A method and system for drawing geological distribution maps based on deep learning

Abstract

The present invention discloses a method and system for drawing a geological distribution map based on deep learning, the method comprising: obtaining geological survey data and influencing factor data of geological survey points; performing cluster analysis on the geological survey points according to the geological survey data to form multiple categories of geological survey points, and assigning values ​​to each category through the influencing factor data; selecting newly built points; obtaining a first category and a second category; generating key engineering geological information parameters of the newly built points according to the geological survey data of the first category and the influencing factor data of the second category; and drawing a geological distribution map of the area to be drawn according to all geological survey points and newly built points in the area to be drawn. The present invention discloses a method and system for drawing a geological distribution map based on deep learning, which can provide a large number of interpolation points for drawing a geological distribution map in a region, and at the same time, the interpolation point data fully considers the comprehensive influence of various environmental factors from the perspective of geological genesis, effectively improving the accuracy of drawing.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering geological survey, and in particular to a method and system for drawing geological distribution maps based on deep learning. Background Art

[0002] A geological distribution map is a thematic map used to display important geological information such as geological structure, stratigraphic lithology, geological age, and mineral resources. It is an important tool for geological research. Through geological distribution maps, people can intuitively understand the geological structural characteristics, rock combinations, stratigraphic sequences, mineral resource distribution, and other information of a region, which can provide important references for scientific research, geological exploration, and mineral resource development. In recent years, with the rapid development of new technologies such as informatization, visualization, and big data, and the continuous advancement of large-scale linear infrastructure construction such as highways, electricity, and railways, the field of engineering geology has gradually emerged with a large number of demands for drawing digital thematic geological distribution maps based on key engineering geological information (such as the thickness of the overburden layer in the region, the basic quality grade of bedrock, etc.), and the relevant results have gradually become important basic data for guiding the above-mentioned engineering construction.

[0003] In the prior art, a Chinese patent with application number 202211125859.6 discloses a method and system for drawing geological distribution maps of power transmission and transformation projects based on multi-source data. Based on digital geological maps, terrain elevation models, and satellite image multi-source data, the digital regional geological map is initialized and partitioned, and the partitions are corrected according to satellite images and terrain elevation models, and further partitioned according to micro-geomorphic partitions; after considering whether to filter and discard the data based on the degree of landform damage and digital geological map information, the coverage layer of the exploration points in the partition is counted, and the assignment processing is performed according to the partition results; the assignment calculation is performed according to the partition category in the order of the geological age of the partition from old to new. In the prior art, for areas with complex topography and insufficient field exploration that cannot be accurately mapped, multi-source data is relied upon for mapping. Although the mapping accuracy can be improved, the multi-scale and high-dimensional data brought by multi-source data are not easy to be processed by computers, and professional users are still required to manually identify, partition, and assign values ​​in multiple steps. There are still problems of complex and cumbersome processes and low efficiency. At the same time, the comprehensive influence of multiple factors such as topography, river systems, and human engineering activities on key engineering geological information (cover thickness, basic bedrock quality grade, etc.) is not considered from the perspective of geological causes. Summary of the invention

[0004] In order to at least overcome the above-mentioned deficiencies in the prior art, the purpose of the present application is to provide a method and system for drawing geological distribution maps based on deep learning.

[0005] In a first aspect, an embodiment of the present application provides a method for drawing a geological distribution map based on deep learning, comprising:

[0006] Acquire geological survey data and influencing factor data of the target area; the geological survey data includes geographic coordinate data of multiple geological survey points, soil cover thickness data and bedrock basic quality grade data; the influencing factor data includes river system data, land use type data, stratum lithology type data, ground elevation data and terrain slope data;

[0007] Performing cluster analysis on the geological survey points according to the geological survey data to form multiple categories of geological survey points, and assigning a value to each category according to the influencing factor data;

[0008] When drawing a geological distribution map for the area to be mapped in the target area, selecting a new point in the area to be mapped;

[0009] Acquire at least one category that best matches the position of the newly created point according to the coordinates of the newly created point as a first category, and acquire at least one category that best matches the newly created point according to the impact factor data corresponding to the newly created point as a second category;

[0010] Generating key engineering geological information parameters of the newly-built point according to the geological survey data of the first category and the influencing factor data of the second category;

[0011] A geological distribution map of the area to be mapped is drawn based on all the geological survey points and the newly-created points in the area to be mapped.

[0012] When the embodiment of the present application is implemented, it is necessary to first construct a relevant database of the target area in order to facilitate the subsequent construction of a geological distribution map of any area in the target area. The database needs to be constructed based on actual geological survey data and influencing factor data, wherein the geological survey data can be obtained based on drilling or geological surveys, and the influencing factor data can be obtained based on aerial photographs, field surveys or related public platform databases, which all belong to the prior art and are not limited by the embodiment of the present application. Among them, the geographic coordinate data needs to include longitude and latitude; the elevation data is generally altitude data; the basic quality grade data of the bedrock is generally the bedrock grade divided according to relevant specifications; the river system data generally includes the straight-line distance of the point from the water system and the concave or convex bank position of the river (water system) corresponding to the point; the land use type generally refers to land types such as paddy fields, dry land, forest land, and construction land; the stratum lithology type generally includes alluvial and diluvial layers, residual slope accumulation layers, sandstone, shale, mudstone, limestone and granite and other stratum lithology types.

[0013] In the embodiment of the present application, in order to realize the rapid generation of the geological distribution map of the subsequent specific area, when constructing the database, it is necessary to classify the geological survey points through deep learning. In addition to the geological survey data it has, each category also needs to be assigned with influencing factor data; it can be assigned according to the location of the geological survey point to characterize the geological survey point due to the river system, land use type, stratum lithology type, ground elevation and terrain slope. Related characteristic attributes. When drawing a geological distribution map for the area to be drawn, it is necessary to encrypt the points in the area to be drawn. The encryption method adopts the method of creating new points. The method of selecting new points can be selected according to the needs of technical personnel in this field. Generally, locations where it is difficult to carry out or have not carried out physical work such as field geological surveys and drilling will be selected. Its main function is to provide data support for the geological distribution map in addition to the existing limited geological survey points.

[0014] In order to allow the newly built points to better obtain corresponding data, the embodiment of the present application adopts a two-round matching method to select two groups of categories, among which the first category is the category that characterizes the geographical location and the newly built point most closely, which can characterize the key engineering geological information parameters of the newly built point to a large extent. These key engineering geological information parameters are similar to geological survey data, mainly including topsoil thickness data and bedrock basic quality grade data. At the same time, in the embodiment of the present application, the second category mainly characterizes the influence of hydrological information, land use, topography and lithology types on the newly built points, which is prominent in areas with relatively mature river system development characteristics. The concave bank of the river is an erosion bank, with serious soil and water loss and a thin cover layer, and the convex bank of the river is a sedimentary bank with a thick cover layer; the closer the straight-line distance to the river system, the thicker the cover layer, and the farther the distance, the thinner the cover layer; generally, the gully valley area in front of the mountain and the middle and lower reaches of the Yangtze River and the Yellow River are alluvial and diluvial strata areas, with developed groundwater, easy formation of paddy fields, thick cover layers, and high mountains, slopes and hills are dry. In the area with high and steep terrain, the water system is not developed or is in the early stage of development. It is a residual slope accumulation stratum or bedrock outcropping area with thin soil layer; in the area with high and steep terrain, large slope, soft to extremely soft stratum, the bedrock is easy to weather and soil erosion is serious, so the soil layer is thin, and the soil layer is thick in the low-lying and gentle area; in the area with strong human activities, artificial abandoned soil filling activities lead to abnormal thickening of the soil layer; in addition, for the basic quality grade of bedrock, the area with thick soil layer has a large bedrock grade, the area with hard rock (limestone, granite, etc.) has a low bedrock grade, and the area with soft rock (mudstone, shale, etc.) has a large grade. Based on the above geological genesis process, the key engineering geological information parameters of the newly built point can be assigned through the first category, and then the key engineering geological information parameters can be corrected through the second category; since the second category is used to characterize the influence of multiple parameters on the key engineering geological information parameters, it is necessary to refer to the influencing factor data for correction, such as the soil erosion coefficient corresponding to different types of strata. After completing the assignment of multiple newly created points, a geological distribution map can be drawn according to the newly created points and the geological survey points, which can be directly implemented in software such as ARGGIS, and the embodiments of this application are not repeated. Through the above technical solution, the embodiments of this application can provide a large number of interpolation points for drawing a geological distribution map in a region. At the same time, the key engineering geological information data of the above interpolation points integrates the influence of various environmental factors, is more in line with reality, and effectively improves the accuracy of drawing.

[0015] In a possible implementation, performing cluster analysis on the geological survey points according to the geological survey data to form multiple categories of geological survey points includes:

[0016] A first cluster space is constructed based on the cover thickness data and the bedrock basic quality grade data, and a second cluster space is constructed based on the geographic coordinate data;

[0017] Inputting the geological survey points into the first clustering space for cluster analysis to generate a first clustering result;

[0018] Inputting each classification in the first clustering result into the second clustering space for clustering analysis to generate a second clustering result;

[0019] The classification of all the second clustering results is used as the category of the geological survey point.

[0020] In a possible implementation, assigning a value to each of the categories using the impact factor data includes:

[0021] An attribute array is constructed for each of the categories; the attribute array is a five-element array, and the elements of the five-element array include river system data, land use type data, stratum lithology type data, ground elevation and terrain slope data.

[0022] In a possible implementation, acquiring at least one category that best matches the position of the newly created point according to the coordinates of the newly created point as the first category includes:

[0023] Calculating a first physical distance between the newly created point and the center points of all the categories according to the coordinates of the newly created point;

[0024] sorting the categories according to the first physical distance, and obtaining a plurality of the categories with the smallest first physical distance as candidate categories;

[0025] Calculate the second physical distance between all the geological survey points in the candidate category and the newly-created point;

[0026] Sorting the corresponding geological survey points according to the second physical distance, and selecting a plurality of geological survey points with the smallest second physical distance as candidate points from the sorting result;

[0027] A category corresponding to the candidate point is selected from the candidate categories as the first category.

[0028] In a possible implementation, generating the key engineering geological information parameters of the newly-built point according to the geological survey data of the first category and the influencing factor data of the second category includes:

[0029] Normalizing the first physical distance corresponding to the first category to generate a first weight value, and taking the ratio of the candidate points corresponding to the first category to the total number of candidate points as a second weight value;

[0030] The product of the first weight value and the second weight value is normalized to generate a third weight value, and weighted calculation is performed based on the third weight value and the corresponding average cover thickness data of the first category and the basic quality grade data of bedrock to generate the key engineering geological information parameters of the newly built point.

[0031] In a possible implementation, acquiring at least one category that best matches the newly created location as the second category according to the impact factor data corresponding to the newly created location includes:

[0032] From the first categories, a category that is located on the concave bank or convex bank of the river system as well as the newly-created point, is less than a preset distance from the river system, and has the same land use type as the second category is selected.

[0033] In a possible implementation, generating the key engineering geological information parameters of the newly-built point according to the geological survey data of the first category and the influencing factor data of the second category includes:

[0034] Obtaining a correction coefficient corresponding to the second category of stratum lithology type from a preset stratum correction table; the stratum lithology correction table is a correspondence between the stratum lithology type and the correction coefficient, and the easier the stratum lithology type is to weather, erode, and cause soil and water loss, the greater the correction coefficient;

[0035] The corresponding third weight value of the second category is corrected according to the correction coefficient, and the key engineering geological information parameters of the newly created point are recalculated.

[0036] In a possible implementation, generating the key engineering geological information parameters of the newly-built point according to the first category of geological survey data and the second category of influencing factor data includes:

[0037] Obtaining the stratum lithology type data, ground elevation and terrain slope in the influencing factor data of the second category as input data, and obtaining the cover thickness data and bedrock basic quality grade data corresponding to the second category as output data to retrain the preset recognition model to generate a secondary model;

[0038] Acquire the stratum lithology type, ground elevation and terrain slope data of the newly-built point as reference data, and input the reference data into the secondary model to acquire the cover soil thickness data and bedrock basic quality grade data output by the secondary model as correction data;

[0039] The corrected data is used as the key engineering geological information parameter.

[0040] In a possible implementation, the construction of the recognition model includes:

[0041] The soil cover thickness data and bedrock grade data of the geological survey points in the target area are obtained as training output data, and the stratum lithology type, ground elevation and terrain slope data corresponding to the geological survey points are obtained as training input data to train a neural network model to generate the recognition model; the data input of the recognition model is the stratum lithology type, ground elevation and terrain slope data, and the data output of the recognition model is the soil cover thickness data and bedrock basic quality grade data.

[0042] In a second aspect, the embodiment of the present application further provides a geological distribution map drawing system based on deep learning, including:

[0043] The acquisition unit is configured to acquire geological survey data and influencing factor data of the target area; the geological survey data includes geographic coordinate data of multiple geological survey points, soil cover thickness data and bedrock basic quality grade data; the influencing factor data includes river system data, land use type data, stratum lithology type data, ground elevation data and terrain slope data;

[0044] a classification unit configured to perform cluster analysis on the geological survey points according to the geological survey data to form multiple categories of geological survey points, and assign a value to each category according to the influencing factor data;

[0045] A new creation unit is configured to select a new point in the area to be mapped when drawing a geological distribution map for the area to be mapped of the target area;

[0046] a selection unit configured to obtain at least one category that best matches the position of the newly created point according to the coordinates of the newly created point as a first category, and to obtain at least one category that best matches the position of the newly created point according to the influencing factor data corresponding to the newly created point as a second category;

[0047] A calculation unit, configured to generate key engineering geological information parameters of the newly-built point according to the geological survey data of the first category and the influencing factor data of the second category;

[0048] The mapping unit is configured to draw a geological distribution map of the area to be mapped based on all the geological survey points and the newly-created points in the area to be mapped.

[0049] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0050] The present invention provides a method and system for drawing a geological distribution map based on deep learning, which can provide a large number of interpolation points for drawing a geological distribution map in a region. At the same time, the acquisition of interpolation point data fully considers the comprehensive influence of various environmental factors from the perspective of geological causes, effectively improving the accuracy of drawing. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings:

[0052] Figure 1 This is a schematic diagram of the steps of the method of the embodiment of the present application;

[0053] Figure 2 This is a schematic diagram of the distribution of geological survey points in an embodiment of the present application. DETAILED DESCRIPTION

[0054] To make the purpose, technical scheme and advantages of the embodiment of the present application clearer, the technical scheme in the embodiment of the present application will be clearly and completely described below in conjunction with the drawings in the embodiment of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the embodiment of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the present application, or remove one or more operations from the flowchart.

[0055] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0056] Please refer to Figure 1 , which is a flow chart of a method for drawing a geological distribution map based on deep learning provided in an embodiment of the present invention. The method for drawing a geological distribution map based on deep learning may specifically include the contents described in the following steps S1 to S6.

[0057] S1: Acquire geological survey data and influencing factor data of the target area; the geological survey data includes geographic coordinate data of multiple geological survey points, soil cover thickness data and bedrock basic quality grade data; the influencing factor data includes river system data, land use type data, stratum lithology type data, ground elevation data and terrain slope data;

[0058] S2: performing cluster analysis on the geological survey points according to the geological survey data to form multiple categories of geological survey points, and assigning a value to each category according to the influencing factor data;

[0059] S3: when drawing a geological distribution map for the area to be mapped in the target area, selecting a new point in the area to be mapped;

[0060] S4: acquiring at least one category that best matches the position of the newly created point according to the coordinates of the newly created point as a first category, and acquiring at least one category that best matches the newly created point according to the influencing factor data corresponding to the newly created point as a second category;

[0061] S5: generating key engineering geological information parameters of the newly-built point according to the geological survey data of the first category and the influencing factor data of the second category;

[0062] S6: Draw a geological distribution map of the area to be mapped based on all the geological survey points and the newly-created points in the area to be mapped.

[0063] When implementing the embodiment of the present application, it is necessary to first construct a relevant database of the target area in order to subsequently construct a geological distribution map of any area in the target area. The database needs to be constructed based on actual geological survey data and influencing factor data, where the geological survey data can be obtained based on drilling or geological surveys, and the influencing factor data can be obtained based on aerial photographs, field surveys or related public platform databases, which are all prior arts and are not limited by the embodiments of the present application. The geographic coordinate data needs to include longitude and latitude; the ground elevation data is generally altitude data; the cover thickness data is generally the vertical thickness data of various soil layers on the surface (sand, silt, clay, gravel, etc.); the basic quality grade data of bedrock is generally the bedrock grade classified according to relevant specifications; the water system data generally includes the straight-line distance from the geological survey point to the river system and the position of the concave bank of the river or the convex bank of the river (water system) corresponding to the point; the land use type generally refers to land types such as paddy fields, dry land, forest land, and construction land; the stratigraphic lithology types generally include alluvial and diluvial layers, residual slope accumulation layers, sandstone, shale, mudstone, limestone and other stratigraphic lithology types; the theoretical value of terrain slope data is 0~90°, which is used to indicate the degree of undulation of the ground surface.

[0064] In the embodiment of the present application, in order to realize the rapid generation of the geological distribution map of the subsequent specific area, when constructing the database, it is necessary to classify the geological survey points through deep learning. In addition to the geological survey data it has, each category also needs to be assigned with influencing factor data; it can be assigned according to the location of the geological survey point to characterize the relevant characteristic attributes of the geological survey point due to the river system, land use type, stratum lithology type, ground elevation and terrain slope. When drawing a geological distribution map for the area to be drawn, it is necessary to encrypt the points in the area to be drawn. The encryption method adopts the method of creating new points. The method of selecting new points can be selected according to the needs of technical personnel in this field. Generally, locations where it is difficult to carry out or have not carried out physical work such as field geological surveys and drilling will be selected. Its main function is to provide data support for the geological distribution map in addition to the existing limited geological survey points.

[0065] In order to allow the newly built points to better obtain corresponding data, the embodiment of the present application adopts a two-round matching method to select two groups of categories, among which the first category is the category that characterizes the geographical location and the newly built point most similarly, which can characterize the key engineering geological information parameters of the newly built point to a large extent. These key engineering geological information parameters are similar to geological survey data, mainly including soil cover thickness data and bedrock basic quality grade data. At the same time, in the embodiment of the present application, the second category mainly characterizes the influence of hydrological information, land use, topography and lithology types on the key engineering geological information of the newly built point, which is prominently manifested in areas with relatively mature river system development characteristics. The concave bank of the river is an erosion bank, with serious soil and water loss and a thin cover layer, and the convex bank of the river is a sedimentary bank with a thick cover layer; the closer the straight-line distance to the river system, the thicker the cover layer, and the farther the distance, the thinner the cover layer; generally, the gully valley area in front of the mountain and the middle and lower reaches of the Yangtze River and the Yellow River are alluvial and diluvial strata areas, where river systems and groundwater are developed, and paddy fields are easily formed, with a thick cover layer, In the high mountains, slopes and hilly dryland areas, the water system is not developed or is in the early stage of development. It is a residual slope accumulation stratum or bedrock outcropping area with a thin soil layer; in the high and steep terrain, the slope is large, the stratum lithology is relatively soft to extremely soft, the bedrock is easily weathered and soil erosion occurs, so the soil layer is thin, and the low-lying and gentle terrain area has a thick soil layer; in the area with intense human activities, artificial abandoned soil filling activities lead to abnormal thickening of the soil layer; in addition, for the basic quality grade of bedrock, the bedrock grade is large in the area with thick soil layer, the bedrock grade is low in the area with hard rock (limestone, granite, etc.), and the grade is large in the area with soft rock (mudstone, shale, etc.). Based on the above geological genesis process, the key engineering geological information parameters of the newly built points can be assigned through the first category, and then the key engineering geological information parameters can be corrected through the second category; since the second category is used to characterize the influence of multiple parameters on the key engineering geological information parameters, it is necessary to refer to the influencing factor data for correction, such as the soil erosion coefficient corresponding to different types of strata. After completing the assignment of multiple newly created points, a geological distribution map can be drawn according to the newly created points and the geological survey points, which can be directly implemented in software such as ARGGIS, and the embodiments of this application are not repeated. Through the above technical solution, the embodiments of this application can provide a large number of interpolation points for drawing a geological distribution map in a region. At the same time, the key engineering geological information data of the above interpolation points integrates the influence of various environmental factors, is more in line with reality, and effectively improves the accuracy of drawing.

[0066] In a possible implementation, performing cluster analysis on the geological survey points according to the geological survey data to form multiple categories of geological survey points includes:

[0067] A first cluster space is constructed based on the cover thickness data and the bedrock basic quality grade data, and a second cluster space is constructed based on the geographic coordinate data;

[0068] Inputting the geological survey points into the first clustering space for cluster analysis to generate a first clustering result;

[0069] Inputting each classification in the first clustering result into the second clustering space for clustering analysis to generate a second clustering result;

[0070] The classification of all the second clustering results is used as the category of the geological survey point.

[0071] When the embodiment of the present application is implemented, when constructing the database, since high-dimensional data performs poorly in the clustering algorithm and the problem of clustering non-convergence is prone to occur, the three geological survey data are planned separately in the embodiment of the present application; the first clustering space constructed with the cover thickness data and the bedrock basic quality grade data can classify the more similar data of the above two data into the same category, and the second clustering space can classify the geological survey points with more similar geographical locations in the first clustering results into the same category for the second time. For the second clustering result, it characterizes the influence of the geographical location on the subsequent newly built points, thereby forming multiple categories in the database for subsequent analysis.

[0072] In a possible implementation, assigning a value to each of the categories using the impact factor data includes:

[0073] An attribute array is constructed for each of the categories; the attribute array is a five-element array, and the elements of the five-element array include river system data, land use type data, stratum lithology type, ground elevation and terrain slope data.

[0074] In a possible implementation, acquiring at least one category that best matches the position of the newly created point according to the coordinates of the newly created point as the first category includes:

[0075] Calculating a first physical distance between the newly created point and the center points of all the categories according to the coordinates of the newly created point;

[0076] sorting the categories according to the first physical distance, and obtaining a plurality of the categories with the smallest first physical distance as candidate categories;

[0077] Calculate the second physical distance between all the geological survey points in the candidate category and the newly-created point;

[0078] Sorting the corresponding geological survey points according to the second physical distance, and selecting a plurality of geological survey points with the smallest second physical distance as candidate points from the sorting result;

[0079] A category corresponding to the candidate point is selected from the candidate categories as the first category.

[0080] When the embodiment of the present application is implemented, in the process of selecting the first category, two selection principles are followed. First, the candidate category is selected based on the distance between the category and the newly built point. Since the category is selected through cluster analysis, sometimes the overall category is close to the newly built point, but there are fewer geological survey points close to the newly built point. At this time, it is necessary to perform a secondary screening based on the distance between the geological survey points and the newly built points to ensure that the selected first category can best match the newly built point in terms of geographical location.

[0081] In a possible implementation, generating the key engineering geological parameters of the newly-built point according to the first category of geological survey data and the second category of influencing factor data includes:

[0082] Normalizing the first physical distance corresponding to the first category to generate a first weight value, and taking the ratio of the candidate points corresponding to the first category to the total number of candidate points as a second weight value;

[0083] The product of the first weight value and the second weight value is normalized to generate a third weight value, and weighted calculation is performed based on the third weight value and the corresponding average cover thickness data of the first category and the basic quality grade data of bedrock to generate the key engineering geological parameters of the newly built point.

[0084] When the embodiment of the present application is implemented, after the first category is selected, it is necessary to perform interpolation calculation on the key engineering geological information parameters of the newly built point according to the corresponding parameters of the first category. In the embodiment of the present application, the interpolation calculation takes into account the weights of two dimensions, one of which is the first physical distance, that is, the physical distance from the category to the newly built point, and the other is the proportion of the alternative points corresponding to the first category in the alternative points, the latter can effectively show the contribution of a category to the key engineering geological information parameters of the newly built point. After performing the corresponding normalization calculation, the final third weight value can be calculated for interpolation calculation. It should be understood that for bedrock grade data, the calculated interpolation data needs to be rounded, and rounding is generally performed in a rounded manner.

[0085] In a possible implementation, acquiring at least one category that best matches the newly created location as the second category according to the impact factor data corresponding to the newly created location includes:

[0086] From the first category, a category that is located on the concave bank or convex bank of the river system at the same time as the newly created point, has a straight-line distance from the river system less than a preset value, and has the same land use type is selected as the second category.

[0087] When the embodiment of the present application is implemented, the selection of the second category is mainly to strengthen the corresponding impacts brought about by river systems and land use types.

[0088] In a possible implementation, generating the key engineering geological parameters of the newly-built point according to the first category of geological survey data and the second category of influencing factor data includes:

[0089] Obtaining a correction coefficient corresponding to the second category of stratum lithology type from a preset stratum correction table; the stratum lithology correction table is a correspondence between the stratum type and the correction coefficient, and the easier the stratum lithology type is to weather, erode, and cause soil and water loss, the greater the correction coefficient;

[0090] The corresponding third weight value of the second category is corrected according to the correction coefficient, and the key engineering geological parameters of the newly created point are recalculated.

[0091] When implementing the embodiments of the present application, in many cases, a river system will not be included in an area to be mapped, and whether a river system is included is often difficult to directly determine. Therefore, in order to simplify the programming calculation process and reduce the code redundancy of secondary development, in this application, it is necessary to first calculate the result of the interpolation according to the first category and output it, and then calculate again after correcting the third weight through the second category. When correcting the third weight value, in order to fully consider the impact of the formation type on the upstream or downstream at the point of the same river system, it is necessary to customize the formation correction table in advance. The formation correction table is essentially the correspondence between different formation lithology types and correction coefficients. The correction coefficient is a parameter that is proportional to the degree of soil erosion of the formation lithology type and is greater than 1. When correcting the third weight value, it is necessary to multiply the correction coefficient by the corresponding third weight value, and re-normalize the third weight value after correction.

[0092] In a possible implementation, generating the key engineering geological parameters of the newly-built point according to the first category of geological survey data and the second category of influencing factor data includes:

[0093] Obtaining the stratum lithology type, ground elevation data and terrain slope data in the influencing factor data of the second category as input data, and obtaining the cover thickness data and bedrock basic quality grade data corresponding to the second category as output data to retrain the preset recognition model to generate a secondary model;

[0094] Acquire the stratum lithology type, ground elevation data and terrain slope data of the newly-built point as reference data, and input the reference data into the secondary model to acquire the cover soil thickness data and bedrock basic quality grade data output by the secondary model as correction data;

[0095] The corrected data is used as the key engineering geological parameters.

[0096] In a possible implementation, the construction of the recognition model includes:

[0097] The soil cover thickness data and bedrock basic quality grade data of the geological survey points in the target area are obtained as training output data, and the stratum lithology type, ground elevation data and terrain slope data corresponding to the geological survey points are obtained as training input data to train a neural network model to generate the recognition model; the data input of the recognition model is the stratum lithology type, ground elevation data and terrain slope data, and the data output of the recognition model is the soil cover thickness data and bedrock basic quality grade data.

[0098] When the embodiment of the present application is implemented, in the above embodiment, a technical solution through weight and weight correction is provided for the situation that it is not easy to obtain the corresponding stratum lithology type, ground elevation data and terrain slope data at the newly built point; and in the present embodiment, a recognition scheme based on a neural network model is also provided for the situation that it is easier to obtain the stratum lithology type, ground elevation data and terrain slope data from the relevant public platform database at the newly built point, wherein, it is necessary to pre-build the recognition model, because for the stratum lithology type, ground elevation data and terrain slope data, it will have an impact on the cover thickness data and the basic quality grade data of the bedrock, but the impact weights are different, so the parameters of the neural network model can be constructed according to these weights, and the neural network model can be trained. The trained recognition model is generally applicable to the entire area, so in order to further improve the acquisition accuracy of key engineering geological information parameters, when predicting the relevant parameters of the newly built point, it is necessary to retrain the recognition model through the second category, so that the output result can better match the river system data and land use type of the newly built point.

[0099] Based on the same inventive concept, the embodiment of the present application also provides a geological distribution map drawing system based on deep learning, including:

[0100] The acquisition unit is configured to acquire geological survey data and influencing factor data of the target area; the geological survey data includes geographic coordinate data of multiple geological survey points, soil cover thickness data and bedrock basic quality grade data; the influencing factor data includes river system data, land use type data, stratum lithology type data, ground elevation data and terrain slope data;

[0101] a classification unit configured to perform cluster analysis on the geological survey points according to the geological survey data to form multiple categories of geological survey points, and assign a value to each category according to the influencing factor data;

[0102] A new creation unit is configured to select a new point in the area to be mapped when drawing a geological distribution map for the area to be mapped of the target area;

[0103] a selection unit configured to obtain at least one category that best matches the position of the newly created point according to the coordinates of the newly created point as a first category, and to obtain at least one category that best matches the position of the newly created point according to the influencing factor data corresponding to the newly created point as a second category;

[0104] A calculation unit, configured to generate key engineering geological information parameters of the newly-built point according to the geological survey data of the first category and the influencing factor data of the second category;

[0105] The mapping unit is configured to draw a geological distribution map of the area to be mapped based on all the geological survey points and the newly-created points in the area to be mapped.

[0106] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0107] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or it can be an electrical, mechanical or other form of connection.

[0108] The units described as separate components may or may not be physically separated. As units, it is obvious that a person of ordinary skill in the art can realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0109] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0110] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a grid device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0111] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for drawing a geological distribution map, characterized in that: include: Acquire geological survey data and influencing factor data of the target area; the geological survey data includes geographic coordinate data of multiple geological survey points, soil cover thickness data and bedrock basic quality grade data; the influencing factor data includes river system data, land use type data, stratum lithology type data, ground elevation data and terrain slope data; Performing cluster analysis on the geological survey points according to the geological survey data to form multiple categories of geological survey points, and assigning a value to each category according to the influencing factor data; When drawing a geological distribution map for the area to be mapped in the target area, selecting a new point in the area to be mapped; Acquire at least one category that best matches the position of the newly created point according to the coordinates of the newly created point as a first category, and acquire at least one category that best matches the newly created point according to the impact factor data corresponding to the newly created point as a second category; Generating key engineering geological information parameters of the newly-built point according to the geological survey data of the first category and the influencing factor data of the second category; Draw a geological distribution map of the area to be mapped based on all the geological survey points and the newly-created points in the area to be mapped; Acquiring at least one category that best matches the newly created location according to the impact factor data corresponding to the newly created location as the second category includes: Select from the first category the category that is located on the concave bank or convex bank of the river system at the same time as the newly-built point, has a straight-line distance from the river system less than a preset value, and has the same land use type as the second category; Acquiring at least one category that best matches the position of the newly created point according to the coordinates of the newly created point as the first category includes: Calculating a first physical distance between the newly created point and the center points of all the categories according to the coordinates of the newly created point; sorting the categories according to the first physical distance, and obtaining a plurality of the categories with the smallest first physical distance as candidate categories; Calculate the second physical distance between all the geological survey points in the candidate category and the newly-created point; Sorting the corresponding geological survey points according to the second physical distance, and selecting a plurality of geological survey points with the smallest second physical distance as candidate points from the sorting result; Selecting a category corresponding to the candidate point from the candidate categories as the first category; The key engineering geological information parameters of the newly-built point are generated according to the geological survey data of the first category and the influencing factor data of the second category, including: Normalizing the first physical distance corresponding to the first category to generate a first weight value, and taking the ratio of the candidate points corresponding to the first category to the total number of candidate points as a second weight value; Normalizing the product of the first weight value and the second weight value to generate a third weight value, and performing weighted calculation based on the third weight value and the corresponding average soil cover thickness data of the first category and the basic quality grade data of bedrock to generate the key engineering geological information parameters of the newly built point; Obtaining a correction coefficient corresponding to the second category of lithology type from a preset lithology correction table; the lithology correction table is a correspondence between the lithology type and the correction coefficient, and the more susceptible the lithology type is to weathering, erosion and soil erosion, the greater the correction coefficient; The corresponding third weight value of the second category is corrected according to the correction coefficient, and the key engineering geological information parameters of the newly created point are recalculated.

2. A method for drawing a geological distribution map according to claim 1, characterized in that: The method of performing cluster analysis on the geological survey points according to the geological survey data to form multiple categories of geological survey points includes: A first cluster space is constructed based on the cover thickness data and the bedrock basic quality grade data, and a second cluster space is constructed based on the geographic coordinate data; Inputting the geological survey points into the first clustering space for cluster analysis to generate a first clustering result; Inputting each classification in the first clustering result into the second clustering space for clustering analysis to generate a second clustering result; The classification of all the second clustering results is used as the category of the geological survey point.

3. A method for drawing a geological distribution map according to claim 1, characterized in that: Assigning a value to each of the categories by using the impact factor data includes: An attribute array is constructed for each of the categories; the attribute array is a five-element array, and the elements of the five-element array include river system data, land use type data, stratum lithology type, ground elevation data and terrain slope data.

4. A geological distribution map drawing system using the method according to any one of claims 1 to 3, characterized in that: include: An acquisition unit configured to acquire geological survey data and influencing factor data of a target area; The geological survey data includes geographic coordinate data, soil cover thickness data and bedrock basic quality grade data of multiple geological survey points; the influencing factor data includes river system data, land use type data, stratum lithology type data, ground elevation data and terrain slope data; a classification unit configured to perform cluster analysis on the geological survey points according to the geological survey data to form multiple categories of geological survey points, and assign a value to each category according to the influencing factor data; A new creation unit is configured to select a new point in the area to be mapped when drawing a geological distribution map for the area to be mapped of the target area; a selection unit configured to obtain at least one category that best matches the position of the newly created point according to the coordinates of the newly created point as a first category, and to obtain at least one category that best matches the position of the newly created point according to the influencing factor data corresponding to the newly created point as a second category; A calculation unit, configured to generate key engineering geological information parameters of the newly-built point according to the geological survey data of the first category and the influencing factor data of the second category; The mapping unit is configured to draw a geological distribution map of the area to be mapped based on all the geological survey points and the newly-created points in the area to be mapped.

Images