105 results about "Tropical cyclone" patented technology

The invention provides a power equipment meteorological monitoring and early warning system based on artificial intelligence. The power equipment meteorological monitoring and early warning system based on artificial intelligence comprises a data acquisition module, a data preprocessing module, a spatio-temporal feature fusion module and a meteorological disaster prediction model, the meteorological disaster prediction model adopts a deep reinforcement learning framework, inputs a multi-dimensional spatio-temporal feature matrix, and carries out meteorological disaster prediction on the multi-dimensional spatio-temporal feature matrix. And outputting meteorological disaster risk levels and key parameter predicted values in a future preset time period, including a wind speed, precipitation, temperature anomaly and tropical cyclone path probability, a dynamic early warning threshold generation module, an early warning decision module and a model optimization module. The power equipment meteorological monitoring and early warning system based on artificial intelligence provided by the invention has the advantages that the data interpolation precision of a complex terrain region can be improved, high-precision prediction of a typhoon path, short-time strong wind and an icing risk can be realized, and the early warning accuracy and defense response efficiency of a power system to meteorological disasters can be comprehensively improved.

The invention belongs to the technical field of ocean remote sensing, and relates to a spaceborne microwave radiometer tropical cyclone wind speed inversion method based on physical constraint deep learning, comprising the following steps: acquiring tropical cyclone parameter information; extracting multi-band brightness temperature data of the satellite-borne microwave radiometer in a corresponding space-time range, and constructing a sample data set; a deep learning inversion algorithm model with physical constraints is loaded and trained; the physical constraint deep learning inversion algorithm model comprises an input layer, a network layer, a physical layer and an output layer; the network layer is composed of a residual neural network, the physical layer is composed of a D matrix remote sensing statistical formula and provides physical constraints for the whole model, and the D matrix is a nonlinear D matrix; and outputting the tropical cyclone wind speed in the current space-time range. According to the method, the brightness temperature information of the satellite-borne microwave radiometer is obtained by utilizing the tropical cyclone trajectory information, and the network model with physical information is constructed by utilizing the combination of the D matrix equation and the neural network, so that more accurate and high-precision tropical cyclone wind speed information is obtained.

The invention relates to a tropical cyclone strength intelligent forecasting method and device based on feature adaptive optimization. The method comprises the following steps: constructing an initial data set; the initial data set is divided into a model training sample and an independent test sample; selecting a pre-training model; inputting the model training sample into a pre-training model for feature adaptive optimization, and obtaining a high impact factor set influencing tropical cyclone strength prediction accuracy; performing model optimization training; and carrying out model robustness test and tropical cyclone strength intelligent forecasting. According to the method, the high impact factor set which is most critical to tropical cyclone strength forecasting can be rapidly extracted, and the tropical cyclone strength forecasting accuracy is remarkably improved.

Disclosed are a tropical cyclone symmetry structure analysis method and apparatus, a device, and a storage medium. TC locations and TC intensities are acquired based on TC best track datasets; polar coordinate systems are created with the TC locations as origins; hourly infrared brightness temperature data are acquired based on satellite data, and are interpolated into the corresponding polar grids to obtain infrared brightness temperature polar grid data; then convection symmetry indexes of inner-core regions of TCs are calculated based on the infrared brightness temperature polar grid data; and finally, the relationship between the convective symmetry indexes and the TC intensities is analyzed.

The invention relates to a tropical cyclone strength prediction method and device based on a large meteorological model, and the method comprises the following stages: 1, mapping tropical cyclone strength information to a discrete vector implicit space through an encoder under the conditions of a satellite image and reanalysis of atmospheric field data, a mapping result is compared with all vectors of a learnable discrete codebook, the closest vector is taken and restored to original tropical cyclone strength information through a decoder, and iterative training is carried out on the encoder, the discrete codebook and the decoder; and a second stage: inputting historical meteorological data into the trained encoder and discrete codebook, converting the historical meteorological data into discrete hidden variables, carrying out autoregression iteration to obtain forecast hidden variables, and restoring tropical cyclone strength information through the decoder by taking wind-wind forecast field data as physical constraints to obtain a tropical cyclone strength prediction result. Compared with the prior art, the method has the advantages that long-term forecasting can be achieved, good performance is preserved, and the calculation cost is reduced.

The invention belongs to the technical field of weather prediction, discloses a tropical cyclone ensemble forecasting method, system and equipment based on a depth generation diffusion model and a medium, and aims to improve the accuracy, reliability and uncertainty quantification capability of forecasting by taking the output of a big fortune weather model as a condition and generating a diversified forecasting set by using the diffusion model. The method comprises the following steps: acquiring global ERA5 reanalysis data at a current moment and a previous moment as initial field data of deterministic forecasting, and inputting the initial field data into a big fortune weather model to generate a deterministic forecasting result at a (t + 1) moment; taking the deterministic forecast result as the conditional input of a conditional probability diffusion model, and generating N ensemble forecast members through the conditional probability diffusion model in combination with random noise data and auxiliary condition information with the same dimension as the deterministic forecast result; and carrying out statistical analysis and calculation on probability distribution of tropical cyclone paths and strength based on the N ensemble forecasting members, and generating an ensemble forecasting product.

The invention discloses a typhoon intensity prediction method and device fused with a space-time deep network, and a medium, and the method comprises the following steps: 1), collecting typhoon historical observation data, and obtaining typhoon data; 2) data preprocessing; 3) extracting data features; 4) feature fusion; 5) establishing a typhoon intensity prediction model; 6) model training; and 7) performing prediction by using the trained model, outputting a final prediction value, and restoring a prediction result into an actual typhoon intensity value through reverse normalization processing. The influence of the remote sensing satellite image and the characteristics of the tropical cyclone on the tropical cyclone strength estimation accuracy is considered, the typhoon strength prediction integrated with the spatio-temporal information is carried out, the spatio-temporal representation of the typhoon focus area is enhanced through the integration of the spatial characteristics and the time sequence characteristics of the typhoon, and the accuracy of the strength prediction result is improved.

The invention discloses an inland area TRP feature recognition and evaluation method based on data driving and numerical simulation, a medium and a program product, and relates to the technical field of meteorological disaster monitoring and early warning and numerical simulation. And objectively identifying a TRP event which occurs outside the typhoon circulation and is connected with the strong water vapor conveying belt by combining the typhoon peripheral circulation radius, the distance constraint and the whole-layer water vapor conveying flux. Key physical fields such as whole-layer water vapor flux, water vapor income and expenditure, dry invasion and monsoon water vapor surge are diagnosed by utilizing a regional numerical mode and reanalysis data, and a characteristic index set reflecting typhoon, monsoon and dry and cold air coupling influence is formed; on the basis, a data-driven learning algorithm is introduced, a TRP occurrence and rainstorm intensity grading recognition model is obtained through training, a risk assessment product is generated through calibration and risk grading, and therefore the inland typhoon long-distance rainstorm recognition and assessment capacity is improved.

The invention relates to the technical field of data analysis, in particular to a mangrove forest health assessment system based on tropical cyclones. The structure risk coefficient, the geological risk coefficient and the ecological risk coefficient are combined to obtain the health risk index of the mangrove forest, so that accurate health assessment is realized, meteorological data and cyclonic state data are monitored to predict a cyclonic prediction path, and the prediction accuracy is improved. And then the cyclonic prediction path and the health risk index of the mangrove forest are combined to form risk response management and control on damaged and undamaged mangrove forests, so that accurate judgment and supervision on key areas are formed, and the situation of excessive damage caused by untimely management and control on the mangrove forest is reduced.

The invention relates to a regional composite disaster chain risk assessment method under the influence of a tropical cyclone, and the method comprises the steps: obtaining and preprocessing the historical multi-source observation data of the tropical cyclone, and constructing a multi-dimensional disaster element data set; analyzing non-linear change characteristic parameters of each disaster element based on the multi-dimensional disaster element data set, and constructing a multi-dimensional disaster element quantitative model and a comprehensive disaster intensity index based on the non-linear change characteristic parameters; modeling the historical change trajectory of the comprehensive disaster intensity index, extracting an abnormal mode and time-space characteristic parameters, and constructing a composite disaster chain spatio-temporal evolution prediction model; and acquiring real-time multi-source observation data of the tropical cyclones, inputting the real-time multi-source observation data into the composite disaster chain spatio-temporal evolution prediction model to predict a composite disaster chain spatio-temporal evolution trend, performing quantitative analysis on the composite disaster chain spatio-temporal evolution trend, and determining risk levels of different regions. According to the method, quantitative description and evaluation of the tropical cyclone composite disaster chain spatio-temporal evolution process are realized by integrating multi-source heterogeneous data.

The invention relates to a tropical cyclone composite disaster multi-source data intelligent fusion early warning system, and the system comprises a data collection module which is used for collecting a multi-source data set; the preprocessing module is used for preprocessing the multi-source data set to obtain a standardized multi-source data set; the feature mining module is used for performing spatial feature mining and time feature mining on the standardized multi-source data set to obtain a spatial feature vector matrix and a time feature vector; the fusion module is used for fusing the spatial feature vector matrix and the time feature vector by adopting an attention mechanism to obtain a multi-dimensional fusion feature; the composite disaster prediction module is used for performing trajectory calculation and intensity evolution analysis on the multi-dimensional fusion features, and acquiring occurrence probabilities of rainstorm, flood and storm surge according to trajectory calculation data and intensity evolution data; and the early warning module is used for obtaining a comprehensive early warning result according to the occurrence probability of the rainstorm, the flood and the storm surge. According to the invention, accurate early warning of tropical cyclones and composite disasters caused by the tropical cyclones can be realized.

The invention discloses a tropical cyclone induced area heavy rainfall event identification and unsteady state characteristic analysis method. The method comprises the following steps: data acquisition; identifying a regional heavy rainfall event; associating a tropical cyclone with a regional heavy rainfall event; identifying the characteristics of regional heavy rainfall caused by the tropical cyclone; analyzing the regional heavy rainfall characteristic change rate caused by the tropical cyclone; unsteady-state frequency analysis of regional heavy rainfall characteristics caused by tropical cyclones is carried out; the action mechanism and the influence of shortening of the recurrence period of a heavy rainfall event in an extreme region caused by tropical cyclone; the method has the beneficial effects that the space-time evolution and movement characteristics of the regional extreme rainfall caused by the tropical cyclone can be fully identified, the change rule of the recurrence period of the severe rainfall event caused by the tropical cyclone in the extreme region is clarified, and the accuracy of forecasting the severe rainfall caused by the tropical cyclone can be further improved; and a scientific basis is provided for resisting disasters caused by tropical cyclones and making decisions.

The invention provides a multi-task tropical cyclone strength prediction method under guidance of physical information, a TC-MulPred tropical cyclone strength prediction model is constructed, and the TC-MulPred tropical cyclone strength prediction model sequentially comprises a feature aggregation module, a backbone prediction module, a feature enhancement module and a feedforward output module. The feature aggregation module performs feature aggregation on an input satellite image through encoding space information and tropical cyclone strength information to obtain global feature representation, and the backbone prediction module predicts the global feature representation based on an encoder and decoder framework to obtain a tropical cyclone strength initial prediction sequence. The feature enhancement module performs data enhancement on the initial prediction sequence of the tropical cyclone strength to obtain an enhanced prediction sequence, and the feed-forward output module maps the enhanced prediction sequence into a tropical cyclone strength index prediction value; in the training process, a physical guidance constraint loss function based on the tropical cyclone air pressure relation is introduced, and the tropical cyclone strength prediction precision is improved.

The present application relates to a kind of tropical cyclone intensity prediction method and device based on meteorological big model, method includes following stage: first stage: with satellite image and reanalysis atmospheric field data as condition, tropical cyclone intensity information is mapped to discrete vector hidden space by encoder, compare the mapping result with all vectors of learnable discrete codebook, take the closest vector and restore back original tropical cyclone intensity information by decoder, and iteration training is carried out to encoder, discrete codebook and decoder;Second stage: historical meteorological data is input into trained encoder and discrete codebook, is converted into discrete hidden variable, and is carried out autoregressive iteration, obtains forecast hidden variable, and with wind-uw forecast field data as physical constraint, tropical cyclone intensity information is restored back by decoder, obtains tropical cyclone intensity prediction result.Compared with prior art, the present application has the advantages of long-term prediction, good performance, reduced computing cost and the like.

The invention relates to the technical field of power system risk assessment, in particular to a power grid risk assessment method, device and equipment under extreme weather and a storage medium, and the method comprises the steps: analyzing an abnormal action mechanism of an extreme weather factor on power grid equipment under a tropical cyclone, and obtaining a wind power abnormal output space-time matrix under the extreme weather; a line fault state space-time matrix is obtained through power transmission line fault probability sampling, and an abnormal state matrix of a power grid is obtained through integration; combining the abnormal state matrix with power flow redistribution to obtain a power grid abnormal coupling process considering the extreme weather and the power flow redistribution; a power grid abnormal propagation path is obtained through re-scheduling and island processing of a unit in a power grid abnormal coupling process, an abnormal propagation path evolution process is determined, and abnormal propagation paths of different power grids are obtained through simulation; and determining risk assessment indexes according to the abnormal propagation paths of different power grids, and calculating to obtain a risk assessment result considering the abnormal space-time evolution of the power grids.

The invention relates to a tropical cyclone strength prediction method and a tropical cyclone strength prediction system based on multi-modal data. According to the method, the tropical cyclone strength prediction is carried out by integrating the multi-modal data and extracting and integrating related characteristics between the multi-modal data. The method comprises the following steps: firstly, acquiring a multi-modal data set, dividing the multi-modal data set according to tropical cyclone batches and time, extracting data features from the divided multi-modal data, and integrating the data features to obtain integrated multi-modal fusion features; carrying out coding and decoding processing on the integrated multi-modal fusion features to obtain a future meteorological feature sequence; carrying out calculation processing on the future meteorological feature sequence by adopting a self-attention mechanism, and obtaining an aggregated long-term global feature; and finally, extracting wind speed information from the gathered long-term global feature sequence to obtain a tropical cyclone strength prediction value. Compared with the prior art, the method has the advantages of high accuracy, good timeliness, strong robustness and the like.

The invention discloses a conditional diffusion method for reconstructing multi-source meteorological data for tropical cyclones. The conditional diffusion method comprises the following steps: acquiring an infrared radiation brightness set, a polarization correction temperature set and a sea surface wind speed of different tropical cyclones in a specified historical period; constructing a polarization correction temperature reconstruction model based on the conditional diffusion model; the input of the polarization correction temperature reconstruction model is an infrared radiation brightness temperature set, and the output target is a polarization correction temperature set; carrying out transfer learning on the trained polarization correction temperature reconstruction model to form a sea surface wind speed reconstruction model; the input of the sea surface wind speed reconstruction model is an infrared radiation brightness temperature set, and the output target is the sea surface wind speed. Therefore, the mapping relation from the infrared radiation brightness temperature to the multi-source meteorological data is established through generative deep learning of conditional diffusion, so that the multi-source meteorological data with the temporal-spatial resolution the same as that of geostationary orbit observation is reconstructed, and good performance is shown on various meteorological indexes and computer vision indexes.

The application discloses a LES super-high-resolution TC atmospheric flow field numerical simulation method and system, and relates to the fields of atmospheric observation, numerical assimilation and high-resolution numerical simulation. The method is characterized in that: three-dimensional dynamic-thermal information is obtained by implementing airship platform radar observation and downward sounding observation in the core area of a tropical cyclone; the radar radial wind and profile observation operators are preprocessed and constructed; a data assimilation strategy is adopted to integrate multi-source observation in a multi-nested grid numerical model to generate a three-dimensional initial / reanalysis field suitable for large eddy simulation; then, a large eddy simulation solver is configured on the innermost grid covering the boundary layer of the tropical cyclone; fine horizontal grids and boundary layer encryption vertical stratification are adopted to explicitly analyze the boundary layer vortex, small-scale convection and turbulent structure; and a super-high-resolution three-dimensional flow field product for fine evaluation of strong wind and disaster risk is output.

The invention discloses a tropical cyclone abnormal path forecasting method based on spatio-temporal multi-scale fusion and evidence learning. The tropical cyclone abnormal path forecasting method comprises the steps of preprocessing collected satellite cloud picture data; marking the preprocessed satellite cloud picture on the basis of the IBTrACS optimal path set; constructing a tropical cyclone abnormal path forecasting model based on space-time multi-scale fusion and evidence learning; training the constructed tropical cyclone abnormal path forecasting model; and forecasting the abnormal path of the tropical cyclone at the future moment by using the trained abnormal path forecasting model of the tropical cyclone. The tropical cyclone abnormal path forecasting model provided by the invention not only can provide a high-precision path forecasting result, but also can accurately identify and forecast an abnormal path type, and provides reliable decision support and reference basis for a service forecasting department.

The invention discloses a tropical cyclone path screening method, system and device, a medium and a product, and relates to the field of ocean and weather forecast, and the method comprises the steps: selecting a tropical cyclone sample, and determining a first path similar typhoon list of the tropical cyclone sample based on a tropical cyclone path similarity method; based on a comparative learning tropical cyclone similarity evaluation model, determining a second path similar typhoon list of the tropical cyclone sample; the comparative learning tropical cyclone similarity evaluation model is obtained by training a training data set; the training data set comprises a CMA tropical cyclone optimal path data set and ERA5 reanalysis data information; according to the first path similar typhoon list and the second path similar typhoon list, a tropical cyclone list similar to the tropical cyclone sample path is determined, and an optimal tropical cyclone path is screened from the tropical cyclone list. And the misjudgment condition is avoided.

The invention discloses a deep learning tropical cyclone center positioning method based on multiband fusion. The method comprises the following steps: preprocessing a collected satellite image; constructing a deep learning model which comprises a backbone network feature extraction module, a feature fusion module and a feature enhancement module; extracting features of each tropical cyclone image through a backbone network feature extraction module; carrying out feature fusion on the extracted feature maps through a feature fusion module; the fused features are enhanced through a feature enhancement module; and the enhanced features are sent to ViT, global feature dependence in the image is captured through a self-attention mechanism, and a final output result is generated. According to the method, the information of the tropical cyclone on different wave band images is fully utilized, the spatial features are extracted, the spatial features extracted on the different wave band images are fully fused, the features of the different wave band images neglected by an existing model can be made up, and the positioning precision of the tropical cyclone center is effectively improved.

The application relates to a tropical cyclone disaster loss assessment method and system, and relates to the technical field of natural disaster risk assessment. The method is executed by a computer device and comprises the following steps: acquiring historical cyclone paths, wind field parameters and social and economic statistical data; performing uniform spatial resolution and coordinate reference alignment processing on population and economic spatial distribution data; calculating a hazard intensity index P; determining a cyclone influence range, extracting population exposure PE and economic exposure G; selecting a population and economic vulnerability index set, constructing a population vulnerability index PV and an economic vulnerability index EV; adopting Poisson regression to construct a death assessment model with P, PE and PV as independent variables; and adopting gamma regression to construct an economic loss assessment model with P, G and EV as independent variables. The application realizes double-dimensional and comparable collaborative attribution analysis of historical tropical cyclone event economic loss and population death, and outputs the relative contribution degrees of hazard, exposure and vulnerability to the two types of losses.

The embodiment of the invention discloses a method and device for evaluating the influence of tropical cyclones on the marine environment. The method comprises the following steps: continuously acquiring marine environment parameters of a tropical cyclone influenced sea area, and constructing a multi-dimensional parameter data set based on the marine environment parameters; derivation features are calculated based on the multi-dimensional parameter data set; taking the cyclone strength in the vortex category and the tropical cyclone data as classification features, taking data except the vortex category and the cyclone strength in the multi-dimensional parameter data set and the derivative features as continuous features, and constructing input data according to the classification features and the continuous features; and outputting an environment evaluation result by the trained multi-parameter coupling model based on the input data. In the embodiment, the classification features and the continuous features can be input into the multi-parameter coupling model at the same time, then the dominant factors are determined by quantifying importance ranking, the environment evaluation result is generated according to the dominant factors to predict the environment evolution in a period of time in the future, and the influence of the tropical cyclone on the marine environment is more accurately and quantitatively predicted.

This invention provides a method and apparatus for reconstructing the three-dimensional temperature and humidity field of a tropical cyclone based on deep learning and sparse observations. The method includes: acquiring radiosonde observation data and satellite remote sensing data for a target tropical cyclone region; mapping the radiosonde observation data onto a two-dimensional grid on multiple preset pressure layers to generate an initial temperature and humidity field containing missing data regions, and generating a mask to identify the missing data locations; interpolating and aligning the satellite remote sensing data onto the two-dimensional grid to form an auxiliary remote sensing field; combining the initial temperature and humidity field, the mask, and the auxiliary remote sensing field at each pressure layer to form a multi-channel input tensor, which is then input into a pre-trained deep neural network model. The model infers and completes the missing data regions, outputting the complete two-dimensional temperature and humidity field for the current layer; and vertically synthesizing the complete two-dimensional temperature and humidity fields corresponding to all pressure layers to obtain the three-dimensional temperature and humidity field of the target tropical cyclone.

The application discloses a kind of tropical cyclone temperature body structure calculation method and system, wherein the method includes: based on satellite microwave detection data and tropical cyclone position information, the three-dimensional temperature data of tropical cyclone area is smoothed, and temperature grid with tropical cyclone center as origin is formed.Three-dimensional temperature anomaly value is calculated according to the smoothed temperature grid.Based on three-dimensional temperature anomaly value, three-dimensional region growth method is used to extract tropical cyclone warm core main area.Based on the extracted tropical cyclone warm core main area, the isosurface is calculated using Marching Cubes algorithm.According to the isosurface, the light model is rendered to draw the three-dimensional visualization structure of tropical cyclone warm core.Based on the three-dimensional temperature anomaly value of tropical cyclone warm core main area, the tropical cyclone warm core intensity index is calculated.Thus, the application effectively solves the problem of insufficient overall understanding of tropical cyclone temperature structure in the prior art, and provides the ability of systematic quantitative analysis.

The present invention discloses a method, apparatus, device, and storage medium for analyzing the symmetry structure of a tropical cyclone. The method obtains hourly tropical cyclone center positions and intensity values from a tropical cyclone's optimal path data set, creates a polar coordinate system with the tropical cyclone center position as the origin, obtains hourly infrared cloud top brightness temperature data for the tropical cyclone, and interpolates the infrared cloud top brightness temperature data into a polar coordinate grid of the corresponding polar coordinate system using an interpolation method to obtain infrared cloud top brightness temperature polar coordinate grid data. The method then calculates convective symmetry index parameters for a preset inner core region of the tropical cyclone based on the infrared cloud top brightness temperature polar coordinate grid data, and finally analyzes the relationship between the convective symmetry index parameters of all tropical cyclones and the intensity of the tropical cyclone. The present invention defines the convective symmetry index of the inner core of the cyclone based on the infrared cloud top brightness temperature data of the tropical cyclone, and explores its relationship with changes in cyclone intensity, so as to explore the application of the index in tropical cyclone intensity forecasting.

The invention discloses a cyclone strength prediction result correction method and device based on a diffusion model, equipment and a medium, and relates to the technical field of meteorological prediction, and the method comprises the steps: obtaining target meteorological data in a target time range; inputting the target meteorological data into a preset meteorological prediction server, so that a meteorological prediction model in the preset meteorological prediction server analyzes the target meteorological data by taking a preset ERA5 reanalysis data set as a boundary condition to obtain a tropical cyclone strength prediction result; and obtaining a tropical cyclone strength prediction result from a preset weather server, and correcting the tropical cyclone strength prediction result by using the target cyclone strength correction model. The model constructed based on the neural network is adopted to transform the initial prediction result, rapid and accurate correction of the tropical cyclone strength is realized, and the problems of insufficient prediction precision and low calculation efficiency are solved.

The invention discloses a tropical cyclone strength grade determination method, and the method comprises the steps: obtaining a plurality of collected historical satellite cloud pictures; classifying the plurality of historical satellite cloud pictures, and determining historical satellite cloud pictures respectively corresponding to a plurality of intensity grades; carrying out data equalization processing on the historical satellite cloud pictures corresponding to the plurality of intensity levels to obtain a target satellite cloud picture; inputting the target satellite cloud picture into a to-be-trained neural network model, performing grade prediction by the neural network model based on the target satellite cloud picture, and training the neural network model according to a grade prediction result to obtain a grade prediction model; wherein the grade prediction model is used for predicting the tropical cyclone strength grade. The problem that the tropical cyclone strength grade determination accuracy is low in the related technology is solved.

The application relates to the field of tropical cyclone tracking, in particular to a tropical cyclone automatic tracking method based on a relative threshold value. The method comprises the following steps: obtaining meteorological historical data through a numerical weather prediction model, obtaining relative vorticity and warm core intensity of historical tropical cyclones according to the meteorological historical data; collecting historical tropical cyclone data, calculating relative thresholds of the relative vorticity and the warm core intensity according to the historical tropical cyclone data; obtaining meteorological data at different times according to the numerical weather prediction model, obtaining candidate areas at different times according to the relative thresholds and the meteorological data; obtaining multiple sets of longitude and latitude data and intensity data of tropical cyclone centers at different times according to the candidate areas at different times; and obtaining path and intensity information of each tropical cyclone changing over time by using a clustering algorithm according to the longitude and latitude data and the intensity data. The application solves the problems of low tracking efficiency and poor precision of multiple tropical cyclones in the prior art.

The invention discloses a cyclone strength prediction method and device. The method comprises the following steps: acquiring physical factor data, satellite cloud picture data and cyclone strength data in a historical period of time; preprocessing the physical factor data, the satellite cloud picture data and the cyclone intensity data to obtain a physical factor image, a satellite image and historical cyclone intensity; inputting the physical factor image, the satellite image and the historical cyclone intensity into a tropical cyclone intensity prediction model to obtain a 24-hour cyclone intensity prediction result; wherein the tropical cyclone strength prediction model comprises a hierarchical fusion sub-network, a deep convolutional neural network, a priori knowledge module and an uncertainty estimation module. And uncertainty estimation and long-term prior are fused, so that the prediction capability of the change trend of the cyclone strength and the accuracy of strength prediction are improved.