Passive microwave remote sensing of snow constrained byhydrological simulations

This paper describes a snow parameter retrieval algorithm from passive microwave remote sensing measurements. The three components of the retrieval algorithm include a dense media radiative transfer (DMRT) model, which is based on the quasicrystalline approximation (QCA) with the sticky particle assumption, a physically-based snow hydrology model (SHM) that incorporates meteorological and topographical data, and a neural network (NN) for computational efficient inversions. The DMRT model relates physical snow parameters to brightness temperatures. The SHM simulates the mass and heat balance and provides initial guesses for the neural network. The NN is used to speed up the inversion of parameters. The retrieval algorithm can provide speedy parameter retrievals for desired temporal and spatial resolutions, Four channels of brightness temperature measurements: 19V, 19H, 37V, and 37H are used. The algorithm was applied to stations in the northern hemisphere. Two sets of results are shown. For these cases, the authors use ground-truth precipitation data, and estimates of snow water equivalent (SWE) from SHM give good results. For the second set, a weather forecast model is used to provide precipitation inputs for SHM. Additional constraints in grain size and density are used. They show that inversion results compare favorably with ground truth observations     

Integrating in situ and multiscale passive microwave data for estimation of subgrid scale snow water equivalent distribution and variability

New multiscale research datasets were acquired in central Saskatchewan, Canada during February 2003 to quantify the effect of spatially heterogeneous land cover and snowpack properties on passive microwave snow water equivalent (SWE) retrievals. Microwave brightness temperature data at various spatial resolutions were acquired from tower and airborne microwave radiometers, complemented by spaceborne Special Sensor Microwave/Imager (SSM/I) data for a 25/spl times/25 km study area centered on the Old Jack Pine tower in the Boreal Ecosystem Research and Monitoring Sites (BERMS). To best address scaling issues, the airborne data were acquired over an intensively spaced grid of north-south and east-west oriented flight lines. A coincident ground sampling program characterized in situ snow cover for all representative land cover types found in the study area. A suite of micrometeorological data from seven sites within the study area was acquired to aid interpretation of the passive microwave brightness temperatures. The in situ data were used to determine variability in SWE, snow depth, and density within and between forest stands and land cover types within the 25/spl times/25 km SSM/I grid cell. Statistically significant subgrid scale SWE variability in this mixed forest environment was controlled by variations in snow depth, not density. Spaceborne passive microwave SWE retrievals derived using the Meteorological Service of Canada land cover sensitive algorithm suite were near the center of the normally distributed in situ measurements, providing a reasonable estimate of the mean grid cell SWE. A realistic level of SWE variability was captured by the high-resolution airborne data, showing that passive microwave retrievals are capable of capturing stand-to-stand SWE variability if the imaging footprint is sufficiently small.     

Neural Network Inverse Modeling and Applications to Microwave Filter Design

In this paper, systematic neural network modeling techniques are presented for microwave modeling and design using the concept of inverse modeling where the inputs to the inverse model are electrical parameters and outputs are geometrical parameters. Training the neural network inverse model directly may become difficult due to the nonuniqueness of the input-output relationship in the inverse model. We propose a new method to solve such a problem by detecting multivalued solutions in training data. The data containing multivalued solutions are divided into groups according to derivative information using a neural network forward model such that individual groups do not have the problem of multivalued solutions. Multiple inverse models are built based on divided data groups, and are then combined to form a complete model. A comprehensive modeling methodology is proposed, which includes direct inverse modeling, segmentation, derivative division, and model combining techniques. The methodology is applied to waveguide filter modeling and more accurate results are achieved compared to the direct neural network inverse modeling method. Full electromagnetic simulation and measurement results of Ku-band circular waveguide dual-mode pseudoelliptic bandpass filters are presented to demonstrate the efficiency of the proposed neural network inverse modeling methodology.     

A neural-network technique for the retrieval of atmospheric temperature and moisture profiles from high spectral resolution sounding data

A novel statistical method for the retrieval of atmospheric temperature and moisture profiles has been developed and evaluated with simulated clear-air and observed partially cloudy sounding data from the Atmospheric InfraRed Sounder (AIRS) and the Advanced Microwave Sounding Unit (AMSU). The algorithm is implemented in two stages. First, a projected principal components (PPC) transform is used to reduce the dimensionality of and optimally extract geophysical profile information from the cloud-cleared infrared radiance data. Second, a multilayer feedforward neural network (NN) is used to estimate the desired geophysical parameters from the PPCs. For the first time, NN temperature and moisture retrievals are presented using actual microwave and hyperspectral infrared observations of cloudy atmospheres, over both ocean and land (with variable terrain elevation), and at all sensor scan angles. The performance of the NN retrieval method (henceforth referred to as the PPC/NN method) was evaluated using global Earth Observing System Aqua orbits colocated with European Center for Medium-range Weather Forecasting fields for seven days throughout 2002 and 2003. Over 350,000 partially cloudy footprints were used in the study, and retrieval performance was compared with the AIRS Science Team Level-2 retrieval algorithm (version 3). Performance compares favorably with that obtained with simulated clear-air observations from the NOAA88b radiosonde set of approximately 7500 profiles. The PPC/NN method requires significantly less computation than traditional variational retrieval methods, while achieving comparable performance.     

可重构功放的新颖NARX神经网络逆向建模研究

针对使用CAD软件设计射频微波电路繁琐且耗时长等缺点,提出一种新颖的带外部输入的非线性自回归(NARX)神经网络逆向建模方法。此方法采用具有激励函数的NARX 神经网络(DAFNN)为模型以提高网络的泛化能力,利用支持向量机(SVM)替代模型的前馈部分完成数据分类,解决设计中的多解问题。然后应用于可以覆盖多个频段的可重构功率放大器中,实验表明,该方法在精度方面分别优于直接逆向建模方法和自适应浊逆向建模方法99.86%和81.32%,计算速度方面优于直接逆向建模方法31.72%,可以降低射频微波可重构功率放大器的设计复杂度、缩短其设计时间。     

Sensitivity of passive microwave snow depth retrievals to weather effects and snow evolution

Snow fall and snow accumulation are key climate parameters due to the snow's high albedo, its thermal insulation, and its importance to the global water cycle. Satellite passive microwave radiometers currently provide the only means for the retrieval of snow depth and/or snow water equivalent (SWE) over land as well as over sea ice from space. All algorithms make use of the frequency-dependent amount of scattering of snow over a high-emissivity surface. Specifically, the difference between 37- and 19-GHz brightness temperatures is used to determine the depth of the snow or the SWE. With the availability of the Advanced Microwave Scanning Radiometer (AMSR-E) on the National Aeronautics and Space Administration's Earth Observing System Aqua satellite (launched in May 2002), a wider range of frequencies can be utilized. In this study we investigate, using model simulations, how snow depth retrievals are affected by the evolution of the physical properties of the snow (mainly grain size growth and densification), how they are affected by variations in atmospheric conditions and, finally, how the additional channels may help to reduce errors in passive microwave snow retrievals. The sensitivity of snow depth retrievals to atmospheric water vapor is confirmed through the comparison with precipitable water retrievals from the National Oceanic and Atmospheric Administration's Advanced Microwave Sounding Unit (AMSU-B). The results suggest that a combination of the 10-, 19-, 37-, and 89-GHz channels may significantly improve retrieval accuracy. Additionally, the development of a multisensor algorithm utilizing AMSR-E and AMSU-B data may help to obtain weather-corrected snow retrievals.     

Advanced microwave modeling framework exploiting automatic model generation, knowledge neural networks, and space mapping

In this paper, we propose an efficient knowledge-based automatic model generation (KAMG) technique aimed at generating microwave neural models of the highest possible accuracy using the fewest accurate data. The technique is comprehensively derived to integrate three distinct powerful concepts, namely, automatic model generation, knowledge neural networks, and space mapping. For the first time, we simultaneously utilize two types of data generators, namely, coarse data generators that are approximate and fast (e.g., two-and-one-half-dimensional electromagnetic), and fine data generators that are accurate and slow (e.g., three-dimensional electromagnetic). Motivated by the space-mapping concept, the KAMG technique utilizes extensive coarse data, but fewest fine data to generate neural models that accurately match the fine data. Our formulation exploits a variety of knowledge neural-network architectures to facilitate reinforced neural-network learning from coarse and fine data. During neural model generation by KAMG, both coarse and fine data generators are automatically driven using adaptive sampling. The KAMG technique helps to increase the efficiency of neural model development by taking advantage of a microwave reality, i.e., availability of multiple sources of training data for most high-frequency components. The advantages of the proposed KAMG technique are demonstrated through practical microwave examples of MOSFET and embedded passive components used in multilayer printed circuit boards.     

Retrieval of crop biomass and soil moisture from measured 1.4 and 10.65 GHz brightness temperatures

Physically based land surface process/radiobrightness (LSP/R) models may characterize well the relationship between radiometric signatures and surface parameters. They can be used to develop and improve the means of sensing surface parameters by microwave radiometry. However, due to a lack in the skill to properly understand the behavior of the data, a statistical approach is often adopted. In this paper, we present the retrieval of wheat plant water content (PWC) and soil moisture content (SMC) profiles from the measured H-polarized and V-polarized brightness temperatures at 1.4 (L-band), and 10.65 (X-band) GHz by an error propagation learning back propagation (EPLBP) neural network. The PWC is defined as the total water content in the vegetation. The brightness temperatures were taken by the PORTOS radiometer over wheat fields through three month growth cycles in 1993 (PORTOS-93) and 1996 (PORTOS-96). Note that, through the neural network, there is no requirement of ancillary information on the complex surface parameters such as vegetation biomass, surface temperature, and surface roughness, etc. During both field campaigns, the L-band radiometer was used to measure brightness temperatures at incident angles from 0 to 50/spl deg/ at L-band and at an incident angle of 50/spl deg/ at X-band. The SMC profiles were measured to the depths of 10 cm in 1993 and 5 cm in 1996. The wheat was sampled approximately once a week in 1993 and 1996 to obtain its dry and wet biomass (i.e., PWC). The EPLBP neural network was trained with observations randomly chosen from the PORTOS-93 data, and evaluated by the remaining data from the same set. The trained neural network is further evaluated with the PORTOS-96 data.     

Inversion of snow parameters from passive microwave remote sensingmeasurements by a neural network trained with a multiple scatteringmodel

The inversion of snow parameters from passive microwave remote sensing measurements is performed with a neural network trained with a dense-media multiple-scattering model. The input-output pairs generated by the scattering model are used to train the neural network. Simultaneous inversion of three parameters, mean-grain size of ice particles in snow, snow density, and snow temperature from five brightness temperatures, is reported. It is shown that the neural network gives good results for simulated data. The absolute percentage errors for mean-grain size of ice particles and snow density are less than 10%, and the absolute error for snow temperature is less than 3 K. The neural network with the trained weighting coefficients of the three-parameter model is also used to invert SSMI data taken over the Antarctic region     

A soft computing approach for rainfall retrieval from the TRMM microwave imager

A neural network model for rainfall retrieval over ocean from remotely sensed microwave (MW) brightness temperature (BT) is proposed. BT data are obtained from the Tropical Rainfall Measuring Mission (TRMM) Microwave Imager (TMI). The BT values from different channels of TMI over the Pacific Ocean (163/spl deg/ to 177/spl deg/W and 18/spl deg/ to 34/spl deg/S) are the input features. The near-surface rainfall rate from the Precipitation Radar (PR) are considered as a target. The proposed model consists of a neural network with online feature selection (FS) and clustering techniques. A K-means clustering algorithm is applied to cluster the selected features. Different networks have been trained to give an instantaneous rainfall rate with all input features as well as with selected features obtained by applying the FS algorithm. It is found that the hybrid network utilizing FS and clustering techniques performs better. The developed network is also validated with two independent datasets on March 14, 2000 over the Atlantic Ocean having stratiform rain and on March 21, 2000 over the Pacific Ocean having both stratiform and convective rain. In both cases, the hybrid network performs well with correlation coefficient improving to 0.78 and 0.81, respectively, in contrast to 0.70 and 0.75 for the network with all features. The rainfall rate retrieved from the hybrid network is also compared with the TMI surface rain rate, and a correlation of 0.84 and 0.75 is found for the two events. The proposed hybrid model is validated with a Doppler Weather Radar, and correlation of 0.52 is observed.     

Artificial neural networks for temperature dependent noise modeling of microwave transistors

In this paper an automated procedure for prediction of microwave transistor noise parameters versus temperature is presented. It is based on an improved Pospieszalski's noise model. In order to avoid extraction of device noise model equivalent circuit parameters (ECP) from the measured scattering and noise parameters for each operating temperature, an artificial neural network is introduced for modeling of the ECP temperature dependence. Therefore, it is necessary to acquire the measured data and extract the ECP only for several operating temperatures used for the network training. Once the network is trained and assigned to the considered noise model, the device noise parameters are easily obtained for each temperature from the operating range. It is done without changes in the network structure and without the need for time consuming and complex measurements and optimiztions.     

基于遗传BP神经网络算法的主被动遥感协同反演土壤水分

提出了一种基于遗传神经网络算法的主被动遥感协同反演地表土壤水分的方法.首先,建立一个BP神经网络,并采用遗传算法对BP网络的节点权值进行了优化.然后分别将TM数据(TM3,TM4,TM6)、不同极化和极化比的(VV,VH,VH/VV)ASAR数据作为神经网络的输入,土壤水分含量作为网络的输出,用部分实测数据对网络进行训练并反演得到研究区土壤水分布图.最后,利用地面实测数据分别对遗传神经网络优化算法的有效性和主被动遥感协同反演的效果进行了验证,结果表明,新优化算法是有效可行的,且TM和ASAR协同反演的结果比两者单独反演的结果明显要好,体现了主被动遥感协同反演土壤水分的优势与潜力.     

Cloud Properties Derived From GOME/ERS-2 Backscatter Data for Trace Gas Retrieval

We focus on the retrieval of cloud properties appropriate for trace gas retrieval from sun-normalized ultraviolet/visible backscatter spectra obtained from the Global Ozone Monitoring Experiment (GOME) onboard the European Space Agency's European Remote Sensing 2 Satellite (ERS-2). Retrieved quantities are the fractional cloud coverage of the GOME footprint, the cloud-top albedo, and the cloud-top height. A data fusion technique is applied to calculate the fractional cloud cover of GOME footprints from GOME's polarization measurement devices. Furthermore, cloud-top albedo and cloud-top height are retrieved simultaneously from GOME measurements around the oxygen A-band by a neural network approach. We compare our results with corresponding results from the Spinning Enhanced Visible and Infrared Imager (SEVIRI) radiometer onboard the first European Organisation for the Exploitation of Meteorological Satellites (EUMETSAT) METEOSAT Second Generation 1 geostationary spacecraft. Our analysis revealed that GOME-derived basic cloud properties are of remarkably high quality. GOME slightly underestimates the cloud coverage of footprints, which was expected since GOME is mainly sensitive to optically thick water clouds. GOME measurements are limited to the ultraviolet and visible part of the solar spectrum, which hampers the detection of optically thin clouds. For both the cloud-top height and the cloud-top albedo, we found a small bias relative to SEVIRI results. The overall uncertainty of retrieved total ozone columns with respect to cloud parameters is about 1%-2%. Our approach is applied to the operational processing of GOME/ERS-2 and will be applied to GOME-2/METOP (launched in 2006) in the framework of EUMETSAT's Satellite Application Facility on Ozone and Atmospheric Chemistry Monitoring (O3M-SAF).     

基于微波高光谱技术的数据仿真及参数反演研究

发展高光谱微波辐射计对于提升大气参数反演精度具有重要意义。利用微波辐射传输模型mpm93以及BP 神经网络方法分别构建正演上行辐射亮温和反演大气温度廓线的模型,并研究了晴空条件下高光谱微波辐射计反演大气温度廓线的精度。54～58 GHz、64～68 GHz 在氧气吸收波段选取80 个通道作为高光谱通道,基于2015 年5～12 月昆明的探空资料进行正、反演仿真实验。选取微波成像仪/ 探测仪(SSMIS)的9 个温度探测通道进行对比实验,评估分析反演效果。实验结果表明:在大气3～10 km 高度范围内,高光谱通道的反演精度较SSMIS 提高了0.3 ～0.6 K;在0～3 km 高度范围内,反演精度提高了1 K。     

A robust algorithm for automatic development of neural-networkmodels for microwave applications

For the first time, we propose a robust algorithm for automating the neural-network-based RF/microwave model development process. Starting with zero amount of training data and then proceeding with neural-network training in a stage-wise manner, the algorithm can automatically produce a neural model that meets the user-desired accuracy. In each stage, the algorithm utilizes neural-network error criteria to determine additional training/validation samples required and their location in model input space. The algorithm dynamically generates these new data samples during training, by automatic driving of simulation tools (e.g., OSA90, Ansoft-HFSS, Agilent-ADS). Initially, fewer hidden neurons are used, and the algorithm adjusts the neural-network size whenever it detects under-learning. Our technique integrates all the subtasks involved in neural modeling, thereby facilitating a more efficient and automated model development framework. It significantly reduces the intensive human effort demanded by the conventional step-by-step neural modeling approach. The algorithm inherently distinguishes nonlinear and smooth regions of model behavior and uses relatively fewer samples in smooth subregions. It automatically deals with large data errors that can occur during dynamic sampling by using a Huber quasi-Newton technique. The algorithm is demonstrated through practical microwave device and circuit examples     

Beam-filling effect correction with subpixel cloud fraction using a neural network

In this study, the effects of cloud inhomogeneity on microwave rain rate retrievals are investigated. A single-channel (85 GHz) empirically based algorithm using a neural network approach is presented. The objective is to correct the beam-filling error (BFE), that might occur because of the inherent variability within coarse microwave pixels, with subpixel information. To this aim, we used the Tropical Rainfall Measuring Mission passive microwave, thermal infrared and radar data. The integration of spatial information into the retrieval algorithm enables us to partially overcome the BFE. We use two parameters which characterize the horizontal cloud inhomogeneity within the microwave radiometer field of view, and we add them to simulated brightness temperatures as inputs of the neural network algorithm. The first one is the cloud fraction derived from infrared measurement, and the second corresponds to the fraction of the rainy area derived from radar measurements. The output rain rates were validated using the Precipitation Radar data. It was found that adding cloud fraction of microwave pixels, can lead to more accurate retrievals. Instantaneous precipitation estimates demonstrated correlations of /spl sim/0.6-0.7 and /spl sim/0.7-0.8 with radar-derived rain rates, for ocean and land retrievals respectively. In spite of the problem inherent in deriving the cloud (or rain) fraction, the initial validation results presented in this study are reasonably encouraging and show the advantage of utilizing the information from different sensors in order to optimize the retrieval of rainfall.     

Advantages of plasma etch modeling using neural networks overstatistical techniques

Due to the inherent complexity of the plasma etch process, approaches to modeling this critical integrated circuit fabrication step have met with varying degrees of success. Recently, a new adaptive learning approach involving neural networks has been applied to the modeling of polysilicon film growth by low-pressure chemical vapor deposition (LPCVD). In this paper, neural network modeling is applied to the removal of polysilicon films by plasma etching. The plasma etch process under investigation was previously modeled using the empirical response surface approach. However, in comparing neural network methods with the statistical techniques, it is shown that the neural network models exhibit superior accuracy and require fewer training experiments. Furthermore, the results of this study indicate that the predictive capabilities of the neural models are superior to that of their statistical counterparts for the same experimental data     

基于星载红外高光谱观测用机器学习算法反演大气温湿廓线

星载红外高光谱垂直探测仪GIIRS （Geostationary Interferometric Infrared Sounder）能够实现大气温度和湿度参数高垂直分辨率的观测，为数值天气预报提供精度更高的初始场。基于GIIRS观测辐射值采用BP神经网络（Back Propagation Neural Network）法和深度学习的卷积神经网络（Convolutional Neural Networks, CNN）法反演大气温度、湿度垂直廓线，重点在于CNN法模型的构建与参数的优化，得到反演精度最高的网络模型配置。将训练样本根据不同地表类型和是否有云的影响分为三种方案（方案一:不分类、方案二:陆地/洋面分类、方案三:晴空/有云分类），分别进行建模、反演和检验。结果表明两种反演算法都有较好的反演精度，相对而言CNN法在所有高度层上反演偏差、均方根误差和平均相对误差均较小，反演精度更高。CNN法温度反演在高层10~200 hPa改进较大，三种分类方案改进的最大值分别为1.15 K、1.06 K和1.02 K；湿度反演在对流层低层500~1000 hPa改进较大，三种分类方案分别平均改进了0.43 g/kg、0.41 g/kg和0.34 g/kg。BP神经网络法方案三时（即分晴空和云时）温度和水汽混合比廓线反演精度最好；CNN算法方案一时（即不对样本数据进行任何分类）反演精度最高。     

Artificial Neural Network Models for Coaxial to Waveguide Adapters

Artificial neural networks provide fast and accurate models for the modeling, simulation, and optimization of microwave and millimeter wave components. In this paper, a multilayer perceptron neural network (MLPNN) is used to model a millimeter wave coaxial to waveguide adapter. The MLPNN is electromagnetically developed with a set of training data that are produced by the full-wave finite-difference time-domain (FDTD) method. One type of the designs of experiments, the central composite technique, is used to allow for a minimum number of FDTD simulations that is needed to be performed. The MLPNN models are useful for the CAD of wideband coaxial to waveguide adapter.     

Modeling uncertainties for passive microwave precipitation retrieval: evaluation of a case study

Physically based microwave spaceborne techniques for rainfall retrieval are usually trained by simulated cloud-radiation databases (CRDs) composed of cloud profiles and associated brightness temperatures (TBs). When generating the database, the evaluation of the associated modeling uncertainties is crucial for retrieval error estimation. However, this is extremely complex due to the large number of free parameters. In this work, a possible methodology for taking into account CRD-related modeling uncertainties is proposed. The methodology-fairly general-is here applied to a limited dataset (a cloud-model resolved numerical output of a tropical cyclone). The modeling errors are obtained from systematic TB sensitivity tests associated to several parameters: particle sizes, temperature, ice content, sea surface wind speed, viewing angle, footprint size, radiative transfer schemes, melting phase, and particle shape. TB uncertainties are eventually summarized in a modeling error covariance matrix representing the intrinsic variability of the generated CRD. For comparison with real observations, the TBs are simulated at the spatial resolution, viewing geometry and frequencies of the Tropical Rainfall Measuring Mission (TRMM) Microwave Imager (TMI). The matrix is evaluated with respect to TMI data in terms of an indicator called database matching index. Since they are based on a single case study and suffer from the lack of direct coupling of the radiative transfer with the cloud-resolving model, the provided results should not be considered an exhaustive evaluation of cloud-radiation modeling errors. Nevertheless, they may be considered a valuable starting point for error characterization, since extensions to larger databases could definitely improve modeling error budgets.