A multilayer perceptron and multiclass support vector machine based high accuracy technique for daily rainfall estimation from MSG SEVIRI data

The current paper introduces a new multilayer perceptron (MLP) and support vector machine (SVM) based approach to improve daily rainfall estimation from the Meteosat Second Generation (MSG) data. In this study, the precipitation is first detected and classified into convective and stratiform rain by two MLP models, and then four multi-class SVM algorithms were used for daily rainfall estimation. Relevant spectral and textural input features of the developed algorithms were derived from the spectral MSG SEVIRI radiometer channels. The models were trained using radar rainfall data set colected over north Algeria. Validation of the proposed daily rainfall estimation technique was performed by rain gauge network data set recorded over north Algeria. Thus, several statistical scores were calculated, such as correlation coefficient (r), root mean square error (RMSE), mean error (Bias), and mean absolute error (MAE). The findings given by: (r = 0.97, bias = 0.31 mm, RMSE = 2.20 mm and MAE = 1.07 mm), showed a quite satisfactory relationship between the estimation and the respective observed daily precipitation. Moreover, the comparison of the results with those of two advanced techniques based on random forests (RF) and weighted ‘k’ nearest neighbor (WkNN) showed higher accuracy obtained by the proposed model.     

An improved approach for rainfall estimation over Indian summer monsoon region using Kalpana-1 data

In this paper, an improved Kalpana-1 infrared (IR) based rainfall estimation algorithm, specific to Indian summer monsoon region is presented. This algorithm comprises of two parts: (i) development of Kalpana-1 IR based rainfall estimation algorithm with improvement for orographic warm rain underestimation generally suffered by IR based rainfall estimation methods and (ii) cooling index to take care of the growth and decay of clouds and thereby improving the precipitation estimation.     

A MLP neural network as an investigator of TEC time series to detect seismo-ionospheric anomalies

Anomaly detection is extremely important for earthquake parameters estimation. In this paper, an application of Artificial Neural Networks (ANNs) in the earthquake precursor’s domain has been developed. This study is concerned with investigating the Total Electron Content (TEC) time series by using a Multi-Layer Perceptron (MLP) neural network to detect seismo-ionospheric anomalous variations induced by the powerful Tohoku earthquake of March 11, 2011.     

Improved rainfall estimation over the Indian region using satellite infrared technique

The GOES Precipitation Index (GPI) technique (Arkin, 1979) for rainfall estimation has been in operation for the last three decades. However, its applications are limited to the larger temporal and spatial scales. The present study focuses on the augmentation on GPI technique by incorporating a moisture factor for the environmental correction developed by Vicente et al. (1998). It consists of two steps; in the first step the GPI technique is applied to the Kalpana-IR data for rainfall estimation over the Indian land and oceanic region and in the second step an environmental moisture correction factor is applied to the GPI-based rainfall to estimate the final rainfall. Detailed validation with rain gauges and comparison with Tropical Rainfall Measuring Mission (TRMM) merged data product (3B42) are performed and it is found that the present technique is able to estimate the rainfall with better accuracy than the GPI technique over higher temporal and spatial domains for many operational applications in and around the Indian regions using Indian geostationary satellite data. Further comparison with the Doppler Weather Radar shows that the present technique is able to retrieve the rainfall with reasonably good accuracy.     

Rainfall estimation over a Mediterranean region using a method based on various spectral parameters of SEVIRI-MSG

The ultimate objective of this paper is the estimation of rainfall over an area in Algeria using data from the SEVIRI radiometer (Spinning Enhanced Visible and Infrared Imager). To achieve this aim, we use a new Convective/Stratiform Rain Area Delineation Technique (CS-RADT). The satellite rainfall retrieval technique is based on various spectral parameters of SEVIRI that express microphysical and optical cloud properties. It uses a multispectral thresholding technique to distinguish between stratiform and convective clouds. This technique (CS-RADT) is applied to the complex situation of the Mediterranean climate of this region. The tests have been conducted during the rainy seasons of 2006/2007 and 2010/2011 where stratiform and convective precipitation is recorded. The developed scheme (CS-RADT) is calibrated by instantaneous meteorological radar data to determine thresholds, and then rain rates are assigned to each cloud type by using radar and rain gauge data. These calibration data are collocated with SEVIRI data in time and space.     

Global cloud water distribution derived from special sensor microwave imager/sounder and its comparison with GCM simulation

An SSM/I algorithm is developed for measuring cloud liquid water of raining and non-raining clouds. Cloud ice water corresponding to precipitation sized ice particles is obtained from the SSM/I scattering index which is calibrated against radar- derived ice water content. Smaller ice particles in upper level clouds are detected using scattering index based on SSM/T2 183±3 and 183±1 GHz channels which allow for removing water vapor emission. It is shown that SSM/I derived cloud liquid water distribution agrees well with GCM simulations, particularly in tropical latitudes.     

基于三维点云重建的助推器位姿估计

助推器分离是运载火箭发射过程中的关键动作之一,常用的激光雷达姿态测量技术在助推器分离阶段受外界干扰严重,难以准确获得位姿。基于视觉的助推器位姿变化测量技术具有优秀的抗干扰能力,通过搭建三维点云重建网络,以图像为输入,三维点云为输出,在构建的助推器分离过程的图像 点云数据上进行了训练和测试,对测试重建的助推器点云使用主成分分析的方法完成了位姿的估算。测试结果表明,所建立的三维点云重建网络可以根据仿真图像数据,精确测量助推器分离阶段的位姿变化,在R2score指标下,对三维坐标的预测分数均在0.98以上,姿态角平均误差约为21°,预测分数则均在0.80以上。     

基于调制卷积神经网络的空地数据链信道估计

针对复杂环境下空地数据链正交频分复用(OFDM)系统信道估计精度不足的问题,提出了一种基于调制卷积神经网络(MCNN)和双向长短时记忆网络(BiLSTM)结合的信道估计算法。利用最小二乘算法(LS)提取初始信道状态信息(CSI);利用MCNN网络提取初始CSI的深度特征,并对网络模型进行压缩;利用BiLSTM网络对最终CSI进行预测,实现信道估计。利用构建的空地信道模型生成信道系数数据集,实现神经网络模型的训练与测试。仿真结果表明:与传统算法和现有深度学习方法相比,所提出的信道估计算法具有更小的估计误差,高信噪比条件下的系统误码率(BER)性能提升接近一个数量级;由于引入了调制滤波器技术,随着神经网络层数增加,网络模型参数量大幅减少。      

输入饱和情形下战斗机大机动动态面控制

针对战斗机大机动飞行输入饱和问题，提出了一种自适应神经网络动态面控制方法。采用径向基(RBF)神经网络逼近飞机系统的不确定性，利用双曲正切函数处理系统的输入饱和问题，根据饱和受限后的实际控制输入与期望控制输入之差定义新误差变量，结合该误差变量设计大机动飞行控制律，并构造鲁棒项抵消神经网络逼近误差、外部干扰和建模误差的影响，利用动态面控制技术避免对虚拟控制器的复杂求导并减小计算量。根据Lyapunov稳定性定理证明了闭环控制系统所有信号有界，且通过选择合适的设计参数能够使姿态角跟踪误差收敛到原点的任意小邻域内。通过仿真结果的分析，验证了所提方法具有较好的鲁棒性和稳定性。      

An Artificial Neural Network based approach for estimation of rain intensity from spectral moments of a Doppler Weather Radar

By using a Doppler Weather Radar (DWR) at Shriharikota (13.66°N & 80.23°E), an Artificial Neural Network (ANN) based technique is proposed to improve the accuracy of rain intensity estimation. Three spectral moments of a Doppler spectra are utilized as an input data to an ANN. Rain intensity, as measured by the tipping bucket rain gauges around the DWR station, are considered as a target values for the given inputs. Rain intensity as estimated by the developed ANN model is validated by the rain gauges measurements. With the help of a developed technique, reasonable improvement in the estimation of rain intensity is observed. By using the developed technique, root mean square error and bias are reduced in the range of 34–18% and 17–3% respectively, compared to Z–R approach.     

Crop parameters estimation by fuzzy inference system using X-band scatterometer data

Learning fuzzy rule based systems with microwave remote sensing can lead to very useful applications in solving several problems in the field of agriculture. Fuzzy logic provides a simple way to arrive at a definite conclusion based upon imprecise, ambiguous, vague, noisy or missing input information. In the present paper, a subtractive based fuzzy inference system is introduced to estimate the potato crop parameters like biomass, leaf area index, plant height and soil moisture. Scattering coefficient for HH- and VV-polarizations were used as an input in the Fuzzy network. The plant height, biomass, and leaf area index of potato crop and soil moisture measured at its various growth stages were used as the target variables during the training and validation of the network. The estimated values of crop/soil parameters by this methodology are much closer to the experimental values. The present work confirms the estimation abilities of fuzzy subtractive clustering in potato crop parameters estimation. This technique may be useful for the other crops cultivated over regional or continental level.     

利用BP神经网络对卫星无热敏设备温度的估测

卫星上测温资源有限，只有部分设备有测温点，难以准确获得其他无测温点设备的温度。基于反向传播（BP）神经网络对复杂非线性系统优秀的拟合能力，建立了估测卫星上无测温点设备温度的神经网络，以在轨有测温点设备温度为输入层，以在轨无测温点设备为输出层，并使用卫星热试验获得的星上温度遥测数据和在轨无测温点设备的热电偶温度数据进行训练和测试。测试结果表明，所建立的神经网络估测精度在1℃以内，可以用来精确估测卫星无测温点设备的温度。针对学习样本对估测误差之间关系进行了研究，计算表明，学习样本的多样性和大数据量能够显著减小估测误差。     

使用深度神经网络检测Cassini ISS图像中圆盘状星体轮廓

Cassini空间探测器光学成像系统（ISS）拍摄的图像中，很多卫星呈现为面元，其轮廓检测是天体测量的重要工作.使用神经网络方法进行ISS图像中面元轮廓检测.每个ISS图像的像素分为轮廓边缘和非轮廓两类.使用神经网络框架TensorFlow，输入每个像素的9个特征，输出每个像素的分类.利用约3.6万个像素训练该网络，通过380幅ISS图像进行测试.与人工标记结果相比，轮廓像素检测的平均精确率为78.26%，平均召回率为73.32%.以检出轮廓像素作为输入，通过椭圆拟合得到面元的轮廓，所得轮廓与面元真实轮廓吻合良好.研究结果表明该方案能够有效检测出面元轮廓，进而给出假图像星的排除范围.      

基于视频的三维人体姿态估计

已有的三维人体姿态估计方法侧重于通过单帧图像来估计人体的三维姿态,忽略了视频中前后帧之间的相关性,因此,通过挖掘视频在时间维度上的信息可以进一步提高三维人体姿态估计的准确率。基于此,设计了一种可以充分提取视频时序信息的卷积神经网络结构,在获得高精度的同时也具有消耗计算资源小的优点,仅仅使用二维关节点的坐标为输入即可恢复完整的三维人体姿态。然后提出了一种新的损失函数利用相邻帧间人体姿态的连续性,来改进视频序列中三维姿态估计的平滑性,同时也解决了因缺少帧间信息而导致准确率下降的问题。通过在公开数据集Human3.6M上进行测试,实验结果表明本文方法相比目前的基准三维姿态估计算法的平均测试误差降低了1.2 mm,对于视频序列的三维人体姿态估计有着较高的准确率。      

BP神经网络预测复合材料热压罐成型均匀性

复合材料热压罐成型过程中的固化度差值是复合材料固化度均匀性的主要表征参数之一。基于3层BP神经网络，以复合材料双平台固化工艺曲线的加热速率、保温时间和保温温度为输入参数，建立了成型过程任一时刻最大固化度差值的快速估算模型。仿真复合材料热压罐成型过程，得到最大固化度差值作为试验样本数据，对BP神经网络进行训练，训练结束后对该模型的准确性进行验证。结果表明:该BP神经网络估算模型准确性和效率较高，为复合材料热压罐成型最大固化度差值的估算提供了一种快速有效的新方法。      

Optimization of One versus All-SVM using AdaBoost algorithm for rainfall classification and estimation from multispectral MSG data

In this paper, we implement the AdaBoost algorithm to optimize the classifications results of precipitations intensities carried out by One versus All strategy using Support Vector Machine (OvA-SVM). The model developed which combines the AdaBoost algorithm with a multiclass SVM is applied to images from the MSG (Meteosat Second Generation) satellite. Other variants to build multiclass SVMs, such as the OvO-SVM (One versus One SVM), SBT-SVM (Slant Binary Tree SVM) and DDAG-SVM (Decision Directed Acyclic Graph) are also implemented on which we tested the AdaBoost algorithm. The study showed that the AdaBoost algorithm performed better in the case of the OvA-SVM variant compared to the other variants.In order to evaluate the elaborated model, some classification techniques, such as the ECST Enhanced Convective Stratiform Technique (ECST), the SART where the Support vector machine, Artificial neural network and Random forest classifiers are combined, the Convective/Stratiform Rain Area Delineation Technique (CS-RADT) and the Random Forest technique (RFT) are applied. The classification results obtained show that AdaBoost with OvA-SVM (AdaOvA-SVM) presents very interesting performances where the evaluation parameters POD, POFD, FAR, BIAS, CSI and PC indicate the values 95.2%, 12.4%, 14.7%, 0.9, 88.1% and 96.5% respectively. Indeed, the AdaOvA-SVM technique has surpassed the CS-RADT, ECST and RFT techniques. As for the comparison with the SART, we noted that OvA-SVM presents very close results. The same trend was also observed when estimating precipitation. At the end of this study, it is shown that the AdaBoost algorithm performs better on a weak classifier or on a strong classifier operating in an unfavorable environment.     

基于深度学习的无人机数据链信噪比估计算法

无人机数据链通信受到各种自然与人为的干扰,信噪比（SNR）是信道状态和通信质量的有效评估指标。为解决传统估计算法信噪比估计精度不足的问题,提出了一种卷积神经网络（CNN）与长短时记忆（LSTM）网络结合的估计模型。利用仿真与实测相结合的方式,构建了一个包含不同信噪比、调制方式、衰落信道等信息的无人机通信信号数据集;在网络训练阶段,将样本序列进行分割,对分割后的每一部分序列使用CNN-LSTM网络提取深度特征,多次训练并保存模型参数;在测试阶段,利用构建好的测试集完成对算法的验证与测试,得到信噪比估计值。实验表明,相比于传统信噪比估计算法与单一网络结构的深度学习算法,所提算法的均方误差最低,实现了对信噪比的高精度估计。      

基于双滤波器的高精度目标跟踪估计方法

针对连续推力的合作航天器，采用双重无迹卡尔曼滤波(DUKF)算法估计其状态和加速度。通过状态滤波器和参数滤波器的配合，提升滤波精度，完成运动状态和参数的估计，从而实现合作目标的运动轨迹跟踪。与合作航天器相比，非合作航天器存在大小未知、发生时刻未知的机动，无法获得加速度，且信息获取和运动状态的估计难度大。针对非合作航天器，基于简化的相对运动方程，结合天基平台获得目标的观测信息，采用两个扩展卡尔曼滤波(EKF)及基于半正焦弦的机动检测策略实现多未知脉冲机动的运动状态的估计。仿真结果表明：相比于无迹卡尔曼滤波（UKF），DUKF在对合作航天器的状态和加速度估计方面具有更快的收敛速度和更高的滤波精度；对于存在未知机动的非合作航天器，通过对比验证机动检测策略与滤波器切换策略相结合的方法的有效性，该方法能够检测到多次机动并且减少误判。     

A multi-spectral spatial convolution approach of rainfall forecasting using weather satellite imagery

Flood forecasting has long been a major topic of hydrologic research. Recent events and studies indicate that the success of flood forecasting in Taiwan depends heavily on the accuracy of real-time rainfall forecasting. In this study, we demonstrate a multi-spectral spatial convolution approach for real-time rainfall forecasting using geostationary weather satellite images. The approach incorporates cloud-top temperatures of three infrared channels in a spatial convolution context. It not only characterizes the input–output relationship between cloud-top temperature and rainfall at the ground level, but also is more consistent with physical and remote sensing principles than single-pixel matches. Point rainfall measurements at raingauge sites are up-scaled to pixel-average-rainfall by block kriging, then related to multi-spectral cloud-top temperatures derived from Geostationary Meteorological Satellite images by spatial convolution. The kernel function of the multispectral spatial convolution equation is solved by the least squares method. Through a cross-validation procedure, we demonstrate that the proposed approach is capable of achieving high accuracy for 1- to 3-h-lead pixel-average-rainfall forecasting.     

基于模型诊断技术的神经网络实现方法

针对基于模型的故障诊断流程中故障检测和故障识别两个关键问题,提出了一种基于神经网络的实现方法.首先利用BP神经网络进行参数估计,并结合系统模型进行故障检测;然后采用ART2神经网络进行数据聚类,并基于聚类结果进行系统故障识别;最后,设计实现了基于BP/ART2神经网络的故障诊断系统.基于BP神经网络的参数估计方法可以准确地估计诊断对象在不同状态下的参数,为故障检测提供有效依据;基于ART2神经网络的数据聚类不仅可以识别对象的已知故障类型,还可以识别出未知故障,对先验信息较少的系统进行故障识别更具有效性.通过永磁直流电机故障诊断案例的应用,证明方法能具有一定的工程实用性.