33 results about "Vegetation classification" patented technology

The invention discloses a remote sensing-based canopy scale urban green land vegetation classification method. The method comprises the following steps of: obtaining and fusing multi-source remote sensing data; constructing a canopy scale multi-dimensional feature set fused with multi-source remote sensing data; constructing an urban green land vegetation enhancement sample set; constructing a low-dimensional feature set after optimization; the invention further discloses an urban green land automatic classification method based on the canopy scale of the improved random forest. According to the method, a multi-dimensional feature set is constructed through multi-source high-resolution remote sensing data; an automatic dynamic feature optimization and weight distribution mechanism based on mRMR is introduced, redundancy is effectively reduced, and discriminative features are highlighted; constructing a heterogeneity-driven adaptive sample set in combination with multi-source prior knowledge; and based on an improved random forest algorithm which introduces dynamic weighted node splitting, neighborhood constraint and adaptive category balance, high-precision, canopy-scale and adaptive classification of urban green land vegetation is realized.

The embodiment of the invention relates to the technical field of artificial intelligence, and provides a coastal salt marsh vegetation carbon sink estimation method and system based on multi-temporal phenological characteristics. The method comprises the following steps: acquiring a remote sensing image of a target coastal salt marsh area in a key phenological period; extracting an initial vegetation contour of a vegetation coverage range in the target area from the remote sensing image by adopting an unsupervised classification method; constructing a phenological decision tree model by taking an NDVI threshold method as a core, and integrating a machine learning enhanced node division mechanism and a phenological period slope analysis method to enhance the phenological decision tree model; inputting the initial vegetation contour into a phenology decision tree model, and performing multi-level classification on vegetation types according to the initial vegetation contour through the phenology decision tree model to distinguish vegetation coverage ranges of various types of vegetation in the target coastal salt marsh area; and vegetation carbon density parameters are obtained, and the estimation of the total carbon sink amount of the target coastal salt marsh area is completed through spatial superposition calculation in combination with a vegetation coverage range, so that accurate classification of vegetation and efficient estimation of carbon sink are realized.

The invention discloses a vegetation image recognition method, system, equipment and medium based on OfficientNet, and belongs to the technical field of computer vision and image processing, and the method comprises the steps: collecting data through image collection and synchronous utilization of a laser radar, and carrying out the preprocessing of the collected data; an improved OfficientNet network model is constructed, and training and optimization are carried out by using the improved OfficientNet network model; and carrying out vegetation classification and hidden danger detection on the input image, inputting the collected real-time data into a comprehensive risk scoring model for hidden danger detection for calculation, and carrying out risk early warning positioning. The hidden danger trees are accurately positioned based on the GIS technology, the omission ratio is reduced through a dynamic early warning system, and the manual inspection risk is reduced through automatic reporting; different climate monitoring requirements are adapted based on the expansibility of the model, the tree barrier hidden danger can be blocked and the maintenance efficiency can be improved in practical application, and an integrated solution integrating accurate identification and real-time positioning is formed.

The invention relates to the technical field of image analysis, in particular to a vegetation fine classification and recognition method and system based on an unmanned aerial vehicle, and the method comprises the following steps: obtaining a multispectral image through the unmanned aerial vehicle, extracting red edge reflectivity, NDVI and gray-level co-occurrence contrast, generating a feature vector in a standardized manner, calculating neighborhood offset to obtain a dynamic weight, and combining the dynamic weight into a weighted vector; high discrete features are screened as effective channels, multi-scale clustering is carried out, center and region growth extension recognition is optimized, and a vegetation classification atlas is generated. According to the method, a neighborhood pixel feature offset dynamic weight mechanism is introduced, multi-spectral feature dimension contribution degree is adjusted in a self-matching mode, effective channels are screened based on full-image dispersion, redundant interference is eliminated, image pyramid multi-scale clustering and consistency constraint are fused, the complex vegetation boundary recognition capability is improved, dynamic weight and multi-scale optimization are coordinated, and the method is high in robustness and high in robustness. Sample dependence is reduced, and accurate distinguishing of spectrum similar vegetation is achieved.

The invention provides a mining area vegetation reconstruction method based on vegetation classification and division. The method relates to the technical field of ecological environment restoration, and comprises the following steps: S1, acquiring mining area environment data by adopting a mode of combining remote sensing images, unmanned aerial vehicle aerial photography and ground sampling, performing spatial interpolation, normalization and filtering preprocessing on the environment data, and outputting a mining area ecological factor database; s2, on the basis of the ecological factor data, constructing a multi-index evaluation model by combining an analytic hierarchy process with clustering analysis to perform vegetation type division on the mining area, and generating partition templates with different ecological functions; and S3, constructing a plant phenological growth prediction model based on years of phenological observation data and weather forecast information. According to the mining area vegetation reconstruction method based on vegetation classification and division, precise planting and spatial layout are completed, the vegetation survival rate, biomass production and community diversity are remarkably improved, and the strict requirements of mining area ecological reconstruction for diversity and adaptability are met.

The invention discloses a mountain vegetation classification method based on a remote sensing image and a vegetation index, and relates to the technical field of mountain vegetation classification, and the method comprises the steps: obtaining remote sensing image data of a research region in a set time span, and dividing the remote sensing image data into a plurality of sub-regions; and analyzing and extracting vegetation index time sequence characteristics and seasonal growth characteristics of each sub-region in a set time span, preliminarily determining the vegetation type of each sub-region as an initial label, and using the obtained initial label, vegetation index time sequence characteristics and seasonal growth characteristics of each sub-region to train a classification model. According to the method, the change of the vegetation index of each sub-region in the time sequence is calculated, and the change of the seasonal vegetation index is combined, so that the static vegetation type is considered, the growth cycle of the vegetation and the change characteristics of the vegetation in different seasons are dynamically captured, and the real change condition of the mountain vegetation can be reflected more accurately.

The application provides a vegetation carbon storage prediction method and device and a storage medium, wherein the method comprises the following steps: extracting a feature set of a to-be-measured region according to a remote sensing image, an elevation model and historical vegetation index information of the to-be-measured region; inputting the feature set into a random forest vegetation classification model for prediction to obtain at least one vegetation type of the to-be-measured region and regional information of each vegetation type in the remote sensing image; performing segmentation processing on the remote sensing image of the to-be-measured region based on a pre-trained vegetation segmentation model to obtain at least one vegetation proportion information of the to-be-measured region and corresponding regional information of each vegetation proportion information in the remote sensing image; and determining the carbon storage of the to-be-measured region according to the vegetation type of the to-be-measured region, the regional information of each vegetation type in the remote sensing image, the vegetation proportion information and the corresponding regional information of each vegetation proportion information in the remote sensing image. The application effectively improves the accuracy of forest carbon storage estimation.

The invention discloses a vegetation species identification method for enhancing AI computing power and time sequence tracing, and the method comprises the steps: collecting and preprocessing multi-source remote sensing data, and constructing a vegetation classification data set with time-space alignment and uniform resolution; generating a vegetation mask based on the vegetation classification data set, obtaining a standardized sample slice, and constructing a training data set in combination with spectral features; performing time-phase-sharing processing on the training data set based on vegetation phenological characteristics, and outputting a preliminary vegetation classification result; performing object-level optimization on the preliminary vegetation classification result to obtain an optimized vegetation classification result; and correcting an optimized vegetation classification result in combination with topographic data, generating a vegetation species classification map of a target year, and realizing vegetation dynamic change inversion in a specified time period through transfer learning. Therefore, traditional resolution limitation can be broken through, the classification error problem caused by independent use of multi-source data is solved, the distinction degree of complex vegetation types is remarkably improved, and historical vegetation dynamic backtracking analysis is supported.

The invention discloses a resident-free island vegetation classification method. The method comprises the steps of S1, data acquisition and preprocessing; s2, constructing a random forest model; s3, feature importance evaluation; s4, evaluating feature correlation; s5, feature optimization; s6, precision evaluation; according to the method, the problem that high-precision classification and time sequence dynamic monitoring of non-resident island coastal blue carbon resources in a complex environment are difficult to realize is solved, a remote sensing fine monitoring method is provided, and only satellite remote sensing and ground monitoring data are used; and fine classification and time sequence change detection of resident-free island vegetation types are realized.

The application provides a ConvNeXt-based remote sensing image vegetation classification method and device, relates to the technical field of vegetation classification, and comprises the following steps: acquiring sample remote sensing image data, expanding the sample remote sensing image data by using an Fmix mixed sample data enhancement algorithm, and obtaining a sample data set; training a vegetation classification model by using the sample data set to obtain a target vegetation classification model, wherein the vegetation classification model comprises a feature encoder constructed based on ConvNeXt and a decoder constructed based on UperNet; after acquiring to-be-classified remote sensing image data, inputting the to-be-classified remote sensing image data into the target vegetation classification model to obtain an initial classification result; performing adjacent category fusion processing on target objects in the initial classification result, and performing contour simplification processing on graph patches in the category fusion processing result to obtain a target classification result, thereby solving the technical problem of low precision of the existing vegetation classification method.

The application provides a loess hilly vegetation disease and pest remote sensing monitoring and evaluation method and device, relates to the technical field of remote sensing monitoring and evaluation methods, and comprises the following steps: calculating the coverage of vegetation by using a double threshold plane method, taking the coverage of vegetation of each grid area as a correction term of ground surface temperature; constructing a temperature difference anomaly index of each grid area; based on the temperature difference anomaly index and transpiration efficiency index of each grid area, calculating the transpiration efficiency index of each grid area by using a vegetation temperature difference method, constructing a vegetation classification model by using a logistic regression method, and classifying each grid area according to a preset threshold value to distinguish a risk grid area and a normal grid area. A prediction model is constructed through the statistical relationship between the vegetation index and the ground surface temperature, the temperature difference anomaly index is quantified, early stress signals of vegetation that are difficult to find can be recognized, the transpiration efficiency is introduced to comprehensively evaluate the water utilization of vegetation, and through a dynamic threshold value and a statistical model, potential risk grids can be recognized before the outbreak of diseases and pests.

[Problem] To provide a vegetation determination system that estimates vegetation proportions of a plurality of plant classifications on the basis of a satellite image. [Solution] In the present invention, an information processing system generates a second trained model by using a training data set which includes a satellite image as input data and includes, as teacher data, an output result of a first trained model generated using a UAV image. The information processing system comprises: a vegetation proportion map generation unit that generates the first trained model by performing training processing for determining a vegetation classification, by using a high-resolution vegetation classification training data set in which the UAV image and the teacher data indicating the vegetation classification are associated with each other, and generates a vegetation proportion map on the basis of a vegetation classification image outputted from the first trained model; a low-resolution vegetation proportion training data generation unit that generates a low-resolution vegetation proportion training data set in which the vegetation proportion map is associated, as the teacher data, with the satellite image; and a second training processing unit that performs machine learning processing for determining vegetation proportions from the satellite image, by using the low-resolution vegetation proportion training data set.

The application discloses a kind of estimation method and system of vegetation canopy combustible moisture content based on meteorology and remote sensing data, comprising the following steps: first, combustible moisture content and various meteorological data and remote sensing data and other several kinds of subsidiary data are selected as combustible moisture content estimation data.Meteorological data includes air temperature, relative humidity, rainfall and wind speed.Remote sensing data includes two vegetation indexes: enhanced vegetation index and normalized vegetation index.Subsidiary data includes: root zone soil moisture, vapor pressure difference, drought index, fire weather factor.Then the long time sequence characteristics of meteorological data are extracted.The size of time window is determined first, and the experimental results show that the correlation coefficient of most sites is relatively high under the time window of 90-210 days.90 days, 150 days and 210 days of time window are selected respectively to extract the time characteristics of four kinds of meteorological data.Secondly, the samples of experimental area are divided into five vegetation classifications, which are closed shrub, sparse shrub, multi-tree tropical grassland, tropical savanna and grassland.Finally, the data sets of the five different vegetation types are sequentially adjusted to obtain the respective estimation model.

The invention discloses a vegetation classification method based on space-time multi-modal deep learning, and relates to the technical field of image processing, and the method comprises the steps: obtaining a multi-temporal optical image, a radar image and digital elevation model data of a to-be-classified region, and forming multi-modal data; extracting spectral features, microwave features, topographic features and texture features to form fusion features; calculating graph node features, and updating the graph node features to form graph features; and fusing the fusion features and the graph features to obtain pixel-level coarse classification logs, carrying out feature extraction and fusion on the fusion features to form region-level coarse classification logs, carrying out fusion to obtain a coarse classification probability, and carrying out fine classification on coarse basic features to obtain a final classification result. The method provided by the invention can adapt to a mountainous area environment with multiple clouds, multiple shadows and large topographic relief, improves the stability and classification fineness of vegetation type identification, and is suitable for wide-range vegetation monitoring and ecological assessment scenes.

The application discloses a power transmission channel vegetation intelligent classification method and device based on UNET and hyperspectrum, and a medium, belongs to the field of computer vision and image processing, including collecting hyperspectrum images of the power transmission channel area by a hyperspectrum remote sensing device and preprocessing; designing and constructing a UNET neural network, training the model using labeled tree category data, classifying using newly collected test data, outputting the tree category to which each pixel point belongs, performing post-processing operations, removing small area noise through morphological operations, using a conditional random field optimization model output, and improving the classification results of similar categories between different tree species. The application improves the accuracy of vegetation classification, improves the processing efficiency and automation degree, effectively solves the classification problem of similar tree species, enhances the spatial consistency of the classification results, saves the labor cost and reduces the error rate.

This application discloses a vegetation classification method based on spatiotemporal multimodal deep learning, relating to the field of image processing technology. The method includes: acquiring multi-temporal optical images, radar images, and digital elevation model data of the region to be classified, forming multimodal data; extracting spectral features, microwave features, topographic features, and texture features to form fused features; calculating graph node features and updating the graph node features to form graph features; fusing the fused features and graph features to obtain pixel-level coarse classification logits; extracting and fusing the fused features to form region-level coarse classification logits; fusing to obtain coarse classification probabilities; and performing fine classification on the coarse class basic features to obtain the final classification result. The method of this application can adapt to mountainous environments with frequent cloud cover, shadows, and large topographic relief, improving the stability and classification precision of vegetation type identification, and is suitable for large-scale vegetation monitoring and ecological assessment scenarios.

The invention provides a vegetation carbon reserve prediction method and device and a storage medium, and the method comprises the steps: extracting a feature set of a to-be-detected region according to a remote sensing image, an elevation model and historical vegetation index information of the to-be-detected region, inputting the feature set into a random forest vegetation classification model, and carrying out the prediction, obtaining at least one vegetation type of the to-be-detected region and region information of each vegetation type in the remote sensing image, and performing segmentation processing on the remote sensing image of the to-be-detected region based on a pre-trained vegetation segmentation model, obtaining at least one piece of vegetation ratio information of the to-be-detected area and corresponding area information of each piece of vegetation ratio information in the remote sensing image, and according to the vegetation type of the to-be-detected area, the area information of each vegetation type in the remote sensing image, the vegetation ratio information and the corresponding area information of each piece of vegetation ratio information in the remote sensing image, obtaining the vegetation ratio information of the to-be-detected area; and determining the carbon reserve of the to-be-detected area. According to the invention, the accuracy of forest carbon reserve estimation is effectively improved.

The invention discloses a UNET and hyperspectrum-based power transmission channel vegetation intelligent classification method and device and a medium, and belongs to the field of computer vision and image processing, and the method comprises the steps: collecting a hyperspectral image of a power transmission channel region through a hyperspectral remote sensing device, and carrying out the preprocessing of the hyperspectral image; designing and constructing a UNET neural network, using labeled tree category data to train a model, using newly collected test data to perform classification, outputting a tree category to which each pixel point belongs, performing post-processing operation, removing small-region noise through morphological operation, and using a conditional random field to optimize model output. And improving classification results of similar categories among different tree species. According to the method, the precision of vegetation classification is improved, the processing efficiency and the automation degree are improved, the classification problem of similar tree types is effectively solved, the space consistency of classification results is enhanced, the labor cost is saved, and the error rate is reduced.

The invention discloses a wetland vegetation classification method and system, and the method comprises the steps: obtaining a synthetic aperture radar SAR image and a multispectral MSI image of a to-be-classified region, and carrying out the preprocessing; inputting the MSI image into a convolutional neural network (CNN) branch, and extracting spectral texture features by using an adaptive scale sensing module (ASPM); performing super-pixel segmentation on the SAR image to construct a super-pixel image; inputting the superpixel image into a GCN (Graph Convolution Network) branch, and extracting structural features by using an ADMS (Adaptive Graph Structure Module); performing pixel-level fusion on the spectral texture features and the structural features by using a gating fusion module GFM to obtain fusion features; and inputting the fusion features into a classifier, and outputting a classification result of the wetland vegetation.

The invention discloses a road area vegetation carbon sink assessment method and system based on the Internet of Things, and a storage medium, relates to the technical field of carbon sink monitoring, and solves the technical problem that the carbon sink assessment precision is low due to the fact that the prior art often depends on a single data source and lacks consideration of the influence of dynamic factors such as traffic interference and soil parameters. Multi-source fusion data is generated based on remote sensing data, sensor data and traffic data; inputting the multi-source fusion data corresponding to the region ID into a vegetation classification model to obtain vegetation result data corresponding to the region ID; generating a regional carbon sink total amount based on the vegetation result data; an alarm signal and an optimization scheme are generated based on the total amount of regional carbon sinks, multiple data sources are considered in real time, fusion weight coefficients are dynamically distributed for all the data sources, multi-source fusion data are more accurate, accurate vegetation result data are obtained through a pre-trained vegetation classification model, accurate data support is provided for carbon sink evaluation, and the carbon sink evaluation efficiency is improved. And the accuracy of the carbon sink evaluation method is improved.

The application discloses a salt marsh vegetation classification method, system, device, medium and product, relates to the field of salt marsh vegetation classification, and comprises the following steps: generating a vegetation index time sequence according to satellite remote sensing data; dividing a coastal zone latitude into several classification latitude zones as classification intervals, calculating the mean value and variance index of each vegetation index in each interval per month, and the mean value index and variance index of the current year; based on the normalized difference vegetation index time sequence and the enhanced vegetation index time sequence, calculating the growth period and decay period indexes of the vegetation by using a double logistic function; calculating the J-M distance of each candidate classification index on different vegetation classification samples; based on the J-M distance of the indexes on different vegetation classification samples and the preliminary classification contribution evaluation, screening out the most separable classification index, and constructing a final random forest classification model to classify the salt marsh vegetation in the coastal salt marsh wetland. The application can efficiently complete the coastal plant classification task at low cost.

The invention discloses an underwater vegetation classification method based on unsupervised learning and feature fusion. The method comprises the following steps: S1, collecting an original image; s2, inputting the original image into a deep convolutional neural network, removing redundant information, and generating a low-dimensional visual feature vector; s3, performing quantification processing on the original image through a multi-modal large model, performing ID processing on the unstructured graph according to the biological cue word, inputting the processed unstructured graph into an EAPCR-AE model, and extracting a low-dimensional high-density semantic feature vector; s4, performing L2 normalization on the low-dimensional visual feature vector and the low-dimensional high-density semantic feature vector respectively, and then performing splicing; constructing an orthogonal subspace by using a principal component analysis technology, extracting a principal component of which the cumulative variance contribution rate reaches a preset threshold value, and outputting a fusion feature vector; and S5, performing clustering and voting judgment on the fused feature vector to form a classification result. According to the underwater vegetation classification method, the feature fusion barrier of visual features and word meaning features in label classification is overcome, and the classification accuracy is high.

The present application provides a kind of vegetation classification method, device, equipment and medium based on space-spectrum neural network, method includes: high spectral dataset is divided into training set, verification set and test set, and quantitative evaluation index is set;Based on the information separation of space-spectrum mixed search space, the differentiable architecture search strategy based on gradient optimization is used to search the neural network architecture, and the target network architecture is obtained, the information separation spectrum transformation operator for extracting spectral features is included in the space-spectrum mixed search space, and the information separation space attention depth convolution operator for extracting spatial features;Based on training set and verification set, the target network architecture is trained to obtain a classification model;Test set is input into the classification model to obtain vegetation classification result, and the classification result is evaluated according to quantitative evaluation index, solves the problem that classification accuracy and efficiency still have room for improvement in complex vegetation fine classification task, cannot meet the demand of large-scale, high-precision remote sensing monitoring.

Techniques to accurately display and identify reflected radar returns for a radar system. Processing circuitry of a radar system, such as an airborne weather radar system, may apportion the returned energy from transmitted radar signals to a ground map or to a weather display. The radar system of this disclosure may include databases with a digital elevation model and terrain type. Different terrain and foliage types may have different radar cross sections and therefore different returned energy to the radar system with different reflectivity characteristics. The radar system may discriminate between clutter and weather such that the radar cross section of water is used to discriminate and apportion returned radar energy when over water. In this manner the radar system of this disclosure may correctly display weather, terrain, and water to resolve ambiguity.

Vegetation management system includes: a data acquisition unit that acquires input data including remote sensing data obtained by photographing, by remote sensing, a facility and vegetation to be analyzed; a vegetation classification unit that classifies the vegetation photographed in the remote sensing data; a wide-area growth prediction unit that predicts a time-series change of a growth range of the vegetation photographed in the remote sensing data; a vegetation amount simulation unit that predicts a fluctuation in the growth amount of each vegetation by a simulation; a three-dimensional construction unit that constructs a three-dimensional model expressing the facility and the vegetation; and a risk determination unit that determines a contact risk indicating a contact possibility between the facility and the vegetation.

The invention discloses a multi-source remote sensing data forest carbon sink dynamic monitoring and evaluation system, and relates to the technical field of forest carbon sink amount measurement and calculation. Comprising a vegetation measurement and calculation module, a forest remote sensing module, an individual detection module, a data summarization module and a data comparison module which are connected in sequence, the vegetation measurement and calculation module is used for obtaining ground plant coverage and obtaining a vegetation segmentation image; the forest remote sensing module is used for classifying different vegetation types in the vegetation segmentation image and dividing a sampling area to obtain a vegetation classification image; the individual detection module is used for detecting the carbon content of different types of individual trees and predicting the growth speed of the trees; the data summarization module is used for constructing and training a carbon-containing model, and predicting and recording the carbon content of the tree according to the age and the growth speed of the tree; and the data comparison module is used for comparing the predicted forest carbon content with the recent actually-measured forest carbon content to obtain a comparison result and then evaluating the comparison result. According to the method, the forest carbon sink change state can be evaluated and early warned.

The invention relates to the technical field of forest and grass resource management, and provides a forest and grass field-oriented multi-modal knowledge graph feature alignment and cooperative completion method, which provides comprehensive and accurate decision support for intelligent management of forest and grass resources. According to the method, four core modules which work cooperatively are designed; a cross-domain feature alignment module effectively unifies multi-source data feature distribution from different geographic regions and time periods through an adversarial training mechanism and dynamic weight adjustment; the multi-modal cooperative completion module is based on an improved generative adversarial network framework and intelligently reconstructs remote sensing images and sensor data lacked due to cloud layer shielding, equipment faults and the like; the knowledge enhancement module applies a bidirectional attention mechanism to deeply fuse professional knowledge in the fields of vegetation classification, pest and disease damage rules and the like to enhance the semantic expression ability of the map; the dynamic feature fusion module enables a knowledge graph to adaptively reflect seasonal changes and periodic laws of an ecological system through real-time calculation of modal weights and relation weights.

The application discloses a vegetation growth condition recognition method based on RGB color clustering, which comprises the following steps: obtaining a vegetation RGB image of a region to be recognized as image data source for recognizing the vegetation growth condition; establishing a growth condition image data set of different vegetation, determining the cluster center and the boundary of the growth condition image data set of different vegetation; performing RGB color clustering analysis on the vegetation RGB image according to the cluster center and the boundary of different vegetation, realizing the vegetation growth condition recognition according to the clustering analysis, and obtaining a vegetation classification region of different vegetation growth conditions. The method can realize the pixel-level precision recognition of the vegetation growth condition in the RGB image, obtain the high-precision vegetation growth condition region size, and thus evaluate the vegetation growth state. The method does not need to make a large number of training images, and can recognize the vegetation growth state without model training, so that the vegetation growth condition can be evaluated scientifically and reliably.

The embodiment of the application relates to the field of artificial intelligence technology, and provides a coastal salt marsh vegetation carbon sink estimation method and system based on multi-temporal phenology characteristics. The method comprises the following steps: acquiring remote sensing images of a target coastal salt marsh area at key phenological periods; using an unsupervised classification method to extract an initial vegetation contour of a vegetation coverage range in the target area from the remote sensing images; constructing a phenological decision tree model with an NDVI threshold method as the core, and integrating a machine learning enhanced node division mechanism and a phenological period slope analysis method to strengthen the phenological decision tree model; inputting the initial vegetation contour into the phenological decision tree model, and performing multi-level classification on the vegetation types according to the initial vegetation contour by the phenological decision tree model to distinguish the vegetation coverage ranges of various types of vegetation in the target coastal salt marsh area; acquiring a vegetation carbon density parameter, combining the vegetation coverage range, and calculating the total carbon sink amount of the target coastal salt marsh area through spatial superposition to realize accurate vegetation classification and efficient carbon sink estimation.

The application discloses a vegetation species identification method for strengthening AI computing power and time sequence tracing, comprising the following steps: collecting multi-source remote sensing data and performing pretreatment, constructing a vegetation classification dataset with spatiotemporal alignment and unified resolution; generating a vegetation mask based on the vegetation classification dataset, obtaining a standardized sample slice, and constructing a training dataset in combination with spectral characteristics; performing time-phase processing on the training dataset based on vegetation phenological characteristics, and outputting a preliminary vegetation classification result; performing object-level optimization on the preliminary vegetation classification result, and obtaining an optimized vegetation classification result; correcting the optimized vegetation classification result in combination with terrain data, generating a vegetation species classification map of a target year, and realizing vegetation dynamic change inversion in a specified time period through transfer learning. Therefore, the traditional resolution limit can be broken through, the classification error problem caused by independent use of multi-source data can be solved, the discrimination of complex vegetation types can be significantly improved, and historical vegetation dynamic backtracking analysis can be supported.