187 results about "Radar remote sensing" patented technology

The invention discloses a landslide monitoring method based on remote sensing data, and the method comprises the steps: obtaining a high-resolution optical remote sensing image and a synthetic aperture radar image of a research region, carrying out the registration processing of the optical and radar remote sensing images, and obtaining a remote sensing image with an accurate spatial position and an accurate geometric shape; generating a landslide area fusion image with high spectral resolution; the matched high-resolution DEM data is obtained; based on the matched high-resolution DEM data, gradient parameters of the research area are calculated, and a gradient threshold value is determined according to gradient distribution characteristics and prior knowledge; extracting slope direction parameters of the research area by adopting a slope direction algorithm based on grids and vectors, and screening out a landslide-prone area in combination with the slope threshold value; obtaining a landslide risk distribution map; and obtaining the occurrence possibility and danger level of the landslide, and obtaining the landslide condition according to the occurrence possibility and danger level of the landslide. According to the invention, precise identification and dynamic monitoring of landslide disasters are realized.

The invention discloses a forest carbon reserve and carbon sink monitoring and evaluating method based on a multi-source remote sensing technology. The method comprises the following steps: multi-source remote sensing data acquisition: respectively acquiring optical remote sensing data and radar remote sensing data; tree species classification and identification: carrying out tree species classification on the forest in the research area to realize tree species scale space distribution information extraction; for different tree species, biomass model parameters obtained through field investigation are combined, a biomass estimation model based on the tree species is established, model input parameters are biomass model parameters, and vegetation biomass is output; calculating the carbon reserve: calculating the vegetation carbon reserve by utilizing the inverted vegetation biomass and combining the carbon content coefficients of different tree species; estimating the soil carbon reserve, and finally obtaining the total carbon reserve of the forest ecosystem: calculating the carbon reserve variation of the forest ecosystem at different time points based on the multi-source remote sensing data of the long-term sequence. According to the invention, large-range, high-precision and continuous forest carbon reserve and carbon sink monitoring and evaluation considering tree species difference is realized.

The invention discloses a high-precision topographic mapping system and method based on multi-source remote sensing data, and relates to the technical field of topographic mapping, and the method comprises the steps: obtaining an optical remote sensing image, a radar remote sensing image, LiDAR point cloud data and meteorological index data of a target region, and carrying out the data preprocessing of the optical remote sensing image, the radar remote sensing image and the LiDAR point cloud data; obtaining the surface feature types of the target area and the coverage area of each surface feature type, and carrying out the weighted fusion of the optical remote sensing image and the radar remote sensing image of the target area according to the surface feature types of the target area and the coverage area of each surface feature type, and obtaining a self-adaptive fusion remote sensing image; according to the method, points in LiDAR point cloud data are divided into distinguished ground points and non-ground points, a digital elevation model is constructed according to the ground points in the LiDAR point cloud data, three-dimensional modeling of the terrain is performed on the basis of the digital elevation model in combination with texture information of a self-adaptive fusion remote sensing image, a three-dimensional terrain model is generated, and the terrain surveying and mapping precision is remarkably improved.

The invention belongs to the technical field of power transmission channel hidden danger recognition, and provides a power transmission channel hidden danger recognition method and system fusing optical and radar remote sensing, and the method comprises the steps: constructing a power transmission channel typical hidden danger feature extraction model based on an improved UNet, and carrying out the feature extraction of optical remote sensing data, and obtaining an optical image feature vector; constructing a power transmission channel typical hidden danger feature extraction model based on the improved TransUNet, and performing feature extraction on the radar remote sensing data to obtain a radar image feature vector; performing feature fusion on the optical image feature vector and the radar image feature vector to obtain a fusion feature; the fusion features are sorted and selected based on feature importance, and a classification probability result is obtained in combination with a mixed loss function. According to the method, image reconstruction from low resolution to high resolution is realized through the multi-channel feature map, and the high-resolution feature map is generated, so that more detail information is reserved, and the feature extraction precision is improved.

The invention relates to the technical field of radar remote sensing image processing, in particular to a multi-scale synthetic aperture radar flood detection method and device, and the method comprises the steps: collecting a plurality of flood disaster SAR images of a flood region, and carrying out the preprocessing of the images, so as to obtain a standard flood disaster SAR image; dividing standard flood disaster SAR images, and constructing training, verification and test data sets; based on a multi-scale feature extraction network and a multi-head self-attention mechanism, constructing a multi-scale SAR flood detection network model, training the multi-scale SAR flood detection network model by using the training data set and the verification data set, and inputting the test data set into the trained multi-scale SAR flood detection network model, therefore, the influence of speckle noise is effectively suppressed, the capability of distinguishing flood from confusion-prone ground features in a complex scene is improved, and the accuracy and robustness of SAR image flood detection are improved.

The invention discloses a glacier jump prediction and data sample enhancement management method, particularly relates to the field of glacier remote sensing monitoring, is used for solving the problem of accurate identification and processing of surface moraine covering type glacier local albedo abnormal effect, and aims at solving the problem of accurate identification and processing of the glacier local albedo abnormal effect by comprehensively analyzing the coupling relationship between spectrum and temperature and the spatial sensitivity of temperature gradient. And accurate identification and processing of the moraine covering glacier local albedo abnormal effect are realized. According to the method, main causes of albedo abnormity can be effectively distinguished, and an abnormal area is corrected in a targeted manner by scientifically selecting an optical and thermal infrared remote sensing fusion mode or an optical and radar remote sensing fusion mode, so that the glacier identification precision and the jump prediction accuracy are remarkably improved. Through multi-level remote sensing data correction and feature extraction, a high-precision data foundation is laid for subsequent analysis; in the process of generating an enhanced sample and optimizing a prediction model, the reliability and response speed of glacier jump prediction are further improved.

The invention discloses a hyperspectral image and laser radar data collaborative classification method and system based on a multi-modal mutual guidance attention network. The method comprises the following steps: obtaining a hyperspectral image and laser radar data; preprocessing the hyperspectral image and the laser radar data to obtain to-be-processed data, wherein the to-be-processed data comprises to-be-processed hyperspectral data and to-be-processed radar data; performing mask processing on the to-be-processed hyperspectral data based on the elevation information of the to-be-processed radar data to obtain hyperspectral modal features; performing mask processing on the to-be-processed radar data based on the spectral information of the to-be-processed hyperspectral data to obtain laser radar modal features; performing cross-modal interaction fusion on the hyperspectral modal features and the laser radar modal features to obtain a fusion result; and using a pre-trained classifier to classify the fusion result to obtain a classification result. The method can effectively improve the classification precision of the ground object pixel sample in the remote sensing image, and provides an efficient and robust solution for the high-precision collaborative classification of hyperspectral and laser radar remote sensing images.

The invention discloses a remote sensing image-based western plateau frozen soil hot melt disaster identification method. The method comprises the following steps of obtaining and preprocessing a satellite remote sensing image and a radar remote sensing image of a western plateau frozen soil preset area; performing multi-scale segmentation on the preprocessed satellite remote sensing image to obtain frozen soil characteristics of a preset area; performing time sequence InSA analysis on the preprocessed radar remote sensing image to obtain the earth surface deformation rate of the preset area; constructing a western plateau frozen soil hot melt disaster identification model based on the frozen soil characteristics and the earth surface deformation rate; and based on the western plateau frozen soil hot melt disaster identification model, completing western plateau frozen soil hot melt disaster identification based on the remote sensing image. According to the invention, the occurrence and evolution trend of frozen soil hot melt disasters can be found in time. By constructing a disaster recognition model, early warning and monitoring of potential disaster areas can be realized, and a scientific basis is provided for disaster prevention and control.

The invention discloses a multi-scale super-pixel-level ground feature classification and recognition method and device, a medium and a product, and relates to the field of image processing. The method comprises the following steps: respectively carrying out principal component analysis on optical and radar remote sensing images to extract principal component feature images; normalizing the principal component feature image, and determining a super-pixel clustering target criterion; performing super-pixel segmentation on the principal component feature image based on a super-pixel clustering target criterion by adopting a plurality of segmentation sizes; the features of texture, polarization and the like are extracted based on the preprocessed optical and radar remote sensing images, the pixel mean value of feature images corresponding to all pixels included in each segmented superpixel is taken as the feature value of each superpixel on different feature images, the extracted multi-dimensional feature value is taken as the input of a machine learning model, and ground feature classification is identified. The adaptability and robustness of superpixel segmentation can be enhanced, diversified classification tasks and complex scenes can be better served, and therefore the precision and efficiency of ground feature classification and recognition are remarkably improved.

The invention relates to the technical field of radar remote sensing, discloses a high-order loose body historical activity detection method based on multi-source DEM data, and aims to solve the problem that the historical activity of a high-order loose body in a glacier coverage area is difficult to accurately and quantitatively evaluate in the prior art. The scheme mainly comprises the steps that drainage basin units are automatically divided based on DEM data, and glacier influence areas are screened; multi-source DEM data are fused, and system errors are eliminated through geographic positioning deviation correction, elevation distortion deviation correction and track mode deviation correction; establishing a penetration depth physical model, and correcting the radar penetration depth in the glacier area by using the C / X wave band elevation difference optimization parameter; calculating an elevation change rate by adopting robust regression; and calculating an activity comprehensive index by integrating multiple factors, and identifying a hot spot region and a time period through probability estimation and spatio-temporal clustering. According to the method, automatic and high-precision quantitative evaluation on the historical activity of the high-position loose body is realized, and the method is particularly suitable for geological disaster early warning and risk evaluation in high mountain areas.

The invention discloses a method for inverting marine primary productivity based on airborne dual-wavelength laser radar remote sensing data, and the method comprises the steps: building a dual-wavelength high-precision water optical characteristic inversion model based on the airborne dual-wavelength laser radar remote sensing data, and obtaining a high-precision marine phytoplankton absorption coefficient vertical section; and inverting the marine primary productivity vertical section distribution coupled with the high-precision phytoplankton absorption coefficient. According to the invention, one laser wavelength is suitable for detecting an offshore sea area, the other laser wavelength is suitable for detecting an open sea area, and the dual-wavelength ocean laser radar improves the maximum detection depth of near and open seas and the inversion precision of the primary productivity vertical section distribution of a typical sea area. And the ocean carbon cycle space-time evolution precision and the observation capability in the aspect of ocean upper-layer energy conversion are further improved.

The invention discloses a flood monitoring and deduction method based on unmanned aerial vehicle time sequence radar remote sensing, which comprises the following steps: S1, collecting multi-source flood disaster high-spatial-resolution time sequence radar remote sensing data through unmanned aerial vehicle radar remote sensing, and processing the data into a remote sensing data set with consistent space-time reference; s2, preprocessing each time sequence radar remote sensing image in the remote sensing data set; s3, segmenting a submerged area and a non-submerged area of the preprocessed time sequence radar remote sensing image, removing fine water in the submerged area, and extracting a radar remote sensing high-resolution submerged range; and S4, quantitatively extracting flood evolution characteristic elements, and performing flood disaster potential influence area deduction on the current submerging range in combination with the digital elevation model and hydrological connectivity. According to the method, the problem that the large-range flood evolution process is difficult to dynamically monitor is solved, and support is provided for rapid emergency and risk avoiding transfer of watershed flood by forward deduction of the potential influence area of flood disasters.

The invention relates to the technical field of radar remote sensing image processing, in particular to a single-polarization synthetic aperture radar change detection method and device.The method comprises the steps that initial single-polarization SAR images of front and back time phases are preprocessed to obtain a final image, a multi-scale feature difference chart is calculated, pseudo tags are generated through fuzzy C-means clustering, and the final image is obtained; a UNet coding and decoding structure is used as a basic framework, a double-branch convolutional neural network structure is designed, an input layer, a convolutional layer, a pooling layer, a full connection layer and an output layer are adopted to form a twin convolutional neural network, residual connection is established between an input tensor and an output tensor after network processing, a change detection model is generated, and a change detection result is obtained. And outputting a detection result of the single-polarization synthetic aperture radar by using the change detection model. Therefore, the problems of low accuracy of a change monitoring result and the like caused by the defects that the processing capacity of speckle noise in an SAR image monitoring method is limited and a static threshold segmentation method is difficult to adapt to the global situation in the prior art are solved.

The invention provides a wake flow redirection control method and system based on cabin type laser radar prediction, and relates to the technical field of laser radar remote sensing detection, and the method comprises the steps: obtaining first wake flow propagation path data of a target unit at different spatial positions and first wake flow speed data of different time points through a cabin type laser radar; performing correlation analysis on the first wake flow propagation path data, the first wake flow speed data and a preset unit wake flow speed attenuation coefficient to obtain a correlation analysis result; obtaining a wake flow prediction result based on the first wake flow propagation path data and the correlation analysis result; obtaining wake flow redirection control demand data based on a preset wake flow control target and the calibrated first wake flow speed data; converting the pulse parameter into a pulse control signal based on wake flow redirection control demand data; based on the pulse control signal, accurate redirection control over the wake flow of the wind turbine generator is achieved, cross interference of the wake flow is reduced, and the overall power generation efficiency of a wind power plant is improved.

The invention discloses an SAR image fine focusing method based on fractional Fourier transform. Relates to the field of radar remote sensing technology application, in particular to the technical field of SAR image focusing processing. The technical problem that a motion compensation method based on inertial navigation data and a self-focusing method based on phase errors, which are commonly used in SAR image motion compensation methods, cannot meet the requirements of fine and rapid focusing is solved. The method comprises the following steps: S1, carrying out distance direction partitioning on a defocused SAR image to obtain a plurality of distance blocks; s2, calculating fractional Fourier transform of a strong point target in each distance block; s3, calculating a kurtosis characteristic of a fractional order Fourier transform result; s4, the maximum value of the kurtosis features is searched in a one-dimensional mode, and the optimal rotation order of each distance block is obtained; and S5, performing fractional Fourier transform on the SAR image based on the optimal rotation order of each distance block to obtain a focused SAR image.

The invention discloses a frozen soil active layer thickness inversion method, medium and equipment, and relates to the field of radar remote sensing image processing, and the frozen soil active layer thickness inversion method mainly comprises the steps: obtaining deformation information according to single-view complex orbit descending data, digital elevation model data and atmospheric delay data; according to the deformation information, obtaining to-be-selected long-term deformation and to-be-selected seasonal deformation of the permafrost by using multiple decomposition algorithms; evaluating the to-be-selected long-term deformation and the to-be-selected seasonal deformation, and determining long-term deformation and seasonal deformation; and obtaining the thickness of the active layer of the research area according to the seasonal deformation and the layered soil water content data. By implementing the frozen soil active layer thickness inversion method, the medium and the equipment provided by the invention, the accuracy of frozen soil active layer thickness inversion can be improved.

The invention provides a landslide area detection method and system based on radar remote sensing data. The method comprises the following steps: extracting a backscattering coefficient and a coherence coefficient when a detection radar detects a target scanning area under each time phase from the radar remote sensing data; determining the earth surface deformation sensitivity of each pixel point in the target scanning area based on a scattering characteristic matrix constructed by the backscattering coefficient under each time phase in combination with the spatial-temporal change characteristics of the coherence coefficient; according to the singular value decomposition result of the scattering characteristic matrix and the earth surface deformation sensitivity of each pixel point, dividing a deformation sensitive area and a stability subarea; according to the scattering entropy of the pixel points in the deformation sensitive area, hidden landslide points of the target scanning area are identified from the stability subarea, and then a landslide risk probability graph is generated through all the hidden landslide points in combination with the deformation sensitive area. According to the technical scheme provided by the invention, the hidden landslide point in the scanning area can be effectively identified when the weak deformation signal is submerged.

The invention discloses a rock mass RQD probability distribution dynamic reconstruction method based on digital twinning. Systematic technical breakthrough is achieved in the aspects of multi-source data fusion, three-dimensional heterogeneity modeling, space probability analysis, a dynamic updating mechanism and the like. By integrating drilling, radar, remote sensing, field sensing and other multi-source information and introducing a dynamic feedback mechanism, real-time sensing and dynamic modeling of rock mass structure continuity, heterogeneity and integrity changes can be achieved, and the spatial resolution and time response capacity of RQD evaluation are effectively improved. Compared with a traditional point location value measurement mode, the method achieves the conversion of a rock mass integrity index from discrete sampling to regional probability distribution, and remarkably enhances the comprehensive perception and fine control capability of a complex underground rock mass environment. According to the overall technical scheme, timeliness and accuracy of risk identification in rock mass engineering are improved, scientific decision support for support design and construction strategies is enhanced, and the method has good engineering adaptability and popularization and application value.

The invention discloses a wetland extraction method based on a neural network. The wetland extraction method comprises the following steps: step 1, acquiring data; the acquisition time interval of the optical remote sensing image data and the acquisition time interval of the radar remote sensing image data have an overlapping part, the overlapping duration is between 30 days and 90 days, and the overlapping duration is comprehensively determined according to the wetland vegetation growth cycle and the hydrological change cycle; the multi-source feature information of the wetland in the key period is reflected by the data; preprocessing operation is carried out on collected original remote sensing image data, and the error rate of radiation correction is strictly controlled within + / -3%. Compared with a traditional artificial remote sensing image interpretation wetland extraction mode, the neural network-based wetland extraction method has the advantages that the processing efficiency is greatly improved, large-scale multi-source remote sensing image data can be quickly processed, and the time and labor cost required by wetland information extraction is reduced.

The invention discloses an SAR (Synthetic Aperture Radar) transmission tower identification method based on deep learning and a three-dimensional electromagnetic scattering model, solves the problems that a data set is single and the data set cannot well simulate an actual condition in the existing method, and belongs to the technical field of radar remote sensing and image processing. The method comprises the following steps: constructing SAR data sets of various transmission towers; constructing three-dimensional electromagnetic scattering models of the various transmission towers at different angles, different terrains and different scenes according to the radar images of the various transmission towers, projecting target three-dimensional scattering echoes obtained by using the three-dimensional electromagnetic scattering models onto a two-dimensional imaging plane, and obtaining two-dimensional data including a distance direction and an azimuth direction as a simulation sample; forming a training data set by the SAR data set and the simulated sample, and training a transmission tower identification model by using the training data set; and inputting an SAR image of a to-be-detected power transmission tower into the trained power transmission tower identification model, and outputting the type by the power transmission tower identification model.

The invention belongs to the technical field of ocean laser radar remote sensing detection, and particularly relates to a multiple scattering correction method for a spaceborne photon counting laser radar water body diffuse attenuation coefficient. Comprising the following steps: preprocessing a point cloud signal; calculating an average sea level; extracting a water body photon signal, and performing refractive index correction; performing histogram statistics on the water photons to obtain pseudo echo signals; correcting the transient response of the detector; calculating the attenuation coefficient of the laser radar system; matching a water body diffuse attenuation coefficient; establishing a multiple scattering correction empirical model; and inputting the calculated attenuation coefficient of the laser radar system into the established multi-scattering correction model so as to obtain an accurate water body diffuse attenuation coefficient. According to the invention, data inconsistency caused by multiple scattering can be effectively reduced. Through the improved multiple scatter correction method, the Kd coefficient can be estimated from the laser radar data more accurately, so that more reliable data support is provided for marine scientific research and environmental monitoring.

A non-leaf green organ coupled crop photosynthetic area index radar inversion method comprises the steps that S1, a photosynthetic area index CAI is calculated, and the photosynthetic area index CAI is equal to the sum of a leaf area index LAI and a non-leaf green organ area index NFAI; s2, crop microwave scattering characteristics are analyzed, and polarization decomposition is carried out on radar remote sensing data; s3, screening out a polarization characteristic combination with the strongest correlation with a photosynthetic area index (CAI); and S4, on the basis of the selected feature combination, utilizing a machine learning algorithm to construct an inversion model of the photosynthetic area index CAI and the preferable polarization feature, and utilizing the inversion model to perform inversion on the photosynthetic area index of the regional crop to obtain a regional inversion result. The invention further provides a non-leaf green organ coupled crop photosynthetic area index radar inversion system. According to the method, the photosynthetic area index CAI is provided, the leaf area and the non-leaf green organ area are comprehensively considered, the mechanism process of crop growth change and yield formation is scientifically reflected, and the crop growth and yield can be accurately monitored.

The invention provides a loose accumulation body stability analysis method and system based on a remote sensing image, and relates to the technical field of geological disaster monitoring, and the method comprises the steps: delimiting a monitoring region through the terrain boundary of a loose accumulation body, continuously capturing multi-period remote sensing images through an optical and radar remote sensing equipment double-track system, and synchronously collecting environment action data; generating a feature response time sequence library recording corresponding change relations, extracting feature change rules from the feature response time sequence library to establish feature response anchor points, connecting the feature response anchor points in series to form a dynamic feature response chain, capturing real-time data in real time, comparing to generate deviation conduction topology, performing fluctuation tracing to position a starting anchor point, and analyzing environmental inducements. And related information is integrated to generate a stability analysis result containing a risk anchor point position, a deviation diffusion range and targeted prevention and control measures, and the stability analysis result is output to a monitoring terminal in a visual form, so that the geological disaster prevention and response capability is effectively improved.

The invention discloses an ocean laser radar polarization signal simulation method based on a semi-analytical Monte Carlo model, and belongs to the technical field of laser radar remote sensing detection. The method comprises the following steps: establishing a global observation geometric coordinate system according to laser radar hardware parameters, and determining simulation model environment medium parameters according to water optical parameters; a semi-analysis Monte Carlo model is constructed, propagation tracking of the photon packets is expanded, and calculation and recording of polarization weight signal contribution are carried out on the photon packets meeting the receiving conditions; and carrying out statistical calculation on the polarization weight signal contribution to obtain a polarization photon number signal and a depolarization ratio of the laser radar. According to the method, a single laser pulse is regarded as a plurality of photon packets, the random propagation process of the photon packets in seawater is tracked, and the photon packets meeting the receiving conditions are subjected to simulation of ocean laser radar polarization signals through a signal estimation model. According to the invention, simulation of the polarization signal and the depolarization ratio of the ocean laser radar with relatively high precision can be realized.

The invention discloses a deep learning-based satellite remote sensing collapsible loess foundation evaluation method, which comprises the following steps of: acquiring an optical remote sensing image, a radar remote sensing image and an infrared remote sensing image of a target area, and preprocessing; collapsibility feature weighted data are screened, and feature weights are distributed; feature extraction is carried out through a local space exhibition structure and a multi-layer Transform structure of the collapsibility foundation evaluation network; collapsibility area self-supervised collaborative learning is carried out, and self-supervised training is carried out based on spatial correlation, pseudo labels and spatial consistency regular terms; and carrying out risk grade division on the target area, and outputting a collapsibility risk result of each spatial position. According to the method, multi-mode remote sensing and deep learning are fused, high-precision intelligent partitioning of the collapsible loess foundation is achieved, and the method has the advantages of being self-adaptive, low in manpower and high in spatial resolution.

The invention relates to the technical field of radar remote sensing monitoring, in particular to an airport runway seaworthiness intelligent evaluation method and system based on satellite-ground collaborative awareness, and the method comprises the steps: calculating the signal prominence intensity through the local saliency based on the SAR image pixel amplitude, and primarily screening highlight pixel points; a side lamp possibility index is constructed by combining double constraints of a straight line distribution rule and time sequence position reproducibility, and high-credibility side lamp pixel points are accurately identified from a low-signal-to-noise-ratio background; reversely positioning a runway pixel point area based on the matched parallel edge lamp fitting straight line; constructing a local deformation reference surface by taking an unwrapping phase of adjacent edge lamp pixel points as a benchmark, calculating the reliability of the runway and reconstructing a phase of an untrusted point, and generating a denoised image for airworthiness evaluation; according to the airport runway airworthiness evaluation method, the runway sidelight is used as a phase reference for time-space stability, the problem of phase incoherence caused by specular reflection in a flat runway area is effectively solved, and the accuracy and robustness of airport runway airworthiness evaluation are remarkably improved.

The invention relates to the technical field of radar remote sensing, and discloses a high-precision deformation monitoring and target imaging method based on MIMO-SAR. The method comprises the following steps: receiving an original MIMO-SAR echo data stream and a Beidou navigation system positioning data stream acquired by an image sensor; performing standardized preprocessing on the original echo data to generate standard radar data blocks; aligning radar data blocks and Beidou positioning data time and space, and establishing a mapping relation between data and a spatial position; performing sub-aperture division on the aligned data blocks to generate a multi-sub-aperture data set; performing beam forming processing on each sub-aperture data set to obtain a multi-view complex image; extracting an interference phase of a plurality of images and carrying out geometric correction by using Beidou data; unwrapping the corrected phase to obtain an absolute phase field; inverting a millimeter-level deformation sequence based on the absolute phase field; dynamically updating imaging focusing parameters according to the deformation sequence time evolution characteristics; and performing high-resolution imaging on subsequent data blocks by using the updated parameters, and outputting a deformation monitoring result and a target image.

The invention belongs to the technical field of radar remote sensing image processing and crop classification, and provides a time sequence polarimetric SAR crop classification method based on a time convolutional neural network, comprising: acquiring a time sequence polarimetric SAR data set of a target area; time sequence polarimetric SAR data preprocessing and crop growth monitoring analysis; time convolutional neural network construction oriented to time sequence polarimetric SAR data: extracting time context information of the time sequence polarimetric SAR data through one-dimensional convolution, and generating high-order time sequence features; hyper-parameter adjustment and crop classification result mapping in the TCN are carried out, and hyper-parameters in the TCN are adjusted through a control variable method; and performing geocoding on the crop classification result under the SAR coordinate system, and outputting a final classification result under a geographic coordinate system through drawing. According to the method, the time sequence information and the polarization characteristics are combined, the time information and the polarization characteristic information of the polarization SAR data are brought into full play, and the classification precision of crops is greatly improved.

The invention discloses a laser radar individual tree segmentation method based on multi-scale feature fusion, and relates to the technical field of laser radar remote sensing forestry resource investigation, and the method comprises the steps: point cloud data preprocessing and multi-scale adaptive sampling, combined denoising in combination with geometric distance and intensity information, and sampling parameter adjustment according to stand density; multi-scale feature extraction and cross-scale association are carried out, and local, morphological and global features and cross-scale association features are extracted; fusing and enhancing dynamic attention features, and constructing a feature pyramid; performing density peak clustering and initial segmentation, adaptively adjusting clustering parameters, screening core points and aggregating adjacent points; segmentation result optimization and morphological constraint are carried out, boundaries are optimized through curvature adjustment, ellipse fitting and closed operation, and abnormal units are corrected in combination with morphological verification. According to the method, the individual tree segmentation precision and form conformity are improved, and different stand densities and point cloud conditions are dynamically adapted; the method is suitable for diversified scenes from low-density pure forests to high-density mixed forests.

The invention provides a flood susceptible area prediction method based on multi-source remote sensing data, which constructs flood susceptible factors by fusing radar remote sensing, optical remote sensing, soil moisture, rainfall, river and topographic data, and evaluates and predicts flood susceptibility based on a machine learning model. The method comprises the following steps: S1, acquiring multi-source remote sensing data of a research area and preprocessing the multi-source remote sensing data; s2, calculating the flood probability of each pixel after the flood event based on the radar remote sensing image; s3, calculating related factors of terrain, hydrology, vegetation, soil moisture and rainfall, and constructing a flood susceptible factor set; s4, adopting XGBoost to train a flood susceptible model, and optimizing an input variable set; and S5, when a flood event is about to occur, inputting latest remote sensing data, calculating a flood easy-to-occur score, and evaluating a flood risk. Multi-source remote sensing data and a machine learning technology are utilized, the flood susceptibility prediction precision is improved, and the method can be widely applied to the field of flood disaster monitoring and early warning.