Coal rock reserve assessment method, system and device, storage medium and product

Abstract

The invention provides a coal rock reserve assessment method, system and device, a storage medium and a product, and the method comprises the steps: collecting multi-source data corresponding to a to-be-assessed region, the multi-source data comprising geological exploration data, remote sensing data and geographic information system data; fusing the multi-source data corresponding to the to-be-evaluated region by adopting a multi-source data fusion algorithm to generate a fused data set corresponding to the to-be-evaluated region; inputting the fusion data set corresponding to the to-be-assessed area into a coal rock reserve assessment model, and obtaining a coal rock reserve assessment result corresponding to the to-be-assessed area output by the coal rock reserve assessment model; wherein the coal rock reserve evaluation model is established based on a machine learning model or a deep learning model, and is obtained by training based on a training set; the coal rock reserves assessment result corresponding to the to-be-assessed area comprises at least one of the following items: coal rock total reserves, reserves distribution, coal seam characteristics and coal quality parameters in the to-be-assessed area. According to the scheme, the accuracy of coal rock reserve assessment is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of coal rock reserve assessment, and in particular to a coal rock reserve assessment method, system, equipment, storage medium and product. Background Art

[0002] As a vital energy resource, coal reserve assessment is crucial for resource development planning, investment decisions, and environmental protection. Traditional coal reserve assessment methods rely primarily on geological exploration data (drilling and logging data), which suffer from a single data source and limited assessment accuracy.

[0003] A single borehole can only capture partial information, failing to fully reflect the entire coalfield. Logging data also contains errors in assessing the structure and properties of coal seams under complex geological conditions. Traditional methods lack effective integration methods for processing diverse data types, resulting in limited assessment accuracy and an inability to meet the demands of refined coal resource development and management.

[0004] Therefore, in the existing technology, the accuracy and reliability of coal reserves assessment are relatively poor. Summary of the Invention

[0005] The present invention provides a coal rock reserve assessment method, system, equipment, storage medium and product to address the defects of poor accuracy and reliability of coal rock reserve assessment in the prior art and achieve accurate assessment of coal rock reserves.

[0006] The present invention provides a coal rock reserve assessment method, comprising: Collect and obtain multi-source data corresponding to the area to be evaluated, wherein the multi-source data includes geological exploration data, remote sensing data, and geographic information system data; Using a multi-source data fusion algorithm to fuse the multi-source data corresponding to the area to be evaluated, to generate a fused data set corresponding to the area to be evaluated; The fused data set corresponding to the area to be evaluated is input into the coal reserve evaluation model to obtain the coal reserve evaluation result corresponding to the area to be evaluated output by the coal reserve evaluation model; wherein, the coal reserve evaluation model is established based on a machine learning model or a deep learning model and is trained based on a training set, and the training set includes multiple historical fused data sets and actual historical coal reserve results corresponding to each historical fused data set; the coal reserve evaluation result corresponding to the area to be evaluated includes at least one of the following: total coal reserves, reserve distribution, coal seam characteristics, and coal quality parameters in the area to be evaluated.

[0007] According to a coal reserve assessment method provided by the present invention, a multi-source data fusion algorithm is used to fuse the multi-source data corresponding to the area to be assessed to generate a fused data set corresponding to the area to be assessed, specifically including: The weighted average method is used to fuse the multi-source data corresponding to the area to be evaluated to generate a fused data set corresponding to the area to be evaluated.

[0008] According to a coal reserve assessment method provided by the present invention, a multi-source data fusion algorithm is used to fuse the multi-source data corresponding to the area to be assessed to generate a fused data set corresponding to the area to be assessed, specifically including: The principal component analysis method is used to fuse the multi-source data corresponding to the area to be evaluated to generate a fused data set corresponding to the area to be evaluated.

[0009] According to a coal reserve assessment method provided by the present invention, a multi-source data fusion algorithm is used to fuse the multi-source data corresponding to the area to be assessed to generate a fused data set corresponding to the area to be assessed, specifically including: The multi-source data corresponding to the generated area to be evaluated is input into a deep learning fusion model to obtain a fused data set corresponding to the area to be evaluated output by the deep learning fusion model.

[0010] According to a coal reserve assessment method provided by the present invention, after obtaining the coal reserve assessment result corresponding to the area to be assessed output by the coal reserve assessment model, the method further includes: According to the coal and rock reserve assessment results corresponding to the area to be assessed, a reserve distribution map and / or a reserve statistics table corresponding to the area to be assessed is generated and output.

[0011] According to a coal reserve assessment method provided by the present invention, before adopting a multi-source data fusion algorithm to fuse the multi-source data corresponding to the area to be assessed to generate a fused data set corresponding to the area to be assessed, the method further includes: Preprocessing is performed on the area to be evaluated, and the preprocessing includes at least one of the following: data cleaning, format conversion, standardization, data denoising, data interpolation, and data alignment.

[0012] The present invention also provides a coal reserve assessment system, comprising the following modules: A data acquisition module is used to acquire multi-source data corresponding to the area to be evaluated, wherein the multi-source data corresponding to the area to be evaluated includes geological exploration data, remote sensing data, and geographic information system data; A data fusion module is used to fuse the multi-source data corresponding to the area to be evaluated using a multi-source data fusion algorithm to generate a fused data set corresponding to the area to be evaluated; A reserve assessment module is used to input the fused data set corresponding to the area to be assessed into the coal reserve assessment model to obtain the coal reserve assessment result corresponding to the area to be assessed output by the coal reserve assessment model; wherein the coal reserve assessment model is established based on a machine learning model or a deep learning model and is trained based on a training set, and the training set includes multiple historical fused data sets and actual historical coal reserve results corresponding to each historical fused data set; the coal reserve assessment result corresponding to the area to be assessed includes at least one of the following: total coal reserves, reserve distribution, coal seam characteristics, and coal quality parameters in the area to be assessed.

[0013] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, any of the above-mentioned coal rock reserve assessment methods is implemented.

[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described coal rock reserve assessment methods.

[0015] The present invention also provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the above-mentioned coal reserve assessment methods.

[0016] The coal reserve assessment method, system, device, storage medium, and product provided by the present invention obtain multi-source data corresponding to the area to be assessed by collecting, the multi-source data including geological exploration data, remote sensing data, and geographic information system data; adopt a multi-source data fusion algorithm to fuse the multi-source data corresponding to the area to be assessed to generate a fused data set corresponding to the area to be assessed; input the fused data set corresponding to the area to be assessed into a coal reserve assessment model to obtain a coal reserve assessment result corresponding to the area to be assessed output by the coal reserve assessment model. This application comprehensively considers data from multiple sources related to coal reserve assessment. By integrating multi-source data such as geological exploration data, remote sensing data, and geographic information system data, it can more comprehensively reflect the distribution and characteristics of coal resources, thereby significantly improving the accuracy of coal reserve assessment. Based on the fused data set obtained by integrating multi-source data, the coal reserve assessment model is used to achieve accurate assessment of coal reserves, thereby improving the accuracy and reliability of the assessment. Therefore, the solution of this application improves the accuracy and reliability of coal reserve assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 It is a flow chart of the coal rock reserve assessment method provided by the present invention.

[0019] Figure 2 Schematic diagram of the data fusion algorithm provided by the present invention.

[0020] Figure 3 It is a structural schematic diagram of the coal rock reserve assessment system provided by the present invention.

[0021] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0022] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0023] It should be noted that the brief descriptions of terms in this application are only for the purpose of facilitating the understanding of the embodiments described below, and are not intended to limit the embodiments of this application. Unless otherwise specified, these terms should be understood according to their ordinary and usual meanings.

[0024] In the specification and claims of this application, as well as in the accompanying drawings, the terms "first," "second," and the like are used to distinguish similar or similar objects or entities, and are not necessarily intended to limit a particular order or precedence, unless otherwise indicated. It should be understood that such terms are interchangeable where appropriate, e.g., embodiments of this application can be implemented in an order other than that shown or described in the drawings or descriptions.

[0025] In addition, the terms "including" and "having" and any variations thereof are intended to cover, but not exclude, inclusion. For example, a product or device comprising a list of components is not necessarily limited to those components explicitly listed, but may include other components not explicitly listed or inherent to such products or devices. The term "module" as used in this application refers to any known or later developed hardware, software, firmware, artificial intelligence, fuzzy logic, or combination of hardware and / or software code that is capable of performing the functions associated with the element.

[0026] The following specific embodiments are used to describe in detail the technical solution of the present application and how the technical solution of the present application solves the above technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. Figure 1 and Figure 2 The coal reserve assessment method of the present invention is described.

[0027] Figure 1 This is a flow chart of the coal reserves assessment method provided by the present invention, such as Figure 1 As shown, the method includes steps 101 to 103.

[0028] Step 101: Collect and obtain multi-source data corresponding to the area to be evaluated, where the multi-source data includes geological exploration data, remote sensing data, and geographic information system data.

[0029] Step 102: Using a multi-source data fusion algorithm, fuse the multi-source data corresponding to the area to be evaluated to generate a fused data set corresponding to the area to be evaluated.

[0030] Step 103: Input the fused data set corresponding to the area to be evaluated into the coal reserve evaluation model to obtain the coal reserve evaluation result corresponding to the area to be evaluated output by the coal reserve evaluation model.

[0031] Among them, the coal rock reserve assessment model is established based on a machine learning model or a deep learning model and is obtained through training based on a training set. The training set includes multiple historical fusion data sets and the actual historical coal rock reserves results corresponding to each historical fusion data set; the coal rock reserve assessment results corresponding to the area to be assessed include at least one of the following: total coal rock reserves, reserve distribution, coal seam characteristics, and coal quality parameters in the area to be assessed.

[0032] In practical applications, the execution entity of the coal reserve assessment method can be a coal reserve assessment system. There are many ways to implement the coal reserve assessment system. For example, it can be implemented through a computer program, such as application software, or a chip. It can also be implemented as a medium storing the relevant computer program, such as a USB flash drive or cloud storage device. Alternatively, it can be implemented through a physical device that integrates or installs the relevant computer program, such as a server or smart device.

[0033] For example, a coal reserve assessment system is used as the execution body of the coal reserve assessment method for detailed description below.

[0034] Specifically, step 101 includes: collecting and obtaining multi-source data corresponding to the area to be evaluated, where the multi-source data includes geological exploration data, remote sensing data, and geographic information system data.

[0035] Geological exploration data refers to data related to underground geological structure and coal resources obtained through geological exploration. Geological exploration data directly reflects key information such as coal seam thickness, dip, and coal quality.

[0036] In practical applications, the coal reserve assessment system collects geological exploration data using geological exploration equipment. Geological exploration equipment refers to various specialized devices used to obtain underground geological information and resource distribution. For example, geological exploration equipment can include drilling equipment and well logging equipment.

[0037] Remote sensing data refers to information about the Earth's surface acquired by remote sensing satellites. Remote sensing data can provide information about surface coverage and topography over a wide area, helping to indirectly infer the distribution of underground coal resources. In practical applications, coal reserve assessment systems acquire remote sensing data using sensors carried by remote sensing satellites.

[0038] Geographic Information System (GIS) data refers to geospatial data processed and analyzed using GIS software. GIS data is represented in the form of maps, including topographic maps, geological maps, and land use maps, used to describe the distribution and relationships of geographic space.

[0039] In this embodiment, the format of multi-source data is not specifically limited, and the multi-source data can be text, numerical values, charts, images, vector graphics, etc. In one example, geological exploration data is a geological cross-section, remote sensing data is a remote sensing image, and geographic information system data is a topographic map.

[0040] It is understandable that collecting data from multiple sources related to coal reserve assessment and integrating multi-source data such as geological exploration data, remote sensing data, and geographic information system data can more comprehensively reflect the distribution and characteristics of coal resources, thereby significantly improving the accuracy of coal reserve assessment.

[0041] Furthermore, the coal reserve assessment system fuses multi-source data to obtain a fused data set.

[0042] Specifically, step 102 includes: using a multi-source data fusion algorithm to fuse the multi-source data corresponding to the area to be evaluated, and generating a fused data set corresponding to the area to be evaluated.

[0043] In this embodiment, fusing multi-source data corresponding to the area to be evaluated refers to integrating and processing data from different sources to generate a comprehensive fused data set so as to more comprehensively and accurately reflect the characteristics of the area to be evaluated.

[0044] Optionally, in a possible implementation manner, the above step 102 specifically includes: The weighted average method is used to fuse the multi-source data corresponding to the area to be evaluated and generate a fused dataset corresponding to the area to be evaluated.

[0045] In practical applications, a comprehensive fused dataset is generated by assigning different weights to each data source and then calculating the weighted average. In the weighted average method, the weight of each data source reflects the importance and reliability of the data source in the fusion process.

[0046] First, determine the weight of each data source. The weight of each data source can be determined based on the reliability of the data source, its relevance to coal reserves assessment, the coverage of the data source, and the experience of experts in this field.

[0047] Furthermore, for each data point, a weighted average is calculated based on the determined weight. The weighted averages of all data points are combined into a comprehensive fused dataset. This fused dataset can be used for subsequent coal reserve assessment.

[0048] For example, multiple data sources include three data sources, geological exploration data is coal seam thickness , remote sensing data is vegetation index , GIS data is terrain slope The weight corresponding to the geological exploration data is , the weight corresponding to the remote sensing data is And the weight corresponding to GIS data is For a certain data point, if the coal seam thickness , remote sensing data is vegetation index , GIS data is terrain slope , then the fusion value of the data point is: In this implementation, multi-source data is integrated through a weighted average method. The calculation process is simple and easy to implement. Weights can be adjusted based on specific needs to adapt to different application scenarios. This method is suitable for large-scale data processing and offers fast computational speed. By using the weighted average method, multi-source data can be integrated into a comprehensive, fused dataset, providing more comprehensive and accurate data support for coal reserve assessment.

[0049] Optionally, in a possible implementation manner, the above step 102 specifically includes: The principal component analysis method is used to fuse the multi-source data corresponding to the area to be evaluated and generate a fused data set corresponding to the area to be evaluated.

[0050] Principal Component Analysis (PCA) is a statistical method used to transform data into a new coordinate system through linear transformation, maximizing the variance of the data along the coordinate axes. The main purpose of PCA is to extract the principal components of the data, reduce the data dimension, and remove redundant information.

[0051] Specifically, the multi-source data corresponding to the area to be evaluated are combined into a data matrix. Assume that n data points, each with m Features, data matrix X The dimension is .

[0052] Furthermore, the data matrix is ​​calculated X The covariance matrix of . Covariance matrix It reflects the correlation between data features.

[0053] Furthermore, the covariance matrix is ​​calculated The eigenvalues ​​and eigenvectors of . The eigenvalues ​​represent the variance of each principal component, and the eigenvectors represent the direction of the principal component.

[0054] Furthermore, the front is selected according to the size of the eigenvalue. k The number of principal components usually chosen k The cumulative variance contribution rate should reach a certain proportion (such as 95%).

[0055] Furthermore, the selected k The eigenvectors form the projection matrix P , the dimension is m ×k .

[0056] Furthermore, the original data matrix X Projected into the new coordinate system, the reduced-dimensional data matrix is ​​obtained Y .

[0057] Furthermore, the reduced data matrix Y As a fused dataset, each data point is represented in the new coordinate system as k The value of the principal component.

[0058] In this implementation, principal component analysis (PCA) is used to fuse multi-source data corresponding to the area under assessment, generating a fused dataset for the area under assessment. PCA reduces data dimensionality and removes redundant information by extracting principal components. PCA can also reveal key trends in data, enhancing data interpretability. Therefore, PCA can fuse multi-source data into a comprehensive fused dataset, providing more comprehensive and accurate data support for coal reserve assessment.

[0059] Optionally, in a possible implementation manner, the above step 102 specifically includes: The multi-source data corresponding to the area to be evaluated are input into the deep learning fusion model to obtain the fused data set corresponding to the area to be evaluated output by the deep learning fusion model.

[0060] Among them, deep learning fusion models utilize deep learning techniques to integrate and process data from multiple sources. They automatically learn correlations within the data and generate comprehensive feature representations, thereby improving data utilization efficiency and analytical effectiveness. Deep learning fusion models offer significant advantages when processing multi-source data, especially when complex nonlinear relationships exist between data features.

[0061] For example, a deep learning fusion model can be a convolutional neural network (CNN), a recurrent neural network (RNN), a multilayer perceptron (MLP), or a hybrid model of multiple networks. In practical applications, multi-source data is input into a trained deep learning fusion model to generate a fused dataset output by the deep learning fusion model.

[0062] In this implementation, the deep learning model automatically learns correlations in the data, reducing the workload of manual feature engineering. Multi-source data corresponding to the area to be assessed is fed into the deep learning fusion model, which then outputs a fused dataset corresponding to the area to be assessed, providing more comprehensive and accurate data support for coal reserve assessment.

[0063] In addition, in a possible implementation manner, before step 102, the coal reserves assessment method further includes: The evaluation area is preprocessed, and the preprocessing includes at least one of the following: data cleaning, format conversion, standardization, data denoising, data interpolation, data alignment, and feature extraction.

[0064] Data cleaning involves removing errors, duplications, or incomplete records from data to ensure its accuracy and completeness. For example, in coal reserve assessment, data cleaning can remove cloud cover from remote sensing images, fill in missing values ​​in geological exploration data, and delete erroneous measurement records.

[0065] Format conversion refers to converting data from different sources into a unified format for subsequent processing. For example, in coal reserve assessment, it may be necessary to convert geological exploration data (such as drill logs) from text to numerical format, convert remote sensing data from image format to matrix format, and convert GIS data from a geographic coordinate system to a unified coordinate system.

[0066] Normalization involves converting data to a uniform scale, eliminating dimensional differences between different data sources. For example, in coal reserve assessment, normalization can convert data of varying dimensions, such as coal seam thickness, ash content, and vegetation index, into values ​​between 0 and 1, facilitating subsequent integration and analysis.

[0067] Data denoising is used to remove noise from data and improve the signal-to-noise ratio. For example, in coal reserve assessment, methods such as median filtering and Gaussian filtering can be used to remove noise from remote sensing images, while smoothing methods can be used to remove random fluctuations in geological exploration data.

[0068] Data interpolation is used to fill missing values ​​in data and ensure data integrity. For example, in coal reserve assessment, methods such as linear interpolation, polynomial interpolation, or kriging interpolation can be used to fill missing values ​​in geological exploration data and fill blank areas in remote sensing data.

[0069] Data alignment is used to align data from different sources in time and space, ensuring they have consistent coordinate systems and resolutions. For example, in coal reserve assessment, geological exploration data, remote sensing data, and GIS data need to be spatially aligned to ensure they have the same coordinate system and resolution. For example, the resolution of remote sensing images can be adjusted to match that of geological exploration data, and the coordinate system of GIS data can be converted to match that of remote sensing data.

[0070] Feature extraction refers to extracting key data related to coal reserve assessment from multi-source data. For example, information such as coal rock thickness and buried layers can be extracted from geological data, vegetation index and surface temperature can be extracted from remote sensing data, and terrain and landform features can be extracted from GIS data.

[0071] In practical applications, the coal reserve assessment system collects and preprocesses multi-source data corresponding to the area to be assessed. Furthermore, the system uses a multi-source data fusion algorithm to fuse the pre-processed multi-source data and generate a fused dataset corresponding to the area to be assessed.

[0072] It should be noted that the above embodiments can be implemented in combination or individually. Figure 2 This is a schematic diagram of the data fusion algorithm provided by the present invention, such as Figure 2 As shown in the figure, the multi-source data includes geological data, remote sensing data, and GIS data. Preprocessing of the multi-source data is performed to extract information such as coal rock thickness and buried layers from the geological data, vegetation index and surface temperature from the remote sensing data, and terrain and landform features from the GIS data. Furthermore, a multi-source data fusion algorithm is used to fuse the multi-source data corresponding to the assessment area to generate a fused dataset for the assessment area.

[0073] Furthermore, the coal reserve assessment system performs coal reserve assessment based on the fused data set corresponding to the area to be assessed to obtain a coal reserve assessment result corresponding to the area to be assessed.

[0074] Specifically, step 103 includes: inputting the fused data set corresponding to the area to be evaluated into the coal reserve evaluation model, and obtaining the coal reserve evaluation result corresponding to the area to be evaluated output by the coal reserve evaluation model.

[0075] In this embodiment, the coal reserve assessment result corresponding to the area to be assessed includes at least one of the following: total coal reserves, reserve distribution, coal seam characteristics, and coal quality parameters in the area to be assessed.

[0076] The total coal reserves within the area to be assessed refer to the total amount of coal resources within the area. In practical applications, total coal reserves are fundamental data for assessing the development potential and economic value of coal resources, and are crucial for resource planning and investment decisions.

[0077] The reserve distribution within the area under evaluation describes the geographic distribution of coal resources within the area under evaluation, typically presented as a reserve distribution map. For example, reserve distribution includes both geographic distribution and depth distribution. Geographic distribution refers to the distribution of coal resources at different geographic locations. Depth distribution refers to the distribution of coal resources at different depths. In practical applications, reserve distribution within the area under evaluation can help determine the optimal mining areas and sequence, thereby optimizing resource development plans.

[0078] The coal seam characteristics within the area to be assessed are used to describe the physical and geological characteristics of the coal seams within the area to be assessed. These characteristics directly affect coal mining and utilization. For example, coal seam characteristics include coal seam thickness, coal seam dip, and coal seam continuity. Coal seam thickness refers to the vertical thickness of the coal seam, coal seam dip refers to the angle of inclination of the coal seam, and coal seam continuity refers to the spatial continuity of the coal seam, such as the presence of faults or folds.

[0079] Coal quality parameters within the assessed region describe the quality and combustion characteristics of the coal. These parameters directly impact the market value and utilization of the coal. Examples include ash content and sulfur content. In practical applications, coal quality parameters are crucial for determining coal's intended use (e.g., power generation, coking, etc.) and assessing its environmental impact.

[0080] In this embodiment, the coal reserve assessment model is established based on a machine learning model or a deep learning model and is obtained through training based on a training set. The training set includes multiple historical fusion data sets and the actual historical coal reserves results corresponding to each historical fusion data set.

[0081] For example, the coal reserve assessment model can be based on a machine learning model, such as a support vector machine (SVM), random forest (RF), K-nearest neighbors (KNN), linear regression (LR), etc. For example, the coal reserve assessment model can also be a deep learning model, such as a convolutional neural network (CNN), a recurrent neural network (RNN), a long short-term memory network (LSTM), a gated recurrent unit (GRU), a multi-layer perceptron (MLP), etc.

[0082] In practical applications, it is necessary to pre-build and train a coal reserve assessment model. For example, in one possible implementation, before step 101, the method further includes: Build an initial coal reserve assessment model based on machine learning models or deep learning models; Collect multi-source data and historical coal reserves in multiple assessment areas over a historical period; A multi-source data fusion algorithm is used to fuse the multi-source data in each assessment area to generate a historical fusion data set corresponding to each assessment area; The actual results of historical coal reserves in each assessment area are used as the actual results of historical coal reserves corresponding to the historical fusion data set corresponding to the assessment area to construct a data set; the data set includes multiple historical fusion data sets and the actual results of historical coal reserves corresponding to each historical fusion data set; The training set is divided into a training set, a test set and a validation set, and the initial coal rock reserve assessment model is trained based on the training set, the test set and the validation set to obtain a coal rock reserve assessment model.

[0083] It can be understood that the fused data set obtained by integrating multi-source data can realize the accurate assessment of coal reserves through the coal reserves assessment model, thereby improving the accuracy and reliability of the assessment.

[0084] In addition, in a possible implementation manner, after step 103, the coal reserves assessment method further includes: Based on the coal and rock reserve assessment results corresponding to the area to be assessed, a reserve distribution map and / or reserve statistics table corresponding to the area to be assessed is generated and output.

[0085] In this embodiment, the fused data set corresponding to the area to be evaluated is input into the coal reserve evaluation model. After obtaining the coal reserve evaluation results corresponding to the area to be evaluated output by the coal reserve evaluation model, the reserve distribution map and / or reserve statistics table corresponding to the area to be evaluated are generated and output based on the coal reserve evaluation results corresponding to the area to be evaluated. This can realize the visualization of the coal reserve evaluation results, provide a comprehensive scientific basis for the subsequent development, planning and management of coal resources, and help users better understand and utilize coal resources.

[0086] The coal reserve assessment method provided in this embodiment acquires multi-source data corresponding to the area to be assessed, including geological exploration data, remote sensing data, and geographic information system data. A multi-source data fusion algorithm is used to fuse the multi-source data corresponding to the area to be assessed, generating a fused dataset corresponding to the area to be assessed. The fused dataset corresponding to the area to be assessed is then input into a coal reserve assessment model, resulting in a coal reserve assessment result corresponding to the area to be assessed, which is output by the coal reserve assessment model. This embodiment comprehensively considers data from multiple sources related to coal reserve assessment. By integrating multiple sources, such as geological exploration data, remote sensing data, and geographic information system data, it can more comprehensively reflect the distribution and characteristics of coal resources, thereby significantly improving the accuracy of coal reserve assessment. Based on the fused dataset obtained through multi-source data integration, the coal reserve assessment model enables precise coal reserve assessment, improving the accuracy and reliability of the assessment. Therefore, the solution of this embodiment improves the accuracy and reliability of coal reserve assessment.

[0087] The coal reserve assessment system provided by the present invention is described below. The coal reserve assessment system described below and the coal reserve assessment method described above can be referenced to each other.

[0088] Figure 3 This is a schematic diagram of the structure of the coal reserve assessment system provided by the present invention. Figure 3 As shown, the coal rock reserve assessment system includes: a data acquisition module 31, a data fusion module 32 and a reserve assessment module 33.

[0089] The data acquisition module 31 is used to acquire multi-source data corresponding to the area to be evaluated, and the multi-source data includes geological exploration data, remote sensing data, and geographic information system data.

[0090] The data fusion module 32 is used to fuse the multi-source data corresponding to the area to be evaluated using a multi-source data fusion algorithm to generate a fused data set corresponding to the area to be evaluated.

[0091] The reserve assessment module 33 is used to input the fused data set corresponding to the area to be assessed into the coal rock reserve assessment model to obtain the coal rock reserve assessment result corresponding to the area to be assessed output by the coal rock reserve assessment model.

[0092] Among them, the coal rock reserve assessment model is established based on a machine learning model or a deep learning model and is obtained through training based on a training set. The training set includes multiple historical fusion data sets and the actual historical coal rock reserves results corresponding to each historical fusion data set; the coal rock reserve assessment results corresponding to the area to be assessed include at least one of the following: total coal rock reserves, reserve distribution, coal seam characteristics, and coal quality parameters in the area to be assessed.

[0093] In practical applications, the coal reserve assessment system can be implemented in a variety of ways. For example, it can be implemented through a computer program, such as application software, or a chip. It can also be implemented as a medium storing the relevant computer program, such as a USB flash drive or cloud storage device. Alternatively, it can be implemented through a physical device that integrates or installs the relevant computer program, such as a server or smart device.

[0094] Specifically, the data acquisition module 31 is used to acquire multi-source data corresponding to the area to be evaluated, where the multi-source data includes geological exploration data, remote sensing data, and geographic information system data.

[0095] Geological exploration data refers to data related to underground geological structure and coal resources obtained through geological exploration. Geological exploration data directly reflects key information such as coal seam thickness, dip, and coal quality.

[0096] In practical applications, the coal reserve assessment system collects geological exploration data using geological exploration equipment. Geological exploration equipment refers to various specialized devices used to obtain underground geological information and resource distribution. For example, geological exploration equipment can include drilling equipment and well logging equipment.

[0097] Remote sensing data refers to information about the Earth's surface acquired by remote sensing satellites. Remote sensing data can provide information about surface coverage and topography over a wide area, helping to indirectly infer the distribution of underground coal resources. In practical applications, coal reserve assessment systems acquire remote sensing data using sensors carried by remote sensing satellites.

[0098] Geographic Information System (GIS) data refers to geospatial data processed and analyzed using GIS software. GIS data is represented in the form of maps, including topographic maps, geological maps, and land use maps, used to describe the distribution and relationships of geographic space.

[0099] In this embodiment, the format of multi-source data is not specifically limited, and the multi-source data can be text, numerical values, charts, images, vector graphics, etc. In one example, geological exploration data is a geological cross-section, remote sensing data is a remote sensing image, and geographic information system data is a topographic map.

[0100] It is understandable that collecting data from multiple sources related to coal reserve assessment and integrating multi-source data such as geological exploration data, remote sensing data, and geographic information system data can more comprehensively reflect the distribution and characteristics of coal resources, thereby significantly improving the accuracy of coal reserve assessment.

[0101] Furthermore, the data fusion module 32 fuses the multi-source data to obtain a fused data set.

[0102] Specifically, the data fusion module 32 is configured to fuse the multi-source data corresponding to the area to be evaluated using a multi-source data fusion algorithm to generate a fused data set corresponding to the area to be evaluated.

[0103] In this embodiment, fusing multi-source data corresponding to the area to be evaluated refers to integrating and processing data from different sources to generate a comprehensive fused data set so as to more comprehensively and accurately reflect the characteristics of the area to be evaluated.

[0104] Optionally, in a possible implementation manner, the data fusion module 32 is specifically configured to: The weighted average method is used to fuse the multi-source data corresponding to the area to be evaluated and generate a fused dataset corresponding to the area to be evaluated.

[0105] In practical applications, a comprehensive fused dataset is generated by assigning different weights to each data source and then calculating the weighted average. In the weighted average method, the weight of each data source reflects the importance and reliability of the data source in the fusion process.

[0106] First, the data fusion module 32 determines the weight of each data source. The weight of each data source can be determined based on the reliability of the data source, its relevance to coal reserve assessment, the coverage of the data source, and the experience of experts in this field.

[0107] Furthermore, for each data point, the data fusion module 32 calculates a weighted average value based on the determined weights. The weighted average values ​​of all data points are combined into a comprehensive fused data set. This fused data set can be used for subsequent coal reserve assessment.

[0108] In this embodiment, data fusion module 32 integrates multi-source data using a weighted averaging method. This method is simple and easy to implement. Weights can be adjusted based on specific needs to accommodate different application scenarios. This method is suitable for large-scale data processing and offers fast computational speed. By using this method, multi-source data can be integrated into a comprehensive, fused dataset, providing more comprehensive and accurate data support for coal reserve assessment.

[0109] Optionally, in a possible implementation manner, the data fusion module 32 is specifically configured to: The principal component analysis method is used to fuse the multi-source data corresponding to the area to be evaluated and generate a fused data set corresponding to the area to be evaluated.

[0110] Principal component analysis (PCA) is a statistical method used to transform data into a new coordinate system through linear transformation, so that the variance of the data along the coordinate axes is maximized in this new coordinate system. The main purpose of PCA is to extract the main components of the data, reduce the data dimension, and remove redundant information.

[0111] Specifically, the multi-source data corresponding to the area to be evaluated are combined into a data matrix. Assume that n data points, each with m Features, data matrix X The dimension is .

[0112] Furthermore, the data matrix is ​​calculated X The covariance matrix of . Covariance matrix It reflects the correlation between data features.

[0113] Furthermore, the covariance matrix is ​​calculated The eigenvalues ​​and eigenvectors of . The eigenvalues ​​represent the variance of each principal component, and the eigenvectors represent the direction of the principal component.

[0114] Furthermore, the front is selected according to the size of the eigenvalue. k The number of principal components usually chosen k The cumulative variance contribution rate should reach a certain proportion (such as 95%).

[0115] Furthermore, the selected k The eigenvectors form the projection matrix P , the dimension is m × k .

[0116] Furthermore, the original data matrix X Projected into the new coordinate system, the reduced-dimensional data matrix is ​​obtained Y .

[0117] Furthermore, the reduced data matrix Y As a fused dataset, each data point is represented in the new coordinate system as k The value of the principal component.

[0118] In this embodiment, data fusion module 32 uses principal component analysis to fuse multi-source data corresponding to the area to be assessed, generating a fused dataset corresponding to the area to be assessed. Principal component analysis reduces data dimensionality and removes redundant information by extracting principal components. Furthermore, principal component analysis can reveal the primary direction of variation in the data, enhancing data interpretability. Therefore, principal component analysis can fuse multi-source data into a comprehensive fused dataset, providing more comprehensive and accurate data support for coal reserve assessment.

[0119] Optionally, in a possible implementation manner, the data fusion module 32 is specifically configured to: The multi-source data corresponding to the area to be evaluated are input into the deep learning fusion model to obtain the fused data set corresponding to the area to be evaluated output by the deep learning fusion model.

[0120] Among them, deep learning fusion models utilize deep learning techniques to integrate and process data from multiple sources. They automatically learn correlations within the data and generate comprehensive feature representations, thereby improving data utilization efficiency and analytical effectiveness. Deep learning fusion models offer significant advantages when processing multi-source data, especially when complex nonlinear relationships exist between data features.

[0121] For example, a deep learning fusion model can be a convolutional neural network (CNN), a recurrent neural network (RNN), a multi-layer perceptron (MLP), or a hybrid model of multiple networks. In practical applications, multi-source data is fed into a trained deep learning fusion model to generate a fused dataset.

[0122] In this embodiment, the deep learning model can automatically learn correlations in the data, reducing the workload of manual feature engineering. Data fusion module 32 generates multi-source data corresponding to the area to be assessed and inputs it into the deep learning fusion model. The deep learning fusion model then outputs a fused dataset corresponding to the area to be assessed, providing more comprehensive and accurate data support for coal reserve assessment.

[0123] In addition, in a possible implementation, the above-mentioned coal reserve assessment system further includes: The preprocessing module is used to perform preprocessing on the area to be evaluated. The preprocessing includes at least one of the following: data cleaning, format conversion, standardization, data denoising, data interpolation, data alignment, and feature extraction.

[0124] Data cleaning involves removing errors, duplications, or incomplete records from data to ensure its accuracy and completeness. For example, in coal reserve assessment, data cleaning can remove cloud cover from remote sensing images, fill in missing values ​​in geological exploration data, and delete erroneous measurement records.

[0125] Format conversion refers to converting data from different sources into a unified format for subsequent processing. For example, in coal reserve assessment, it may be necessary to convert geological exploration data (such as drill logs) from text to numerical format, convert remote sensing data from image format to matrix format, and convert GIS data from a geographic coordinate system to a unified coordinate system.

[0126] Normalization involves converting data to a uniform scale, eliminating dimensional differences between different data sources. For example, in coal reserve assessment, normalization can convert data of varying dimensions, such as coal seam thickness, ash content, and vegetation index, into values ​​between 0 and 1, facilitating subsequent integration and analysis.

[0127] Data denoising is used to remove noise from data and improve the signal-to-noise ratio. For example, in coal reserve assessment, methods such as median filtering and Gaussian filtering can be used to remove noise from remote sensing images, while smoothing methods can be used to remove random fluctuations in geological exploration data.

[0128] Data interpolation is used to fill missing values ​​in data and ensure data integrity. For example, in coal reserve assessment, methods such as linear interpolation, polynomial interpolation, or kriging interpolation can be used to fill missing values ​​in geological exploration data and fill blank areas in remote sensing data.

[0129] Data alignment is used to align data from different sources in time and space, ensuring they have consistent coordinate systems and resolutions. For example, in coal reserve assessment, geological exploration data, remote sensing data, and GIS data need to be spatially aligned to ensure they have the same coordinate system and resolution. For example, the resolution of remote sensing images can be adjusted to match that of geological exploration data, and the coordinate system of GIS data can be converted to match that of remote sensing data.

[0130] Feature extraction refers to extracting key data related to coal reserve assessment from multi-source data. For example, information such as coal rock thickness and buried layers can be extracted from geological data, vegetation index and surface temperature can be extracted from remote sensing data, and terrain and landform features can be extracted from GIS data.

[0131] In practical applications, the coal reserve assessment system collects and preprocesses multi-source data corresponding to the area to be assessed. Furthermore, the system uses a multi-source data fusion algorithm to fuse the pre-processed multi-source data and generate a fused dataset corresponding to the area to be assessed.

[0132] Furthermore, the reserve assessment module 33 performs coal and rock reserve assessment based on the fused data set corresponding to the area to be assessed to obtain a coal and rock reserve assessment result corresponding to the area to be assessed.

[0133] Specifically, the reserve assessment module 33 is used to input the fused data set corresponding to the area to be assessed into the coal reserve assessment model to obtain the coal reserve assessment result corresponding to the area to be assessed output by the coal reserve assessment model.

[0134] In this embodiment, the coal reserve assessment result corresponding to the area to be assessed includes at least one of the following: total coal reserves, reserve distribution, coal seam characteristics, and coal quality parameters in the area to be assessed.

[0135] The total coal reserves within the area to be assessed refer to the total amount of coal resources within the area. In practical applications, total coal reserves are fundamental data for assessing the development potential and economic value of coal resources, and are crucial for resource planning and investment decisions.

[0136] The reserve distribution within the area under evaluation describes the geographic distribution of coal resources within the area under evaluation, typically presented as a reserve distribution map. For example, reserve distribution includes both geographic distribution and depth distribution. Geographic distribution refers to the distribution of coal resources at different geographic locations. Depth distribution refers to the distribution of coal resources at different depths. In practical applications, reserve distribution within the area under evaluation can help determine the optimal mining areas and sequence, thereby optimizing resource development plans.

[0137] The coal seam characteristics within the area to be assessed are used to describe the physical and geological characteristics of the coal seams within the area to be assessed. These characteristics directly affect coal mining and utilization. For example, coal seam characteristics include coal seam thickness, coal seam dip, and coal seam continuity. Coal seam thickness refers to the vertical thickness of the coal seam, coal seam dip refers to the angle of inclination of the coal seam, and coal seam continuity refers to the spatial continuity of the coal seam, such as the presence of faults or folds.

[0138] Coal quality parameters within the assessed region describe the quality and combustion characteristics of the coal. These parameters directly impact the market value and utilization of the coal. Examples include ash content and sulfur content. In practical applications, coal quality parameters are crucial for determining coal's intended use (e.g., power generation, coking, etc.) and assessing its environmental impact.

[0139] In this embodiment, the coal reserve assessment model is established based on a machine learning model or a deep learning model and is obtained through training based on a training set. The training set includes multiple historical fusion data sets and the actual historical coal reserves results corresponding to each historical fusion data set.

[0140] For example, the coal reserve assessment model can be based on a machine learning model, such as a support vector machine (SVM), random forest (RF), K-nearest neighbor (KNN), linear regression (LR), etc. For example, the coal reserve assessment model can also be a deep learning model, such as a convolutional neural network (CNN), a recurrent neural network (RNN), a long short-term memory network (LSTM), a gated recurrent unit (GRU), a multi-layer perceptron (MLP), etc.

[0141] In practical applications, it is necessary to pre-build and train a coal reserve assessment model. For example, in one possible implementation, the system further includes: a training module; the training module is used to: Build an initial coal reserve assessment model based on machine learning models or deep learning models; Collect multi-source data and historical coal reserves in multiple assessment areas over a historical period; A multi-source data fusion algorithm is used to fuse the multi-source data in each assessment area to generate a historical fusion data set corresponding to each assessment area; The actual results of historical coal reserves in each assessment area are used as the actual results of historical coal reserves corresponding to the historical fusion data set corresponding to the assessment area to construct a data set; the data set includes multiple historical fusion data sets and the actual results of historical coal reserves corresponding to each historical fusion data set; The training set is divided into a training set, a test set and a validation set, and the initial coal rock reserve assessment model is trained based on the training set, the test set and the validation set to obtain a coal rock reserve assessment model.

[0142] It can be understood that the fused data set obtained by integrating multi-source data can realize the accurate assessment of coal reserves through the coal reserves assessment model, thereby improving the accuracy and reliability of the assessment.

[0143] In addition, in a possible implementation, the above-mentioned coal reserve assessment system further includes: The output module is used to generate and output a reserve distribution map and / or reserve statistics table corresponding to the area to be evaluated based on the coal and rock reserve evaluation results corresponding to the area to be evaluated.

[0144] In this embodiment, the reserve assessment module 33 inputs the fused data set corresponding to the area to be assessed into the coal rock reserve assessment model. After obtaining the coal rock reserve assessment result corresponding to the area to be assessed output by the coal rock reserve assessment model, the output module generates and outputs the reserve distribution map and / or reserve statistics table corresponding to the area to be assessed based on the coal rock reserve assessment result corresponding to the area to be assessed, which can realize the visualization of the coal rock reserve assessment results, provide a comprehensive scientific basis for the subsequent development, planning and management of coal resources, and help users better understand and utilize coal resources.

[0145] In the coal reserve assessment system provided by the present invention, a data acquisition module acquires multi-source data corresponding to the area to be assessed, including geological exploration data, remote sensing data, and geographic information system data. A data fusion module employs a multi-source data fusion algorithm to fuse the multi-source data corresponding to the area to be assessed, generating a fused dataset corresponding to the area to be assessed. The reserve assessment module inputs the fused dataset corresponding to the area to be assessed into a coal reserve assessment model, obtaining a coal reserve assessment result corresponding to the area to be assessed, as output by the coal reserve assessment model. This embodiment comprehensively considers data from multiple sources related to coal reserve assessment. By integrating multiple sources such as geological exploration data, remote sensing data, and geographic information system data, it can more comprehensively reflect the distribution and characteristics of coal resources, thereby significantly improving the accuracy of coal reserve assessment. Based on the fused dataset obtained by integrating multiple source data, the coal reserve assessment model enables precise coal reserve assessment, improving the accuracy and reliability of the assessment. Therefore, the solution of this embodiment improves the accuracy and reliability of coal reserve assessment.

[0146] Figure 4 Schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 4As shown, the electronic device may include: a processor (processor) 410 , a communication interface (Communications Interface) 420 , a memory (memory) 430 and a communication bus 440 , wherein the processor 410 , the communication interface 420 , and the memory 430 communicate with each other via the communication bus 440 . The processor 410 can call the logic instructions in the memory 430 to execute the coal reserve assessment method, which includes: collecting and obtaining multi-source data corresponding to the area to be assessed, the multi-source data including geological exploration data, remote sensing data, and geographic information system data; using a multi-source data fusion algorithm to fuse the multi-source data corresponding to the area to be assessed to generate a fused data set corresponding to the area to be assessed; inputting the fused data set corresponding to the area to be assessed into the coal reserve assessment model to obtain the coal reserve assessment result corresponding to the area to be assessed output by the coal reserve assessment model; wherein the coal reserve assessment model is established based on a machine learning model or a deep learning model and is trained based on a training set, the training set including multiple historical fused data sets and actual historical coal reserve results corresponding to each historical fused data set; the coal reserve assessment result corresponding to the area to be assessed includes at least one of the following: total coal reserves, reserve distribution, coal seam characteristics, and coal quality parameters in the area to be assessed.

[0147] Furthermore, the logic instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product, stored in a storage medium, includes instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0148] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the coal reserve assessment method provided by the above-mentioned methods, the method including: collecting and obtaining multi-source data corresponding to the area to be assessed, the multi-source data including geological exploration data, remote sensing data, and geographic information system data; using a multi-source data fusion algorithm to fuse the multi-source data corresponding to the area to be assessed to generate a fused data set corresponding to the area to be assessed; inputting the fused data set corresponding to the area to be assessed into a coal reserve assessment model to obtain a coal reserve assessment result corresponding to the area to be assessed output by the coal reserve assessment model; wherein the coal reserve assessment model is established based on a machine learning model or a deep learning model and is trained based on a training set, the training set including multiple historical fused data sets and actual historical coal reserve results corresponding to each historical fused data set; the coal reserve assessment result corresponding to the area to be assessed includes at least one of the following: total coal reserves, reserve distribution, coal seam characteristics, and coal quality parameters in the area to be assessed.

[0149] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the coal reserve assessment method provided by the above-mentioned methods, the method comprising: acquiring multi-source data corresponding to the area to be assessed, the multi-source data comprising geological exploration data, remote sensing data, and geographic information system data; fusing the multi-source data corresponding to the area to be assessed using a multi-source data fusion algorithm to generate a fused data set corresponding to the area to be assessed; inputting the fused data set corresponding to the area to be assessed into a coal reserve assessment model to obtain a coal reserve assessment result corresponding to the area to be assessed output by the coal reserve assessment model; wherein the coal reserve assessment model is established based on a machine learning model or a deep learning model and is trained based on a training set, the training set comprising multiple historical fused data sets and actual historical coal reserve results corresponding to each historical fused data set; the coal reserve assessment result corresponding to the area to be assessed comprises at least one of the following: total coal reserves, reserve distribution, coal seam characteristics, and coal quality parameters in the area to be assessed.

[0150] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0151] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0152] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for evaluating coal reserves, characterized in that: include: Collect and obtain multi-source data corresponding to the area to be evaluated, wherein the multi-source data includes geological exploration data, remote sensing data, and geographic information system data; Using a multi-source data fusion algorithm to fuse the multi-source data corresponding to the area to be evaluated, to generate a fused data set corresponding to the area to be evaluated; The fused data set corresponding to the area to be evaluated is input into the coal reserve evaluation model to obtain the coal reserve evaluation result corresponding to the area to be evaluated output by the coal reserve evaluation model; wherein, the coal reserve evaluation model is established based on a machine learning model or a deep learning model and is trained based on a training set, and the training set includes multiple historical fused data sets and actual historical coal reserve results corresponding to each historical fused data set; the coal reserve evaluation result corresponding to the area to be evaluated includes at least one of the following: total coal reserves, reserve distribution, coal seam characteristics, and coal quality parameters in the area to be evaluated.

2. The coal reserve assessment method according to claim 1, characterized in that: The multi-source data fusion algorithm is used to fuse the multi-source data corresponding to the area to be evaluated to generate a fused data set corresponding to the area to be evaluated, specifically including: The weighted average method is used to fuse the multi-source data corresponding to the area to be evaluated to generate a fused data set corresponding to the area to be evaluated.

3. The coal reserve assessment method according to claim 1, characterized in that: The multi-source data fusion algorithm is used to fuse the multi-source data corresponding to the area to be evaluated to generate a fused data set corresponding to the area to be evaluated, specifically including: The principal component analysis method is used to fuse the multi-source data corresponding to the area to be evaluated to generate a fused data set corresponding to the area to be evaluated.

4. The coal reserve assessment method according to claim 1, characterized in that: The multi-source data fusion algorithm is used to fuse the multi-source data corresponding to the area to be evaluated to generate a fused data set corresponding to the area to be evaluated, specifically including: The multi-source data corresponding to the generated area to be evaluated is input into a deep learning fusion model to obtain a fused data set corresponding to the area to be evaluated output by the deep learning fusion model.

5. The coal reserve assessment method according to claim 1, characterized in that: After obtaining the coal reserve assessment result corresponding to the area to be assessed output by the coal reserve assessment model, the method further includes: According to the coal and rock reserve assessment results corresponding to the area to be assessed, a reserve distribution map and / or a reserve statistics table corresponding to the area to be assessed is generated and output.

6. The coal reserve assessment method according to any one of claims 1 to 5, characterized in that: Before adopting a multi-source data fusion algorithm to fuse the multi-source data corresponding to the area to be evaluated to generate a fused data set corresponding to the area to be evaluated, the method further includes: Preprocessing is performed on the area to be evaluated, and the preprocessing includes at least one of the following: data cleaning, format conversion, standardization, data denoising, data interpolation, and data alignment.

7. A coal rock reserve assessment system, characterized in that: include: A data acquisition module is used to acquire multi-source data corresponding to the area to be evaluated, wherein the multi-source data corresponding to the area to be evaluated includes geological exploration data, remote sensing data, and geographic information system data; A data fusion module is used to fuse the multi-source data corresponding to the area to be evaluated using a multi-source data fusion algorithm to generate a fused data set corresponding to the area to be evaluated; A reserve assessment module is used to input the fused data set corresponding to the area to be assessed into the coal reserve assessment model to obtain the coal reserve assessment result corresponding to the area to be assessed output by the coal reserve assessment model; wherein the coal reserve assessment model is established based on a machine learning model or a deep learning model and is trained based on a training set, and the training set includes multiple historical fused data sets and actual historical coal reserve results corresponding to each historical fused data set; the coal reserve assessment result corresponding to the area to be assessed includes at least one of the following: total coal reserves, reserve distribution, coal seam characteristics, and coal quality parameters in the area to be assessed.

8. An electronic device 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 coal reserve assessment method according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the coal reserve assessment method according to any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the coal reserve assessment method according to any one of claims 1 to 6 is implemented.

Images