1153 results about "Earth surface" patented technology

The invention belongs to the field of geotechnical engineering and engineering geological information modeling, and relates to a stratum-parameter coupling randomness three-dimensional random field modeling and shield construction ground surface settlement rapid prediction method and device based on multi-source data fusion. According to the method, a three-dimensional joint random field acting on stratum types and rock-soil key physical property parameters at the same time can be constructed under the joint constraint of multi-source data such as drilling, geophysical prospecting, geotechnical tests and terrains, and a calibrated, explainable and updatable geological section automatic generation and uncertainty quantification channel is formed; on the premise that geological rationality is guaranteed, section geometry and parameter distribution under the conditions of complex structures and lateral phase change are restored robustly, the accuracy, consistency and interpretability of the three-dimensional geological section are remarkably improved, and a combined uncertainty result which can be directly used for rapid prediction and risk assessment of shield construction settlement is output. The technical problems that a geological section generated by an existing method is not accurate enough, uncertainty is difficult to quantify, and the extrapolation capacity of a complex scene is weak are solved.

The invention discloses a deep learning and machine learning fused soil moisture inversion construction method, and relates to the technical field of measurement of physical properties of materials, and the method comprises the steps: capturing complementary information and spatial context of multi-source data through a multi-source heterogeneous data space-time adaptive fusion step by using a cross-modal attention mechanism and a graph neural network; through a deep learning and machine learning dual-path collaborative inversion step, advantage complementation is realized by combining data-driven nonlinear modeling and a physical constraint interpretable model; according to the method, the defects of single data source, insufficient model generalization ability and incomplete physical mechanism consideration in the prior art are overcome, the inversion precision is improved by 12%-18% under the complex earth surface condition, and the method has the advantages that the method is suitable for large-scale popularization and application. And a high-precision, strong-generalization and reliable technical means is provided for precise monitoring of soil moisture.

The invention provides a geological disaster intelligent early warning method based on fusion of a physical information neural network and space-air-ground monitoring, and the method comprises the following steps: S10, obtaining geological structure features of different depths under the ground of a city, and recognizing the spatial distribution and thickness of an underground abnormal body; acquiring a surface deformation time sequence, crack and landform information, a three-dimensional point cloud and a continuous vibration signal of a surface-shallow stratum; s20, constructing a three-dimensional twin substrate, performing space-time alignment and resampling on multi-source heterogeneous data, mapping the data to a three-dimensional grid of a unified coordinate system, and extracting and fusing geological disaster precursor features; s30, taking the generated fusion feature field as an input training neural network model, carrying out geological disaster forward prediction and parameter inversion, and outputting future stability probability distribution, a potential slip plane and key parameter evolution; and S40, adaptively adjusting a risk threshold and an early warning rule, constructing an incremental data set, and carrying out periodic incremental training and parameter optimization on the physical information neural network in the step S30.

The invention relates to the technical field of geological engineering, and discloses a geological safety risk dynamic assessment method based on multi-source data fusion, which comprises the following specific steps: step 1, collecting and standardizing multi-source geological data; 2, performing semantic fusion and conflict resolution on the geologic features; 3, constructing a dynamic risk assessment model; 4, risk situation real-time updating and early warning are carried out; the satellite remote sensing system in the first step adopts the synthetic aperture radar interference measurement technology, the spatial resolution is better than 3 meters, the revisit period is shorter than 7 days, and the earth surface deformation monitoring precision reaches the millimeter level. Through standardized processing and semantic fusion of the multi-source geological data, the problem of heterogeneous data integration is effectively solved, the data basic quality of risk assessment is improved, a space-time coupling neural network model is adopted, nonlinear features and space-time correlation characteristics of geological risk evolution are accurately captured, and prediction precision and timeliness are improved.

The invention relates to the technical field of remote sensing data processing and earth surface parameter inversion, and discloses an earth surface matrix parameter hyperspectral data inversion method and system based on machine learning. Comprising the following steps: constructing a multi-source heterogeneous hyperspectral data set; performing feature screening on the preprocessed hyperspectral data set based on an adaptive band selection algorithm, constructing a dynamic weight matrix by calculating mutual information entropy and inter-class distance measurement between spectral bands to realize intelligent screening of key feature bands, and combining spectral derivative conversion and spectral index calculation to generate an enhanced feature vector; and a multi-task transfer learning neural network model is constructed, and an output layer realizes multi-parameter collaborative inversion based on a multi-task learning architecture. And performing preprocessing and feature enhancement operation which is the same as that of the training data on the hyperspectral image data of the to-be-inverted region, inputting the trained neural network model, and outputting a surface matrix parameter inversion result.

The invention is suitable for the technical field of road construction, and provides a wind power plant road intelligent line selection method based on multi-dimensional constraint dynamic modeling, and the method comprises the steps: obtaining a multi-dimensional constraint condition of wind power plant road line selection, and constructing a constraint model; generating a slope grid map based on a digital elevation model, and fusing the slope grid map with a constraint map layer reflecting geological stability and a land cover type to generate a dynamic cost surface; adopting an improved heuristic search algorithm to perform parallel path search from the road starting point to each target fan position, generating a plurality of initial feasible paths, and calculating a comprehensive cost value; screening a candidate line set according to a comparison result of the comprehensive cost values; receiving real-time updating data in a construction process and environment monitoring, inputting the real-time updating data into the constraint model to trigger model updating, performing iterative optimization on the candidate line set based on the updated constraint model, and outputting a final line selection scheme; and the line selection efficiency, economy and reliability are effectively improved.

The invention belongs to the crossing field of space geodetics, satellite navigation positioning technology and atmospheric science, and discloses a real-time troposphere delay modeling method for enhancing a global forecasting system. The method comprises the following specific steps: firstly, acquiring zenith fluid static delay and zenith wet delay predicted by earth surface GFS, and constructing a regional grid difference time sequence by taking a fusion result of ERA5 data and a GNSS troposphere delay product as a reference; secondly, fitting the difference to form a GFS enhanced core model; meanwhile, a troposphere delay correction model from the grid height to the target site height is constructed based on ERA5 stratified atmosphere data, time sequence modeling is carried out on model coefficients, and finally refined troposphere delay output at different heights is achieved. The method has the advantages that (1) the real-time troposphere model is high in precision; (2) real-time application can keep robust performance without depending on a GNSS network; (3) expansion and deployment are facilitated; and (4) the real-time performance is strong, and seamless integration precision positioning application can be realized.

The invention relates to the field of coal mine geological disaster monitoring, in particular to a coal mine surface slope remote sensing data fusion monitoring method and system, and the method comprises the steps: collecting multi-source data through a satellite-unmanned aerial vehicle-ground three-stage network, and carrying out the cleaning, correction and standardization preprocessing; utilizing an improved LSTM model which introduces an attention mechanism and a geological parameter correction item to predict slope displacement and risk levels; distributing monitoring resources through a PSO (Particle Swarm Optimization) algorithm, dynamically adjusting an equipment state through a fuzzy PID (Proportion Integration Differentiation) algorithm, and fusing multi-source data through a Bayesian algorithm to generate a high-dimensional matrix; and finally, storing data based on the alliance chain and performing early warning based on a dynamic threshold value. The system correspondingly comprises six core modules. The problems of narrow coverage, poor timeliness and low data utilization rate of traditional monitoring are solved, millimeter-level precision monitoring is realized, the early warning response is less than or equal to 5 minutes, the cost is reduced by more than 40%, and the method is suitable for safety and ecological monitoring of various coal mine slopes.

The invention discloses a three-dimensional terrain construction method based on multi-modal semantic constraints, and relates to the technical field of three-dimensional terrain modelling, and the method comprises the steps: obtaining an optical remote sensing image and a digital earth surface model, constructing unified space reference data, and carrying out the joint semantic analysis of ground features under the guidance of the multi-modal semantic constraints; generating a semantic mask set with structural consistency; further performing regional geometric reconstruction on the digital earth surface model on the basis of a mapping relation between semantic categories and earth surface physical attributes to form a three-dimensional terrain entity conforming to ground feature space expression characteristics; meanwhile, by analyzing the project cost document and extracting the project cost data with spatial directivity, under the constraint of spatial consistency and semantic consistency, the project cost information and the three-dimensional topographic entity are subjected to association mapping, and finally a three-dimensional topographic data result fusing topographic geometric information and project economic attributes is formed.

The invention discloses a geological disaster real-time monitoring system based on the Internet of Things, and relates to the technical field of geological disaster intelligent early warning. Original data such as earth surface displacement, rainfall and earth sound signals are acquired through a multi-source sensing acquisition module; the edge intelligent processing module extracts disturbance characteristics and calculates disturbance entropy and an energy index; constructing a regional topological graph by using a graph neural network, and predicting a propagation path and a risk probability of an induction factor; fusing meteorological prediction and topographic factors to construct a multi-dimensional mapping model, and identifying a disaster development trend; judging whether a critical state is entered or not based on a causal reasoning map and triggering early warning; the sampling frequency and the communication priority of the sensor are dynamically adjusted in combination with the historical anomaly similarity, and resource optimization configuration is achieved; the system has the advantages of high recognition precision, high response speed, low energy consumption and high deployment adaptability, and is suitable for intelligent monitoring and early warning of geological disasters such as landslide and debris flow.

The invention discloses an urban flood mapping and driving factor analysis method based on multi-source remote sensing data, and the method comprises the steps: respectively extracting an optical semi-permanent water body and an SAR semi-permanent water body based on a global surface water body data set and a Sentinel-1 image, and taking the intersection of the optical semi-permanent water body and the SAR semi-permanent water body to generate an enhanced semi-permanent water body mask; extracting a water body in a flood period by using the Sentinel-1 image to obtain flood water body distribution, and performing water body extraction precision verification in combination with the Sentinel-2 image; the precision of the SRTM DEM is improved based on a DEM error prediction model of a Transform network, and a corrected DEM is generated; and constructing a multi-dimensional spatial analysis model based on the elevation, gradient and surface coverage type of the corrected DEM, and identifying spatial distribution characteristics and a terrain driving mechanism of the flood water body. According to the method, comprehensive analysis is performed in combination with terrain factors, and the spatial precision and timeliness of flood risk assessment can be improved.

The invention discloses ground penetrating radar equipment based on an all-wheel-drive unmanned aerial vehicle and an underground geological three-dimensional map construction method, and relates to the technical field of three-dimensional map construction. The invention aims to solve the problems of terrain information perception distortion, difficulty in constructing a three-dimensional geologic model which is fused with terrain information and has space authenticity and the like caused by vehicle bumping and inclination in the prior art of integrating a ground penetrating radar into an intelligent unmanned vehicle platform for underground detection. According to the integrated structure design of the all-wheel-drive unmanned aerial vehicle integrated ground penetrating radar, the attitude of the whole unmanned aerial vehicle is kept stable when the unmanned aerial vehicle carries the radar for flight operation, data loss and noise introduction caused by attitude jitter of the unmanned aerial vehicle in the radar acquisition process are reduced, and a data foundation is laid for subsequent accurate three-dimensional geological map construction. According to the multi-sensor fusion method, the absolute precision of RTK, the high resolution of laser ranging and the dynamic response characteristic of an accelerometer are fully utilized, and the centimeter-level absolute position of the unmanned aerial vehicle, the height of the unmanned aerial vehicle to the ground and the absolute altitude of the ground surface below a scanning point are obtained. According to the invention, decoupling control of six degrees of freedom corresponding to the full-drive unmanned aerial vehicle is realized, so that the unmanned aerial vehicle can fly close to the rugged topography, and automatic and full-coverage scanning path flight is carried out with a constant ground clearance and a stable attitude.

The invention relates to the technical field of mining exploration, and discloses a surface mine mining system and method based on a three-dimensional model, and the system comprises a three-dimensional modeling module which is used for fusing earth surface and deep geological data to construct a dynamic digital twinborn body, receiving environment dynamic sensing data, and calculating rock mass stress and a water flow coupling field in real time; the mining planning module is used for generating a mining step design and equipment scheduling instruction based on the lithologic parameters and stress distribution of the dynamic digital twin; the equipment control module is used for converting the equipment dispatching instruction into centimeter-level action control signals of a mine truck and an electric shovel through a low-delay communication chain; and the monitoring feedback module is used for collecting mining surface deformation and muck pile characteristic data. Through the dynamic digital twinborn body fusing earth surface centimeter-level scanning and deep quantum detection and stress and water flow coupling field real-time calculation, synchronous visualization of the rock mass mechanical state and hydrological response is achieved, full-time-domain geological perspective capacity is provided for mining decision, and mining efficiency is improved.

The invention provides a data processing method and device based on a smart city, and relates to the technical field of data processing.The method comprises the steps that a city-level spatial data base is constructed through oblique photography of an unmanned aerial vehicle, and a unified and real spatial foundation is formed by generating a live-action three-dimensional model, a digital orthoimage and a digital elevation model; on this basis, a building base and a building white model are extracted, spatial logic verification is carried out on multi-source business basic data, a standard address system stably associated with a building three-dimensional entity is further constructed, precise spatial anchoring of governance objects such as population, houses and units is achieved, and the method is suitable for mass production. And finally, the associated data is uniformly converged to a city information model platform, and reliable and updatable spatial data support is provided for smart city application. According to the invention, the timeliness of smart city data processing in a dynamic earth surface deformation scene can be improved.

The invention discloses a water-rich stratum underground cavity targeted treatment method, and relates to the field of underground cavity targeted treatment, and the method comprises the steps: constructing an underground cavity recognition model through improved YOLOv8, and recognizing an underground cavity in a water-rich stratum; a three-dimensional geologic model is constructed, a drilling track pointing to the cavity from the earth surface or the existing structure is designed, targeted drilling is constructed, and a treatment channel is formed; with the cavity as the center, curtain grouting holes are formed, rapid-hardening type double-liquid grout is injected, and a three-dimensional waterproof curtain is formed; underground water in the three-dimensional waterproof curtain is guided and drained through part of targeted drill holes, and desilting is conducted; and self-compacting filling materials are pumped into the cavity through the other targeted drill holes for main body backfilling, and cavity cracks are reinforced by adopting a sleeve valve pipe grouting technology. And the filling and reinforcing effect is verified, and a monitoring system is arranged to monitor the stratum stability. Through a technical path of combining artificial intelligence identification, three-dimensional accurate positioning and active three-dimensional water stop, safe and efficient targeted treatment of the underground cavity of the water-rich stratum is realized.

The invention relates to the technical field of slope disaster monitoring, in particular to a high and steep slope geological disaster monitoring method and system based on multi-source data fusion. The method comprises the following steps: tracking surface deformation through PS-InSAR time sequence analysis and atmospheric phase correction to obtain surface deformation characteristics; identifying the apparent diseases of the slope, and extracting spatial and temporal distribution characteristics of the apparent diseases of the slope; analyzing spatio-temporal evolution characteristics under geologic structure constraints by utilizing slope rock mass structure characteristics and the earth surface deformation characteristics; according to underground water level dynamic and potential sliding surface weakening features and the slope apparent disease spatial and temporal distribution features, extracting disaster-causing key factor features after cooperative correction; and combining the disaster-causing key factor characteristics, the true three-dimensional geological environment background characteristics and the spatio-temporal evolution characteristics to analyze the comprehensive early warning grade and the potential instability mode of the landslide. Scientific support is provided for high and steep slope geological disaster prevention and control, and engineering construction and operation safety can be guaranteed.

The invention discloses an engineering surveying and positioning method and system based on Beidou. The method comprises the following steps: S1, establishing an oil field operation environment three-dimensional model, and performing satellite visibility and multipath prediction; according to the invention, by constructing a multi-path geometric model and a dual-antenna array discrimination and weighted suppression algorithm, reflection interference caused by a metal facility dense environment in a well site and a station site is effectively weakened; by fusing a local DEM terrain model and earth surface reflection characteristics and introducing vertical Kalman filtering, the stability and precision of Beidou elevation calculation are significantly improved; under the scene of insufficient visibility such as shielding of a drilling machine and large equipment, continuous and high-reliability positioning capability is kept through a tight coupling fusion strategy of IMU and vision assistance, so that high-robustness and high-precision Beidou engineering measurement positioning can be realized in a complex environment of an oil field.

The invention provides a physical information long-short-term memory network site seismic response prediction method based on kinematics derivative constraint and data folding. The method comprises the following steps: collecting and preprocessing bedrock and ground surface seismic oscillation data; displacement, speed and acceleration supervision labels are constructed through surface acceleration integration; constructing a long-short-term memory network containing a data folding and unfolding module; physical constraint loss is constructed by utilizing kinematics derivative relations between displacement and speed and between speed and acceleration, and a network is trained by combining an adaptive weight strategy; and outputting earth surface displacement, speed and acceleration time history by adopting the trained network. According to the method, under the condition that constitutive parameters of a soil layer are not explicitly given, physical consistency constraint can be applied to the field seismic response prediction process, the long-time program train training burden is reduced through sequence folding processing, and the method is suitable for field seismic response prediction.

The invention relates to the technical field of mining face rock movement data analysis, in particular to a coal mine surface deformation monitoring method. The method specifically comprises the steps that a ground rock movement observation control network is established, and ground control points are arranged for combined measurement; a ground rock movement observation station is established, rock movement observation lines are set, and observation points are buried; the observation points are comprehensively measured before mining, and original observation data are obtained; during mining, collecting observation data in real time, and calculating and drawing deformation analysis after mining of the working face; and calculating surface movement parameters according to the observation data. According to the method, the technologies of GNSS-RTK observation, airborne LiDAR monitoring, InSAR monitoring and the like are utilized, modeling is conducted on the surface form before stoping, a database is established, along with stoping, real-time data and modeling data are compared, and the deformation amount is calculated. And large-area, all-weather and continuous observation of data can be realized, so that the research level of the surface movement rule of the mountainous area is further improved.

The invention discloses a multi-platform SAR (Synthetic Aperture Radar) data and ground monitoring image fused earth surface deformation identification method, and belongs to the technical field of remote sensing monitoring and geological disaster early warning. According to the method, SAR images before and after deformation of a target area are obtained through a spaceborne, airborne or foundation SAR platform, and radar sight direction and azimuth direction deformation fields are extracted through preprocessing and offset tracking or interference processing; synchronously utilizing an unmanned aerial vehicle or ground photography equipment to obtain a high-resolution optical image, and calculating an east-west horizontal deformation field and a south-north horizontal deformation field through an image matching technology; after unifying the multi-source deformation fields to the same spatial resolution, constructing a deformation observation equation set based on a three-dimensional deformation decomposition model by combining radar geometric parameters, and inverting three-dimensional deformation in the vertical, east-west and north-south directions of the earth surface by adopting a weighted fusion algorithm (such as Helmert variance component estimation to determine a weight matrix); and finally, performing time sequence optimization on the deformation field by using Kalman filtering or a stress-strain model to generate a space-time continuous three-dimensional deformation product.

The invention discloses a method for realizing fine terrain analysis through image fusion by integrating multivariate surveying and mapping data, and relates to the technical field of remote sensing surveying and mapping data processing and image fusion of terrain analysis, and the method comprises the steps: generating grid elevation, ground point density and visual angle information based on a point cloud, constructing a risk index, and extracting a residual error; residual errors are calculated in a track transverse window and are related to view angle cosine, and a strip-shaped error mask is generated; estimating a deviation field through weighted least squares based on observation fitting and smoothing along an air route, correcting the earth surface and obtaining a pixel-level weight; the correction result and the exogenous elevation are fused according to the weight, and the fused elevation, the gradient, the curvature and other indexes are output. The method can improve the precision and reliability of the terrain index under the complex earth surface.

The invention relates to the field of surveying and mapping science and technology, in particular to a complex waterline identification and extraction method based on point cloud. The method comprises the following steps: acquiring airborne laser point cloud and ground laser point cloud, and carrying out coordinate unification and fusion to obtain an original point cloud set; setting a height threshold based on the elevation distribution characteristics of the original point cloud set, and filtering noisy points of a near-shore water area to obtain a preprocessed point cloud set; repeated random sampling is carried out in the preprocessed point cloud set, and a preset threshold value is utilized to fit an optimal plane as a projection reference plane; therefore, by introducing a neighborhood geometric analysis and circle center backstepping judgment mechanism based on the projection point cloud, robust recognition of the waterline points in the complex terrain is realized, and the problem that a traditional method is easy to cause misjudgment in vegetation interference, local mutation and multi-scale slope break areas is solved; and the continuity and reliability of waterline extraction in a complex surface environment are improved.

The invention relates to the technical field of underground water state evaluation, and discloses an underground water level dynamic evaluation method based on multi-source data mapping and fluid model correction. The invention aims to solve the technical problems of insufficient underground water level monitoring precision and lack of space details caused by low spatial resolution of existing satellite gravity detection data and difficulty in accurately separating a deep underground water change signal from a land total water reserve signal. According to the method, through space-time reference unification of multi-source heterogeneous data, high-resolution surface texture features are utilized to guide a low-resolution gravitational field to carry out space downscaling reconstruction; surface water body and soil water reserve signals are removed layer by layer in combination with spectral characteristics and a thermal inertia principle; and introducing measured data to construct a spatial error correction curved surface of specific yield parameters, and identifying the underground water funnel by using an image connected domain analysis technology.

The invention discloses a deep displacement monitoring method and device based on a GNSS (Global Navigation Satellite System) and an array type flexible inclinometer, and relates to the field of geological survey, and the deep displacement monitoring method comprises the following steps: acquiring earth surface deformation displacement at a drill hole by adopting GNSS equipment; corresponding deep dip angle change values are measured based on three-axis acceleration sensor modules arranged on the upper portion and the lower portion in the array type flexible inclinometer respectively; collecting the earth surface deformation displacement and the deep dip angle change value by using a controller, and forming sequence data after adding a time attribute; an absolute displacement value of each three-axis acceleration sensor module is calculated by using a differential accumulation method; performing displacement fitting on the section where the three-axis acceleration sensor module is not arranged by adopting a function fitting method with constraint conditions; connecting the upper actual measurement displacement curve, the middle fitting displacement curve and the lower actual measurement displacement curve to generate a complete deep displacement monitoring image; a complete deep displacement monitoring image can be generated without a full-depth sensor, and the equipment cost is greatly reduced.

The invention belongs to the technical field of data processing, and discloses a Mars rover non-contact trafficability estimation method and system based on thermal inertia, and the method comprises the steps: obtaining a ground surface temperature time sequence and environment parameters of a target region; constructing a thermal inertia estimation model, and inputting the earth surface temperature time sequence and the environmental parameters into the thermal inertia estimation model to obtain a thermal inertia estimation value of the fire soil; constructing a thermal inertia and trafficability index relation model, inputting the thermal inertia estimation value of the fire soil into the thermal inertia and trafficability index relation model, and outputting a predicted trafficability index; and determining a trafficability state grade according to the predicted trafficability index, and generating a navigation control suggestion, so that the Mars rover passes through the target area according to the Mars rover navigation control suggestion. According to the method, the trafficability index of the Mars rover is predicted by extracting the thermal inertia estimation value of the fire soil in the target area, the evaluation precision of the Mars rover passing through the target area can be effectively improved, and the driving safety of the Mars rover is ensured.

The invention discloses a cross-sensor long-time-sequence InSAR deformation monitoring method and device, a medium and a product, and relates to the field of synthetic aperture radar interferometry, the method comprises the following steps: obtaining image data sets of a plurality of SAR sensors in a monitoring area, and sequentially carrying out differential interference and time sequence deformation calculation to obtain an LOS direction deformation result; geocoding all results to unify a coordinate system; screening high-coherence point targets and constructing an observation geometry unified analysis model; time information is obtained by combining the images, and a long-time-sequence earth surface deformation resolving function model after observation geometric correction is established; and further introducing a truncated singular value decomposition operator, constructing a cross-sensor long-time-sequence deformation resolving analysis model, and finally resolving to obtain a high-precision and long-time-span earth surface deformation product in the monitoring area. According to the method, the problems of rank deficiency and solution failure caused by time shortage and observation geometric difference in multi-platform InSAR data joint solution are effectively solved, and the precision and applicability of long-time-sequence deformation monitoring are remarkably improved.

There is provided a device, etc. that generates construction assistance data that can be used for generating an image that allows a user to easily understand a position and posture of an underground buried object, and for controlling operation of a construction machine to avoid contact with the buried object. In at least part of a plurality of underground search areas Si1, Si2, . . . , Sim, Sim+1, underground search points P1, . . . . Pi−1, Pi, Pi+1, . . . . Pn−1, Pn of the underground buried objects each have a depth position from the ground surface, measured by an underground search machine 60, and the depth positions are consolidated into a representative depth position. Then, construction assistance image data is generated that represents a three-dimensional image including closed surfaces m1, m2 as objects each representing the representative depth position arranged at each of the plurality of underground search areas Si1, Si2, . . . , Sim, Sim+1.

The embodiment of the invention discloses an automatic rock extraction method and system based on deep learning and Mars rover camera images, and aims to solve the problems that an existing Mars rock segmentation algorithm is insufficient in generalization ability under a complex earth surface background, high in model calculation load and difficult to deploy on satellite-borne edge equipment. The core of the method is that a lightweight encoder-decoder network is constructed, and the network integrates three key modules: a frequency-assisted enhancement Mama module, which accurately captures rock texture and contour by fusing the global sequence modeling capability of Mama and the frequency domain enhancement of wavelet transform; the multi-scale feature intensifier is used for adaptively fusing multi-level features by using a parallel double attention mechanism; and the boundary perception auxiliary branch improves the integrity of the segmented contour through an explicit edge supervision and feature decoupling mechanism. According to the method, the rock extraction precision is remarkably improved, meanwhile, the model complexity and the calculation overhead are greatly reduced, the method is suitable for outer space exploration scenes with limited communication bandwidth and calculation resources such as Mars rovers, and effective balance of high precision and light weight is achieved.

The invention belongs to the technical field of tunnels, and particularly relates to a treatment method for a building door tunnel penetrating a karst underground river reach, which comprises the following steps: step 1, multi-source geophysical prospecting fusion investigation: aiming at the tunnel karst underground river reach and the range of 500m around the tunnel karst underground river reach; the method comprises the following steps of: delineating a karst abnormal area by adopting semi-aviation transient electromagnetism; screening a strong corrosion area by adopting a depression analysis method; verifying parameters of the abnormal area through surface drilling and coring; identifying surface hydrology, lithology and seepage data characteristics through unmanned aerial vehicle-mounted high-resolution multispectral and thermal infrared cooperative remote sensing; karst water dynamic conditions including underground water flow velocity, flow direction and permeability coefficient, corrosion evolution characteristics including cavern forming time and expansion rate, and key physical and mechanical parameters including cavern filler porosity, permeability coefficient, surrounding rock integrity coefficient, uniaxial compressive strength, elastic modulus and Poisson's ratio are obtained. According to the treatment method for the building door tunnel to penetrate through the karst underground river section, the karst space characteristics are clearly presented through the arrangement of the treatment method for the building door tunnel to penetrate through the karst underground river section.

The invention discloses a landslide susceptibility analysis method based on a graph neural network, and the method comprises the steps: obtaining image data sets of a target region at different time points based on a preset time period; dividing the target area into a plurality of geological units according to terrains, and setting each geological unit as a node in the graph structure; for each geological unit node, extracting earth surface deformation feature vectors of the geological unit node at different time points; performing iterative optimization on the surface deformation feature vectors of each geological unit node at different time points to obtain optimized surface deformation feature vectors; sending the optimized surface deformation feature vector to a preset graph neural network model to obtain a landslide susceptibility probability value of the corresponding geological unit; and if the landslide susceptibility probability value of any geological unit is greater than a preset probability threshold, triggering warning information. According to the invention, through dynamic calibration of the multi-time-sequence characteristics, the accuracy and reliability of landslide susceptibility complex analysis are significantly improved.