111 results about "Spatial Autocorrelations" patented technology

The invention provides an airfield pavement detection method based on an earthquake background noise imaging technology, and relates to the technical field of airfield pavement detection. Comprising the following steps: acquiring seismic background noise data of an airport pavement to be measured; preprocessing the seismic background noise data to obtain preprocessed noise data; carrying out cross-correlation calculation on the preprocessed noise data and carrying out empirical Green function extraction; according to the empirical Green function, a surface wave group velocity frequency dispersion curve is extracted by adopting spatial autocorrelation and multiple filtering methods; inverting shear wave velocity distribution of each layer of the pavement based on the surface wave group velocity dispersion curve, and constructing a three-dimensional velocity model; determining a shear wave velocity distribution diagram according to the three-dimensional velocity model; and determining a detection result of the airfield pavement to be detected according to the transverse wave velocity distribution diagram. According to the invention, the problems of low detection precision and poor real-time performance of a common detection technology in the prior art are solved.

The invention relates to the technical field of medical elastography and material multi-scale mechanical measurement, in particular to an elastography method and system based on an instantaneous scattering displacement field, and the method comprises the steps: driving a passive / active method scattering displacement field excitation device through a frequency domain controllable sine wave signal, and generating a scattering displacement field on a target material, an instantaneous displacement field is obtained through high spatial resolution measurement, then sliding window local interception, two-dimensional autocorrelation calculation and nonlinear fitting based on the Rayleigh / shear wave spatial autocorrelation theory are performed on the single-frame instantaneous displacement field, shear wave velocity distribution is obtained, and then the viscoelasticity modulus of a target area is inverted to achieve comprehensive characterization of the viscoelasticity of the material. According to the scheme, the single-frame scattering displacement field is excited and collected, and the elasticity inversion is performed based on the instantaneous displacement field, so that the dependence of traditional elasticity imaging on high-frame-rate equipment is broken through, the material viscoelasticity evaluation can be efficiently completed at low cost, and the application prospect in the fields of clinical diagnosis and mechanical measurement is wide.

The invention relates to the technical field of regional ecological risk assessment and space management and control, in particular to a regional ecological risk assessment and partitioning method based on a multi-system spatio-temporal dynamic relationship, which comprises the following steps: collecting and preprocessing multi-source spatio-temporal data; a natural ecological risk index and a human social risk index are fused, and a comprehensive ecological risk assessment model based on a social-ecological system is constructed; divariate spatial autocorrelation analysis and cold and hot spot analysis are adopted, and a region is divided into three-level subareas including a management and control area, a monitoring area and a prevention area and six types of subareas; and analyzing the partition dominant driving factor by using the optimal parameter geographic detector, and generating a differentiated control strategy. The method realizes quantitative coupling of natural ecology and human social system risk spatio-temporal dynamic relationships, solves the problems of strong subjectivity, insufficient system comprehensiveness and lack of dynamic association mechanisms of a traditional method through multi-dimensional index fusion and spatial analysis technologies, and provides systematic technical support for accurate management of regional ecological risks.

The invention specifically discloses a long-time-sequence high-frequency ecological environment quality space-time differentiation and driving analysis method, and relates to the technical field of remote sensing and ecological environment. The method comprises the following steps: determining an evaluation area, and constructing a macroscopic ecological safety risk evaluation framework; ecological indexes of greenness, humidity, temperature and dryness are calculated, and a time sequence data set is constructed; reconstructing a time sequence data set and constructing a remote sensing ecological index model based on the reconstructed time sequence data set; verifying the precision of the model, and evaluating the reconstruction precision by taking the screened high-quality pixels as true values; analyzing the spatial and temporal change trend and significance output by the model by using slope estimation and trend test, outputting future change continuity by using a Hurst index analysis model, and measuring spatial autocorrelation output by the model by using a Moran index; remote sensing ecological index evolution factors are researched by means of an optimal parameter geographic detector. According to the invention, the precision and timeliness of ecological assessment are improved, and decision support is provided for ecological management.

The invention relates to the technical field of machine learning, and particularly discloses a spatial local XGBoost machine learning model based on multi-scale geographic weighting, and the model comprises a feature decoupling module which is used for constructing a two-channel input structure of geographic features and non-geographic features, and achieves the feature decoupling and fusion through a multi-scale spatial weight matrix; the bandwidth allocation module dynamically determines the bandwidth scale in the XGBoost tree splitting process, and establishes a dynamic weight bound by tree levels; the constraint gain module generates split points with scale marks; a contribution decoupling module extracts split features and associates geographic and non-geographic features to realize salinization prediction and contribution index extraction; and the verification optimization module optimizes model parameters through a multi-scale thermodynamic diagram and spatial autocorrelation analysis. The model can capture geospatial effects of different scales, improves the spatial local prediction precision, and is applied to soil salinization analysis scenes with spatial heterogeneity.

The invention discloses an ecological vulnerability evaluation method based on road domain landscape pattern optimization, and the method comprises the steps: obtaining expressway road domain environment data as training data, and obtaining ecological environment data; calculating an ecological environment quality index of the ecological environment data, and obtaining landscape structure features in the target area; integrating the landscape pattern index into an ecological sensitive factor, and constructing an ecological vulnerability evaluation model by adopting an SRP structure; performing spatial autocorrelation analysis on space-time evolution of the ecological vulnerability of the road domain according to the ecological vulnerability evaluation index, establishing an ecological vulnerability multi-scene simulation model, performing overlay analysis on an ecological vulnerability evaluation result and a land utilization type, obtaining a specific restoration strategy, tracking space-time evolution characteristics of the ecological vulnerability, and performing road region ecological vulnerability evaluation. Ecological vulnerability influence factors are adjusted based on different scenes, future possible ecological vulnerability risks are simulated, specific restoration strategies are made according to different partition standards, and effective configuration and use efficiency of resources are ensured.

The invention discloses a high-standard farmland construction time sequence optimization method, and relates to the technical field of agricultural information, and the method comprises the steps: superposing a permanent basic farmland distribution diagram layer and a high-standard farmland distribution diagram layer, and recognizing a permanent basic farmland region which is not constructed into a high standard; obtaining multi-source basic data in the region, and representing the grain yield by adopting an LAI average value after S-G filtering; constructing a high-standard farmland construction ecological toughness evaluation index system; the combined weight of each evaluation index is calculated according to the combination of an entropy weight method and a CRITIC method, and a set pair analysis model is established to calculate the farmland ecological toughness; a spatial interaction relationship between grain yield and farmland ecological toughness is obtained based on a bivariate local spatial autocorrelation analysis method, a preferential plot of high-standard farmland construction is identified in combination with a self-organizing mapping neural network and a K-means method, and a construction time sequence arrangement and spatial layout optimization scheme is formed. According to the invention, the problem of high-standard farmland construction priority can be solved.

The invention belongs to the field of tunnel engineering, and relates to a tunnel defect detection data spatial resolution enhancement method and device based on a Vine Copula dependent structure and a conditional random field, a computer readable medium and a computer program product. The method comprises the following steps: firstly, separating an overall trend and random fluctuation from original tunnel defect monitoring data; then establishing a Vine Copula multivariable dependence model to represent a statistical correlation relationship among the plurality of defect indexes; and then generating defect distribution data with high spatial resolution by using a conditional random field interpolation simulation technology in combination with a spatial autocorrelation analysis result. According to the invention, while the accuracy of the existing measuring point data is ensured, the spatial correlation structure and multivariable joint distribution characteristics of the defect data are maintained, and the precision of spatial interpolation prediction is improved.

The invention discloses an expressway bridge construction state real-time monitoring method and system, and relates to the technical field of bridge construction monitoring. An expressway bridge construction state real-time monitoring system comprises a data acquisition and processing module, a data expansion and analysis module, a multi-point data fusion module, a state comprehensive evaluation module and a construction scheme adjustment module. According to the method, data interpolation and expansion are carried out on the preprocessed vibration monitoring data through the Kriging interpolation method, the spatial autocorrelation between the vibration monitoring data can be fully utilized, and the monitoring data are expanded, so that the problem of insufficient coverage of monitoring points can be effectively solved, and the integrity and precision of the monitoring data are improved; the change trend and the distribution rule of vibration in space can be reflected more accurately, a more comprehensive and reliable basis can be provided for evaluation of the highway bridge construction state, and the state evaluation accuracy of the highway bridge construction state real-time monitoring method and system is improved.

The invention provides an integrated circuit hot spot detection method based on multi-modal feature fusion and dynamic optimization, which relates to the technical field of integrated circuits, and comprises the following steps: acquiring multi-modal feature data, executing progressive block clustering to extract multi-scale features, fusing the features by using a multi-head attention mechanism, and constructing a hot spot feature map. A hot spot area is determined by combining spatial autocorrelation analysis, and a detection result is optimized based on synchronization analysis of a morphological evolution and energy evolution sequence. The hot spot detection accuracy and robustness can be improved, the false detection rate can be reduced, and the potential hot spot area in the complex layout can be effectively identified.

The invention relates to the technical field of data processing, in particular to a topological consistency risk analysis and monitoring early warning method for a tower inclination state, and the method carries out the time alignment and quality control of multi-modal data, such as an inclination angle, a wind speed and direction, temperature and humidity, positioning and an equipment state. Constructing a time-varying adjacency matrix based on line topology, geographical adjacency and wind field elements, and normalizing the time-varying adjacency matrix to form a graph model; the inclination angle or the trend of the inclination angle serves as a graph signal, space consistency measurement is calculated, and linkage with sliding window trend detection of a single rod and EWMA and ADWIN drift detection is carried out; identifying segment-level or region aggregation anomalies by synthesizing image smoothing energy, adjacent rod difference and spatial self-correlation; and outputting early warning grades under wind direction, wind speed, duration time window and data quality gating, and adaptively adjusting a threshold value, a time window and a model weight during drifting. The method can reduce false alarm and missing alarm, improves early warning accuracy and interpretability, and is suitable for centralization or edge cloud collaborative deployment.

The invention discloses a tourism rail transit passenger flow characteristic analysis method based on mobile phone signaling data, and the method comprises the following steps: S1, collecting and cleaning the mobile phone signaling data of multiple operators, and obtaining the cleaned mobile phone signaling data; s2, performing spatial registration and reconstructing a track according to a user identifier and a timestamp to form a user track sequence; s3, counting passenger flow indexes, constructing a spatial weight matrix and calculating spatial autocorrelation factors; s4, introducing the space factors into a hidden Markov model and training parameters; s5, complementing a missing track, and generating a complete travel state sequence; and S6, analyzing passenger flow indexes, identifying a gathering area, an abnormal area and a diffusion path, and outputting monitoring information. According to the method, the spatial autocorrelation factor is introduced into the hidden Markov model, spatial dependence modeling and state completion are performed on the rail transit passenger flow based on mobile phone signaling data, and accurate identification and monitoring of passenger flow distribution, hot spot areas and abnormal events are realized.

The invention relates to the technical field of environmental science and engineering, and discloses a water body sediment heavy metal pollution diagnosis and risk zoning method, which comprises the following steps of: firstly, performing functional zoning and differentiated point distribution sampling based on hydrodynamic topographic features; secondly, carrying out multi-dimensional index detection on the sediment sample to obtain a multi-dimensional data set containing a chemical occurrence form; secondly, combining a positive definite matrix factorization model with bivariate local space autocorrelation analysis, quantitatively analyzing the contribution of the pollution source and verifying the space fate of the pollution source; then, constructing a two-dimensional risk assessment system based on the chemical occurrence form, and calculating a migration release risk index and a bio-availability risk index; and finally, according to source-sink positioning and risk assessment results, a differentiated partition control strategy is generated. According to the invention, through coupling chemical morphology and spatial analysis, the concealment risk that the total amount does not exceed the standard but the bioavailability is high can be accurately identified, and accurate positioning and migration path verification of the composite pollution source are realized.

The invention relates to a tunnel portal road icing early warning method based on digital twinning, and the method comprises the steps: generating a clean data set through integrating rock mass fracture, underground water level and meteorological monitoring data; filling the monitoring blind area based on the spatial self-correlation weight to form a dynamic water seepage distribution diagram; combining laser radar point cloud data to construct a freezing early warning digital twinborn body, and dynamically mapping a rock mass fracture network and water seepage space distribution; and finally, inputting the real-time weather and the road surface temperature field into the twinborn body, quantifying the icing probability of the tunnel portal pavement microporous structure through a thermodynamic model, and generating an icing risk spatial distribution diagram. The method solves the core defects of geology and tunnel portal road monitoring splitting, three-dimensional space perception deficiency, response lag and insufficient probability quantification in traditional early warning, realizes whole-process dynamic early warning from rock mass water seepage migration to road surface ice coagulation, improves the identification precision and response speed of tunnel portal road sudden ice coagulation risk, and improves the early warning efficiency. And a reliable basis is provided for intelligent traffic decision making.

The invention discloses a soil nutrient inversion method based on multi-source physical constraint and a multi-scale attention network, and aims to solve the problems that a soil nutrient inversion method based on remote sensing lacks enough truth value marking data and does not consider spatial autocorrelation of soil nutrients in geographic space and a physical imaging rule influenced by a microenvironment and an earth surface structure. Therefore, the problems of deviation of the inversion value and lack of spatial texture constraint and geographical continuity of the soil nutrient content distribution map generated by inversion are solved. According to the method, the collaborative Kriging trend and soil microenvironment and earth surface structure characteristics are introduced as physical constraints, a sample expansion confrontation model is constructed, sample expansion is performed by a scientific method integrating a physical environment and a spatial law, the physical imaging law of soil nutrients is fully considered, and the accuracy of the sample expansion confrontation model is improved. In combination with a designed multi-scale residual attention inversion model for extracting key information from a spectrum, the generated soil nutrient content distribution map is relatively excellent in spatial texture constraint and geographical continuity.

The invention provides a livestock building temperature data fusion monitoring method, a livestock building temperature data fusion monitoring device and electronic equipment. The livestock building temperature data fusion monitoring method comprises the steps of acquiring temperature data acquired by a multi-source sensor network, heating equipment power and nursing period animal space density in real time; and constructing a topological network based on the obtained animal husbandry building planar graph, taking each temperature sensor as a node in the topological network, and calculating an effective path distance between all temperature sensor node pairs. Dynamically calculating a heat source influence factor based on the power of heating equipment and the space density of the animals in the nursing period; and inputting the effective path distance and the heat source influence factor into an improved geographically weighted regression model to obtain a composite weight. And performing fusion processing on the temperature data by using the composite weight to generate a temperature distribution diagram. And local space autocorrelation analysis is carried out on the temperature distribution map, and a temperature anomaly aggregation area in the livestock building is positioned as a temperature data fusion monitoring result. The defect that a traditional temperature monitoring method is insufficient in precision in a spatial heterogeneity environment is effectively overcome.

The invention provides a mineral variable spatial autocorrelation enhancement method and system based on second-order clustering, and the method comprises the steps: firstly obtaining a mineral variable original collection set corresponding to a plurality of sampling positions in a mineral exploration region, and carrying out the spatial correlation preliminary analysis of the mineral variable original collection set, thereby obtaining a spatial correlation relation set; and executing first-order clustering processing based on the spatial association relationship set to generate a first-order clustering unit. Performing variable association deepening analysis on mineral variable information in each first-order clustering unit to obtain an internal association feature set, and performing second-order clustering processing based on all the internal association feature sets to generate a second-order clustering unit; and finally, enhancing the spatial autocorrelation characteristics of the original collection set of the mineral variables in combination with a second-order clustering unit to obtain an enhanced mineral variable set, so that the spatial autocorrelation characteristics of the mineral variables can be comprehensively and deeply enhanced.

The invention discloses a shared bicycle passenger flow prediction method based on a geographically weighted regression model and a related device. The method comprises the following steps: collecting spatial data and social economic data of a shared bicycle putting point of a target city; inputting the effective independent variable data set, the spatial autocorrelation of the effective independent variables, the multi-collinearity test result and the housing price factor data into a least square regression model and a geographical weighted regression model, and outputting a regression coefficient, a significance level and a goodness of fit; and according to the regression coefficient, the significance level, the goodness of fit, the delivery point category and the actual shared bicycle passenger flow data, calculating the prediction precision and the lifting amplitude at different delivery point categories. According to the method, the spatial heterogeneity relationship between the shared bicycle passenger flow volume and the influence factors is considered through the geographically weighted regression model, the regression coefficient is adjusted according to different geographic positions, the influence characteristics of a local area are reflected more accurately, and the prediction precision is remarkably improved.

The present invention discloses a method for intelligent positioning of deep geothermal target areas based on a machine learning algorithm, and the present invention relates to the field of geothermal resource exploration technology. The method comprises the following steps: S1, multi-source heterogeneous data fusion acquisition and preprocessing; S2, geological feature entropy quantification and spatial autocorrelation analysis; S3, deep feature extraction and multimodal feature fusion; S4, multi-model adaptive integration and dynamic weight optimization; S5, reinforcement learning dynamic adjustment to participate in abnormal threshold determination; S6, three-dimensional geothermal target area intelligent positioning and risk assessment. This positioning technology integrates geological structure, geophysical field, geochemistry and remote sensing data through a machine learning algorithm to construct a high-dimensional feature vector, thus solving the limitation of the existing technology that relies solely on physical detection. At the same time, it introduces reinforcement learning to dynamically optimize model parameters, combined with real-time geothermal well data updates, so that the model can adapt to changes in geological conditions, and the prediction accuracy is greatly improved compared with traditional methods.

The present application relates to the technical field of medical elastic imaging and material multi-scale mechanical measurement, and particularly discloses an elastic imaging method and system based on a scattering displacement gradient field, which comprises the following steps: generating a scattering displacement field by arranging an excitation device around a target material, measuring an out-of-plane displacement gradient field by using transverse shear interference imaging, selecting a single-frame instantaneous gradient field or a frequency-domain gradient field obtained by time-frequency domain Fourier transform as a target field; obtaining a global shear wave velocity distribution by adaptive sliding window interception, two-dimensional autocorrelation calculation and Rayleigh wave spatial autocorrelation theoretical model fitting, and then reconstructing viscoelastic modulus distribution by using an inversion algorithm. The present application supports single-frame scattering displacement gradient field inversion elastic imaging, can be used without high-frame-rate equipment, has strong anti-environmental vibration interference ability and high system stability, is suitable for scenes with poor isolation conditions, has low cost, high efficiency and high measurement precision, and can meet the requirements of medical clinical diagnosis and material multi-scale mechanical measurement.

The present invention discloses a method for predicting the stability of microbial communities in river water bodies by utilizing the patch density of land use in a watershed. The present invention relates to the technical field of microbial community stability prediction and watershed water ecology research, and addresses the deficiencies of traditional research methods in revealing the association and prediction between land use and microbial community stability. The method comprises obtaining land use data of the target watershed, calculating the patch density of each sampling point in the buffer zone; collecting samples to determine the composition of microbial species; preprocessing the data, and performing hierarchical clustering grouping based on the patch density; calculating the average variation dissimilarity of the groups to characterize the stability of the microbial community; conducting statistical analysis and performing a spatial autocorrelation test; comparing the prediction performance of different regression models, and selecting the best model to predict the stability of the microbial community in unsampled areas. This method significantly improves the prediction efficiency and accuracy, and provides reliable technical support for watershed ecological management and land planning.

The invention discloses a wind and light resource prediction method and device based on terrain and climate characteristics, a medium and equipment. Historical climate data is interpolated to a spatial resolution consistent with that of topographic data, and global spatial autocorrelation analysis is combined, so that topographic-climate coupling characteristics of resource distribution and a self-aggregation rule of wind and light resources are accurately captured. And identifying key environment factors for driving resource distribution heterogeneity and local correlation coefficients of the key environment factors by utilizing correlation analysis, and carrying out partitioning, so that wind and light resource forming mechanisms in each sub-region tend to be consistent. On the basis, a model is independently trained for each same proton region, so that the model can be more focused on learning a unique rule of resource evolution along with time in the specific environment. The prediction model can accurately capture the internal association between the sub-region wind and light resources and the environmental factors, and finally output target time period prediction data is closer to reality. Therefore, the capturing of the fluctuation characteristics of the wind and light resources is more accurate and robust, and the accurate prediction of the future wind and light resources is realized.

This application relates to a method, apparatus, and equipment for soil erosion analysis. A pre-set model is trained by comprehensively considering soil erosion driving factor data, spatial structure characteristics, and soil erosion modulus data of the sample area. During training, the spatial autocorrelation of the prediction residuals of the soil erosion prediction model is ensured to meet a pre-set non-significant condition, thereby overcoming the problem of existing machine learning models neglecting spatial characteristics. In the prediction stage, the trained model is used in conjunction with the soil erosion driving factor data and spatial structure characteristics of the target prediction area to obtain accurate soil erosion modulus data, thus obtaining reliable soil erosion analysis information.

A method for detecting an underground cavity by using an irregular three-dimensional array belongs to the technical field of underground detection, and is characterized in that a plurality of high-sensitivity digital seismographs are utilized, a detection area is well covered with a ray path, and each digital seismograph collects irregular micro-amplitude vibration information of the surface of the detection area all the time; a surface wave signal is extracted from micro-amplitude vibration information, then a cross-correlation function between digital seismometers is obtained through background noise cross-correlation calculation and superposition, and a Rayleigh wave phase velocity frequency dispersion curve is obtained based on a multiple filtering and extended space autocorrelation (ESPAC) method. And finally, inverting a three-dimensional phase velocity structure below the detection area based on the frequency dispersion curve of each grid node, and performing two-dimensional or three-dimensional mapping display on an inversion calculation result through mapping software. The method is simple in field work operation, flexible in laying according to field conditions, simple and rapid in data processing flow and mature in algorithm, and can rapidly and accurately position the underground cavity position.

The invention relates to the technical field of regional rare earth prediction, in particular to a landscape pattern and spatial statistics coupled ion adsorption type rare earth enrichment region prediction method, and the method comprises the steps: obtaining an ion adsorption type rare earth ore control index parameter set, rare earth abundance data and rare earth content actual measurement data of a target region; constructing an effect coefficient set according to the geological-hydrological index parameter set and the rare earth content measured data; constructing a landscape resistance field according to the landscape index parameter set to obtain the landscape resistance field; obtaining a spatial weight matrix; performing spatial autocorrelation analysis according to the rare earth abundance data and the spatial weight matrix to obtain spatial autocorrelation analysis indexes; performing rare earth enrichment probability index prediction according to the geological-hydrological index parameter set, the effect coefficient set, the landscape resistance field and the spatial autocorrelation analysis index to obtain rare earth enrichment probability index data; and performing rare earth enrichment area prediction on the target area according to the rare earth enrichment probability index data to obtain a rare earth enrichment area prediction result of the target area.

The invention discloses an unmanned aerial vehicle-WSN space-time collaborative optimization method for urban fire monitoring, and the method comprises the steps: carrying out the spatial self-correlation analysis based on fire data, dividing an extremely high risk region, a high risk region, a medium risk region and a low risk region, assisting in the judgment of the access priority of an unmanned aerial vehicle, and carrying out the simulation in a time dimension through employing XG-Boost, and evaluating the reasonability; secondly, clustering fire points by using a mean shift method to obtain sensor node layout coordinates, clustering a cluster head, carrying out load balancing adjustment, and generating an initial inspection path of the unmanned aerial vehicle; thirdly, path deviation caused by wind interference is modeled, an overall-to-local precision control method is introduced, and unmanned aerial vehicle flight precision control is performed according to real-time feedback to reduce the path deviation; and finally, solving a global optimal path by using a system energy consumption scheduling algorithm. Therefore, manpower and material resources are saved, effective decision support is provided for dynamic deployment of fire rescue resources, and path deviation caused by wind interference is reduced as much as possible.

The application provides a sensor-based seasonal frozen soil monitoring method and system, wherein the method comprises the following steps: dividing a monitored area into a grid, deploying a sensor group in the monitored area, acquiring geographical parameters of the monitored area, and acquiring a topographic influence factor of seasonal frozen soil according to the geographical parameters; acquiring heat flux between sensor monitoring points i and j in the monitored area; calculating a maximum weight matrix, calculating spatial autocorrelation between the sensor monitoring points based on the topographic influence factor, the heat flux and the maximum weight matrix; screening out unnecessary monitoring points according to the spatial autocorrelation, and sorting the monitoring points according to the spatial autocorrelation values, wherein the monitoring points with larger absolute values are sorted in front, and the monitoring points sorted in front are preferentially monitored. The method and the corresponding system can reduce the number of sensors deployed and the maintenance cost, and reduce the operation cost of the whole monitoring system by screening out redundant monitoring points in the seasonal frozen soil monitoring.

The invention provides a cultivated land feature extraction method for satellite monitoring pattern spots, a medium and a system, and belongs to the technical field of electrical digital data process.The cultivated land feature extraction method for satellite monitoring pattern spots comprises the steps that firstly, multi-temporal satellite remote sensing data is obtained and preprocessed, then vegetation indexes are calculated, and a time sequence feature matrix is constructed; pattern spot change features are obtained through spatial-temporal scale decomposition, a multi-dimensional feature extraction model is established, accurate recognition of cultivated land pattern spots is achieved, finally, a feature distribution matrix is generated through an evaluation model, and accurate extraction and characterization of cultivated land pattern spot features are completed. According to the method, the boundary and the internal structure of the cultivated land pattern spots are accurately identified by analyzing the time sequence change characteristics of the vegetation indexes and combining spatial autocorrelation analysis. According to the method, the accuracy of feature extraction is improved through kernel density estimation and spatial clustering analysis, and the technical problem that farmland pattern spot features in a multi-temporal remote sensing image are difficult to accurately recognize and extract in the prior art is solved.

This invention provides a method and system for analyzing anomalies in toxic and harmful gas concentrations based on spatial autocorrelation, relating to the field of mine ventilation safety technology. The method includes: tracking and sensing the concentration of toxic and harmful gases in a mine sensor network to obtain time-series slices of concentration; analyzing these slices to obtain a global Moran's index and multiple local spatial autocorrelation indices; when the global Moran's index deviates from the dynamic baseline, clustering of significantly anomalous sensor nodes based on geographical coordinate distances according to the Z-test results of multiple local spatial autocorrelation indices to locate areas of ventilation structural imbalance; performing spatiotemporal collaborative anomaly root cause analysis; and outputting a structured anomaly tracing report. This addresses the problem in existing technologies that use single-point sensors to independently monitor mine toxic gas concentrations and issue threshold alarms, which have blind spots in monitoring the spatial correlation characteristics of gases and ventilation structural anomalies. This leads to frequent false alarms and missed alarms in mine gas concentration anomaly identification and airflow control decisions, and also fails to dynamically adapt to changes in roadway engineering.

The application discloses a kind of fusions of multi-source data and its spatial autocorrelation soil property spatial prediction method, the environmental variable of target area is collected;The environmental variable of the target area is respectively input into the linear relationship model of pre-trained soil property data and environmental variable and the nonlinear relationship model of pre-trained soil property data and environmental variable, respectively linear model soil property data prediction value and nonlinear model soil property data prediction value are obtained;Linear model soil property data prediction value and nonlinear model soil property data prediction value are fused using multi-scale geographic normalization weighted fusion model, and the final prediction value of the soil property data of the target area is obtained.The advantages are: the prediction result accuracy is greatly improved compared with the original fused data, and is better than conventional linear and nonlinear fusion method;The spatial autocorrelation of soil property is considered, and the application can maintain good prediction performance in various complex environments.