Underwater geological interpretation method and system based on multi-source data integration algorithm

Abstract

The present invention relates to the fields of water conservancy and hydropower engineering, and shipping engineering technology, and discloses a method for underwater geological interpretation based on a multi-source data integration algorithm, comprising the following steps: acquiring underwater geological data, resistivity data, topographic data, and water level data; constructing a relationship between relative resistivity and formation threshold; calculating water depth data and distance from the abyssal line; selecting an integrated learning algorithm to predict relative resistivity to achieve formation prediction; calculating the underwater terrain slope to determine the formation condition; and integrating the results of the integrated learning algorithm's formation prediction and the results of the underwater terrain slope determination to achieve underwater geological interpretation. The present invention not only efficiently achieves underwater geological interpretation and reduces the safety risks of geological workers working above water, but also provides more reliable results and saves costs, providing a new approach to underwater geological interpretation.

Description

Technical Field

[0001] The present invention relates to the technical fields of water conservancy and hydropower engineering and shipping engineering, and in particular to an underwater geological interpretation method and system based on a multi-source data integration algorithm. Background Art

[0002] River siltation hinders the smooth flow of water downstream in water conservancy and hydropower projects, hindering the normal operation of navigation and significantly impacting project operations. In recent years, underwater silt removal has become the primary means of addressing this problem. However, conventional drilling methods are not only costly but also pose significant safety risks due to the influence of water flow and limited operating space on operators. Furthermore, drilling only reflects the geological conditions at a single borehole location, which is a significant limitation. Geophysical exploration can improve geological exploration efficiency, but it is also costly, and its accuracy is significantly affected by flow velocity, and the interpretation level is greatly affected by the technical staff. Therefore, researchers must continuously innovate and optimize methods to develop more efficient, accurate, and adaptable underwater geological interpretation systems based on data from multiple sources.

[0003] In recent years, multi-source data analysis has enabled the integration of basic data obtained from various channels. By selecting appropriate machine learning methods, high-precision proxy models can be generated to achieve target value predictions. Using multi-source data for predictions can overcome the significant errors caused by single-source data and maximize prediction accuracy. Research on multi-source data has yielded achievements such as highway construction early warning based on road and vehicle data; lithospheric density inversion methods based on residual gravity anomalies, residual geoid anomalies, and residual topographic anomalies; and ensemble algorithms that leverage the strengths of individual weak learners to improve prediction accuracy. By establishing multiple weak evaluators and integrating their results using certain ensemble rules, these algorithms can achieve better results than a single weak evaluator. For example, Adaboost optimizes the BLS model based on factors influencing water source identification to achieve water source identification; and a concrete mix design method was developed using ensemble learning based on the "Ordinary Concrete Mix Design Code" and existing data. Although machine learning research based on multi-source data has been applied in a growing number of fields, no machine learning methods for determining underwater geological conditions have been reported. Summary of the Invention

[0004] To overcome the deficiencies of the above-mentioned prior art, the present invention provides an underwater geological interpretation method and system based on a multi-source data integration algorithm. The method reveals the geological conditions through limited drilling based on the exploration method, obtains the resistivity of multiple survey lines using the geophysical method, and obtains water depth data and underwater topography data using RTK, a single-beam bathymetry system, and a multi-beam bathymetry system. The method integrates the three methods to obtain data and combines them with integrated learning to realize the prediction of relative resistivity, ultimately achieving high-precision interpretation of underwater geological conditions, greatly improving the prediction accuracy and efficiency.

[0005] According to one aspect of the present invention, there is provided an underwater geological interpretation method based on a multi-source data integration algorithm, comprising:

[0006] Obtain underwater geological data, resistivity data, topographic data, and water level data;

[0007] Based on the acquired underwater geological data and resistivity data, a relationship between relative resistivity and formation threshold is constructed. The formation threshold is a critical value for different rock layers, such as silt alluvial layer, boulder alluvial layer and hard rock.

[0008] Calculate water depth data and distance to the deep channel based on the acquired topographic data and water level data;

[0009] Selecting a trained ensemble learning model to predict relative resistivity to achieve formation prediction; the ensemble learning model uses water depth, formation depth, and distance from the abyssal line as known quantities, and relative resistivity as a predicted value;

[0010] Based on the predicted relative resistivity and the relationship between relative resistivity and formation threshold, formation prediction is achieved.

[0011] As a further technical solution, after obtaining the formation prediction results, it also includes:

[0012] Calculate the underwater terrain slope and review the predicted strata based on the calculated underwater terrain slope.

[0013] As a further technical solution, underwater geological data, resistivity data, topographic data and water level data are obtained, including:

[0014] The underwater geological data is obtained using drilling equipment; the resistivity data is obtained using high-density electrical method, including apparent resistivity; the topographic data and water level data are obtained using real-time differential positioning, single-beam sounding system or multi-beam sounding system.

[0015] As a further technical solution, a relationship between relative resistivity and formation threshold is constructed, including:

[0016] Threshold division is performed on the underwater geological data and apparent resistivity, and a relationship between relative resistivity and formation threshold is constructed, wherein the underwater terrain is divided into silt alluvial layer, boulder alluvial layer and hard rock layer according to the underwater geological data, and relative resistivity is obtained according to the apparent resistivity conversion, and the relative resistivity and formation threshold corresponding to different rock layers of the silt alluvial layer, boulder alluvial layer and hard rock layer are obtained.

[0017] As a further technical solution, the water depth data and the distance to the abyss line are calculated, including:

[0018] Calculate water depth data: Determine the difference between the water surface elevation measured by real-time differential positioning and the underwater topography obtained by the single-beam bathymetry system or the multi-beam bathymetry system;

[0019] Calculate the distance to the thalassocentrism line: Draw a cross section perpendicular to the water flow direction based on the measured three-dimensional coordinate data of the terrain, determine the thalassocentrism points on the cross section perpendicular to the water flow direction and form a complete thalassocentrism line; introduce the geophysical detection line based on the formed thalassocentrism line, and the distance between the measuring point and the thalassocentrism line is controlled by the two thalassocentrism points closest to the measuring point. The straight-line distance determined perpendicular to these two points is the distance between the measuring point and the thalassocentrism line.

[0020] As a further technical solution, the acquisition of water depth at geophysical survey points and drilling points includes:

[0021] The vector elevation data of multiple points closest to the target point are obtained and assigned different weights. The weights are determined by the Euclidean distance from the target point. The coordinates of the target point are obtained by multiplying the coordinates of multiple points closest to the target point by the weights.

[0022] As a further technical solution, the trained ensemble learning model is selected to predict relative resistivity to achieve formation prediction, including:

[0023] Through the ensemble learning model, different base learners are selected to train the multi-source data including water depth, formation depth, distance to the deep line and relative resistivity. The three base learners with the highest scores are selected as the base learners of the proxy model.

[0024] Based on the selected base learner combined with the meta-learner, a proxy model is constructed as the trained ensemble learning model;

[0025] The trained ensemble learning model is used to predict relative resistivity, and the predicted formation is obtained based on the predicted value combined with the relationship between relative resistivity and formation threshold.

[0026] According to one aspect of the present invention, there is provided an underwater geological interpretation system based on a multi-source data integration algorithm, comprising:

[0027] The first main module is used to obtain underwater geological data, resistivity data, topographic data and water level data;

[0028] The second main module is used to construct a relationship between relative resistivity and formation threshold based on the acquired underwater geological data and resistivity data. The formation threshold is a critical value for different rock layers such as silt alluvial layer, boulder alluvial layer and hard rock;

[0029] The third main module is used to calculate the water depth data and the distance to the deep channel based on the acquired terrain data and water level data;

[0030] The fourth main module is used to select a trained ensemble learning model to predict relative resistivity and realize formation prediction; the ensemble learning model uses water depth, formation depth and distance from the abyss line as known quantities, and relative resistivity as a predicted value;

[0031] The fifth main module is used to realize formation prediction based on the predicted relative resistivity and the relationship between the relative resistivity and the formation threshold.

[0032] According to one aspect of the present invention, an electronic device is provided, comprising a memory and a processor, wherein the memory stores program instructions executed by the processor, and the processor calls the program instructions to execute the steps of the underwater geological interpretation method based on a multi-source data integration algorithm.

[0033] According to one aspect of the present invention, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions enable the computer to execute the steps of the underwater geological interpretation method based on the multi-source data integration algorithm.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] 1. The present invention aims to solve the problem that dredging is required in water conservancy and hydropower projects and waterway projects, and that underwater geological conditions are affected by water bodies and are difficult to predict comprehensively, at low cost, and with high precision. Therefore, an underwater geological interpretation method based on a multi-source data integration algorithm is proposed. Specifically, underwater geological data, resistivity data, and topographic data and water level data are first obtained through water drilling, geophysical exploration, and measurement. Then, a relationship between relative resistivity and formation threshold is constructed to achieve the critical value division of different rock layers, such as silted alluvial layers, boulder alluvial layers, and hard rock. Then, water depth data and distance from the abyss line are calculated through measured topography. Then, an integrated learning algorithm is selected, using water depth, formation depth, and distance from the abyss line as known quantities, and relative resistivity as predicted values for training. Formation determination is then achieved through the set relationship between relative resistivity and formation threshold.

[0036] 2. The present invention also calculates the underwater terrain slope and determines the stratum situation based on the relationship between the underwater terrain slope and the underwater angle of repose of the gravel layer. Finally, the results of the stratum prediction algorithm and the results of the underwater terrain slope determination are integrated to achieve underwater geological interpretation.

[0037] 3. This invention efficiently determines underwater geological conditions through multi-source data fusion, reducing the operational risks for geologists. Therefore, this invention provides solid technical support for underwater geological interpretation and contributes to reducing operational risks for geophysical prospectors. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, a brief introduction will be given below to the drawings used in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0039] Figure 1 This is a flow chart of an underwater geological interpretation method based on a multi-source data integration algorithm provided by an embodiment of the present invention.

[0040] Figure 2 This is a flow chart of water drilling in an embodiment of the present invention.

[0041] Figure 3 This is a measurement flow chart of a multi-beam bathymetric system in an embodiment of the present invention.

[0042] Figure 4 It is a schematic diagram of the principle of the geophysical exploration method in an embodiment of the present invention.

[0043] Figure 5 1 is a diagram of the arrangement of object detection lines in an embodiment of the present invention.

[0044] Figure 6 This is an integrated learning flow chart in an embodiment of the present invention. DETAILED DESCRIPTION

[0045] This invention addresses the difficulty of comprehensively, cost-effectively, and accurately predicting underwater geological conditions, which are affected by water bodies and require dredging in water conservancy and hydropower projects and waterway engineering. The invention provides an underwater geological interpretation method based on a multi-source data integration algorithm. First, underwater geological data, resistivity data, topographic data, and water level data are acquired; then, a relationship between relative resistivity and formation thresholds is constructed; then, water depth data and distance to the abyssal line are calculated; finally, an integrated learning algorithm is selected to predict relative resistivity to achieve formation prediction and underwater geological interpretation. This invention not only efficiently achieves underwater geological interpretation and reduces the safety risks of geological workers working above water, but also provides more reliable and cost-effective results, providing a new approach to underwater geological interpretation.

[0046] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. In addition, the technical features in the various embodiments or single embodiments provided by the present invention are arbitrarily combined with each other to form a new technical solution. This combination is not restricted by the sequence of steps and / or structural composition mode, but must be based on the ability of ordinary technicians in this field to implement it. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that this combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0047] The following is combined with Figure 1-6 The present invention is described in further detail.

[0048] The embodiment of the present invention discloses an underwater geological interpretation method based on a multi-source data integration algorithm. Figure 1 ,The underwater geological interpretation method based on multi-source data integration algorithm includes the following steps:

[0049] S100. Acquire underwater geological data, resistivity data, topographic data, and water level data through different systems.

[0050] The underwater geological data refers to the classification of underwater terrain into silt alluvial layer, boulder alluvial layer and hard rock layer based on the degree of core fragmentation, weathering degree and structural surface conditions at different depths.

[0051] The underwater geological data is obtained by using water drilling equipment, and different drill bits are used for drilling according to different geological conditions. During the drilling process, casings of different diameters are used from the water surface to the river bottom and alluvial layer according to actual conditions.

[0052] The resistivity data is obtained by high-density electrical method, in which an artificial electric field is formed by supplying power to the underground through electrodes. The electrodes are arranged with a spacing of 5 to 15 meters and a Wenner device is used to collect data. According to the detection depth requirements, each arrangement collects data at the maximum detection depth. The apparent resistivity distribution data is obtained by scanning and measuring the artificial electric field at different parts of the surface.

[0053] The terrain data and water level data are obtained through various methods such as RTK, single-beam bathymetry system, and multi-beam bathymetry system. A single-beam bathymetry system is used for underwater measurement in areas with poor navigation conditions and shallows to obtain plane coordinates and elevation three-dimensional data of the measuring points in the same coordinate system; a multi-beam bathymetry system is used for deep water areas of reservoirs to perform detailed three-dimensional scanning of the underwater terrain and obtain high-density plane and elevation three-dimensional vector data of the underwater terrain; water level data is measured and obtained using RTK.

[0054] Specifically, the following steps are included:

[0055] S110, obtain geological data of different rock layers at the drilling points based on water drilling: refer to Figure 2 Surface soil layers such as silt can be obtained using larger-diameter soil samplers. Alluvial layers consisting of boulders and gravels should be drilled using diamond or composite drill bits, with larger casing used for isolation to ensure coring. The borehole should then be completed to the designated elevation using a smaller diameter. Casing no smaller than 273 mm should be used for isolation between the water surface and the riverbed. 219, 173, or 146 mm casing can be used for alluvial layers; final borehole diameters should be 110, 91, or 75 mm. After core collection and airing, stratigraphic delineation of strata at different depths is achieved. Cores obtained by drilling are grouped and numbered. Underwater rock masses obtained after airing and airing are classified into three categories: silted alluvial layer, boulder alluvial layer, and hard rock layer, based on the degree of fragmentation, weathering, drilling difficulty, and coring integrity. Table 1 shows the stratigraphic depths of different boreholes.

[0056] Table 1 Different drilling depths

[0057]

[0058] S120, Obtaining Resistivity Data by High-Density Electrical Method: See Figure 4 and Figure 5 , an electrode spacing of 10m is arranged and a Wenner device is used to collect data. According to the detection depth requirements, each arrangement collects data at the maximum detection depth. By scanning and measuring the artificial electric field at different parts of the surface, the apparent resistivity distribution data is obtained. During measurement, the electrode spacing AM=MN=NB=AB / 3 is one electrode spacing, and A, M, N, and B move to the right synchronously to obtain the profile line of the first layer depth; then AM, MN, and NB increase one electrode spacing, and A, M, N, and B move to the right synchronously to obtain the profile line of the second layer depth.

[0059] S130. Obtain terrain data and water level data: Real-time differential positioning (RTK) can be used for water surface line measurement and geophysical positioning. A single-beam bathymetry system is used for underwater measurement in areas with poor navigation conditions and shallows to obtain the plane coordinates and elevation three-dimensional data of the measuring points in the same coordinate system. A multi-beam bathymetry system is used for deep water areas of reservoirs to perform detailed three-dimensional scanning of the underwater terrain and obtain high-density plane and elevation three-dimensional vector data of the underwater terrain.

[0060] The water depth and underwater elevation data of geophysical detection points and drilling points are obtained by obtaining the 5 nearest vector elevation data near the prediction point, and the weight is calculated by the Euclidean distance from the target point. S j To determine, the greater the distance, the smaller the weight. . Therefore, through the target point Y Multiply the coordinates by the weight product to get the target point coordinates .

[0061] Reference Figure 3 The use of a multi-beam echo sounder system to obtain underwater terrain requires following the conventional RTK operation process. After setting up the RTK base station, conduct joint measurements of two or more control points, connect the mobile station receiver to the multi-beam echo sounder system, and output the data of the navigation measurement system to the real-time acquisition system during the measurement process to record the position and motion posture of the vessel. At the same time, perform parameter settings, network settings, and output settings for the navigation measurement system.

[0062] A multi-beam bathymetry system utilizes a real-time data acquisition workstation system to monitor the data collection process and guide the vessel along the designated survey lines. Software controls the sonar's operating status, adjusting the sonar's beam angle, range, central beam direction, and transmission power based on the real-time reservoir environment. Vessel attitude and transducer installation corrections, including time delay correction, roll deflection correction, pitch deflection correction, and bow deflection correction, are performed. Repeated round-trip measurements are conducted in both flat and undulating underwater terrain areas. After fully examining the reservoir's survey area, the beam angle is determined based on the average water depth, ensuring a minimum 10% overlap between survey lines.

[0063] Use data acquisition software to collect multi-beam field data, use a real-time data acquisition workstation system to monitor the data collection process, and guide the ship's operation according to the arranged survey line. According to changes in the reservoir environment, adjust the sonar's beam angle, range, central beam direction, transmission power, etc., and finally complete the field data collection work.

[0064] Using a multibeam bathymetry system, attitude correction parameters, sound velocity profile data, and tide level data were imported into the project. The field-acquired xtf data was converted to HDCS format and then merged. A depth data surface was created. Based on this merged depth data, a depth data surface, or gridded underwater terrain data elevation model, was constructed.

[0065] The water depth data collected in the field contains noise and erroneous points caused by various error factors. These are removed during data post-processing. Each survey line is edited, and residual large jump points are filtered out manually and automatically using parameters. Then, points outside the water depth data surface are filtered out based on the surface.

[0066] S200, underwater geological conditions and resistivity threshold R Divide and form the division result x Since the apparent resistivity fluctuates from single digits to thousands of digits, the relative resistivity is obtained by reducing the apparent resistivity by 100 times. , obtain different water drilling exposures of silt alluvial layer, boulder alluvial layer, hard rock layer and determine the corresponding threshold value for different rock layers 、 , recorded as . Combine n groups of different result data in pairs and construct the second-order determinant After deleting the data with the largest deviation from 0 in the second-order determinant, the remaining thresholds are weighted averaged to obtain the corresponding thresholds for the final silt alluvial layer, boulder alluvial layer, and hard rock layer, which are rounded to 1 and 5, as shown in Table 2.

[0067] It should be noted that the threshold here can be regarded as the measurement boundary value, or the resistivity at the boundary between two rock layers.

[0068] Table 2 The corresponding thresholds for different rock formations

[0069]

[0070] S300, calculate and obtain the water depth data of the measuring point and the distance to the deep channel. H 1 Determined by the difference between the water surface elevation measured by RTK and the underwater topography obtained by single-beam or multi-beam sounding. Distance to the deep sea line L Import the measured terrain 3D coordinate data into the mapping software, draw a cross section perpendicular to the water flow direction through the river direction, the lowest point on the cross section is the abyss point, connect the abyss points of all cross sections to form a complete abyss line. Draw the geophysical detection line into the mapping software, the distance between the measuring point and the abyss line is controlled by the two abyss line control points closest to the measuring point, and the straight line distance determined by the two points perpendicular to the two points is L , is the distance between the measuring point and the abyss line.

[0071] S400: Select an integrated learning model to predict relative resistivity to achieve formation prediction. The integrated learning model uses water depth, formation depth, and distance to the abyss line as known quantities and relative resistivity as a predicted value.

[0072] Reference Figure 6 , select different base learners to obtain water depth H 1. Stratum depth H 2. Distance from the abyss line L , relative resistivity R ' and other multi-source data for training, and select the three base learners with high scores as the base learners of the proxy model. H 1. Stratum depth H 2. Distance from the abyss line L Multi-source data such as α and β were used as independent variables to measure the relative resistivity. R As the dependent variable, GBDT, ET, RF, ADA, XGB, and SVR were selected as base models. Logistic regression and linear regression were used as meta-models for optimization, and a stacking-based proxy model was constructed. MAE was used as the criterion for measuring model accuracy. Bayesian optimization was performed on the selected base learner pairs, and the three models with the highest prediction rate were selected using MAE as the criterion for measuring model accuracy. This example ultimately selected GBDT, ET, and RF as the base learners, and the Linear Regression model as the meta-model. The calculation results and MAE are shown in Tables 3 and 4.

[0073] Table 3 Corresponding errors of different base learners and meta-models after Bayesian optimization parameters

[0074]

[0075] Table 4 Computational results error using Stacking, optimal base learner and meta-model

[0076]

[0077] Furthermore, the strata are predicted using the proxy model and the selected threshold. The prediction of strata is achieved by using the corresponding relationship between the predicted resistivity results and the threshold, which is the result of regression analysis based on ensemble learning for the predicted locations of silt alluvial layers, boulder alluvial layers, and hard rock layers.

[0078] To evaluate the prediction accuracy, the following steps are also included:

[0079] S500, calculating the underwater terrain slope to determine the stratum conditions: further, performing a slope analysis on the terrain surrounding the prediction point using the acquired terrain vector data, selecting measurement points within a 10m diameter range for the slope analysis, obtaining contour lines through linear interpolation, and calculating the comprehensive slope of the vertical contour lines within the selected range. A gravel layer with a slope equal to or greater than the underwater repose angle of 32° is determined to be bedrock, which is used to determine whether the underwater geological surface layer is a hard rock layer.

[0080] S600, calculating the underwater terrain slope to determine the stratum conditions: interpreting the underwater geology based on the integrated learning model and the geological interpretation results of the underwater terrain slope prediction.

[0081] In the embodiment of the present invention, the MAE of the underwater geological interpretation method based on the multi-source data integration algorithm is 0.56.

[0082] As can be seen, the underwater geological interpretation method of the present invention, based on a multi-source data integration algorithm, uses an integrated algorithm to determine relative resistivity and terrain slope based on multi-source data with an error within 1. This method is fully capable of interpreting different underground geological conditions, demonstrating excellent accuracy and efficiency, saving labor investment and reducing construction risks for geologists. This invention aligns with geophysical research methods and enhances the scientific nature and credibility of design decisions. This is particularly helpful for geological interpretation of dredging projects involving water conservancy and hydropower projects and waterway engineering. Through precise design and interpretation, this invention improves the accuracy and efficiency of geological interpretation, providing strong technical support for underwater geological determination.

[0083] The implementation of each embodiment of the present invention is based on programmed processing performed by a device with processor functionality. Therefore, in practical engineering, the technical solutions and functions of each embodiment of the present invention are packaged into various modules. Based on this reality, and in addition to the aforementioned embodiments, an embodiment of the present invention provides an underwater geological interpretation system based on a multi-source data integration algorithm. This system is used to implement the underwater geological interpretation method based on a multi-source data integration algorithm described in the aforementioned method embodiments.

[0084] The system includes: a first main module for acquiring underwater geological data, resistivity data, topographic data and water level data; a second main module for constructing a relationship between relative resistivity and formation threshold based on the acquired underwater geological data and resistivity data, wherein the formation threshold is a critical value for different rock formations such as silt alluvial layer, boulder alluvial layer and hard rock; a third main module for calculating water depth data and distance from the abyss line based on the acquired topographic data and water level data; a fourth main module for selecting a trained integrated learning model to predict relative resistivity and realize formation prediction; the integrated learning model uses water depth, formation depth and distance from the abyss line as known quantities, and relative resistivity as a predicted value; a fifth main module for realizing formation prediction based on the predicted relative resistivity in combination with the relationship between relative resistivity and formation threshold.

[0085] The underwater geological interpretation system based on the multi-source data integration algorithm provided by the embodiment of the present invention addresses the problem that dredging is required in water conservancy and hydropower projects and waterway projects, and underwater geological conditions are affected by water bodies and are difficult to predict in a comprehensive, low-cost, and high-precision manner. By adopting the aforementioned modules, the underwater geological conditions are efficiently determined through the fusion of multi-source data, thereby reducing the construction risks of geological personnel.

[0086] It should be noted that the system embodiments provided by the present invention are not only used to implement the methods in the above-mentioned method embodiments, but also used to implement the methods in other method embodiments provided by the present invention. The only difference lies in the setting of corresponding functional modules, and the principles thereof are basically the same as the principles of the above-mentioned system embodiments provided by the present invention. As long as those skilled in the art refer to the specific technical solutions in other method embodiments on the basis of the above-mentioned system embodiments, obtain corresponding technical means and technical solutions composed of these technical means by combining technical features, and on the premise of ensuring the practicality of the technical solutions, improve the modules in the above-mentioned system embodiments to obtain corresponding system class embodiments for implementing the methods in other method class embodiments.

[0087] Based on the same inventive concept as the aforementioned embodiment, an embodiment of the present invention further provides an electronic device, comprising a memory and a processor, wherein the memory stores program instructions executed by the processor, and the processor calls the program instructions to execute the steps of the underwater geological interpretation method based on the multi-source data integration algorithm.

[0088] Based on the same inventive concept as the aforementioned embodiment, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions enable the computer to execute the steps of the underwater geological interpretation method based on the multi-source data integration algorithm.

[0089] In summary, the present invention acquires underwater geological data, resistivity data, topographic data, and water level data, constructs a relationship between relative resistivity and formation threshold, calculates water depth data and distance from the abyssal line, and selects an ensemble learning algorithm to predict relative resistivity to achieve formation prediction. Furthermore, the formation conditions are determined by calculating the slope of the underwater terrain. The results of the ensemble learning algorithm's formation prediction and the results of the underwater terrain slope determination are combined to achieve underwater geological interpretation. This present invention not only efficiently achieves underwater geological interpretation, reducing the safety risks of geological personnel working above water, but also provides more reliable and cost-effective results, providing a new approach to underwater geological interpretation.

[0090] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. An underwater geological interpretation method based on a multi-source data integration algorithm, characterized in that: include: Obtain underwater geological data, resistivity data, topographic data, and water level data; Based on the acquired underwater geological data and resistivity data, a relationship between relative resistivity and formation threshold is constructed. The formation threshold is a critical value for different rock layers, such as silt alluvial layer, boulder alluvial layer and hard rock. Calculate water depth data and distance to the deep channel based on the acquired topographic data and water level data; Selecting a trained ensemble learning model to predict relative resistivity to achieve formation prediction; the ensemble learning model uses water depth, formation depth, and distance from the abyssal line as known quantities, and relative resistivity as a predicted value; Based on the predicted relative resistivity and the relationship between relative resistivity and formation threshold, formation prediction is achieved.

2. The underwater geological interpretation method based on multi-source data integration algorithm according to claim 1, characterized in that: After obtaining the formation prediction results, it also includes: Calculate the underwater terrain slope and review the predicted strata based on the calculated underwater terrain slope.

3. The underwater geological interpretation method based on multi-source data integration algorithm according to claim 1 is characterized in that: Acquire underwater geological data, resistivity data, topographic data, and water level data, including: The underwater geological data is obtained using drilling equipment; the resistivity data is obtained using high-density electrical method, including apparent resistivity; the topographic data and water level data are obtained using real-time differential positioning, single-beam sounding system or multi-beam sounding system.

4. The underwater geological interpretation method based on multi-source data integration algorithm according to claim 3 is characterized in that: Construct the relationship between relative resistivity and formation threshold, including: Threshold division is performed on the underwater geological data and apparent resistivity, and a relationship between relative resistivity and formation threshold is constructed, wherein the underwater terrain is divided into silt alluvial layer, boulder alluvial layer and hard rock layer according to the underwater geological data, and relative resistivity is obtained according to the apparent resistivity conversion, and the relative resistivity and formation threshold corresponding to different rock layers of the silt alluvial layer, boulder alluvial layer and hard rock layer are obtained.

5. The underwater geological interpretation method based on multi-source data integration algorithm according to claim 3 is characterized in that: Calculate water depth data and distance to the abyss line, including: Calculate water depth data: Determine the difference between the water surface elevation measured by real-time differential positioning and the underwater topography obtained by the single-beam bathymetry system or the multi-beam bathymetry system; Calculate the distance to the thalassocentrism line: Draw a cross section perpendicular to the water flow direction based on the measured three-dimensional coordinate data of the terrain, determine the thalassocentrism points on the cross section perpendicular to the water flow direction and form a complete thalassocentrism line; introduce the geophysical detection line based on the formed thalassocentrism line, and the distance between the measuring point and the thalassocentrism line is controlled by the two thalassocentrism points closest to the measuring point. The straight-line distance determined perpendicular to these two points is the distance between the measuring point and the thalassocentrism line.

6. The underwater geological interpretation method based on multi-source data integration algorithm according to claim 1, characterized in that: Obtaining water depth at geophysical survey points and drilling points, including: The vector elevation data of multiple points closest to the target point are obtained and assigned different weights. The weights are determined by the Euclidean distance from the target point. The coordinates of the target point are obtained by multiplying the coordinates of multiple points closest to the target point by the weights.

7. The underwater geological interpretation method based on multi-source data integration algorithm according to claim 1 is characterized in that: Select the trained ensemble learning model to predict relative resistivity to achieve formation prediction, including: Through the ensemble learning model, different base learners are selected to train the multi-source data including water depth, formation depth, distance to the deep line and relative resistivity. The three base learners with the highest scores are selected as the base learners of the proxy model. Based on the selected base learner combined with the meta-learner, a proxy model is constructed as the trained ensemble learning model; The trained ensemble learning model is used to predict relative resistivity, and the predicted formation is obtained based on the predicted value combined with the relationship between relative resistivity and formation threshold.

8. An underwater geological interpretation system based on a multi-source data integration algorithm is characterized by: include: The first main module is used to obtain underwater geological data, resistivity data, topographic data and water level data; The second main module is used to construct a relationship between relative resistivity and formation threshold based on the acquired underwater geological data and resistivity data. The formation threshold is a critical value for different rock layers such as silt alluvial layer, boulder alluvial layer and hard rock; The third main module is used to calculate the water depth data and the distance to the deep channel based on the acquired terrain data and water level data; The fourth main module is used to select a trained ensemble learning model to predict relative resistivity and realize formation prediction; the ensemble learning model uses water depth, formation depth and distance from the abyss line as known quantities, and relative resistivity as a predicted value; The fifth main module is used to realize formation prediction based on the predicted relative resistivity and the relationship between the relative resistivity and the formation threshold.

9. An electronic device, characterized in that: It comprises a memory and a processor, wherein the memory stores program instructions executed by the processor, and the processor calls the program instructions to execute the steps of the underwater geological interpretation method based on the multi-source data integration algorithm as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that The non-transitory computer-readable storage medium stores computer instructions, which enable the computer to execute the underwater geological interpretation method based on a multi-source data integration algorithm according to any one of claims 1 to 7.

Images