Three-dimensional geological model construction method and system based on multi-modal data

Abstract

The invention relates to the technical field of three-dimensional geologic model construction, in particular to a three-dimensional geologic model construction method and system based on multi-modal data, and the method comprises the steps: obtaining drilling data, geophysical prospecting data, multispectral remote sensing data, geological mapping data and elevation data for three-dimensional geologic model construction in a to-be-modeled region; the method comprises the following steps of: acquiring a deviation coefficient of reflection characteristics of each pixel under different wavebands according to correlation conditions of reflection intensities of the multispectral remote sensing data in a local range of each pixel under different wavebands and a reflection intensity difference between each pixel and the pixels in the local range under the same wavelength, and further acquiring a judgment coefficient of reflection characteristic similarity between different pixels; the method comprises the following steps of: clustering pixels, adjusting a smoothing parameter when the reflection intensity is filtered according to the distribution characteristic of the deviation coefficient of the reflection characteristic of the pixels in each cluster, and further constructing a three-dimensional geologic model by adopting three-dimensional modeling software. According to the invention, the three-dimensional geologic model construction precision can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of three-dimensional geological model construction, and specifically to a method and system for constructing a three-dimensional geological model based on multimodal data. Background Art

[0002] Three-dimensional geological models can digitize and visualize underground geological structures, lithologic distribution, and structural characteristics. They are widely used in geological resource exploration, engineering construction, and environmental governance. Nowadays, the construction of three-dimensional geological models based on multimodal data has achieved a comprehensive and multi-dimensional depiction of geological structures, fully reflecting geological characteristics through data from different modalities.

[0003] However, in the process of constructing three-dimensional geological models, due to the influence of various interference factors, the data quality used for constructing three-dimensional geological models is poor, which in turn affects the accuracy of three-dimensional geological model construction; among them, remote sensing data reflects the macroscopic geological characteristics of the surface and shallow areas. In the actual construction process, interference factors such as atmospheric scattering and sensor noise will cause the quality of remote sensing data to deteriorate, and the interference effects at different times are different, which makes the traditional filtering correction method have a large deviation for remote sensing data, affecting the accuracy of surface connection and shallow structure characterization in the process of multi-source data fusion, resulting in reduced accuracy of three-dimensional geological model construction. Summary of the Invention

[0004] In order to solve the above technical problems, the purpose of this application is to provide a method and system for constructing a three-dimensional geological model based on multimodal data. The technical solutions adopted are as follows: The present invention provides a method for constructing a three-dimensional geological model based on multimodal data, comprising the following steps: Acquire multimodal data for constructing a 3D geological model in the area to be modeled, including borehole data, geophysical data, multispectral remote sensing data, geological mapping data, and elevation data; The deviation coefficient of the reflection characteristics of each pixel in different bands is obtained by analyzing the correlation between the reflection intensity of each pixel in the local range at different bands and the difference in reflection intensity between each pixel and the pixels in the local range at the same wavelength. The judgment coefficient of the similarity of the reflection characteristics between different pixels is obtained by combining the position and reflection intensity difference between different pixels. The coefficient is used to cluster the pixels. The smoothing parameter when filtering the reflection intensity corresponding to the pixels in each cluster is adjusted according to the distribution characteristics of the deviation coefficient of the reflection characteristics of the pixels in each cluster. Based on the processed three-dimensional geological model multimodal data, the three-dimensional geological model is constructed using three-dimensional modeling software.

[0005] Preferably, the deviation coefficient of the reflection characteristic of each pixel is obtained further as follows: ; in, Indicates the current band Deviation coefficient of the reflection characteristics of each pixel; Indicates the Pixel and its The difference value of the reflection characteristics of neighboring pixels in the current band; No. The first pixel The characteristic value of the change in the reflectance characteristics of the neighboring pixels compared to the entire neighborhood range; Indicates the The number of neighboring pixels of a pixel.

[0006] Preferably, the reflection intensity value of each pixel in the multispectral remote sensing data at all wavelengths is mapped to a two-dimensional rectangular coordinate system with the horizontal axis being the wavelength and the vertical axis being the reflection intensity value, and the reflection characteristic curve corresponding to each pixel is obtained by curve fitting.

[0007] Preferably, the mean curve of the reflection characteristic curves of each pixel and its neighboring pixels is calculated, and the absolute value of the Pearson correlation coefficient between the reflection characteristic curves of the neighboring pixels of each pixel and the mean curve in the current band corresponding to the reflection intensity values ​​is calculated as the characteristic value of the change in the reflection characteristic association of each neighboring pixel compared to the overall neighborhood range.

[0008] Preferably, the absolute value of the difference between the reflection intensity values ​​of each pixel and its neighboring pixels at the same wavelength is calculated, and the average of the absolute values ​​of the difference obtained between each pixel and its neighboring pixels in the current band at all wavelengths is taken as the difference value of the reflection characteristics of each pixel and its neighboring pixels in the current band.

[0009] Preferably, the determination coefficient of the similarity of the reflection characteristics between different pixels is further obtained as follows: ; in, Indicates the and The judgment coefficient of the similarity of reflection characteristics between pixels; Indicates the and The Euclidean distance between pixels; Indicates the and The pixel in the DTW distance of reflection intensity values ​​within a band; Indicates the In the band and The mean of the deviation coefficients of the reflection characteristics of pixels, Indicates the The cumulative sum of the mean values ​​of the deviation coefficients of the reflection characteristics of any two pixels in a band, m is the number of preset bands.

[0010] Preferably, in the process of clustering pixels, the judgment coefficient of the similarity of the reflection characteristics between different pixels is used as the metric distance between different pixels.

[0011] Preferably, the Gaussian smoothing parameter after the adjustment of the Gaussian filtering of the reflection intensity of the current cluster in the current band is The acquisition is further as follows: ,in, Indicates the initial Gaussian smoothing parameter when Gaussian filtering is performed on the reflection intensity of the current cluster in the current band. Represents the normalized result of the difference value of the reflection intensity deviation characteristics of the pixels in the current cluster in the current band.

[0012] Preferably, for the current band, probability statistics are performed on the deviation coefficients of the reflection characteristics of all pixels in the cluster, and the probability statistical result curve is fitted to calculate the KL divergence value between the fitting curve of the current cluster and each other cluster in the current band, and the mean of all the KL divergence values ​​is used as the difference value of the reflection intensity deviation characteristics of the pixels in the current cluster in the current band.

[0013] An embodiment of the present application also provides a three-dimensional geological model construction system based on multimodal data, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above-mentioned methods for constructing a three-dimensional geological model based on multimodal data are implemented.

[0014] As can be seen from the above, the method and system for constructing a three-dimensional geological model based on multimodal data provided by this application have at least the following beneficial effects: In the process of constructing a three-dimensional geological model through multimodal data, the impact of the quality of multi-source data on the overall construction accuracy is considered, which leads to the problem of reduced construction accuracy of the three-dimensional geological model. Therefore, this application first collects multimodal data of the modeling area, and conducts neighborhood analysis on the reflection characteristics of different positions in view of the impact of regional strip noise and random noise interference differences on data quality during remote sensing data processing. Based on the analysis results, the interference differences between different positions in different bands are compared, and then the reflection intensity data of all positions are divided. Based on the division results, the interference influence characteristics in different regions and different bands are accurately judged and analyzed, and the Gaussian smoothing process is optimized through the analysis results. The beneficial effect is to accurately reduce the noise of the reflection intensity data of the remote sensing data, improve the accuracy of the spatial position correction of the geological mapping data, and the accuracy of the surface connection and shallow structure depiction in the three-dimensional model construction process. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0016] Figure 1 This is a flowchart of the steps of the method for constructing a three-dimensional geological model based on multimodal data provided in this application. DETAILED DESCRIPTION

[0017] To further illustrate the technical means and effectiveness of this application's objectives, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effectiveness of the method and system for constructing a 3D geological model based on multimodal data proposed in this application. In the following description, references to different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0018] Unless otherwise specified and limited, terms such as "comprises", "includes" or any other variants thereof are intended to cover non-exclusive inclusion, so that a circuit structure, article or device comprising a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the article or device comprising the element. In addition, the term "and\or" used herein includes any and all combinations of one or more related listed items. All technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs.

[0019] The specific scheme of the method and system for constructing a three-dimensional geological model based on multimodal data provided by this application is described in detail below with reference to the accompanying drawings.

[0020] See also Figure 1 , which shows a flowchart of a method for constructing a three-dimensional geological model based on multimodal data provided by an embodiment of the present application, including the following steps: Step 1: Obtain multimodal data for constructing a 3D geological model in the area to be modeled, including borehole data, geophysical data, multispectral remote sensing data, geological mapping data, and elevation data.

[0021] First, in this embodiment, data will be obtained in the process of constructing a three-dimensional geological model based on multimodal data, including drilling data, geophysical data, remote sensing data, geological mapping data and elevation data. Specifically, in the area to be modeled, core sampling and logging technology are used to record the lithology and physical parameters, geophysical characteristic information, hole coordinates and hole inclination data at different depths; geophysical data are collected through seismic exploration technology; multispectral remote sensing data of the area to be modeled are obtained through satellite remote sensing; geological mapping data of the area to be modeled are obtained through geological surveys of the area to be modeled, including surface outcrops, bottom contact relationships and fault strike information; for the collection of elevation data of the area to be modeled, total station, GPS or lidar measurement can be used.

[0022] Step 2: Through the correlation of the reflection intensity of each pixel in the local range of the multispectral remote sensing data in different bands, and the difference in reflection intensity between each pixel and the pixels in the local range at the same wavelength, the deviation coefficient of the reflection characteristics of each pixel in different bands is obtained. Combined with the position and reflection intensity difference between different pixels, the judgment coefficient of the similarity of the reflection characteristics between different pixels is obtained, which is used to cluster the pixels. According to the distribution characteristics of the deviation coefficient of the reflection characteristics of the pixels in each cluster, the smoothing parameters when filtering the reflection intensity corresponding to the pixels in each cluster are adjusted.

[0023] In the process of building a three-dimensional model, the quality of multimodal data is a key factor affecting the accuracy of model construction. When collecting drilling data and geophysical data based on the single-point lithologic characteristics of the area to be modeled, interference may cause data anomalies and missing data at different depths and in different areas. Therefore, the neighboring depth difference method and anomaly detection algorithm are used to process outliers and fill missing values. In order to address the environmental noise interference in the geophysical data, the geophysical data are processed through Wiener filtering, static correction and time-depth conversion. For elevation data, the Kriging interpolation method is used to fill blank areas, and the geological mapping data needs to be further corrected in spatial position based on remote sensing data. However, the quality of remote sensing data affects the accuracy of surface connection and shallow structure depiction in the process of building a three-dimensional model. When the remote sensing data has a large deviation, it may cause a large error in the spatial deviation correction of the geological fill data, affecting the accuracy of the final three-dimensional geological model.

[0024] Based on the above analysis process, in this embodiment, for the remote sensing data acquired, the error caused by atmospheric scattering during the actual acquisition process is first considered, and the surface reflection characteristic data is obtained through radiation calibration, geometric correction and atmospheric correction to avoid the influence of atmospheric scattering interference; however, in the actual acquisition process, due to cloud cover, strip noise is generated in local areas, and electronic noise and pulse interference during data transmission cause random noise interference, which increases the error in spectral feature judgment in remote sensing data and blurs the stratum boundary, thereby affecting the accuracy of multi-source data fusion. Therefore, in order to improve the accuracy of the construction of three-dimensional geological models based on multimodal data, considering the impact of remote sensing data deviation on surface connection and shallow structure characterization during actual processing, the interference influence characteristics of the collected remote sensing data are corrected and optimized, thereby improving the accuracy of the construction of the three-dimensional geological model. The specific analysis and processing process is as follows: Step 1: First, the geological characteristics of different locations in the area to be modeled are quite different, and the interference influence characteristics of the reflection characteristics affected by different interference differences are different. Therefore, for each pixel in the multispectral remote sensing data, the reflection intensity values ​​at all wavelengths corresponding to the pixel are mapped to a two-dimensional rectangular coordinate system with the horizontal coordinate being the wavelength and the vertical coordinate being the reflection intensity value. At the same time, in this embodiment, the least squares method is used to perform curve fitting on the mapping result, and the fitting result is used as the reflection characteristic curve corresponding to each pixel; considering the consistency of the local reflection characteristics of the geological structure, the mean curve of the reflection characteristic curve of each pixel and its neighboring pixels is calculated. The mean curve is calculated by taking the mean of the reflection intensity values ​​of the pixel and its neighboring pixels at the same wavelength, and the neighboring pixels are the pixels within the neighborhood of each pixel.

[0025] Furthermore, the wavelength range of each pixel is divided, and then the difference in reflection characteristics in different bands in the local range is compared. Under the influence of interference in the data acquisition and transmission process, random high-frequency interference and strip noise may occur in the local reflected light intensity, resulting in differences in reflection characteristics in different directions and frequency bands in the local range of the geological area. Therefore, the wavelength range corresponding to each pixel is evenly divided. Specifically, in this embodiment, the number of evenly divided wavelengths is 20, that is, 20 bands are obtained.

[0026] Furthermore, taking the current band as an example, in this embodiment, the absolute value of the Pearson correlation coefficient between the reflection characteristic curve corresponding to the neighboring pixels of each pixel and the mean curve in the current band corresponding to the reflection intensity value is calculated, and used as the characteristic value of the correlation change of the reflection characteristics of each neighboring pixel compared with the overall neighborhood range. The larger the characteristic value, the more significant the correlation feature of the reflection characteristics of the pixel position in the corresponding band compared with the overall reflection characteristics of the neighborhood range, and the greater the impact on the accuracy of deviation judgment caused by the interference of the central pixel.

[0027] Further, based on the above analysis, for each pixel within the 8 neighborhoods where the reflection spectrum characteristics are analyzed, the correlation characteristics of each pixel in the domain range in different bands compared with the reflection characteristics of the overall neighborhood range are compared. The more significant the correlation characteristics are, the more significant the correlation characteristics are, indicating that the reflection intensity values ​​in different bands are deviated due to the interference of stripe noise and random noise; specifically, for the current band, the absolute value of the difference between the reflection intensity values ​​of each pixel and its neighboring pixels at the same wavelength is calculated, and the average of the absolute values ​​of the differences obtained between each pixel in the current band and its neighboring pixels at all wavelengths is taken as the difference value of the reflection characteristics of each pixel and its neighboring pixels in the current band. Based on the difference value of the reflection characteristics of the pixel in the current band and the difference in the reflection characteristics of each pixel in the domain range compared with the overall neighborhood range in different bands, the degree of deviation of the reflection characteristics of the pixel in different bands due to interference is analyzed, and the deviation coefficient of the reflection characteristics of each pixel in each band is constructed. Preferably, the specific calculation relationship is: ; in, Indicates the current band Deviation coefficient of the reflection characteristics of each pixel; Indicates the Pixel and its The difference value of the reflection characteristics of neighboring pixels in the current band; No. The first pixel The characteristic value of the change in the reflectance characteristics of the neighboring pixels compared to the entire neighborhood range; Indicates the The number of neighboring pixels of a pixel.

[0028] It can be understood that the larger the calculated deviation coefficient, the more seriously the reflection characteristics of the pixel location are affected by noise interference, based on the difference between the reflection characteristics of each pixel location and the reflection characteristics of neighboring pixels in different directions, as well as the analysis of the correlation characteristics of different pixels compared with the overall field range.

[0029] Step 2: Based on the above analysis, during the collection of multispectral remote sensing data in the area to be modeled, a comprehensive analysis is conducted on the deviation characteristics caused by interference at each location in different bands, and then the differences in multispectral reflectance intensity between different locations are analyzed; based on the analysis results, the multispectral remote sensing data are divided, and the stripe noise and random noise interference in different areas are analyzed.

[0030] Therefore, for any two pixels in the multispectral remote sensing data, by comparing the difference in reflection intensity between different pixels in different bands, the data with similar reflection characteristics are divided. Specifically, the DTW distance of the reflection intensity values ​​corresponding to the any two pixels is calculated within each band, and the Euclidean distance between the two pixels is calculated. The larger the Euclidean distance, the farther the distance between the corresponding positions of the pixels, and the larger the DTW distance, the greater the difference in the change of the reflection intensity between the corresponding pixels in the current band; further, the mean of the deviation coefficients of the reflection characteristics of the two pixels in each band is calculated. The larger the mean, the greater the difference in the reflection characteristics between the two pixels due to interference within the corresponding band. Based on the above analysis process, the judgment coefficient of the similarity of the reflection characteristics between the pixels is calculated, and the calculation relationship is: ; in, Indicates the and The judgment coefficient of the similarity of reflection characteristics between pixels; Indicates the and The Euclidean distance between pixels; Indicates the and The pixel in the DTW distance of reflection intensity values ​​within a band; Indicates the In the band and The mean of the deviation coefficients of the reflection characteristics of pixels, Indicates the The cumulative sum of the mean values ​​of the deviation coefficients of the reflection characteristics of all two pixels in a band, m is the number of preset bands, which is 20 in this embodiment, where The larger the value, the greater the influence of the reflection intensity difference between pixels in the corresponding band on the accuracy of the reflection feature similarity judgment; the larger the calculated judgment coefficient, the greater the difference in reflection characteristics between pixels in different band ranges.

[0031] Furthermore, all pixels are taken as input and the K-means clustering algorithm is used to cluster the pixels. In the clustering process, the metric distance between different pixels is the judgment coefficient of the similarity of the reflection characteristics between different pixels. The number of clusters and the maximum number of iterations are 8 and 200, respectively. The specific implementation process of the K-means clustering algorithm is well known to those skilled in the art and will not be described in detail.

[0032] Step 3: Based on the above clustering results, the pixels with similar reflection characteristics under the influence of interference in different bands during the actual acquisition process were divided. Based on the division results, the deviation of the reflection intensity data under the influence of different interference areas was analyzed, and then the filtering processing effect of the reflection intensity data in different areas was optimized.

[0033] Specifically, for the current band, for each divided cluster, firstly, the deviation coefficients of the reflection characteristics of all pixels in the cluster are subjected to probability statistics, and the probability statistical results are subjected to curve fitting by the least squares method; further, the KL divergence value between the fitting curves of the current cluster and each other cluster in the current band is calculated, and the mean of all the KL divergence values ​​is used as the difference value of the reflection intensity deviation characteristics of the pixels in the current cluster in the current band.

[0034] Furthermore, the difference values ​​of the reflection intensity deviation characteristics obtained from all clusters are normalized. In this embodiment, the Softmax function is used for normalization. Based on the normalization results, Gaussian filtering is performed on the reflection intensity data of the pixels in each cluster in different bands.

[0035] In this embodiment, specifically, for each cluster, the reflection intensity of all pixels in the cluster in each band is used as input, and a Gaussian filter is used to perform filtering and noise reduction processing on the reflection intensity data in each band; according to the influence characteristics of pixels in different regions under the interference of strip noise and random noise, the smoothing parameters of the Gaussian filtering processing of different bands are adjusted, thereby improving the filtering processing effect of the reflection intensity data in different bands in different regions, avoiding the problem of large deviation of remote sensing data caused by strip noise and random noise interference, and thus affecting the accuracy of three-dimensional geological model construction; wherein the relationship between the adjustment of Gaussian smoothing parameters of different clusters in the processing process is: , Indicates the Gaussian smoothing parameter after adjustment when Gaussian filtering is performed on the reflection intensity of the current cluster in the current band. Indicates the initial Gaussian smoothing parameter when Gaussian filtering is performed on the reflection intensity of the current cluster in the current band. The size is 2. Represents the normalized result of the difference value of the reflection intensity deviation characteristics of the pixels in the current cluster in the current band.

[0036] Among them, it can be understood that, in the area where all pixels in the cluster are located, the more significant the difference in the reflection intensity on the corresponding band under the influence of noise interference, that is, the greater the difference value of the reflection intensity deviation characteristic, the more significant the corresponding noise interference influence. Therefore, the smoothing parameter of the Gaussian filtering processing is larger to reduce the influence of noise interference; the specific Gaussian filtering processing process is well known to those skilled in the art and will not be repeated here.

[0037] Step 3: Based on the processed 3D geological model multimodal data, a 3D geological model is constructed using 3D modeling software.

[0038] Furthermore, a three-dimensional geological model is constructed based on the processed three-dimensional geological model multimodal data. Preferably, in this embodiment, the three-dimensional geological model is constructed using the processed multimodal information data for the three-dimensional geological model as input using GOCAD three-dimensional modeling software.

[0039] Specifically, a terrain surface model of the area to be modeled is first generated based on the elevation data. The terrain surface model serves as the upper boundary of the three-dimensional geological model, so that the three-dimensional geological model is accurately connected with the surface morphology. Furthermore, the fused stratigraphic interface, fault, and rock structure information are imported into the three-dimensional modeling software, and the three-dimensional morphology of each layer of stratum is constructed through surface modeling technology, and the contact relationship between the strata, such as conformable contact and unconformable contact, is clarified. The intersection relationship between faults and strata is processed through Boolean operations to ensure the accuracy of the structural logic.

[0040] Furthermore, within the model framework constructed above, this embodiment uses a collaborative Kriging interpolation algorithm to distribute discrete attribute data, such as lithology and porosity, to a three-dimensional grid to obtain an attribute model. Furthermore, the overall morphology of the constructed model is visualized using three-dimensional visualization technology, and the model accuracy is evaluated using verification drilling data. For example, the deviation between the predicted formation depth and the actual drilling depth is compared for evaluation. If the deviation meets the standard, the final three-dimensional geological model is output; if it does not meet the standard, the model is returned to the data fusion stage for re-optimization until the model meets the accuracy requirements. It should be noted that the implementer can use other existing technologies for three-dimensional model construction and evaluation to implement the construction and accuracy evaluation of the three-dimensional model, and this is not specifically limited in this embodiment.

[0041] Based on the same inventive concept as the above method, an embodiment of the present application also provides a three-dimensional geological model construction system based on multimodal data, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above-mentioned methods for constructing a three-dimensional geological model based on multimodal data are implemented.

[0042] It should be understood that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0043] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0044] The above content is only an implementation method of the present application and is not intended to limit the scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the scope of protection of the present application.

Claims

1. A method for constructing a three-dimensional geological model based on multimodal data, characterized in that: The following steps are involved: Acquire multimodal data for constructing a 3D geological model in the area to be modeled, including borehole data, geophysical data, multispectral remote sensing data, geological mapping data, and elevation data; The deviation coefficient of the reflection characteristics of each pixel in different bands is obtained by analyzing the correlation between the reflection intensity of each pixel in the local range at different bands and the difference in reflection intensity between each pixel and the pixels in the local range at the same wavelength. The judgment coefficient of the similarity of the reflection characteristics between different pixels is obtained by combining the position and reflection intensity difference between different pixels. The coefficient is used to cluster the pixels. The smoothing parameter when filtering the reflection intensity corresponding to the pixels in each cluster is adjusted according to the distribution characteristics of the deviation coefficient of the reflection characteristics of the pixels in each cluster. Based on the processed three-dimensional geological model multimodal data, the three-dimensional geological model is constructed using three-dimensional modeling software.

2. The method for constructing a three-dimensional geological model based on multimodal data according to claim 1, wherein: The deviation coefficient of the reflection characteristics of each pixel is further obtained as follows: ； in, Indicates the current band Deviation coefficient of the reflection characteristics of each pixel; Indicates the Pixel and its The difference value of the reflection characteristics of neighboring pixels in the current band; No. The first pixel The characteristic value of the change in the reflectance characteristics of the neighboring pixels compared to the entire neighborhood range; Indicates the The number of neighboring pixels of a pixel.

3. The method for constructing a three-dimensional geological model based on multimodal data according to claim 2, wherein: The reflection intensity value of each pixel in the multispectral remote sensing data at all wavelengths is mapped to a two-dimensional rectangular coordinate system with the horizontal axis as the wavelength and the vertical axis as the reflection intensity value, and the reflection characteristic curve corresponding to each pixel is obtained by curve fitting.

4. The method for constructing a three-dimensional geological model based on multimodal data according to claim 3, wherein: The mean curve of the reflection characteristic curves of each pixel and its neighboring pixels is calculated. The absolute value of the Pearson correlation coefficient between the reflection characteristic curves of each pixel's neighboring pixels and the mean curve in the current band corresponding to the reflection intensity value is calculated as the characteristic value of the associated change of the reflection characteristics of each neighboring pixel compared to the overall neighborhood range.

5. The method for constructing a three-dimensional geological model based on multimodal data according to claim 2, wherein: The absolute value of the difference between the reflection intensity values ​​of each pixel and its neighboring pixels at the same wavelength is calculated, and the average of the absolute values ​​of the difference between each pixel and its neighboring pixels in the current band at all wavelengths is taken as the difference value of the reflection characteristics of each pixel and its neighboring pixels in the current band.

6. The method for constructing a three-dimensional geological model based on multimodal data according to claim 1, wherein: The determination coefficient of the similarity of the reflection characteristics between different pixels is further obtained as follows: ； in, Indicates the and The judgment coefficient of the similarity of reflection characteristics between pixels; Indicates the and The Euclidean distance between pixels; Indicates the and The pixel in DTW distance of reflection intensity values ​​within a band; Indicates the In the band and The mean of the deviation coefficients of the reflection characteristics of pixels, Indicates the The cumulative sum of the mean values ​​of the deviation coefficients of the reflection characteristics of any two pixels in a band, m is the number of preset bands.

7. The method for constructing a three-dimensional geological model based on multimodal data according to claim 1, wherein: In the process of clustering pixels, the judgment coefficient of the similarity of reflection characteristics between different pixels is used as the metric distance between different pixels.

8. The method for constructing a three-dimensional geological model based on multimodal data according to claim 1, wherein: The adjusted Gaussian smoothing parameter when Gaussian filtering is performed on the reflection intensity of the current cluster in the current band The acquisition is further as follows: ,in, Indicates the initial Gaussian smoothing parameter when Gaussian filtering is performed on the reflection intensity of the current cluster in the current band. Represents the normalized result of the difference value of the reflection intensity deviation characteristics of the pixels in the current cluster in the current band.

9. The method for constructing a three-dimensional geological model based on multimodal data according to claim 8, wherein: For the current band, the deviation coefficients of the reflection characteristics of all pixels in the cluster are subjected to probability statistics, and the probability statistical result curve is fitted to calculate the KL divergence value between the fitting curve of the current cluster and each other cluster in the current band, and the mean of all the KL divergence values ​​is taken as the difference value of the reflection intensity deviation characteristics of the pixels in the current cluster in the current band.

10. A three-dimensional geological model construction system based on multimodal data, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method for constructing a three-dimensional geological model based on multimodal data as described in any one of claims 1 to 9 are implemented.

Images