-dimensional feature analysis. Similarly, the cosine similarity matching and interpolation processing combined with the pattern data of the knowledge base ensure that the map reflects the true distribution rule of the ore body. This method works through multiple steps in cooperation, providing efficient and reliable anomaly identification and distribution analysis support for geological exploration.

[0181] Further, the unmanned aerial vehicle airborne geophysical prospecting method based on big data provided by the embodiment comprises the following steps:

[0182] In step S510, the magnetic field signal and the spectrum signal data are obtained from the geological anomaly distribution map, and a data fusion algorithm is used to process the magnetic field signal and the spectrum signal by a weighted average method to obtain a fusion signal data set.

[0183] In geological exploration, extracting the magnetic field signal and the spectrum signal data from the geological anomaly distribution map is a key step. The magnetic field signal usually reflects the magnetic difference of the underground rock layer, while the spectrum signal reveals the spectral characteristics of the mineral composition. The magnetic field signal may contain the magnetic field intensity value of a certain region, such as 100nT, while the spectrum signal may record the reflectivity at a specific wavelength, such as 0.6.

[0184] The data fusion algorithm integrates the two types of signals by a weighted average method to generate a fusion signal data set. In one embodiment, the weights of the magnetic field signal and the spectrum signal are 0.7 and 0.3 respectively, which are determined based on signal reliability and exploration target. For example, the fusion signal value of a certain point is 0.7x100nT+0.3x0.6=70.18. This fusion method balances the contribution of the two signals and improves the comprehensiveness of the data.

[0185] In step S520, according to the fusion signal data set, a three-dimensional inversion algorithm is used to calculate the fusion signal data set by an iterative least squares method to determine the preliminary spatial distribution data.

[0186] The observation data vector in the fusion signal data set is calculated by the following formula:

[0187] (15)

[0188] In formula (15), represents the observation data vector of the fusion signal data set, represents the Green function matrix describing the relationship between the spatial position and the observation data, represents the three-dimensional spatial distribution parameter vector to be solved, represents the observation noise vector.

[0189] The fusion signal dataset is used for a three-dimensional inversion algorithm to calculate the preliminary spatial distribution data by the iterative least squares method. The iterative process adjusts the model parameters multiple times to make the calculation results approximate the observation data. For example, the initial model assumes that the magnetic field in a certain area is uniform, and after 5 iterations, the preliminary spatial distribution data reflecting the gradient change of the magnetic field is generated.

[0190] In step S530, if the inversion accuracy of the preliminary spatial distribution data is lower than the preset threshold, the preliminary spatial distribution data is spatially discretized by a grid division algorithm, and the discrete data is enhanced by a stereoscopic microscopy technique to obtain optimized spatial distribution data.

[0191] The inversion accuracy of the preliminary spatial distribution data is calculated and compared with the preset threshold by the following formula:

[0192] (16)

[0193] In formula (16), represents the inversion accuracy evaluation index, represents the total number of spatial distribution data points, represents the th observation data value, represents the th inversion calculation value.

[0194] The grid division and discretization processing of the preliminary spatial distribution data is realized by the following formula:

[0195] (17)

[0196] In formula (17), represents the discretization weight of the grid unit, , , represent the grid spacing in three directions respectively, represents the total volume, represents the spatial distribution function value at the coordinates .

[0197] The feature enhancement processing of the discrete data by the stereoscopic microscopy technique is realized by the following formula:

[0198] (18)

[0199] In formula (18), represents the data after feature enhancement, represents the original discrete data, represents the feature data extracted by the stereoscopic microscopy technique, represents the original data weight coefficient, represents a stereoscopic feature weight coefficient, represents a Laplacian operator.

[0200] If the inversion accuracy is lower than a preset threshold, such as 0.85, further optimization is required. The grid division algorithm discretizes the space into a 100x100x50 grid, and each grid stores the fusion signal value, such as a certain grid value of 70nT. Stereoscopic microscopy then enhances the features of the discretized data, highlighting key features. For example, by analyzing the signal gradient between grids, the edge features of the magnetic anomaly area are enhanced, making the anomaly area boundary clearer.

[0201] Step S540, according to the optimized spatial distribution data, using coordinate mapping algorithm through interpolation algorithm to smooth the optimized spatial distribution data, generate three-dimensional geological structure data.

[0202] The optimized spatial distribution data is smoothed by the coordinate mapping algorithm to generate three-dimensional geological structure data.

[0203] The interpolation algorithm, such as spline interpolation, fills the gap between grids. The signal values of two adjacent grids in a certain area are 70nT and 65nT respectively, and the interpolated middle point value is 67.5nT. This smoothing makes the three-dimensional geological structure data more continuous, clearly showing the spatial form of the underground ore body distribution, such as the spatial form of the iron ore body.

[0204] The coordinate mapping algorithm needs to adjust the grid resolution according to the size of the exploration area. For example, a 50x50x25 grid can be used in a large mine area to improve accuracy.

[0205] The generation of the fusion signal data set takes into account the complexity of the geological environment. For example, the magnetic field signal may present non-uniformity due to rock layer interference, while the spectral signal is affected by surface vegetation.

[0206] The weighted average method reduces the influence of interference by dynamically adjusting the weight. The application of stereoscopic microscopy enhances the ability to identify abnormal features through multi-angle analysis of grid data. This multi-step collaborative work ensures the accuracy of three-dimensional geological structure data, providing a reliable basis for mineral exploration.

[0207] Further, the unmanned aerial geophysical prospecting method based on big data provided by the embodiment, step S600 includes:

[0208] Step S610, obtain spatial position information from three-dimensional geological structure data and three-dimensional coordinate data set, use coordinate mapping algorithm through linear transformation method to preliminarily align three-dimensional geological structure data and three-dimensional coordinate data set, get preliminary registration data set.

[0209] Obtaining spatial position information from three-dimensional geological structure data and three-dimensional coordinate data sets is a basic step of geological modeling. Three-dimensional geological structure data usually contains physical properties of underground ore bodies, such as density or magnetism, while three-dimensional coordinate data sets record the longitude, latitude and depth information of spatial points. For example, the three-dimensional geological structure data of a certain mining area may record the density value of a point as 2.7 g / cm³, and the coordinate data set records the spatial position of the point as (x: 500m, y: 300m, z: -200m).

[0210] Through the coordinate mapping algorithm, linear transformation method is used to preliminarily align the two types of data. Linear transformation aligns the reference system of the coordinate data set with the reference system of the geological structure data through translation and rotation operations. For example, assuming that the origin of the coordinate data set deviates from the origin of the geological structure data by 10m, linear transformation will translate all coordinate points by 10m, ensuring the spatial consistency of the two data sets, thereby generating a preliminary registration data set. This alignment operation ensures that the data for subsequent processing has a unified spatial reference.

[0211] Step S620, according to the preliminary registration data set, a grid division algorithm is used to perform spatial discretization processing on the preliminary registration data set through uniform grid division method, to obtain a discretized registration data set.

[0212] Based on the preliminary registration data set, the grid division algorithm performs spatial discretization processing through uniform grid division method. Uniform grid division divides the three-dimensional space into regular cubic grids, such as each grid with a side length of 5m, generating a 100x100x50 grid system. Each point in the preliminary registration data set is assigned to the corresponding grid, for example, the density value of a certain point 2.7 g / cm³ is recorded in the grid (i: 50, j: 30, k: 20). The discretized data set facilitates subsequent algorithm processing.

[0213] Step S630, if the registration error of the discretized registration data set is higher than the preset threshold, a support vector machine algorithm is used to perform feature enhancement on the discretized registration data set through classification method, to obtain an optimized registration data set.

[0214] The registration error of the discretized registration data set is calculated by the following formula:

[0215] (19)

[0216] In formula (19), represents the registration error, represents the number of samples in the discretized registration data set, represents the registration result, represents the preset target value.

[0217] The optimized feature set after feature enhancement is:

[0218] (20)

[0219] In formula (20), represents the optimized feature set after feature enhancement, represents the support vector machine algorithm, represents the original discretized registration data set, represents the corresponding classification label set.

[0220] The optimized registration data set is:

[0221] (21)

[0222] In formula (21), represents the optimized registration data set, represents the feature fusion operation, represents the original discretized registration data set, represents the optimized feature set after feature enhancement.

[0223] If the registration error is higher than the preset threshold, such as 0.9, further optimization is needed. The support vector machine algorithm enhances the features of the discretized registration data set through a classification method. For example, the algorithm identifies grid points with abnormal density values and marks them as ore body boundary features, generating an optimized registration data set. This classification method highlights the features of the ore body edge and improves the discrimination of the data.

[0224] In step S640, according to the optimized registration data set, an interpolation smoothing algorithm is used to smooth the optimized registration data set through a spline interpolation method, generating a three-dimensional geological model containing ore body distribution characteristics.

[0225] The optimized registration data set is processed by the interpolation smoothing algorithm, and the spline interpolation method is used to fill the gaps between the grids. For example, the density values of two adjacent grids are 2.7 g / cm³ and 2.5 g / cm³, respectively, and the density value of the middle point calculated in the spline interpolation is 2.6 g / cm³. This smoothing processing makes the data transition more natural, and finally generates a three-dimensional geological model containing ore body distribution characteristics. For example, the model clearly shows the spatial form of a certain iron ore body, such as the ore body showing an elliptical distribution at a depth of -200 m. This model provides intuitive spatial information for mineral exploration and helps to accurately locate the position of the ore body.

[0226] The application relates to a big data-based unmanned aerial vehicle (UAV) airborne geophysical exploration system for realizing the big data-based UAV airborne geophysical exploration method.

[0227] Further, the big data-based UAV airborne geophysical exploration system provided by the embodiment comprises a first acquisition module, a second acquisition module, a judgment module, a determination module, a generation module and an output module. The first acquisition module is used for acquiring positioning data of a global navigation satellite system and measurement data of an inertial measurement unit, correcting the positioning data through a differential positioning technology, combining a terrain height model to perform height compensation on the corrected data, and obtaining a three-dimensional coordinate data set. The second acquisition module is used for collecting magnetic field signals and spectrum signals according to the three-dimensional coordinate data set, performing denoising processing on the magnetic field signals and the spectrum signals through an adaptive filtering algorithm, and obtaining preprocessed signal data. The judgment module is used for judging whether the signal data amount of the preprocessed signal data exceeds a preset threshold value. If the signal data amount exceeds the preset threshold value, the preprocessed signal data is subjected to sharding processing through a distributed computing framework, a convolutional neural network is used to extract feature vectors in each shard data, and a feature vector set is generated. The determination module is used for inputting the feature vector set into a random forest classification model, acquiring a geological anomaly classification result, combining mode data in a ore body distribution knowledge base, and determining a geological anomaly distribution atlas. The generation module is used for performing three-dimensional inversion calculation on the magnetic field signals and the spectrum signals according to the geological anomaly distribution atlas, establishing a spatial distribution model of an underground ore body, and generating three-dimensional geological structure data. The output module is used for performing spatial registration on the three-dimensional geological structure data and the three-dimensional coordinate data set, and outputting a three-dimensional geological model containing ore body distribution characteristics.

[0227] Further, the big data-based UAV airborne geophysical exploration system provided by the embodiment comprises a first acquisition module, a second acquisition module, a judgment module, a determination module, a generation module and an output module. The first acquisition module is used for acquiring positioning data of a global navigation satellite system and measurement data of an inertial measurement unit, correcting the positioning data through a differential positioning technology, combining a terrain height model to perform height compensation on the corrected data, and obtaining a three-dimensional coordinate data set. The second acquisition module is used for collecting magnetic field signals and spectrum signals according to the three-dimensional coordinate data set, performing denoising processing on the magnetic field signals and the spectrum signals through an adaptive filtering algorithm, and obtaining preprocessed signal data. The judgment module is used for judging whether the signal data amount of the preprocessed signal data exceeds a preset threshold value. If the signal data amount exceeds the preset threshold value, the preprocessed signal data is subjected to sharding processing through a distributed computing framework, a convolutional neural network is used to extract feature vectors in each shard data, and a feature vector set is generated. The determination module is used for inputting the feature vector set into a random forest classification model, acquiring a geological anomaly classification result, combining mode data in a ore body distribution knowledge base, and determining a geological anomaly distribution atlas. The generation module is used for performing three-dimensional inversion calculation on the magnetic field signals and the spectrum signals according to the geological anomaly distribution atlas, establishing a spatial distribution model of an underground ore body, and generating three-dimensional geological structure data. The output module is used for performing spatial registration on the three-dimensional geological structure data and the three-dimensional coordinate data set, and outputting a three-dimensional geological model containing ore body distribution characteristics.

[0228] Preferably, the big data-based unmanned aerial vehicle airborne geophysical exploration system provided in this embodiment comprises a fifth acquisition unit, a sixth acquisition unit, a seventh acquisition unit and an eighth acquisition unit. The fifth acquisition unit is configured to calibrate the magnetic field sensor and the spectrum sensor by a sensor calibration algorithm, correct the sensor output by using preset calibration parameters, and obtain calibrated magnetic field signals and spectrum signals. The sixth acquisition unit is configured to collect data in a preset time interval by using a signal collection module according to the calibrated magnetic field signals and spectrum signals, ensure the time axis of the three-dimensional coordinate dataset by using a time stamp alignment algorithm, and obtain an original signal dataset. The seventh acquisition unit is configured to perform denoising processing on the magnetic field signals and the spectrum signals by using an adaptive filtering algorithm for the original signal dataset, remove environmental interference by dynamically adjusting filtering parameters, and obtain a preprocessed signal dataset. The eighth acquisition unit is configured to perform coordinate association on the preprocessed signal dataset and the three-dimensional coordinate dataset by using a data fusion algorithm if the signal-to-noise ratio of the preprocessed signal dataset is lower than a preset threshold, optimize the correspondence between the signals and the coordinates by using a weighted average method, and obtain the preprocessed signal data.

[0229] The big data-based unmanned aerial vehicle airborne geophysical exploration method and system provided in this embodiment can obtain data of a global navigation satellite system and an inertial measurement unit, correct and compensate by combining differential positioning technology and a terrain height model, and obtain an accurate three-dimensional coordinate dataset. On this basis, magnetic field and spectrum signals are collected and adaptive filtering denoising is performed. For large-scale data, distributed computing and convolutional neural network are used to extract features, and a random forest classification model is used in combination with a mineral body distribution knowledge base to generate a geological anomaly distribution atlas. Finally, a spatial distribution model of underground mineral bodies is established by three-dimensional inversion calculation, and is registered with the three-dimensional coordinate dataset to output a three-dimensional geological model containing the distribution characteristics of the mineral bodies. The beneficial effects achieved by this embodiment are as follows:

[0230] ‌1. High-precision three-dimensional spatial positioning

[0231] GNSS (such as Beidou and GPS) and inertial navigation system (INS) are fused, RTK differential positioning technology is combined, horizontal positioning accuracy is improved to centimeter level (±1 cm), elevation accuracy is controlled within ±2 cm, and reliable positioning ability is maintained in signal shielding areas such as tunnels and dense forests; the ionospheric error and terrain undulation influence are effectively compensated by a terrain height model (such as EHP technology) and double-frequency carrier phase difference technology, and vertical direction cumulative error is reduced.

[0232] ‌2. Multi-source data fusion and denoising capability

[0233] Adaptive filtering technology suppresses environmental noise (such as electromagnetic interference, atmospheric disturbance) in magnetic field, spectral signal, improves data signal-to-noise ratio, and lays a foundation for feature extraction; Distributed computing framework (such as RTMC system) supports massive data parallel processing, significantly shortens the feature extraction period of large-scale geological data.

[0234] ‌3、Intelligent feature recognition and classification optimization‌

[0235] Convolutional neural network (CNN) automatically extracts deep features of spectral and magnetic field data (such as mineral reflectance features and magnetic anomaly shapes), reduces the subjectivity of manual interpretation; Random forest model combined with ore body distribution knowledge base realizes high-precision classification of geological anomaly areas (such as discrimination between mineralized and non-mineralized areas), and the classification accuracy is improved by 20%-30%.

[0236] ‌4、High-fidelity reconstruction of three-dimensional geological model‌

[0237] Three-dimensional inversion algorithm combined with multi-physical field constraints (such as gravity and electromagnetic data) quantitatively analyzes the shape and physical parameters of underground ore bodies, and the matching degree of the model with the actual ore body space is more than 90%; The model is dynamically registered with the three-dimensional coordinate data set to support millimeter-level precision display of ore body burial depth, dip angle and other geometric properties.

[0238] ‌5、Resource exploration efficiency and cost optimization‌

[0239] Full-process automation reduces human intervention, shortens single exploration period by 40%-50%, and reduces exploration cost by more than 30% in complex terrain areas; The generated three-dimensional geological model can directly guide the optimization of drilling target area, reduce the number of invalid drill holes, and improve the resource exploration rate by more than 25%.

[0240] In summary, the embodiment realizes the full-link optimization from data acquisition to ore body prediction through multi-technology cooperation and data-driven modeling, and provides a high-precision and high-efficiency digital solution for mineral exploration.

[0241] Although the preferred embodiments of the present application have been described, those skilled in the art can make further changes and modifications to the embodiments once they know the basic inventive concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application. Obviously, those skilled in the art can make various modifications and changes to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and changes of the present application fall within the scope of the claims of the present application and their equivalents, the present application also intends to include these modifications and changes.

Claims

1. A UAV airborne geophysical exploration method based on big data, characterized in that, Includes the following steps: The positioning data of the Global Navigation Satellite System and the measurement data of the Inertial Measurement Unit are acquired. The positioning data is corrected by differential positioning technology. The corrected data is then height-compensated by combining the terrain height model to obtain a three-dimensional coordinate dataset. Based on the three-dimensional coordinate dataset, magnetic field signals and spectral signals are acquired, and an adaptive filtering algorithm is used to denoise the magnetic field signals and spectral signals to obtain preprocessed signal data. Determine whether the amount of signal data in the preprocessed signal data exceeds a preset threshold. If the amount of signal data exceeds the preset threshold, then the preprocessed signal data is segmented using a distributed computing framework, and a convolutional neural network is used to extract the feature vectors from each segment to generate a feature vector set. The set of feature vectors is input into a random forest classification model to obtain geological anomaly classification results. Combined with pattern data in the ore body distribution knowledge base, the geological anomaly distribution map is determined. Based on the geological anomaly distribution map, three-dimensional inversion calculations are performed on the magnetic field signal and spectral signal to establish a spatial distribution model of the underground ore body and generate three-dimensional geological structure data. Spatially register the three-dimensional geological structure data with the three-dimensional coordinate dataset to output a three-dimensional geological model containing the distribution characteristics of ore bodies.

2. The UAV airborne geophysical exploration method based on big data as described in claim 1, characterized in that, The steps of acquiring positioning data from the Global Navigation Satellite System and measurement data from the Inertial Measurement Unit, correcting the positioning data using differential positioning technology, and performing height compensation on the corrected data using a terrain height model to obtain a three-dimensional coordinate dataset include: The system acquires positioning data from the Global Navigation Satellite System and measurement data from the Inertial Measurement Unit. It then aligns the positioning data and measurement data along the time axis using a time synchronization algorithm and preprocesses the measurement data using Kalman filtering to obtain preprocessed data. Differential positioning technology is used to correct the error in the preprocessed data. Correction data is generated by differential calculation between the base station and the rover station. The correction data is then unified to a preset reference coordinate system by a coordinate transformation algorithm to obtain corrected two-dimensional coordinate data. Based on the corrected two-dimensional coordinate data, the corresponding digital elevation information is obtained from the pre-established terrain height model. The height component of the corrected two-dimensional coordinate data is adjusted through a height compensation algorithm to obtain a preliminary three-dimensional coordinate dataset. If the accuracy of the initial 3D coordinate dataset is lower than a preset threshold, the corrected positioning data and measurement data are fused a second time using a data fusion algorithm, and the initial 3D coordinate dataset is optimized using a weighted average method to obtain the final 3D coordinate dataset.

3. The UAV aerial geophysical exploration method based on big data as described in claim 1, characterized in that, Based on the three-dimensional coordinate dataset, the steps of acquiring magnetic field signals and spectral signals, and using an adaptive filtering algorithm to denoise the magnetic field signals and spectral signals to obtain preprocessed signal data include: The magnetic field sensor and the spectral sensor are calibrated using a sensor calibration algorithm. The sensor output is then corrected for deviation using preset calibration parameters to obtain the calibrated magnetic field signal and spectral signal. Based on the calibrated magnetic field and spectral signals, the signal acquisition module synchronously acquires data within a preset time interval. The time stamp alignment algorithm ensures that the data is consistent with the time axis of the three-dimensional coordinate dataset, thus obtaining the original signal dataset. For the original signal dataset, an adaptive filtering algorithm is used to denoise the magnetic field signal and the spectral signal. By dynamically adjusting the filtering parameters, environmental interference is removed to obtain the preprocessed signal dataset. If the signal-to-noise ratio of the preprocessed signal dataset is lower than a preset threshold, the preprocessed signal dataset is correlated with the three-dimensional coordinate dataset using a data fusion algorithm, and the correspondence between the signal and the coordinates is optimized using a weighted average method to obtain the preprocessed signal data.

4. The UAV aerial geophysical exploration method based on big data as described in claim 1, characterized in that, The step of determining whether the amount of preprocessed signal data exceeds a preset threshold, and if the amount of signal data exceeds the preset threshold, then performing segmentation processing on the preprocessed signal data through a distributed computing framework, and extracting feature vectors from each segment using a convolutional neural network to generate a feature vector set includes: If the amount of signal data exceeds a preset threshold, the preprocessed signal data is segmented using a distributed computing framework and distributed to distributed nodes according to the data dimension using a hash mapping algorithm to obtain a segmented data set. For the aforementioned fragmented data set, a convolutional neural network is used to extract features from each fragmented data through convolutional layers and pooling layers, generating feature vectors for each fragmented data, thus obtaining a set of feature vectors.

5. The UAV aerial geophysical exploration method based on big data as described in claim 1, characterized in that, The steps of inputting the feature vector set into a random forest classification model to obtain geological anomaly classification results, and combining this with pattern data in the ore body distribution knowledge base to determine the geological anomaly distribution map include: The classification input data is obtained from the feature vector set, and the feature vectors are classified using a random forest classification model. The classification result is obtained by traversing the decision tree set and voting on each feature vector. Based on the classification results, pattern data is obtained from a pre-established ore body distribution knowledge base. The cosine similarity algorithm is used to calculate the similarity value between the classification results and the pattern data to determine the matching pattern data. If the similarity value between the matched pattern data and the classification result exceeds a preset threshold, the classification result is mapped to two-dimensional spatial coordinates through a grid partitioning algorithm to generate an initial geological anomaly distribution map. Based on the initial geological anomaly distribution map, the two-dimensional spatial coordinates are smoothed using an interpolation algorithm, and combined with the spatial distribution characteristics of the model data, a final geological anomaly distribution map is generated.

6. The UAV aerial geophysical exploration method based on big data as described in claim 1, characterized in that, Based on the geological anomaly distribution map, the steps of performing three-dimensional inversion calculations on the magnetic field and spectral signals to establish a spatial distribution model of the underground ore body and generate three-dimensional geological structure data include: Magnetic field and spectral signal data are obtained from geological anomaly distribution maps. A data fusion algorithm is used to process the magnetic field and spectral signals using a weighted average method to obtain a fused signal dataset. Based on the fused signal dataset, a three-dimensional inversion algorithm is used to calculate the fused signal dataset using the iterative least squares method to determine the preliminary spatial distribution data; If the inversion accuracy of the preliminary spatial distribution data is lower than a preset threshold, the preliminary spatial distribution data is spatially discretized using a grid partitioning algorithm, and the discretized data is enhanced using stereomicroscopy to obtain optimized spatial distribution data. Based on the optimized spatial distribution data, a coordinate mapping algorithm is used to smooth the optimized spatial distribution data through an interpolation algorithm to generate three-dimensional geological structure data.

7. The UAV aerial geophysical exploration method based on big data as described in claim 1, characterized in that, The steps of spatially registering the three-dimensional geological structure data with the three-dimensional coordinate dataset to output a three-dimensional geological model containing ore body distribution characteristics include: Spatial location information is obtained from three-dimensional geological structure data and three-dimensional coordinate dataset. A coordinate mapping algorithm is used to perform preliminary alignment of the three-dimensional geological structure data and three-dimensional coordinate dataset through linear transformation method to obtain a preliminary registration dataset. Based on the preliminary registration dataset, a grid partitioning algorithm is used to spatially discretize the preliminary registration dataset using a uniform grid segmentation method to obtain a discretized registration dataset. If the registration error of the discretized registration dataset is higher than a preset threshold, a support vector machine algorithm is used to perform feature enhancement on the discretized registration dataset through a classification method to obtain an optimized registration dataset. Based on the optimized registration dataset, an interpolation smoothing algorithm is used to smooth the optimized registration dataset through spline interpolation to generate a three-dimensional geological model containing the distribution characteristics of ore bodies.

8. A big data-based UAV airborne geophysical exploration system, used to implement the big data-based UAV airborne geophysical exploration method as described in any one of claims 1 to 7, characterized in that, The big data-based UAV airborne geophysical exploration system includes: The first acquisition module is used to acquire positioning data from the Global Navigation Satellite System and measurement data from the Inertial Measurement Unit, correct the positioning data using differential positioning technology, and perform height compensation on the corrected data using a terrain height model to obtain a three-dimensional coordinate dataset. The second acquisition module is used to acquire magnetic field signals and spectral signals based on the three-dimensional coordinate dataset, and to perform noise reduction processing on the magnetic field signals and spectral signals using an adaptive filtering algorithm to obtain preprocessed signal data. The judgment module is used to determine whether the amount of signal data in the preprocessed signal data exceeds a preset threshold. If the amount of signal data exceeds the preset threshold, the preprocessed signal data is segmented through a distributed computing framework, and a convolutional neural network is used to extract the feature vectors in each segment of data to generate a feature vector set. The determination module is used to input the feature vector set into the random forest classification model, obtain the geological anomaly classification results, and combine them with the pattern data in the ore body distribution knowledge base to determine the geological anomaly distribution map; The generation module is used to perform three-dimensional inversion calculations on the magnetic field signal and spectral signal based on the geological anomaly distribution map, establish a spatial distribution model of the underground ore body, and generate three-dimensional geological structure data; The output module is used to spatially register the three-dimensional geological structure data with the three-dimensional coordinate dataset and output a three-dimensional geological model containing the distribution characteristics of the ore body.

9. The UAV aerial geophysical exploration system based on big data as described in claim 8, characterized in that, The first acquisition module includes: The first acquisition unit is used to acquire positioning data from the global navigation satellite system and measurement data from the inertial measurement unit, align the positioning data and measurement data on the time axis using a time synchronization algorithm, and preprocess the measurement data using Kalman filtering to obtain preprocessed data. The second acquisition unit is used to perform error correction on the preprocessed data using differential positioning technology. It generates correction data through differential calculation between the base station and the rover station, and combines the correction data with a coordinate transformation algorithm to unify it into a preset reference coordinate system to obtain corrected two-dimensional coordinate data. The third acquisition unit is used to obtain the corresponding digital elevation information from the pre-established terrain height model based on the corrected two-dimensional coordinate data, and adjust the height component of the corrected two-dimensional coordinate data through a height compensation algorithm to obtain a preliminary three-dimensional coordinate dataset. The fourth acquisition unit is used to perform secondary fusion of the corrected positioning data and measurement data through a data fusion algorithm if the accuracy of the preliminary three-dimensional coordinate dataset is lower than a preset threshold, and to optimize the preliminary three-dimensional coordinate dataset using a weighted average method to obtain the final three-dimensional coordinate dataset.

10. The UAV aerial geophysical exploration system based on big data as described in claim 8, characterized in that, The second acquisition module includes: The fifth acquisition unit is used to calibrate the magnetic field sensor and the spectral sensor through a sensor calibration algorithm, and to correct the deviation of the sensor output using preset calibration parameters to obtain the calibrated magnetic field signal and spectral signal. The sixth acquisition unit is used to synchronously acquire data within a preset time interval using a signal acquisition module based on the calibrated magnetic field signal and spectral signal, and to ensure consistency with the time axis of the three-dimensional coordinate dataset through a timestamp alignment algorithm to obtain the original signal dataset; The seventh acquisition unit is used to perform noise reduction processing on the magnetic field signal and spectral signal using an adaptive filtering algorithm on the original signal dataset, and remove environmental interference by dynamically adjusting the filtering parameters to obtain the preprocessed signal dataset. The eighth acquisition unit is used to, if the signal-to-noise ratio of the preprocessed signal dataset is lower than a preset threshold, perform coordinate association between the preprocessed signal dataset and the three-dimensional coordinate dataset through a data fusion algorithm, and optimize the correspondence between the signal and the coordinates using a weighted average method to obtain the preprocessed signal data.

Images