77 results about "Topographic correction" patented technology

The invention relates to the technical field of growth state evaluation, and discloses a crop growth state evaluation method and system based on multi-dimensional monitoring. The method comprises the steps of collecting multi-source remote sensing data of a farmland area according to a crop growth period, and performing topographic correction on the multi-source remote sensing data to obtain target vegetation data; based on the multi-source remote sensing data, farmland plot boundaries are extracted, and a farmland space association graph is constructed; inputting the target vegetation data and the farmland space association graph into an elevation perception graph convolutional network for elevation feature analysis, and calculating to obtain a crop abnormal growth index; and generating a growth state evaluation result based on the target vegetation data and the crop abnormal growth index. According to the method, crop growth abnormity caused by regional factors can be accurately identified, so that the accuracy of evaluation results under different terrain and environmental conditions is ensured.

The invention discloses a terrain and time sequence-based power transmission line icing risk prediction method, system and device, and a medium. The prediction method comprises the following steps: acquiring meteorological elements, topographic features and time sequence features, unifying the meteorological elements, the topographic features and the time sequence features to the same time step length and geographic coordinate grid, and performing topographic correction on the meteorological elements according to the topographic features; constructing and optimizing an icing risk prediction model based on the meteorological elements after terrain correction and the time sequence features as input; inputting real-time weather forecast data into the optimized icing risk prediction model, dividing icing risk grades according to model output, and performing spatial visualization and early warning through a GIS platform; and quantizing the contribution of each element to a prediction result, optimizing model parameters and a feature extraction method, and carrying out interpretable driven model iteration. According to the invention, refined prediction and dynamic early warning of the icing risk are realized, accurate operation and maintenance of a power system are effectively supported, and the icing disaster risk is reduced.

The invention discloses a deep learning-based multi-source remote sensing image water body identification method and system, and the method comprises the steps: carrying out the topographic correction of a water body radar image, obtaining a water body radar correction image, carrying out the image registration and image division of the water body radar correction image and a water body optical image, and obtaining a water body optimization image; respectively inputting the water body optimization image into a double-branch feature extraction model and a depth feature extraction model to obtain water body characterization features and water body depth features, carrying out time sequence feature fusion on the water body characterization features and the water body depth features to obtain water body multi-source remote sensing features, and constructing a water body recognition model, and inputting a to-be-recognized water area water body multi-source remote sensing image into the water body recognition model to obtain a water body recognition result. The method not only can improve the efficiency and accuracy of multi-source remote sensing image water body recognition, but also has good interpretability, and can be directly applied to a multi-source remote sensing image water body recognition system.

The invention relates to the technical field of data processing, and discloses an accumulated snow depth detection method and system based on satellite navigation signals. The method comprises the steps that GNSS multi-band signals are collected through a multi-angle fusion antenna array, and direct and reflected signal components are obtained; performing phase tracking on the signal component to obtain an instantaneous phase difference sequence and a Doppler compensation parameter; analyzing the phase difference sequence by using an improved Lomb-Scargle algorithm, and extracting accumulated snow characteristic frequency and amplitude parameters; establishing a double-layer medium reflection model based on the characteristic parameters and performing terrain correction to obtain a theoretical phase difference curve; and through a multi-satellite collaborative inversion algorithm matching theory and an actually measured phase difference, outputting an accumulated snow depth measurement value. According to the invention, the problems of difficult multipath signal separation, poor terrain adaptability and unstable inversion precision in the existing GNSS reflected signal accumulated snow detection technology are solved, and the accuracy and reliability of accumulated snow depth detection under complex terrain conditions are improved.

The embodiment of the invention provides a ground distance geometric imaging grid division method and system for back projection of a synthetic aperture radar, and belongs to the technical field of radars. According to the scheme, satellite orbit parameters, radar parameters and radar echo data are acquired; center coordinate information of a scene center point is determined according to the satellite orbit parameters and the radar parameters, and the scene center point represents a geometric center point of the imaging area; dividing grids on the three-dimensional ground distance plane according to the central coordinate information and the imaging resolution by combining a digital elevation model to obtain a ground distance geometric imaging grid; and performing backward projection imaging processing on the ground distance geometric imaging grid according to the radar echo data to obtain an imaging result. According to the method, the process of terrain correction after conversion from a slant distance imaging plane to a ground distance imaging plane is not needed, the processing efficiency can be improved, and the synthetic aperture radar image with geocoding can be directly generated.

The invention relates to the technical field of photovoltaic power generation system optimization, in particular to a multi-objective collaborative optimization photovoltaic dip angle determination method, which comprises the following steps of: calculating solar radiation intensity received by a photovoltaic module based on a sun trajectory algorithm by collecting resource data, engineering parameters, terrain correction parameters and economic parameters; the assembly spacing and the land utilization rate are optimized in combination with full-time shadow analysis, and the minimum value of the occupied area is determined; a dynamic weight distribution strategy is adopted, factors such as power generation capacity, land rent and operation cost are coupled to calculate annual income, and the optimal photovoltaic dip angle is solved through a segmented iterative algorithm with the purpose of maximizing the total investment internal return rate (IRR). According to the method, collaborative optimization of land resource utilization and economic benefits can be realized, and a scientific dip angle decision basis is provided for photovoltaic projects with different land costs and topographic conditions.

The invention provides a remote sensing estimation method for the ablation rate of the bottom of an ice shelf, and the method comprises the steps: calculating the time difference between the data timestamp of ICESat-2 ATL15 and the data reference time of ATL14, multiplying the time difference by ATL15 to obtain the elevation change in the corresponding time, obtaining the elevation of the ice shelf of the corresponding timestamp based on ATL14, and taking the obtained elevation of the ice shelf as the reference to estimate the ablation rate of the bottom of the ice shelf. Repeating the steps to obtain ice shelf elevations of different timestamps; carrying out average dynamic terrain correction and ellipsoid elevation conversion on the elevation of the ice shelf; correcting the influence of the air content of the snow on the elevation change of the ice shelf; obtaining the thickness of the ice shelf through a static balance method; based on the principle of mass conservation, the thickness change caused by surface mass balance and rapid movement of the ice shelf is subtracted from the total thickness change of the ice shelf, then the thickness change caused by ice shelf bottom ablation is obtained, and finally the bottom ablation rate is estimated. According to the method, the ice shelf bottom ablation rate can be quickly and efficiently obtained from the ICESat-2 data.

The invention discloses a mountain geological disaster monitoring method and system based on remote sensing data, and relates to the field of geological disaster monitoring, and the system comprises an analysis module which is used for receiving satellite and unmanned aerial vehicle remote sensing data, and carrying out the topographic correction and noise filtering of the remote sensing data based on the mountain topographic features, extracting multi-dimensional characteristic parameters of earth surface deformation, vegetation coverage and water body distribution; the coupling module is used for receiving the multi-dimensional characteristic parameters output by the analysis module, dynamically associating the multi-dimensional characteristic parameters with the geological structure and rock-soil body property data of the mountainous area, and constructing a space-time matching and coupling calculation model of the multi-source data; according to the method, remote sensing data processing is optimized based on mountain topographic features, the multi-dimensional feature extraction accuracy is improved, data relevance is enhanced through multi-source data space-time matching and coupling calculation, disaster hidden danger points are accurately recognized and positioned in combination with dynamic weight distribution, and meanwhile the disaster development rate and the influence range are scientifically deduced according to a time sequence evolution model.

The invention discloses a physical constraint deep learning forest biomass estimation method and system. The method specifically comprises the steps of satellite-borne laser radar GEDI footprint preprocessing and quality screening; sAR radiometric calibration, terrain correction and speckle noise filtering are carried out; optical data radiation correction, atmospheric correction and geometric correction; multi-source remote sensing data space-time alignment and feature variable extraction; constructing a deep learning model fused with physical constraints; feature optimization and model reconstruction are carried out based on space-time interpretability analysis (SHAP); performing comparison and precision verification on the reconstructed final model; and generating a high-resolution annual forest biomass map based on the optimal deep learning model. The estimation result obtained by the method provided by the invention has relatively high precision and accuracy, and scientific data support and decision suggestions are provided for regional forest resource management and carbon sink capability evaluation.

The invention relates to the technical field of remote sensing image processing, computer vision and three-dimensional modeling, discloses a monocular remote sensing image building three-dimensional automatic reconstruction method based on an improved UNet network and a multi-parameter coupling model, and aims to solve the problems that a traditional reconstruction method depends on DSM or laser radar data, and is poor in complex terrain adaptability and low in automation degree. According to the method, a single high-resolution remote sensing image serves as input, building and roof pixel-level segmentation is achieved through an improved UNet network fusing a channel-space-semantic three-mode CBAM attention mechanism and a resolution adaptive SMU activation function, and footprint regularization extraction is completed in combination with contour curvature constraint and Hough transform. And constructing an elevation inversion model based on the roof and footprint offset, the imaging geometric parameters and the terrain correction coefficient, and finally generating a three-dimensional white model through a CGA parametric modeling rule. Experimental verification shows that the average absolute error of the method is about 1.06 m (the mountain scene error is smaller than or equal to 1.2 m), the height error of more than 93% of buildings is smaller than 2 m, the method does not need to depend on additional auxiliary data, the process automation degree is high, the method is adaptive to complex terrain scenes, and the method can be directly connected with a smart city and a digital twin system.

The invention discloses a vegetation coverage index algorithm and system based on an unmanned aerial vehicle. The algorithm comprises the following steps: S1, data acquisition and multi-source data preprocessing; s2, dynamic environment correction and multi-source data fusion; s3, red edge enhanced vegetation index calculation and terrain correction; s4, vegetation coverage intelligent prediction and precision verification; and S5, result visualization and decision support: generating a vegetation coverage spatial distribution map and a statistical report, and supporting a resource management decision. By integrating the unmanned aerial vehicle, the multispectral imaging sensor, the dynamic environment correction model and the data fusion algorithm, efficient and high-precision technical support is provided for precision agriculture, ecological resource management and disaster monitoring.

The invention relates to the technical field of positioning, and discloses a special operation safety guarantee method and system based on Beidou high-precision positioning, and the method comprises the steps: obtaining original coordinates, signal intensity, acceleration and angular velocity, and obtaining an estimated position through data integration and complementary calculation; signal state judgment is carried out in combination with the signal intensity, position correction is carried out according to a judgment result, and an accurate position is obtained; noise suppression and motion trail prediction are carried out in combination with the acceleration and the angular velocity, and smooth trail data are obtained; carrying out deviation analysis on the track data and pre-stored historical track data, and carrying out position optimization according to a deviation analysis result to obtain optimized track data; performing terrain correction and environment compensation in combination with a pre-established geographic information database to obtain continuous trajectory data; and according to the continuous trajectory data, performing integrity optimization through time sequence alignment and data filling to obtain complete trajectory data, and outputting low-risk positioning. According to the method, the navigation reliability and safety in a complex environment are improved.

The invention discloses a reservoir plane distribution feature fine description method based on landform control, and the method comprises the steps: carrying out fine well-seismic calibration based on three-dimensional seismic data and well-seismic combination, and tracking and explaining a top interface and a bottom interface of a target reservoir; calculating an initial reservoir sensitive seismic attribute; obtaining a target reservoir deposition ancient landform; according to the fine well-seismic calibration time-depth relation, the current terrain of the target reservoir is obtained; and correcting the initial reservoir sensitive seismic attribute according to the target reservoir sedimentary ancient landform and the current terrain of the target reservoir to obtain a final target reservoir sensitive seismic attribute, and compiling a target reservoir sedimentary facies map according to the final target reservoir sensitive seismic attribute. Aiming at the reservoir characteristic analysis uncertainty caused by strong reflection of the substrate and the gas-bearing reservoir, the method for correcting the sensitive seismic attributes of the reservoir by adopting the ancient landform and the current topography is adopted, the reservoir response error information caused by strong reflection of the substrate and the gas-bearing reservoir is eliminated, the reservoir characterization precision is improved, and the reservoir analysis uncertainty is effectively reduced.

The invention relates to the field of remote sensing image processing and terrain correction, and particularly discloses a radar geometric field-driven SAR distortion information adaptive neighborhood propagation identification method, which comprises the following steps of: S1, acquiring a Golden digital elevation model of a research area and a pixel-by-pixel ellipsoid incident angle graph generated by SAR satellite precision orbit parameters and imaging geometry, and carrying out geometric unified processing on the Golden digital elevation model and the pixel-by-pixel ellipsoid incident angle graph; s2, calculating a terrain parameter, an effective slope angle, an R geometric response field and an R field directivity gradient based on the unified raster data; s3, main distortion region classification is carried out according to the effective slope angle and the pixel-by-pixel ellipsoid incident angle; s4, defining an adjacent gradient and constructing a self-adaptive threshold value and a shadow self-adaptive threshold value; and S5, performing passive region propagation from the boundary of the main distortion region, and generating a final classification grid map after space overlapping correction. According to the method, the defect of blind propagation of the existing method is overcome, and high-precision automatic identification of SAR geometric distortion under complex terrains is realized.

The invention provides an airport severe convective cloud evolution monitoring method and system based on stationary satellite multispectral characteristics, and relates to the technical field of civil aviation meteorological monitoring and early warning, and the method comprises the steps: obtaining multispectral remote sensing data of an airport monitored by a stationary satellite in real time and in a preset range; performing radiometric calibration and geometric calibration on the multispectral remote sensing data to obtain a calibrated multispectral image; extracting visible light reflectivity and infrared brightness temperature based on the calibrated multispectral image, and generating gridding feature data through spatial resampling; and based on the gridding feature data, performing semantic segmentation by adopting a full convolutional neural network integrating spatial pyramid pooling and dense up-sampling convolution so as to identify and locate a target cloud cluster with strong convection features. According to the invention, the severe convective cloud cluster is identified based on the stationary satellite data, after topographic correction and evolution prediction, graded early warning is generated in real time by fusing the airport operation state, a full-chain monitoring early warning technology is formed, and the meteorological safety guarantee capability of the airport is improved.

This invention discloses a machine learning-based method for reconstructing snow cover area in mountainous areas, comprising: acquiring and preprocessing optical remote sensing data and topographic data; the optical remote sensing data includes MOD09GA data and Landsat8OLI data; the preprocessing includes topographic correction and snow cover identification; using the snow cover area generated from the Landsat8OLI data using a snow cover identification algorithm as the ground truth label, and constructing a sample dataset based on the preprocessed MOD09GA data and topographic data; dividing the sample dataset into a training set and a validation set at a 4:1 ratio to train and validate an XGBoost model; the XGBoost model improves prediction performance by combining multiple decision trees; and using the trained XGBoost model to predict snow cover area on new input data. This method can generate daily 30-meter (m) snow cover area data, which has important research significance and value for mountainous snow cover monitoring, hydrological process simulation, and ecosystem evolution.

The invention relates to the technical field of natural gas gathering and transportation engineering, in particular to a rugged topography gas-liquid two-phase pipeline virtual metering method based on flow pattern self-adaption. A rugged topography gas-liquid two-phase pipeline virtual metering method based on flow pattern self-adaption is characterized in that the method comprises the following steps that an equivalent Reynolds number related to a topography correction factor is constructed, flow patterns are distinguished through the equivalent Reynolds number, and according to a flow pattern adaption and flow pattern self-adaption machine learning prediction model divided by the equivalent Reynolds number, the flow pattern correction factor is obtained; and the prediction of the gas flow is further realized. According to the method, the dependence on a physical sensor is reduced, the equipment cost is reduced, the prediction precision and adaptability of the gas flow in the fluctuating pipeline are improved, and the method can be widely applied to gas-liquid two-phase flow measurement in gas field development.

U I T T R E K S E L Disclosed is a remote sensing image enhancement method and system based on homomorphic filtering topographic correction. The method includes: after acquiring a remote sensing image to be enhanced, converting the image from a red—green—blue (RGB) color space to a hue—saturation—value (HSV) color space, and extracting a brightness component; performing homomorphic filtering processing on the brightness component; combining’ the processed. brightness component with saturation and. hue, and. inverting the component back to the RGB color space to complete image enhancement; acquiring grayscale distribution of the enhanced image, and calculating image information entropy; further calculating contrast of the image through grayscale values of pixels; calculating an enhancement score of the image based on the information entropy' and. contrast, and. comparing' the enhancement score with a preset score to determine whether the image enhancement is completed. The present invention can effectively improve the image quality of remote sensing images. (+ Fig. 1)

The invention discloses a mountain photovoltaic power station output characteristic evaluation method and system based on a guarantee rate, and relates to the technical field of photovoltaic power generation. Comprising the following steps: acquiring basic data of a mountain photovoltaic power station, the basic data comprising topographic data, meteorological data, photovoltaic module parameters and power station layout data, and preprocessing the basic data to obtain standardized data; and constructing a mountain photovoltaic power station output calculation model based on the standardized data. According to the method, the illumination intensity calculation error is reduced to be within 5% by introducing a terrain correction illumination intensity calculation model and considering the influence of gradient and slope direction on solar radiation, the precision is improved by 10-15% compared with that of a traditional plane model, meanwhile, quantization of special mountain loss factors such as temperature and dust is achieved through subentry calculation of a dynamic power loss coefficient, and the calculation accuracy is improved. And the deviation between the theoretical output and the actual output is further reduced.

The present application relates to the technical field of remote sensing information extraction and snow monitoring, and particularly relates to a sub-pixel snow mapping method based on medium-resolution remote sensing data, comprising the following steps: obtaining medium-resolution remote sensing images, a digital elevation model, and ground meteorological station snow observation data, and preprocessing the remote sensing images to obtain surface reflectivity; identifying cloud-covered pixels, filling in the cloud-free dataset by temporal and spatial interpolation and ground object spectral similarity matching; selecting snow, vegetation, and water as spectral endmembers and extracting features; constructing a linear mixing model, and using the least square method to retrieve the snow proportion in the pixel to obtain preliminary data; and generating a high temporal and spatial accuracy snow distribution map through meteorological station data verification, digital elevation model terrain correction, and model parameter optimization, which solves the problems of mixed pixels, cloud coverage, terrain errors, and the lack of accuracy verification.

This invention discloses a fully automated atmospheric and topographic radiometric correction method and device for high-resolution remote sensing imagery, belonging to the field of remote sensing science and technology. The method includes: constructing a fully automated batch processing framework; developing an atmospheric correction module based on the 6S radiative transfer model to automatically retrieve atmospheric parameters and eliminate their influence; and developing a topographic radiometric correction module based on the digital elevation model (DEM) and VECA model to compensate for radiometric distortion caused by complex terrain. The key innovation lies in constructing a joint correction framework and integrating a geomorphic feature recognition algorithm, which can automatically identify and select to execute either single atmospheric correction or a combined atmospheric-topographic correction process based on the degree of topographic relief in the image. This invention achieves fully automated batch processing from data input to result output, requiring no manual intervention, significantly improving the processing efficiency, intelligence level, and adaptability to different terrain scenarios in high-resolution image radiometric correction.

This invention discloses an information processing method and system for severe convective weather forecasting in plateau regions. The method includes acquiring data of a preset type within the plateau region and preprocessing the data; performing topographic correction on specified physical quantities in the preprocessed data based on real-time DEM data; extracting specified physical quantities from the corrected data to obtain real-time key physical quantity feature data; inputting the real-time key physical quantity feature data into a pre-trained model to output the occurrence probabilities of three types of severe convective weather; generating a classified severe convective weather forecast product with a specified resolution based on the occurrence probabilities; and generating hourly classified severe convective weather forecast and warning information for the next N hours based on the severe convective weather forecast product and a specified benchmark. This method overcomes the problem of large forecast deviations caused by the complex topography of plateau regions.

The present application relates to the technical field of snow remote sensing modeling, and particularly relates to a snow black carbon concentration remote sensing inversion method. Remote sensing terrain data of a target region is acquired and terrain correction is performed; reflectivity of a snow area in the terrain-corrected remote sensing terrain data is acquired; a pure snow optical model is established according to the reflectivity of the snow area using an analytical asymptotic radiative transfer theory; ice-black carbon composite particle absorption characteristics are introduced to the pure snow optical model to construct a dirty snow optical model, and a rigorous radiative transfer model fitting result is used to optimize and solve the dirty snow optical model; and the black carbon concentration of the snow area is inverted according to the optimized dirty snow optical model. The snow remote sensing inversion method proposed in the present application can effectively reduce the influence of terrain shadows, model the black carbon absorption coefficient as a function of wavelength based on a snow radiative transfer model, greatly reduce the calculation complexity, and improve the calculation efficiency and accuracy.

The invention relates to the technical field of biodiversity research, and discloses a mountain tree species diversity remote sensing estimation method, which comprises the following steps: acquiring mountain tree species distribution data, acquiring a mountain remote sensing image, preprocessing the data, and calculating a tree species diversity index according to tree species distribution. Calculating the correlation between the spectral heterogeneity index and the tree species diversity index, constructing a mountain tree species diversity remote sensing mapping model according to the influence factor calculated by the spectral heterogeneity index, extracting the optimal parameter of mountain tree species diversity remote sensing estimation, and making a tree species diversity index spatial distribution map according to the spectral heterogeneity index to realize tree species diversity estimation. A terrain correction mechanism is introduced into the spectral heterogeneity index constructed by the method, the stability and reliability of the spectral heterogeneity index are improved, spectral response of the model to different tree species is improved after a weighted distance construction mechanism between pixels is combined, and the method is suitable for mountain forest areas with obvious topographic relief and has good application prospects. And multi-source input of multi-sensor remote sensing images is supported.

The invention provides a coal mine extremely shallow goaf geophysical prospecting data analysis method based on a transient electromagnetic method, which is characterized by comprising the following steps of: optimizing data acquisition parameters and correcting terrain; data preprocessing and noise suppression are carried out, multi-stage preprocessing is carried out on the original data, and preprocessing comprises outlier elimination, filtering noise reduction, null drift correction and background field deduction; time-depth conversion and resistivity inversion are carried out; quantitative analysis of goaf response characteristics; carrying out three-dimensional data fusion and visual modeling, integrating multi-measuring-line data and geological information, and constructing a goaf space distribution model; and the conclusion reliability is improved through field drilling verification and error source analysis. Aiming at the detection difficulty of an extremely shallow goaf, electromagnetic response details of a shallow medium are captured through small coil high-frequency excitation and microsecond-level signal acquisition. The terrain laser correction and the whole-period apparent resistivity inversion are combined, so that the tiny holes are accurately identified; and through drilling entity verification and error simulation, the misjudgment rate is remarkably reduced.

The invention discloses a mountain high-precision displacement monitoring method based on frequency domain digital image cross correlation, and relates to the technical field of remote sensing measurement and digital image processing. Comprising the steps of obtaining multi-stage optical images; pre-processing the obtained multi-stage optical image; implementing orthotopography correction by using a digital elevation model (DEM); interference caused by vegetation and shadow is suppressed; constructing a multi-level resolution pyramid and carrying out frequency domain cross-correlation operation; performing sub-pixel peak value positioning to obtain a sub-pixel level displacement value; and generating a continuous displacement field, performing quality control and uncertainty expression at the same time, and finally outputting a single-source displacement field result. According to the method, through DEM orthographic projection, the two-stage projection difference caused by mountain fluctuation is reduced.

The invention relates to a watershed scale inland pond classification method and device and electronic equipment, and the method comprises the steps: obtaining multi-source geographic space data of a target watershed, including remote sensing images, a digital elevation model, land coverage data, JRC global surface water products, urban boundary data and photovoltaic power station distribution data; carrying out radiation calibration, terrain correction, noise removal and space cutting on the remote sensing image; generating an inland pond water body baseline map based on the multi-source geographic space data; and performing differential combination application according to differential characteristics of the aquaculture pond, the urban pond, the photovoltaic pond, the tailing pond and the farmland pond, and outputting identification and classification results of multiple types of inland ponds. According to the method, the detection rate of small-scale ponds is remarkably improved through multi-source geographic space data fusion, the recognition precision of inland ponds is improved, the whole-process classification precision is remarkably improved compared with a single algorithm, consumed time is remarkably reduced, and high-precision recognition and classification of various ponds in the watershed scale are achieved.

The present disclosure provides a gravity anomaly extraction method, device, equipment and storage medium, and belongs to the technical field of gravity exploration. The method comprises: performing terrain correction and curving processing on the Bouguer gravity anomaly of a target region to obtain a first gravity anomaly; performing constant-density gravity stripping processing on the first gravity anomaly to obtain a second gravity anomaly; performing variable-density gravity stripping processing on the second gravity anomaly to obtain a third gravity anomaly, wherein the density of the multiple layers of strata between the stratum where the target geological body is located and the surface is variable in the along-layer lateral direction; determining a first gravity regional field of the target region; and extracting the gravity anomaly of the target geological body according to the third gravity anomaly and the first gravity regional field. The variable-density gravity stripping processing on the second gravity anomaly can eliminate the influence of the variable density of the strata in the along-layer lateral direction on the gravity anomaly of the target geological body, thereby improving the accuracy of the extracted target gravity anomaly.

The invention discloses a forest fire occurrence real-time prediction method and system. The method comprises the following steps: collecting multi-source data monitored in a forest region in real time; performing space-time alignment processing on the multi-source data by using sampling and topographic correction; constructing a space-time collaborative perception network model based on convolution, a graph neural network and an attention mechanism, and constructing a sample data set by using multi-source data for training to obtain a forest fire prediction model; and inputting the multi-source data into the forest fire prediction model to obtain a forest fire prediction result. According to the technical scheme provided by the invention, multi-source data of a forest region can be processed, multi-level spatial features can be extracted through convolution, an attention mechanism can dynamically weight key space-time dimensions, a graph neural network can model a spatial relationship between complex terrains and vegetation distribution, spatial distribution features of fire risks can be captured, and the spatial distribution features of the fire risks can be extracted. In addition, the method can identify the time evolution rule, can effectively overcome the defects of a conventional method in the aspect of space-time modeling, and greatly improves the prediction accuracy.

The application discloses a kind of vegetation cover index algorithm and system based on unmanned plane, wherein algorithm includes the following steps: S1, data acquisition and multi-source data preprocessing;S2, dynamic environment correction and multi-source data fusion;S3, red edge enhanced vegetation index calculation and terrain correction;S4, vegetation coverage intelligent prediction and precision verification;S5, result visualization and decision support: generate vegetation coverage spatial distribution map and statistical report, support resource management decision.The application provides efficient, high-precision technical support for precision agriculture, ecological resource management and disaster monitoring by integrating unmanned plane, multispectral imaging sensor, dynamic environment correction model and data fusion algorithm.