161 results about "Radar reflectivity" patented technology

The invention relates to a wind resource prediction method based on quality control assimilation of multi-source observation data, and the method comprises the steps: integrating the multi-source observation data, including a multi-band radar reflectivity factor, a radial speed, a ground observation station, and wind profile radar data; quality control processing such as mottle removal, data filling, speed folding removal and discontinuous data removal is carried out, so that the accuracy and continuity of the data are improved; then, through lattice point interpolation and three-dimensional variation assimilation technologies, the processed observation data are fused into an initial background field, and an analysis field closer to the actual atmospheric state is generated, so that the reliability of severe convective weather risk assessment is remarkably improved, and the accuracy of wind energy prediction is also enhanced; and more comprehensive, detailed and stable information support is provided for weather forecast and energy management.

The embodiment of the invention provides a simulated target reflectivity factor quantitative generation method for weather radar far-field region calibration, and is applied to the technical field of weather radar calibration. The method comprises the following steps: acquiring radar antenna and emission parameters, a distance between a target simulator erection point and a radar, a simulation target distance, and a transmit-receive radiance ratio of a target simulator; according to a pre-constructed simulation target equivalent sectional area quantitative model, based on the radar antenna and emission parameters, the distance between the target simulator erection point and the radar, the transmit-receive radiance ratio of the target simulator and the simulation target distance, calculating to obtain a simulation target equivalent sectional area; and calculating to obtain a radar reflectivity factor expected value according to the equivalent sectional area of the simulation target, the radar antenna and emission parameters and a weather radar equation. In this way, a simulated target reflectivity factor for weather radar far-field region calibration can be quantitatively generated.

The invention relates to the technical field of meteorological satellite observation, and discloses a mode rainfall forecast correction method based on deep learning and a wind cloud satellite, and the method comprises the steps: constructing a rainfall correction main model, collecting multi-source data, and carrying out the primary processing of the collected multi-source data, and obtaining a fusion input data set A; carrying out feature extraction and generating a satellite feature tensor B, generating a mode physical feature tensor C, generating a fusion feature tensor D based on inter-modal correlation, generating a corrected rainfall prediction tensor E, and generating a radar reflectivity prediction tensor F and an uncertainty estimation tensor G; and deploying the trained model into the system, and inputting a fusion data set A at the current time. By introducing the physical consistency loss and combining with the physical constraint to optimize the rainfall prediction model, strict conformity between the rainfall prediction result and the meteorological physical law is realized, the rainfall field better conforming to the physical reality is obtained, unreasonable fluctuations and errors in the prediction result are effectively reduced, and the physical consistency of rainfall prediction is improved.

The invention discloses a thunder and lightning positioning method and system based on multi-source data fusion, and belongs to the technical field of thunder and lightning monitoring and positioning. The method comprises the following steps: in a preset time window, collecting first and second arrival time of a lightning event received by each ground lightning detection device, and calculating the arrival time difference; and extracting a lightning detection distance, a capture time difference and an observation included angle in combination with the lightning area image, obtaining an electric field change rate, a radar reflectivity and an equipment distance, substituting into a combined lightning positioning formula, and calculating a space distance between a lightning striking point and the first receiving equipment. Through the position information of the equipment, the geographical coordinate of the lightning striking point is calculated. According to the scheme, the spatial resolution and accuracy of lightning positioning can be effectively improved, positioning errors caused by a traditional radar or single-point monitoring method are reduced, simultaneous positioning of a plurality of lightning striking points is supported, and accurate data support and spatial decision basis are provided for subsequent lightning risk early warning, power equipment protection and disaster traceability.

The invention discloses a microwave link-weather radar combined rainfall inversion method based on Z-R relation adaptive adjustment, and the method comprises the steps: defining a related parameter set of microwave link rainfall estimation and weather radar reflectivity measurement in observation time, and carrying out the matching and space-time averaging processing, and obtaining rainfall intensity-radar reflectivity characteristics; fitting a radar reflectivity-rainfall intensity relation within observation time by using a least square method based on the rainfall intensity-radar reflectivity characteristics; according to the radar reflectivity-rainfall intensity relation sample of the known position, calculating the spatial distribution of the radar reflectivity-rainfall intensity relation in the research area by using an inverse distance weighted interpolation method; and according to the spatial distribution of the radar reflectivity-rainfall intensity relationship within the observation time and the average reflectivity factor measured by the radar, calculating to obtain a spatial distribution result of the accumulated rainfall within the observation time. According to the invention, the accuracy of regional rainfall monitoring is effectively improved.

The invention discloses a hail prediction method and device, a medium and a program product, and relates to the technical field of meteorology, and the method comprises the steps: obtaining a neural network model; acquiring historical lightning characteristic variable data and historical hail characteristic variable data; dividing the historical lightning characteristic variable data and the historical hail characteristic variable data into a training set and a verification set of corresponding characteristic variables; training the neural network model through the training set and the verification set of the corresponding feature variables, and taking the trained neural network model as a target neural network model; acquiring current lightning characteristic variable data; determining a dynamic weighting loss function according to the target neural network model; and predicting hail weather according to the current lightning characteristic variable data and the dynamic weighted loss function to obtain hail prediction parameters. According to the technology provided by the invention, misjudgment caused by forecasting the hail by independently using the radar reflectivity factor is reduced, and the hail forecasting precision is improved by indicating the factor through the lightning characteristic data.

The invention relates to the technical field of radar reflectivity factor calibration, and discloses a terahertz cloud measurement radar calibration method based on channel perception, which comprises the following steps: S1, acquiring two types of input data; s2, constructing a multi-scale channel model; s3, constructing a distance error estimation model; s4, constructing a dynamic time correction model; and S5, constructing a calibration module. According to the method, a high-precision physical channel model is constructed to independently predict path attenuation of signals, the concepts of gain deviation and path attenuation factors are put forward, the influence of thermal noise attenuated by radar on radar waves in the atmospheric environment is reflected respectively, and a Kalman filtering algorithm is used to estimate the path attenuation of the signals. And filtering errors generated in the time direction, and finally, calibrating the radar reflectivity factor by using the channel data by means of a calibration formula.

The invention refers to a method for computer-implemented generation of a data-driven model for computer-implemented processing of a single-look complex (SLC) image (10) captured with a SAR system adapted to obtain radar reflectivity, wherein the SLC image (10) comprises a real part and an imaginary part, and wherein the data-driven model is adapted to jointly despeckle and compress the SLC image (10). The generation of the data-driven model comprises the following steps: - providing a training data set (TDS) comprising a plurality of SLC images (10) each of them comprising a real part and an imaginary part; - training a neural network (NN) with the training data set (TDS), the neural network (NN) comprising an input for inputting either the real part or the imaginary part of a respective SLC image (10) of the plurality of SLC images (10) as input information, where a latent space (y) resulting from encoding the input information with an encoder (100) is concatenated and compressed to a compressed bitstream (MBS, SBS), and an output for outputting an estimated intensity (Î), where the estimated intensity (Î) results from splitting and decoding the compressed bitstream (MBS, SBS), the trained neural network (NN) representing the generated data-driven model.

The embodiment of the invention provides a spaceborne radar and ground-based millimeter wave cloud radar reflectivity factor uniformity evaluation method, which is applied to the technical field of atmospheric detection. The method comprises the following steps: acquiring reflectivity factor data of a spaceborne radar and a ground-based millimeter wave cloud radar; establishing reflectivity factor space-time matching data of the spaceborne radar and the ground-based millimeter wave cloud radar according to the reflectivity factor data by taking vertical direction scanning as a reference; preprocessing the time-space matching data of the reflectivity factors; and based on a preset uniformity evaluation algorithm, an evaluation result is calculated according to the preprocessed reflectivity factor space-time matching data. In this way, errors between original data can be better revealed, and a good foundation is laid for product inversion in the next step.

The invention relates to the technical field of reflectivity factor testing, and discloses a weather radar reflectivity factor precision calibration testing system, which comprises a radar data acquisition module for acquiring reflectivity factor data and finishing time synchronization by adopting an IEEE1588 protocol; the reference data management module is used for generating an electronic reference data set by utilizing a block chain technology; the calibration processing module is used for performing multi-source joint correction on the reflectivity factor data, the rain gauge data, the standard meteorological target template and the environmental parameters, and outputting the corrected reflectivity data; the precision verification module is used for carrying out real-time precision test on the correction data based on a sliding window, continuously generating test results, forming a precision evaluation vector by adopting weighted average, extracting a quality index to obtain a comprehensive score, and judging whether the correction data is normal or abnormal; and the alarm and report module is used for triggering graded alarm in case of abnormity and generating a calibration certificate and a test report. According to the invention, the precision monitoring capability is improved, manual judgment errors are reduced, and the operation efficiency is improved.

The invention discloses a convective cloud in-cloud temperature gradient joint inversion method based on a laser radar, and relates to the technical field of meteorological detection, and the method comprises the steps: synchronously collecting multi-modal meteorological remote sensing data through a multi-modal meteorological remote sensing device; constructing an adversarial unsupervised correction network, inputting the multi-modal meteorological remote sensing data into the adversarial unsupervised correction network, and generating corrected multi-source observation data; mapping the corrected multi-source observation data to a uniform space-time grid to form a space-time aligned multi-modal data set; and based on the vertical profile of the temperature gradient, in combination with the radar reflectivity factor and the fusion feature vector, calculating the vertical distribution of the liquid water content, the water vapor density and the particle effective radius in the convective cloud, and generating a quantitative analysis report of the macro and micro characteristics of the convective cloud. According to the invention, by constructing the antagonistic unsupervised correction network, errors in multi-source observation data can be effectively corrected, and a high-quality data basis is provided for fusion and inversion in meteorological service.

The invention discloses a ground-based radar calibration deviation estimation method based on satellite-ground precipitation radar verification, and the method mainly comprises the steps: carrying out the frequency correction of a satellite-borne radar SR reflectivity factor from a Ku wave band to an S wave band, and carrying out the projection conversion of a polar coordinate system with a ground-based radar GR as a center after the correction; the converted SR and GR reflectivity factors are subjected to overlapping matching in time and space which are accurate to seconds; the mean value precision is improved through inverse distance weight, and the precipitation space heterogeneity of SR and GR in the matching space is reduced through the in-pixel non-uniform beam filling quality control technology; a satellite-ground precipitation radar quality control factor threshold standard system is established, whole-process quality control is carried out in the calibration deviation estimation process, and finally ground-based radar GR calibration deviation estimation is realized through comparison verification of spaceborne radar SR and ground-based radar GR reflectivity factors after quality control processing. According to the invention, the error of satellite-ground radar inspection can be effectively reduced, and the precision of rainfall estimation is improved.

The invention relates to the technical field of automatic detection and early warning of weather radar gust front, and discloses a weather radar gust front automatic identification system based on deep learning, which comprises a radar data acquisition and preprocessing module used for acquiring radar echo data from weather radar equipment, carrying out format conversion on the data, and sending the converted data to a server; the radar reflectivity is converted from a polar coordinate format to a Cartesian coordinate format, and meanwhile, normalization processing of the radar reflectivity value is carried out; and the feature extraction and region candidate generation module is used for performing feature extraction on the radar image by adopting a deep convolutional neural network and generating a target region candidate box through a region candidate network, and the region candidate network comprises a classification branch and a regression branch. According to the method, rapid and accurate gust front identification is realized through a deep learning target detection and mask segmentation technology, the stability and robustness of detection are remarkably improved, false alarms and missing alarms are effectively reduced through dynamic alarm threshold calculation and trend analysis, and the accuracy and timeliness of alarm are improved.

The invention relates to the technical field of artificial influence weather, and discloses a multi-source data fused artificial precipitation enhancement operation control method, which comprises the following steps: acquiring cloud body data of a target cloud body, including cloud body height, radar reflectivity and temperature intervals and boundaries of a plurality of temperature layers, and executing cloud body type judgment. Firstly, whether a preset temperature layer exists or not is judged, and if the preset temperature layer does not exist or the height of the cloud body is lower than a preset threshold value, the cloud body is determined as a non-operation cloud body; if the cloud body exists and the height meets the condition, calculating the fluctuation amount of the height, the temperature and the reflectivity, and dividing the cloud body into a first target cloud body or a second target cloud body according to the fluctuation amount. If the target cloud body is the first target cloud body, directly issuing a rainfall enhancement instruction; and if the target cloud body is a second target cloud body, carrying out secondary data acquisition and judgment, and if the target cloud body is still the second target cloud body, giving up the operation. Therefore, the scientificity and the accuracy of the rainfall enhancement operation are guaranteed.

The invention discloses a radar reflectivity inversion method based on satellite infrared data and lightning observation data, which belongs to the technical field of meteorological monitoring, and comprises the following steps: taking a three-channel input image formed by the lightning observation data and two infrared images from different infrared channels as the input of a scattering model; the lightning activity is closely related to severe convective weather, so that the scattering model can be helped to perform radar reflectivity inversion in areas lacking radar data, such as an open sea, a plateau and a desert, and the defect of insufficient accurate modeling of strong weather events in the prior art is overcome; more comprehensive and multi-dimensional input information is provided for radar data reconstruction, and the accuracy of radar reflectivity inversion is remarkably improved.

The invention relates to the technical field of three-dimensional wind field inversion, in particular to a three-dimensional wind field inversion method in a thunderstorm cloud strong echo region based on a single Doppler weather radar, which comprises the following steps of: 1, carrying out lattice processing on a radar reflectivity factor to obtain a radar reflectivity factor; the reflectivity factor is converted from a polar coordinate system to a Cartesian rectangular coordinate system through interpolation; 2, performing same-layer continuous moment strong echo graph similarity recognition through an image similarity recognition technology; 3, calculating the horizontal movement speed of the thunderstorm cloud at different heights; and 4, comparing the observation result of the radial speed of the radar with the horizontal movement speed of the thunderstorm, and calculating the rising or sinking airflow speed. According to the method, the grid data of the single Doppler weather radar and the observation data of the radial speed of the radar can be utilized to accurately describe the three-dimensional wind field of the strong echo region in the thunderstorm cloud.

The invention discloses a cloud micro-physical model optimization and numerical verification method for a hail wet growth process, and the method comprises the steps: constructing a hail wet growth process parameterization scheme based on the physical principle that hail and supercooled water drops collide and freeze, and coupling the hail wet growth process parameterization scheme to a Morrison cloud micro-physical scheme of a CMA-MESO mode for detection. By calculating a hail ventilation coefficient and combining the environment temperature, the air density and the diffusion coefficient, the condition of wet growth is judged, and the change of the hail mass mixing ratio is updated. The CMA-MESO mode is used for carrying out actual severe convection hail reduction example simulation, and the forecast improvement effect of the newly-added process on variables such as radar reflectivity, hail mass mixing ratio and number concentration vertical section, time horizontal integral vertical profile of part of hydrogel in cloud and maximum estimated hail size is evaluated. According to the invention, the simulation capability of the mode on the generation and development process of large hail is improved, and the accuracy of quantitative simulation of hail in severe convection weather is enhanced.

The invention provides a plateau multi-source rainfall data fusion method and device based on a deep bidirectional sequential network. The method comprises the following steps: acquiring historical multi-source rainfall data; constructing and training a bidirectional time sequence attention multi-source fusion network model, and performing feature extraction and fusion calculation training; and performing precipitation estimation on the target area by using the bidirectional time sequence attention multi-source fusion network model, and outputting fused precipitation grid point data. Through multi-branch feature fusion, the network shows good nonlinear expression ability when processing a multi-scale rainfall field, the estimation precision of complex terrains and extreme rainfall events is effectively improved, a lightweight design is adopted, the network greatly reduces the calculation complexity while guaranteeing the multi-source rainfall fusion precision, and the calculation efficiency is improved. The method improves the flexibility of practical application, improves the fusion precision of multi-channel information such as radar reflectivity, satellite brightness temperature and ground rainfall, and greatly improves the precision and calculation efficiency of multi-source rainfall fusion.

The invention discloses a forest fire automatic identification and risk assessment method based on X-band and S-band dual-band joint detection, and the method comprises the steps: deploying an X-band radar and an S-band radar to construct a cooperative detection network, and forming a detection region covering short and long ranges through space-time registration; a Kalman filtering algorithm is adopted to fuse dual-source radar data, and the method comprises the following steps: defining a four-dimensional state vector containing a plane position coordinate and a velocity component; directly mapping the position component of the state vector to a radar reflectivity plane observation value by using a position mapping type observation matrix; fire point identification based on a random forest model comprises the following steps: inputting feature fusion space reflectivity parameters and time dynamic features; calculating the heat release rate per unit area through the linear combination of the dual-polarization radar reflectivity and the differential reflectivity; calculating fire intensity by combining the fire point area; and coupling the fire intensity with the wind field spreading prediction, and generating graded early warning information oriented to power grid safety.

The invention relates to a satellite-ground radar reflectivity factor consistency evaluation and deviation traceability method and system, and belongs to the field of radar calibration evaluation, and the method comprises the steps: generating reference ground radar scanning parameters according to geographical environment multi-source heterogeneous data; acquiring satellite-ground radar data according to the scanning parameters of the reference ground-based radar when the satellite-borne radar passes the scene, and performing preprocessing and space-time matching to obtain a satellite-ground radar data pair; based on the target correction information of each height level region, performing sectional frequency correction on the spaceborne radar data to obtain an optimal satellite-ground radar data pair; and carrying out reflectivity factor consistency evaluation on the optimal satellite-ground radar data pair, taking an obtained evaluation result as a tracing reference, and carrying out deviation tracing calibration estimation on the service ground-based radar in combination with a satellite-ground radar reflectivity factor consistency evaluation result of the service ground-based radar. According to the method, the technical problems of precise evaluation of systematic deviation of satellite-ground radar data and unified evaluation and calibration of multi-service satellite-ground radars are solved.

The invention relates to a verification method and system for ground-based millimeter wave cloud radar data, and belongs to the technical field of meteorological analysis. The method comprises the following steps: establishing a clear sky echo identification and filtering method, and generating ground-based millimeter wave cloud radar base data after quality control; classifying the ground-based millimeter wave cloud radar base data after quality control into cloud data and rainfall data; the Cloud Sat satellite and the ground-based millimeter wave cloud radar after quality control have reflectivity factor matching and evaluation in cloud data; and matching and evaluating reflectivity factors in GPM satellite and quality-controlled ground-based millimeter wave cloud radar rainfall data. According to the invention, a ground-based millimeter wave cloud radar quality control and classification method is established, a high-quality refined ground-based millimeter wave cloud radar database can be generated, and a good basis is provided for ground-based millimeter wave cloud radar data application; a matching and evaluation method of spaceborne radar and ground-based millimeter wave cloud radar reflectivity factors under different conditions is established, and reference is provided for ground-based millimeter wave cloud radar calibration correction and satellite-ground radar combined application.

The invention relates to the technical field of rainfall prediction, in particular to a high-frequency second-length time sequence short-imminent forecasting method and system based on generative AI, and the method comprises the following steps: compressing an original radar reflectivity sequence into a compact hidden variable Token sequence through employing a pre-trained variational auto-encoder; in the compressed hidden space, with the hidden variable Token sequence as a condition, a prediction hidden variable Token sequence in a future time period is generated step by step in a probability generation mode; and reconstructing the predicted hidden variable Token sequence into a predicted radar reflectivity sequence in a future time period by using a decoder of the variational auto-encoder. According to the method, high-resolution and long-time-efficiency radar nowcasting is realized, the accuracy of rainfall forecasting in a 2-6-hour short-term and imminent forecasting grey area time window is improved, and a solid support is provided for constructing early warning and accurate decision-making of extreme weather.

This invention discloses a radar echo extrapolation method that incorporates three-dimensional environmental field data. Radar baseline data is collected; each set of 21 consecutive radar reflectivity maps is converted into a sample, with the first 11 serving as input and the last 10 serving as labels. Based on the sample information, matching ERA5 global analysis data is collected. The radar reflectivity sequence and the corresponding environmental field are used as input to train a 3D convolutional neural network model. Experimental results show that the inclusion of the environmental field improves the extrapolation performance compared to a model without the environmental field, and is more consistent with meteorological interpretation of the extrapolation principle. By incorporating simultaneous three-dimensional environmental field data, the invention achieves accurate constraints and corrections on the extrapolation results.

The invention relates to the technical field of meteorology and hydrology, and discloses a quantitative rainfall estimation method and system based on multi-source data correction radar echoes, and the method comprises the steps: collecting the multi-source data, such as rainfall station actually measured rainfall data, elevation data, hydrometric station flow, radar reflectivity, soil humidity and environmental attributes, in a target region; a Z-R relation parameter of each radar sampling grid is dynamically calibrated by combining a collaborative Kriging interpolation and physical constraint hybrid neural network model, and a radar reflectivity correction parameter of each grid is calculated by using a difference between rainfall station observation data and radar data; in real-time application, based on the corrected radar reflectivity and the calibrated Z-R parameter, the rainfall intensity of each grid is inverted, and the precision of quantitative rainfall estimation is improved.

The invention discloses a cloud supercooled water content prediction method based on deep learning and spatio-temporal data driving, and the method comprises the steps: obtaining satellite multi-channel radiation transmission data, carrying out the channel screening and feature extraction, obtaining radar reflectivity data, and carrying out the data interpolation and feature extraction; the method comprises the following steps: acquiring conventional meteorological data of a ground automatic meteorological station, performing feature extraction, fusing the features by using a multi-head attention mechanism to obtain fused features, establishing a deep learning neural network model, and predicting the content of supercooled water in cloud in a future time period. The method can more comprehensively and accurately predict the content and the distribution condition of the supercooled water in the cloud, and has important scientific and practical significance for relieving water resource shortage, improving the ecological environment and guaranteeing low-altitude economic safety.

The invention relates to a phased array radar reflectivity factor simulation method based on sparse sounding data, belongs to the field of radio, designs a sparse reconstruction simulation scheme based on acquired multi-point multi-height-layer sparse sounding data, and realizes high-quality restoration and three-dimensional continuous field construction of original sparse observation data. A multivariate dictionary base matrix is constructed; through a sparse representation theory and a Bayesian optimization model, a sparse coefficient reflecting rainfall essential characteristics is obtained, and high-spatial-resolution reconstruction of a temperature and humidity field and a rainfall micro-physical parameter field is realized. Thereafter, a meteorological parameter-driven phase judgment and probability field calculation model is constructed, and three-dimensional simulation of liquid, solid and mixed rainfall echoes is realized. And finally, calculating a unit direction vector and an azimuth guidance coding matrix of a beam ray of the phased array radar, introducing a radar volume scanning data implicit sampling simulator, and realizing high-precision reflectivity factor simulation of the phased array radar in a three-dimensional scanning mode.

The invention discloses a radar reflectivity factor forecasting method based on an FY-4A satellite, and the method comprises the following steps: obtaining the remote sensing observation data of a visible light channel VIS and an infrared channel IR of a target region, and carrying out the preprocessing; a DeepLabv3 + model is constructed; training and optimizing the model; taking the preprocessed satellite data as input, taking a radar reflectivity factor as a supervision label, and taking a mean square error (MSE) as a loss function; using an independent test set to calculate a mean absolute error MAE and a mean square error MSE as evaluation indexes; testing the stability of the model through K-fold cross validation; deploying the trained model to a meteorological service system, inputting an FY-4A satellite image in real time, and outputting a radar reflectivity prediction image; according to the invention, noise in radar reflectivity prediction can be reduced.

The invention relates to a broadband wave-absorbing and anti-bullet integrated material and a preparation method thereof. The broadband wave-absorbing and anti-bullet integrated material sequentially comprises an outer skin layer, a wave-absorbing and anti-bullet layer and an inner skin layer, the wave-absorbing anti-elastic layer comprises a plurality of anti-elastic plate layers and wave-absorbing material layers arranged among the plurality of anti-elastic plate layers; the anti-elastic plate layer is a high-density polyethylene fiber anti-elastic plate layer; the wave-absorbing material layer is of a hollowed-out woven structure. According to the broadband wave-absorbing and anti-bullet integrated material, the broadband wave-absorbing and anti-bullet integrated effect is achieved, the advantages of being small in thickness, low in surface density and the like are further achieved, and the maximum radar reflectivity of the broadband wave-absorbing and anti-bullet integrated wave-absorbing material is-10 dB or below within the range of 2 GHz to 18 GHz and 26.5 GHz to 40 GHz.

The invention discloses an automatic driving risk assessment method and device, a vehicle, equipment and a medium, and belongs to the technical field of automatic driving. The method comprises the following steps: respectively acquiring a visual image and a radar reflectivity graph of a target road surface; after time synchronization and space calibration are carried out on the visual image and the radar reflectivity graph, visual features of an area where a lane line is located are extracted from the visual image by adopting a convolutional neural network, a target reflectivity area higher than a reflectivity threshold in the radar reflectivity graph is identified, and reflectivity distribution features of the target reflectivity area are extracted; fusing the visual features and the reflectivity distribution features according to time synchronization and space calibration results to obtain a lane line comprehensive feature set; generating a lane line sensing result according to the lane line comprehensive feature set; and matching is performed from the risk level relationship according to the aging degree of the lane line and the complexity of the road surface, and the target risk level corresponding to the lane line modeling information is obtained, so that the safety of automatic driving is improved.

The present invention discloses a method for identifying and classifying Doppler radar clutter based on SE-Res2Net-101, including extracting radar reflectivity Z in the base data H , differential reflectivity Z DR , correlation coefficient ρ HV and differential propagation phase shift rate K DP numerical data; preprocessing the extracted numerical data to generate a data set; constructing an SE-Res2Net-101 model; inputting the training set data into SE-Res2Net-101 for model training; inputting the test data set into the trained model, and making clutter judgments through the prediction probability given by the model. Solve the technical problem of current clutter detection technology that requires digital simulation of ground terrain and the provision of DEM, and establish a clutter prediction model from the variables of Z H , Z DR , ρ HV and K DP A method for identifying clutter in a Doppler radar and classifying biological clutter and ground clutter based on a residual convolutional network with an SE attention mechanism, which improves accuracy and speeds up the prediction speed