Three-dimensional Fusion of Spaceborne and Ground Radar Reflectivity Data Using a Neural Network–Based Approach

The spaceborne precipitation radar onboard the Tropical Rainfall Measuring Mission satellite （TRMM PR） can provide good measurement of the vertical structure of reflectivity, while ground radar （GR） has a relatively high horizontal resolution and greater sensitivity. Fusion of TRMM PR and GR reflectivity data may maximize the advantages from both instruments. In this paper, TRMM PR and GR reflectivity data are fused using a neural network （NN）-based approach. The main steps included are： quality control of TRMM PR and GR reflectivity data; spatiotemporal matchup; GR calibration bias correction; conversion of TRMM PR data from Ku to S band; fusion of TRMM PR and GR reflectivity data with an NN method： interpolation of reflectivity data that are below PR＇s sensitivity; blind areas compensation with a distance weighting-based merging approach; combination of three types of data： data with the NN method, data below PR＇s sensitivity and data within compensated blind areas. During the NN fusion step, the TRMM PR data are taken as targets of the training NNs, and gridded GR data after horizontal downsampling at different heights are used as the input. The trained NNs are then used to obtain 3D high-resolution reflectivity from the original GR gridded data. After 3D fusion of the TRMM PR and GR reflectivity data, a more complete and finer-scale 3D radar reflectivity dataset incorporating characteristics from both the TRMM PR and GR observations can be obtained. The fused reflectivity data are evaluated based on a convective precipitation event through comparison with the high resolution TRMM PR and GR data with an interpolation algorithm.

Radar emitter multi-label recognition based on residual network

In low signal-to-noise ratio(SNR)environments,the traditional radar emitter recognition(RER)method struggles to recognize multiple radar emitter signals in parallel.This paper proposes a multi-label classification and recognition method for multiple radar-emitter modulation types based on a residual network.This method can quickly perform parallel classification and recognition of multi-modulation radar time-domain aliasing signals under low SNRs.First,we perform time-frequency analysis on the received signal to extract the normalized time-frequency image through the short-time Fourier transform(STFT).The time-frequency distribution image is then denoised using a deep normalized convolutional neural network(DNCNN).Secondly,the multi-label classification and recognition model for multi-modulation radar emitter time-domain aliasing signals is established,and learning the characteristics of radar signal time-frequency distribution image dataset to achieve the purpose of training model.Finally,time-frequency image is recognized and classified through the model,thus completing the automatic classification and recognition of the time-domain aliasing signal.Simulation results show that the proposed method can classify and recognize radar emitter signals of different modulation types in parallel under low SNRs.

New structure of Kalman filter for radar networking

Due to the different data rates of the sensors and communication delays in the radar netting, the research of the asynchronous multisensor data fusion problem is more practical than that of the synchronous one. Through discussing the sequential approach, which is the classical asynchronous multisensor data fusion algorithm, a new algorithm based on distributed computation structure is proposed. The new algorithm can meet the requirement of real-time computation of netting fusion system, and is more practical for engineering compared with the classical sequential approach. Simulation results show the validity of the presented algorithm.

Deep convolutional neural network for meteorology target detection in airborne weather radar images

Considering the problem that the scattering echo images of airborne Doppler weather radar are often reduced by ground clutters,the accuracy and confidence of meteorology target detection are reduced.In this paper,a deep convolutional neural network(DCNN)is proposed for meteorology target detection and ground clutter suppression with a large collection of airborne weather radar images as network input.For each weather radar image,the corresponding digital elevation model(DEM)image is extracted on basis of the radar antenna scan-ning parameters and plane position,and is further fed to the net-work as a supplement for ground clutter suppression.The fea-tures of actual meteorology targets are learned in each bottle-neck module of the proposed network and convolved into deeper iterations in the forward propagation process.Then the network parameters are updated by the back propagation itera-tion of the training error.Experimental results on the real mea-sured images show that our proposed DCNN outperforms the counterparts in terms of six evaluation factors.Meanwhile,the network outputs are in good agreement with the expected mete-orology detection results(labels).It is demonstrated that the pro-posed network would have a promising meteorology observa-tion application with minimal effort on network variables or parameter changes.

An Approach for Radar Quantitative Precipitation Estimation Based on Spatiotemporal Network

Radar quantitative precipitation estimation(QPE)is a key and challenging task for many designs and applications with meteorological purposes.Since the Z-R relation between radar and rain has a number of parameters on different areas,and the rainfall varies with seasons,the traditional methods are incapable of achieving high spatial and temporal resolution and thus difficult to obtain a refined rainfall estimation.This paper proposes a radar quantitative precipitation estimation algorithm based on the spatiotemporal network model(ST-QPE),which designs a convolutional time-series network QPE-Net8 and a multi-scale feature fusion time-series network QPE-Net22 to address these limitations.We report on our investigation into contrast reversal experiments with radar echo and rainfall data collected by the Hunan Meteorological Observatory.Experimental results are verified and analyzed by using statistical and meteorological methods,and show that the ST-QPE model can inverse the rainfall information corresponding to the radar echo at a given moment,which provides practical guidance for accurate short-range precipitation nowcasting to prevent and mitigate disasters efficiently.

APPLICATION OF NOISE REDUCTION METHOD BASED ON CURVELET THRESHOLDING NEURAL NETWORK FOR POLAR ICE RADAR DATA PROCESSING

Due to the demand of data processing for polar ice radar in our laboratory, a Curvelet Thresholding Neural Network (TNN) noise reduction method is proposed, and a new threshold function with infinite-order continuous derivative is constructed. The method is based on TNN model. In the learning process of TNN, the gradient descent method is adopted to solve the adaptive optimal thresholds of different scales and directions in Curvelet domain, and to achieve an optimal mean square error performance. In this paper, the specific implementation steps are presented, and the superiority of this method is verified by simulation. Finally, the proposed method is used to process the ice radar data obtained during the 28th Chinese National Antarctic Research Expedition in the region of Zhongshan Station, Antarctica. Experimental results show that the proposed method can reduce the noise effectively, while preserving the edge of the ice layers.

Track-to-Track Association Technique in Radar Network in the Presence of Systematic Errors

The presence of systematic measuring errors complicates track-to-track association, spatially separates the tracks that correspond to the same true target, and seriously decline the performances of traditional track-to-track association algorithms. Consequently, the influence of radar systematic errors on tracks from different radars, which is described as some rotation and translation, has been analyzed theoretically in this paper. In addition, a novel approach named alignment-correlation method is developed to estimate and reduce this effect, align and correlate tracks accurately without prior registration using phase correlation technique and statistic binary track correlation algorithm. Monte-Carlo simulation results illustrate that the proposed algorithm has good performance in solving the track-to-track association problem with systematic errors in radar network and could provide effective and reliable associated tracks for the next step of registration.

IMMUNE RBF NETWORK AND ITS APPLICATION IN THE MODULATION-STYLE RECOGNITION OF RADAR SIGNALS

Based on Immune Programming(IP), a novel Radial Basis Function (RBF) networkdesigning method is proposed. Through extracting the preliminary knowledge about the widthof the basis function as the vaccine to form the immune operator, the algorithm reduces thesearching space of canonical algorithm and improves the convergence speed. The application ofthe RBF network trained with the algorithm in the modulation-style recognition of radar signalsdemonstrates that the network has a fast convergence speed with good performances.

Layer-Constrained Triangulated Irregular Network Algorithm Based on Ground Penetrating Radar Data and Its Application

In this paper,a layer-constrained triangulated irregular network（ LC-TIN） algorithm is proposed for three-dimensional（ 3 D） modelling,and applied to construct a 3 D model for geological disease information based on ground penetrating radar（ GPR） data. Compared with the traditional TIN algorithm,the LCTIN algorithm introduced a layer constraint to the discrete data points during the 3 D modelling process,and it can dynamically construct networks from layer to layer and implement 3 D modelling for arbitrary shapes with high precision. The experimental results validated this method,the proposed algorithm not only can maintain the rationality of triangulation network,but also can obtain a good generation speed. In addition,the algorithm is also introduced to our self-developed 3 D visualization platform,which utilized GPR data to model geological diseases. Therefore the feasibility of the algorithm is verified in the practical application.

Improved Weather Radar Echo Extrapolation Through Wind Speed Data Fusion Using a New Spatiotemporal Neural Network Model

Weather radar echo extrapolation plays a crucial role in weather forecasting.However,traditional weather radar echo extrapolation methods are not very accurate and do not make full use of historical data.Deep learning algorithms based on Recurrent Neural Networks also have the problem of accumulating errors.Moreover,it is difficult to obtain higher accuracy by relying on a single historical radar echo observation.Therefore,in this study,we constructed the Fusion GRU module,which leverages a cascade structure to effectively combine radar echo data and mean wind data.We also designed the Top Connection so that the model can capture the global spatial relationship to construct constraints on the predictions.Based on the Jiangsu Province dataset,we compared some models.The results show that our proposed model,Cascade Fusion Spatiotemporal Network(CFSN),improved the critical success index(CSI)by 10.7%over the baseline at the threshold of 30 dBZ.Ablation experiments further validated the effectiveness of our model.Similarly,the CSI of the complete CFSN was 0.004 higher than the suboptimal solution without the cross-attention module at the threshold of 30 dBZ.

基于CNN-Swin Transformer Network的LPI雷达信号识别

针对在低信噪比(SNR)条件下,低截获概率雷达信号调制方式识别准确率低的问题,提出一种基于Transformer和卷积神经网络(CNN)的雷达信号识别方法。首先,引入Swin Transformer模型并在模型前端设计CNN特征提取层构建了CNN+Swin Transformer网络(CSTN),然后利用时频分析获取雷达信号的时频特征,对图像进行预处理后输入CSTN模型进行训练,由网络的底部到顶部不断提取图像更丰富的语义信息,最后通过Softmax分类器对六类不同调制方式信号进行分类识别。仿真实验表明:在SNR为-18 dB时,该方法对六类典型雷达信号的平均识别率达到了94.26%,证明了所提方法的可行性。

Study on Quantitative Precipitation Estimation by Polarimetric Radar Using Deep Learning

Accurate radar quantitative precipitation estimation(QPE)plays an essential role in disaster prevention and mitigation.In this paper,two deep learning-based QPE networks including a single-parameter network and a multi-parameter network are designed.Meanwhile,a self-defined loss function(SLF)is proposed during modeling.The dataset includes Shijiazhuang S-band dual polarimetric radar(CINRAD/SAD)data and rain gauge data within the radar’s 100-km detection range during the flood season of 2021 in North China.Considering that the specific propagation phase shift(KDP)has a roughly linear relationship with the precipitation intensity,KDP is set to 0.5°km^(-1 )as a threshold value to divide all the rain data(AR)into a heavy rain(HR)and light rain(LR)dataset.Subsequently,12 deep learning-based QPE models are trained according to the input radar parameters,the precipitation datasets,and whether an SLF was adopted,respectively.The results suggest that the effects of QPE after distinguishing rainfall intensity are better than those without distinguishing,and the effects of using SLF are better than those that used MSE as a loss function.A Z-R relationship and a ZH-KDP-R synthesis method are compared with deep learning-based QPE.The mean relative errors(MRE)of AR models using SLF are improved by 61.90%,51.21%,and 56.34%compared with the Z-R relational method,and by 38.63%,42.55%,and 47.49%compared with the synthesis method.Finally,the models are further evaluated in three precipitation processes,which manifest that the deep learning-based models have significant advantages over the traditional empirical formula methods.

Anti-swarm UAV radar system based on detection data fusion

There is a growing body of research on the swarm unmanned aerial vehicle(UAV)in recent years,which has the characteristics of small,low speed,and low height as radar target.To confront the swarm UAV,the design of anti-UAV radar system based on multiple input multiple output(MIMO)is put forward,which can elevate the performance of resolution,angle accuracy,high data rate,and tracking flexibility for swarm UAV detection.Target resolution and detection are the core problem in detecting the swarm UAV.The distinct advantage of MIMO system in angular accuracy measurement is demonstrated by comparing MIMO radar with phased array radar.Since MIMO radar has better performance in resolution,swarm UAV detection still has difficulty in target detection.This paper proposes a multi-mode data fusion algorithm based on deep neural networks to improve the detection effect.Subsequently,signal processing and data processing based on the detection fusion algorithm above are designed,forming a high resolution detection loop.Several simulations are designed to illustrate the feasibility of the designed system and the proposed algorithm.

Generalization Capabilities of Feedforward Neural Networks for Pattern Recognition

This paper studies the generalization capability of feedforward neural networks (FNN).The mechanism of FNNs for classification is investigated from the geometric and probabilistic viewpoints. It is pointed out that the outputs of the output layer in the FNNs for classification correspond to the estimates of posteriori probability of the input pattern samples with desired outputs 1 or 0. The theorem for the generalized kernel function in the radial basis function networks (RBFN) is given. For an 2-layer perceptron network (2-LPN). an idea of using extended samples to improve generalization capability is proposed. Finally. the experimental results of radar target classification are given to verify the generaliztion capability of the RBFNs.

A Short-Range Quantitative Precipitation Forecast Algorithm Using Back-Propagation Neural Network Approach

A back-propagation neural network （BPNN） was used to establish relationships between the shortrange （0-3-h） rainfall and the predictors ranging from extrapolative forecasts of radar reflectivity, satelliteestimated cloud-top temperature, lightning strike rates, and Nested Grid Model （NGM） outputs. Quan- titative precipitation forecasts （QPF） and the probabilities of categorical precipitation were obtained. Results of the BPNN algorithm were compared to the results obtained from the multiple linear regression algorithm for an independent dataset from the 1999 warm season over the continental United States. A sample forecast was made over the southeastern United States. Results showed that the BPNN categorical rainfall forecasts agreed well with Stage Ⅲ observations in terms of the size and shape of the area of rainfall. The BPNN tended to over-forecast the spatial extent of heavier rainfall amounts, but the positioning of the areas with rainfall ≥25.4 mm was still generally accurate. It appeared that the BPNN and linear regression approaches produce forecasts of very similar quality, although in some respects BPNN slightly outperformed the regression.

Automatic Identification of Clear-Air Echoes Based on Millimeter-wave Cloud Radar Measurements

Millimeter-wave cloud radar(MMCR)provides the capability of detecting the features of micro particles inside clouds and describing the internal microphysical structure of the clouds.Therefore,MMCR has been widely applied in cloud observations.However,due to the influence of non-meteorological factors such as insects,the cloud observations are often contaminated by non-meteorological echoes in the clear air,known as clear-air echoes.It is of great significance to automatically identify the clear-air echoes in order to extract effective meteorological information from the complex weather background.The characteristics of clear-air echoes are studied here by combining data from four devices:an MMCR,a laser-ceilometer,an L-band radiosonde,and an all-sky camera.In addition,a new algorithm,which includes feature extraction,feature selection,and classification,is proposed to achieve the automatic identification of clear-air echoes.The results show that the recognition algorithm is fairly satisfied in both simple and complex weather conditions.The recognition accuracy can reach up to 95.86%for the simple cases when cloud echoes and clear-air echoes are separate,and 88.38%for the complicated cases when low cloud echoes and clear-air echoes are mixed.

Dataset of human motion status using IR-UWB through-wall radar

Ultra-wideband(UWB)through-wall radar has a wide range of applications in non-contact human information detection and monitoring.With the integration of machine learning technology,its potential prospects include the physiological monitoring of patients in the hospital environment and the daily monitoring at home.Although many target detection methods of UWB through-wall radar based on machine learning have been proposed,there is a lack of an opensource dataset to evaluate the performance of the algorithm.This published dataset is measured by impulse radio UWB(IR-UWB)through-wall radar system.Three test subjects are measured in different environments and several defined motion status.Using the presented dataset,we propose a human-motion-status recognition method using a convolutional neural network(CNN),and the detailed dataset partition method and the recognition process flow are given.On the well-trained network,the recognition accuracy of testing data for three kinds of motion status is higher than 99.7%.The dataset presented in this paper considers a simple environment.Therefore,we call on all organizations in the UWB radar field to cooperate to build opensource datasets to further promote the development of UWB through-wall radar.

Optimization method of linear barrier coverage deployment for multistatic radar

To address the problem of building linear barrier coverage with the location restriction, an optimization method for deploying multistatic radars is proposed, where the location restriction splits the deployment line into two segments. By proving the characteristics of deployment patterns, an optimal deployment sequence consisting of multiple deployment patterns is proposed and exploited to cover each segment. The types and numbers of deployment patterns are determined by an algorithm that combines the integer linear programming(ILP)and exhaustive method(EM). In addition, to reduce the computation amount, a formula is introduced to calculate the upper threshold of receivers’ number in a deployment pattern. Furthermore, since the objective function is non-convex and non-analytic, the overall model is divided into two layers concerning two suboptimization problems. Subsequently, another algorithm that integrates the segments and layers is proposed to determine the deployment parameters, such as the minimum cost, parameters of the optimal deployment sequence, and the location of the split point. Simulation results demonstrate that the proposed method can effectively determine the optimal deployment parameters under the location restriction.

An interference suppression algorithm for cognitive bistatic airborne radars

Interference suppression is a challenge for radar researchers, especially when mainlobe and sidelobe interference coexist. We present a comprehensive anti-interference approach based on a cognitive bistatic airborne radar. The risk of interception is reduced by lowering the launch energy of the radar transmitting terminal in the direction of interference;main lobe and sidelobe interferences are suppressed via cooperation between the two radars. The interference received by a single radar is extracted from the overall radar signal using multiple signal classification(MUSIC), and the interference is cross-located using two different azimuthal angles. Neural networks allowing good, non-linear nonparametric approximations are used to predict the location of interference, and this information is then used to preset the transmitting notch antenna to reduce the likelihood of interception. To simultaneously suppress mainlobe and sidelobe interferences, a blocking matrix is used to mask mainlobe interference based on azimuthal information, and an adaptive process is used to suppress sidelobe interference. Mainlobe interference is eliminated using the data received by the two radars. Simulation verifies the performance of the model.

Underground Disease Detection Based on Cloud Computing and Attention Region Neural Network

Detecting the underground disease is very crucial for the roadbed health monitoring and maintenance of transport facilities,since it is very closely related to the structural health and reliability with the rapid development of road traffic.Ground penetrating radar(GPR)is widely used to detect road and underground diseases.However,it is still a challenging task due to data access anywhere,transmission security and data processing on cloud.Cloud computing can provide scalable and powerful technologies for large-scale storage,processing and dissemination of GPR data.Combined with cloud computing and radar detection technology,it is possible to locate the underground disease quickly and accurately.This paper deploys the framework of a ground disease detection system based on cloud computing and proposes an attention region convolution neural network for object detection in the GPR images.Experimental results of the precision and recall metrics show that the proposed approach is more efficient than traditional objection detection method in ground disease detection of cloud based system.