114 results about "Geological analysis" patented technology

The invention discloses an advanced geological prediction method for underground engineering. With geology as pivot, the advanced geological prediction method for underground engineering comprises four stages of long-term advanced geological prediction, middle-term advanced geological prediction, short-term advanced geological prediction and impending advanced geological prediction. The advanced geological prediction method comprises the following steps of: (1) making advanced geological prediction tasks for underground engineering for the underground engineering clear; (2) collecting data; (3) carrying out field geological review; (4) perfecting the modification of a longitudinal section drawing of the underground engineering; and (5) adopting combined geological method, geophysical prospecting method and horizontal drilling method to obtain advanced geological prediction. The invention provides the advanced geological prediction method for underground engineering; with geology as pivot, comprehensive geological analysis is carried out in the whole process of advanced geological prediction for underground engineering and the long-term, middle-term, short-term and impending advanced geological predictions are closely combined together to implement combination of geological method, geophysical prospecting method and horizontal drilling method; the comprehensive application of the geophysical prospecting method is optimized; and the advanced geological prediction method for underground engineering, provided by the invention, has the advantages of improving the predication accuracy, reducing predication cost and obtaining wide application range, etc.

This invention relates to a structure and analysis method for geographical 3-D unified models of water conservancy and water and electricity engineering, which couples multi-source data by the mixed data structure of NURBS YIN and BRep to realize 3-D unified modeling to all modeling objects and analyze said 3-D model including: analyzing the space geographical structure of the coupled multi-source data, carrying out sorted geometry modeling based on the mixed data structure of the NURBS, TIN and the BRep, carrying out Boolean operation based on the space relation among them and analysis and test for reliability to finish the structure of the 3-D unified model and finish the geographical analysis to water conservancy and water electricity engineering.

The invention discloses a three-dimensional geological model constructing and integrating method for a mountain city area, and belongs to the field of three-dimensional geological models. The construction of the three-dimensional geological model for the mountain city area is achieved through the method; due to the fact that the features of the geological structure of the mountain city area are combined, according to the process of constructing a sectional framework, drawing a section and constructing a geological model and the method for constructing the geological model by utilizing the section, the construction of the three-dimensional geological model for the mountain city area is completed more accurately. According to the three-dimensional geological model constructing and integrating method, visualization integration of the three-dimensional regional geological model is further achieved, and a data basis is provided for application analysis of geological topics. Moreover, with regard to the result data of the formed three-dimensional regional geological model, visual integration simulation on a three-dimensional digital city platform is achieved, and real-time geological analysis of the three-dimensional geological model can be achieved in a three-dimensional scene.

The invention belongs to the field of mineral exploration, and in particular relates to a comprehensive prediction method for a prospective area of a granite type uranium mine field, which aims at improving the space positioning accuracy and reliability of a metallogenic prediction area by virtue of remote sensing, geophysical, geological and geochemical methods. The method comprises the following steps: identifying and verifying structures, namely interpreting a remote sensing structure, and geophysically verifying and geologically analyzing a framework structure; screening metallogenic areas, namely screening the framework structure conditions, magmatic activity conditions, uranium source layer conditions and faulted red basin conditions of metallogenic parts; and predicting the prospective area of the mine field, namely grading key area structure conditions, evaluating remote sensing image texture characteristics, aero-radioactive characteristics and geochemical characteristics, and delimitating and grading the prospective area of the mine field. The method can be applied to evaluation and prediction of the metallogenic prospective area of the hydrothermal uranium mine field, especially the granite type uranium mine field.

The invention discloses a coal-mine gas geology four-dimensional analysis method. The method includes acquiring depositional environment data, geologic structure data and hydrocarbon generating history data, and determining a gas enrichment save state, a gas occurrence main controlling factor and a coal and gas outburst risk degree in a study area; then performing gas geology unit division and testing point arrangement; and finally establishing a gas occurrence mathematical model and forming a gas geologic map. According to the coal-mine gas geology four-dimensional analysis method which is established from four-dimensional angles of space ( an area or a layer ) and time, original coal-mine gas geology analysis methods are broken through; the difference problems of gas occurrence or coal and gas outburst disasters on different coal layers, which can not be explained by traditional gas geological theories under same geologic structure conditions on the layer, are solved; and area and layer analysis of coal-mine gas geologies is achieved, problems that a gas geology unit is difficult to divide and different persons acquire different results according to the same data are solved, the work loads of gas geology analysis are reduced, and the guide of safety production is truly achieved.

The invention discloses a grouting integrated controlling method for an underground engineering top weakly cemented rock mass permeation damage region. The grouting integrated controlling method for the underground engineering top weakly cemented rock mass permeation damage region comprises the following steps that means of geological analysis and geophysical exploration are utilized jointly, and hydrogeological conditions of a treated region are ascertained; supporting reinforcement is conducted on a permeation instable damaged section and an affected region; treatment schemes of water releasing and pressure reducing layered grouting are designed; water releasing and pressure reducing drilling construction and layered grouting engineering are implemented and regulated dynamically; water releasing and pressure reducing holes are blocked in flowing water with high pressure and large volume; and monitoring for surrounding rock deformation is enhanced. After the grouting integrated controlling method for the underground engineering top weakly cemented rock mass permeation damage region is adopted for construction, weakly cemented rock mass reinforcement and blocking of water surge with high pressure and large volume are implemented in different levels and stages, the different problems that treatment engineering is long in period and secondary geological disasters are prone to trigger are effectively solved, grouting efficiency is improved, and good social and economic benefits are created.

The invention relates to a petroleum migration pathways quantitative evaluation method. The method combines geological analysis and hierarchical analysis. Parameters affecting the migration performance of faults and sand bodies in fault-sand body migration pathways are considered more comprehensively, including fault mobility, lithology opposition relationship between the two sides of faults, section morphology in the longitudinal direction, section morphology in the moving direction and level of fault as well as sand body effective thickness, porosity and permeability, sand body top morphology, sand body slope and sedimentary facies. On the basis of fault and sand body migration pathways multiple-parameter geological analysis, a hierarchical analysis mathematical method is adopted, the roles of the multiple parameters in the migration pathways are considered in a unified way, and quantitative evaluation of the fault-sand body migration pathways is realized. Meanwhile, the migration performances of unit migration pathways of different structures are compared quantitatively, and a favorable exploration area is easier to select. Compared with the existing evaluation method, geological analysis and the quantitative evaluation of the migration pathways are more accurate, and the success rate of petroleum exploration is effectively improved.

The invention discloses a subway shield section boulder refining detecting method based on resistivity trans-hole CT (computed tomography). The subway shield section boulder refining detecting method includes a scientific and reasonable drilling plane layout scheme of an unexcavated in front of a tunneling side; a detecting scheme of paving a resistivity trans-hole CT wiring net and combining two-dimensional general detecting survey with three-dimensional detailed detecting survey. Data acquisition acquires a novel combined observation mode, and more effective information related to abnormal boulder bodies can be acquired; by structuring a three-dimensional resistivity inversion target function and an inversion equation of a carrying distance weighting function, algorithms can be quickly analyzed and solved parallelly by a partial derivative matrix; a resistivity image result diagram of detection of the abnormal boulder body within a ranging range is formed, and size and spatial distribution and the like of the boulder body are deduced by being combined with geological analysis. Three-dimensional high-resolution accurate imaging of the abnormal boulder body can be realized, and power technical support is provided for safety and quick tunneling of construction tunnels by subway shield tunneling machines.

The invention relates to a geological logging interpretation and evaluation method for oil drilling exploration. The method is based on wellbore information and collects drilling time, oil and gas characteristics of rock samples, fluorescence characteristics, gas measurement parameters, mud tank surface conditions, storage 20 parameters of 6 categories of layer electrical measurement parameters are stored in the corresponding table, and then the scoring method is used to assign specific points to each parameter item; geological analysis experts make interpretation and evaluation conclusions based on the above parameter information to guide on-site personnel to judge the underground The properties of the reservoir fluid can achieve the goal of protecting oil and gas layers and safe drilling, and provide accurate and reliable geological parameters in time to provide a basis for the next step of work measures or construction plan formulation. The geological interpretation and evaluation method provided by the present invention analyzes and defines the parameters reflecting reservoir characteristics and fluid properties, so that qualitative data can be transformed into quantitative or semi-quantitative interpretation, and from a single evaluation to a comprehensive analysis and evaluation of multiple parameters, which can make Reservoir interpretation and evaluation results or conclusions are more scientific and rational.

The invention relates to a method for predicting three-dimensional abnormal pore pressure based on rock physical seismic information. The method comprises the steps that the lithologic stratum matrix bulk modulus is calculated by applying parameters of the rock physical longitudinal wave velocity, transverse wave velocity and density, rock core geological analysis is additionally conducted so as to calculate the dry pore spatial rigidity, the pore pressure coefficient is obtained accordingly, and the single-well stratum abnormal pore pressure is calculated; and secondly, a three-dimensional data cube of the longitudinal wave impedance, the transverse wave impedance, Poisson ratio and the density is obtained by applying a three-dimensional seismic reflection data cube and three-dimensional prestack elastic wave impedance retrieval method, and the three-dimensional stratum abnormal pore pressure is predicted by reference to the single-well stratum abnormal pore pressure calculation method and an obtained empirical formula. According to the method for predicting the three-dimensional abnormal pore pressure based on the rock physical seismic information, rock physical parameters obtained indirectly through logging and seismic geophysical methods are applied to prediction of the abnormal stratum pore pressure, and the practice is easier compared with direct measuring of rock physical parameters in a laboratory, more scientific compared with subjective parameter presetting, and finer compared with calculation separately through post-stack seismic velocity.

The invention belongs to the technical field of oil and gas field reservoir geological analysis, in particular to a braided river sedimentary heterogeneous tight sandstone gas reservoir geological modeling method comprising the following steps: establishing a braided river reservoir internal structure model; establishing a braided river reservoir geological knowledge base; and taking the braided river reservoir internal structure model as a framework, applying the stochastic modeling method based on the target, inputting the parameters of the braided river reservoir geological knowledge base,establishing multiple implementation models and selecting the implementation model with the highest coincidence rate as the training image of multi-point geostatistical modeling, and selecting seismicattributes as the soft constraint conditions of the training image to establish multiple implementation models again and selecting the implementation model with the highest coincidence rate as the braided river sedimentary facies model. The problem of low average coincidence rate of establishing the geological model in the prior art can be solved, and the existing mine field data are fully integrated and the coincidence rate of the established geological model can be enhanced.

The invention provides a geographical physical characterization method for channel sand reservoir type oil and gas gathering conditions. The geographical physical characterization method for the channel sand reservoir type oil and gas gathering conditions comprises the following steps of (1) constructing ridge characterization; (2) describing an oil source fracture net; (3) performing batched sand automatic track; (4) performing fracture and sand configuration analysis; and (5) comprehensively predicting favorable oil-bearing areas. By the geographical physical characterization method for the channel sand reservoir type oil and gas gathering conditions, reasonable characterization and comprehensive analysis can be carried out through an advanced mathematical algorithm and a signal processing means, macroscopic favorable oil-bearing areas are indicated, and a potential exploration target can be provided on the basis of geological analysis and comprehensive assessment of an oil and gas detection result.

The invention discloses an earthquake attribute cluster method and apparatus. The earthquake attribute cluster method employs earthquake attribute clustering based on a rapid K-mean value, a preclustering category number and earthquake attribute data to be clustered are input, category labels which the earthquake attribute data belongs to are output, and during processing, according to a triangle inequality principle, a part of unnecessary calculation for calculating the distance from each earthquake attribute data to a category center to update the category label which each earthquake attribute data belongs to for every cyclic iteration by use of a conventional K-mean value method is saved. Besides, the method can also comprise performing Gauss normalization processing on each earthquake attribute data before the earthquake attribute data to be clustered is input and rejecting wrongly recorded original time sequence signal abnormal values in the earthquake attribute data before the Gauss normalization processing is carried out. According to the invention, cluster analysis of batch earthquake attribute data can be finished within short time, and a basis for further detailed geological analysis is provided for explorers.

The invention discloses a method for overbreak-underbreak control of a tunnel based on building information modeling (BIM). According to the method, a full intelligent drill jumbo is connected with acentral processing unit of a user terminal, the precise positioning and multi-arm synchronous attitude adjustment of the drill jumbo are realized in the tunnel, multiple-drilling-arm automatic operation is achieved, and the peripheral contour of the tunnel and the positions of positioning boreholes are measured automatically. Geological analysis is carried out by combining advanced level drillinggeological exploration data with BIM technology analysis, according to drilling and blasting design matched with the implanted drilling and blasting design scheme, in cooperation with the constructionexperience of blasting personnel, the drilling and blasting design scheme is dynamically adjusted, and an LS-DYNA program is combined to perform drilling and blasting simulation, so that the best drilling and blasting program is formulated. The drill jumbo performs drilling according to the scheme, overbreak-underbreak is controlled strictly, and the intelligent and automatic management of personnel and machineries at a tunnel excavation construction site is realized, so that the control of overbreak and underbreak of the tunnel is achieved.

The invention discloses a method and a system for forecasting tunnel geology. The method comprises steps as follows: surveying the tunnel geology with a seismic reflection method according to the geological condition of a peripheral zone of a tunnel; determining a suspicious geological section according to a result surveyed with the seismic reflection method; surveying the determined suspicious geological section with a short distance method; determining an unfavorable geological section according to a result surveyed with the short distance method; surveying the unfavorable geological section with an advanced drilling method, and obtaining geological analysis data of the unfavorable geological section; and performing geological forecast according to the geological analysis data of the unfavorable geological section. According to the method and the system, the potential safety hazard problem during tunnel construction due to the fact that the tunnel geological condition cannot be accurately forecasted with a single tunnel geological survey method is solved, and the forecasting practicability is improved.

The present invention provides a method for detecting a tunnel bottom base multi-layer karst cave. According to the method, firstly a geological analysis method is used to analyze geomorphology, and with foundation excavation, an infrared ray temperature detection method and a geological drilling detection method are used to determine the natures of strata rocks and lithologic distribution and aninterface; the subsequent geological radar detection and positions of survey lines and survey points of an acoustic reflection method; after the completion of the above foundation trench excavation, the survey lines and survey points are demarcated, and a geological radar detection method is used to carry out linear scan of the geological radar; and finally a sound wave reflection method test is carried out. The detection method provided by the invention is a reasonable and effective combination of multiple detection methods, the combination of qualitative judgment and quantitative judgment isadopted, and a condition that a large number of field implementation processes occupies the effective time of construction is reduced. Used radar detection equipment is highly practical and is easy and convenient to operate.

The invention relates to the technical field of sandstone type uranium ore mineralization prediction, and particularly discloses a big data geological analysis method for sandstone type uranium ore mineralization prediction. The method specifically comprises the following steps of 1, collecting data and performing preprocessing to form a database; 2, establishing a sandstone type uranium ore prospecting model; 3, performing technical analysis and effective information extraction on main ore control factors and ore prospecting marks of the to-be-searched sandstone-type uranium ore region; and 4, carrying out sandstone uranium ore prediction. The invention relates to a big data geological analysis method for sandstone type uranium ore mineralization prediction. geological features are synthesized and summarized, a big data platform is applied, ore control conditions and prospecting marks of sandstone-type uranium ore are considered, the method is also combined with digital geology, database technology, modeling and visualization technology, the combination of geology technology and computer big data technology is formed, and the method is a new technology for prospecting prediction at present and can be applied to prospecting initial prediction of the type.

The invention discloses a method for coal mine gas geology dynamic analysis based on GIS. In the method, based on a GIS platform, a gas geological analysis method is used to dynamically establish a gas geology mathematic model of content of gas and geological effective factors, and gas content, pressure, and other gas information is dynamically calculated and updated on the basis of dynamic variation of the effective factors. Combining with influence of geologic structure, protective layer mining, and gas extraction on gas, dynamic analysis of gas contents, pressure, and coal and gas outburst risks of coal seams in different regions of a coal mine. The method realizes dynamic analysis and calculation update of coal mine gas geological information, changes current situations that an existing technology is lack of spatial data analysis and cannot reflect geological information in time, the method is beneficial for a coal mine management layer to master gas dynamic information in time, and provides decision support for gas disaster prevention and cure, and improves gas disaster prevention and cure capability of a mine.

he invention relates to a ground penetrating radar underground horizon detection method. The method comprises steps that S1, a ground penetrating radar echo signal is inputted; S2, an initial reference track and an initial search point are determined through the echo signal, a search track is determined, a relevant threshold Tc and a distance threshold D are determined, and sizes of a reference window and a search window are determined; S3, a cross-correlation value r(m) of a signal in the reference race reference window and a signal in a next signal search track window is calculated; S4, a search track horizon, a next reference track and a next signal search track are determined according to the calculation result and the set thresholds Tc and D; and S5, horizon detection is carried out through iteration of the steps S3-S4. According to the method, on the basis of correlation and continuity among ground penetrating radar signals, rapid effective extraction of the underground horizon information of the ground penetrating radar signals is realized, and great importance to ground penetrating radar data interpretation and geological analysis in engineering applications is realized.

The invention relates to an integrated recognition method for an overpressured crack. The method is used for comprehensively recognizing the overpressured crack and a development zone thereof on the basis of application of geological analysis, core observation and imaging logging information from an overpressured development geology background, so that corresponding features of all types of conventional logging information in the crack development zone are integrated, and conventional logging types with good distinguishing effect and recognition significance and a combination thereof are preferably selected so as to forecast the distribution of the overpressured crack; by integrated analysis, the bottleneck problems that the conventional overpressured crack is hard to recognize and the conventional logging recognition is low in accuracy can be solved; the integrated recognition method has the characteristics of high efficiency, quickness, economy and accuracy; therefore, the recognition cost of the overpressured crack is greatly reduced, and the forecast precision is improved; a research idea and a method are provided for analysis of the overpressured crack in a hydrocarbon expulsion channel of a hydrocarbon source rock; the judgment accuracy of oil-gas transportation direction is improved, the exploration success ratio is increased, large-range popularization in the overpressured oil-containing gas basin is facilitated; the integrated recognition method has active significance for guiding exploration and development of oil gas.

The invention provides a regional geological disaster susceptibility prediction method and device based on machine learning, relates to the field of geological analysis, and aims to alleviate the technical problem of low prediction precision in the prior art and improve the prediction precision. The method comprises the following steps: acquiring monitoring data of preset acquisition parameters ofeach monomer monitoring point in a target area in a preset time period; preprocessing the monitoring data of each single monitoring point to obtain standardized data of each single monitoring point;performing feature engineering on the standardized data of each single monitoring point to obtain training parameter data of each single monitoring point; performing monomer index prediction on each monomer monitoring point by utilizing a preset machine learning method based on the training parameter data of each monomer monitoring point to obtain a monomer prediction result of each monomer monitoring point; and integrating the monomer prediction results of the monomer monitoring points to obtain a regional prediction result of the target area.

The present invention generally provides methods of geological analysis. The method includes collecting wellbore data from a well undergoing underbalanced drilling. The wellbore data is then correlated to a seismic data to predict geological properties away from the wellbore. In one embodiment, correlating the seismic data with the wellbore data involves converting the seismic data and the wellbore data to a one-dimensional numerical series, respectively. The two respective one-dimensional numerical series are compared to each other to produce a mathematical formulation relating the two series. In another embodiment, the wellbore data may be separated into different categories or classifications and individually compared to the seismic data. Preferably, the categories are compared to two or more variations of seismic data and their attributes to derive at unique “signatures” for the respective category. The signatures may then be used to produce “classification” maps of the wellbore data.

The invention provides a reservoir automatic identification method based on log data. The reservoir automatic identification method based on log data comprises: step 1, loading and analyzing log data; step 2, performing log data preprocessing; step 3, drawing a comprehensive logging curve graph; step 4, performing comprehensive geological analysis on the comprehensive logging curve graph in an interactive manner; step 5, performing reservoir automatic identification and geological parameter automatic explanation, identifying reservoir lithology and oiliness physical property, and performing oil deposit geological parameter analysis in an interactive manner; step 6, displaying an explanation result on the comprehensive logging curve graph; step 7, storing analysis results. The reservoir automatic identification method based on log data is advantaged by automatic identification, diverse explanation methods, good interactivity, and simple operation.

The invention discloses a forecasting method and a forecasting system for tunnel geology. The method comprises the following steps: surveying the geology of a tunnel with a seismic reflection method according to the geological condition of the peripheral area of the tunnel; determining a suspicious geological segment according to the surveying result of the seismic reflection method; surveying the determined suspicious geological segment with an advanced drilling method to obtain the geological analysis data of suspicious geological segment; and forecasting the geology according to the geological analysis data of the suspicious geological segment. According to the method and the system, the problem of potential safety hazard existing in tunnel construction since the geological condition of the tunnel cannot be forecasted accurately with a single tunnel geological surveying method is solved, and the practicability of forecasting is improved.

The invention discloses a method and a system for forecasting tunnel geology. The method comprises steps as follows: surveying the tunnel geology with a short distance method; determining an unfavorable geological section according to a result surveyed with the short distance method; surveying the unfavorable geological section with an advanced drilling method, and obtaining geological analysis data of the unfavorable geological section; and performing geological forecast according to the geological analysis data of the unfavorable geological section. According to the method and the system, the potential safety hazard problem during tunnel construction due to the fact that the tunnel geological condition cannot be accurately forecasted with a single tunnel geological survey method is solved, and the forecasting practicability is improved.

The invention belongs to the technical field of geological exploration and particularly relates to a three-dimensional drilling mineral mapping method based on a rock core hyperspectral scanning image. The three-dimensional drilling mineral mapping method comprises the following steps: step one, scanning a drilling rock core hyperspectral image; step two, pre-processing the rock core hyperspectralimage; step three, carrying out mineral mapping on the rock core hyperspectral image; step four, carrying out statistical calculation and numerical cataloging on relative content of rock core minerals; step five, constructing a three-dimensional spatial drilling database; step six, integrating relative content data of the rock core minerals with a drilling database; step seven, realizing three-dimensional visualization under a three-dimensional modeling platform. The three-dimensional drilling mineral mapping method has the advantages that various mineral information of drilling rock core development can be quantitatively reflected, and spatial distribution of various minerals can be visually presented in a three-dimensional space, so that geological analysis is better facilitated.

The invention relates to a tunnel face analysis method based on image data, and the method comprises the steps of carrying out the quality judgment of a collected face image, and carrying out the three-dimensional reconstruction of a qualified face image, and obtaining a three-dimensional point cloud model; acquiring a tunnel face area and two-dimensional joint data in the two-dimensional image; extracting structural plane features of the image by using a neural network model, and processing the structural plane feature image to extract structural plane line data; and carrying out combined analysis on the structural plane projected to the two-dimensional image by the three-dimensional analysis and the structure extracted by the neural network, obtaining all identified tunnel face joints byclustering and grouping, and drawing a tunnel face sketch map by utilizing a computer. The invention has the advantages that geological analysis is carried out based on the geometric structure of thetunnel face, and meanwhile ultra-short-distance prediction is carried out on the front tunnel face. By combining three-dimensional geological information and by means of deep learning and image recognition technologies, a structural plane is identified, and sketch difficulty and operation time are reduced.

The invention discloses a three-dimensional cross-hole electrical resistivity CT imaging method suitable for any hole distribution of an urban environment. Geological analysis is conducted on a targetarea, and the rough range in which unfavorable geology such as karsts or underground cavities possibly exists in the target area is preliminarily inferred; according to site conditions, exploration holes, drilling measuring lines and ground surface measuring lines are arranged in a selected detection area, and the separation distances between drilling measuring line electrodes and ground surfaceelectrodes are determined; corresponding electrode laying modes selected according to hole distribution modes, and three-dimensional cross-hole electrical resistivity CT detection is performed; lattice dividing modeling of the detected area is completed by adopting automatic modeling, and an inversion imaging results of unfavorable geologic bodies of the target area are obtained through inversion.Modeling of irregular detection areas is achieved by utilizing an automatic modeling method.

The invention discloses a method and a device for building a land subsidence prediction model of a double-dissolved-cavity salt cavern reservoir and belongs to the technical field of underground space. The method comprises steps as follows: acquiring information of the double-dissolved-cavity salt cavern reservoir, and building a three-dimensional geological analysis model of the double-dissolved-cavity salt cavern reservoir according to the information of the double-dissolved-cavity salt cavern reservoir; selecting a key point of the three-dimensional geological analysis model of the double-dissolved-cavity salt cavern reservoir, and performing rheological analysis on the key point of the three-dimensional geological analysis model of the double-dissolved-cavity salt cavern reservoir under the conditions of different rheological time and different internal pressure to obtain a rheological analysis result of the key point; building the land subsidence prediction model of the double-dissolved-cavity salt cavern reservoir according to the rheological analysis result of the key point. According to the method and the device, the anisotropic double-dissolved-cavity salt cavern reservoir three-dimensional geological analysis model of a reaction salt layer in three-dimensional space is built, and the land subsidence prediction model of the double-dissolved-cavity salt cavern reservoir is built according to rheological analysis of the key point on the model, so that land subsidence of the double-dissolved-cavity salt cavern reservoir is accurately predicted.

The invention relates to a spatial data random simulation method based on deep learning, and relates to the technical field of image processing. A technical problem to be solved is to improve the random simulation quality. The method comprises the steps: building a training image mode library through a data template method, extracting image essence structural features in the training image mode library through a deep learning method of a deep belief network; carrying out the classification of the image essence structural features through a clustering algorithm; and carrying out the MPS simulation of a simulation target area of a training image. The method provided by the invention can be widely used for the fields of environment monitoring, exploration and development of oil and gas, geological analysis and weather forecast.