基于Sentinel-1/2遥感数据的冬小麦覆盖地表土壤水分协同反演

冬小麦是我国重要粮食作物之一,对冬小麦覆盖地表土壤水分进行监测有助于解决因土壤供水导致的冬小麦歉收和农业用水浪费等问题.为了降低冬小麦覆盖地表土壤水分微波遥感反演过程中冬小麦对雷达后向散射系数的影响,该文基于Sentinel-1携带的合成孔径雷达(SAR)数据和Sentinel-2携带的多光谱成像仪(MSI)数据,结合水云模型,开展冬小麦覆盖地表土壤水分协同反演研究.首先,基于MSI数据,该文定义了一种新的植被指数,即融合植被指数(FVI),用于冬小麦含水量反演;然后,该文发展了一种基于主被动遥感数据的冬小麦覆盖地表土壤水分反演半经验模型,校正冬小麦在土壤水分反演过程中对雷达后向散射系数的影响;最后,以河南省某地冬小麦农田为研究区域,开展归一化水体指数(NDWI)和FVI两种指数与VV,VH,VV/VH 3种极化组合而成的6种反演方式下的土壤水分反演对比实验.结果表明:以FVI为植被指数,能够更好地去除冬小麦在土壤水分反演过程中对雷达后向散射系数的影响;6种反演方式中,FVI与VV/VH组合下的反演效果最优,其决定系数为0.7642,均方根误差为0.0209 cm3/cm3,平均绝对误差为0.0174 cm3/cm3,展示了该文所提土壤水分反演模型的研究价值和应用潜力.     

基于Sentinel-1/2遥感数据的冬小麦覆盖地表土壤水分协同反演

冬小麦是我国重要粮食作物之一,对冬小麦覆盖地表土壤水分进行监测有助于解决因土壤供水导致的冬小麦歉收和农业用水浪费等问题。为了降低冬小麦覆盖地表土壤水分微波遥感反演过程中冬小麦对雷达后向散射系数的影响,该文基于Sentinel-1携带的合成孔径雷达(SAR)数据和Sentinel-2携带的多光谱成像仪(MSI)数据,结合水云模型,开展冬小麦覆盖地表土壤水分协同反演研究。首先,基于MSI数据,该文定义了一种新的植被指数,即融合植被指数(FVI),用于冬小麦含水量反演;然后,该文发展了一种基于主被动遥感数据的冬小麦覆盖地表土壤水分反演半经验模型,校正冬小麦在土壤水分反演过程中对雷达后向散射系数的影响;最后,以河南省某地冬小麦农田为研究区域,开展归一化水体指数(NDWI)和FVI两种指数与VV, VH, VV/VH 3种极化组合而成的6种反演方式下的土壤水分反演对比实验。结果表明:以FVI为植被指数,能够更好地去除冬小麦在土壤水分反演过程中对雷达后向散射系数的影响;6种反演方式中,FVI与VV/VH组合下的反演效果最优,其决定系数为0.7642,均方根误差为0.0209 cm3/cm3,平均绝对误差为0.0174 cm3/cm3,展示了该文所提土壤水分反演模型的研究价值和应用潜力。     

基于可见光红外与被动微波遥感的土壤水分协同反演

利用MODIS传感器的可见光、红外波段数据反演土壤水分在一定时段内的基准值,用被动微波传感器AMSR-E数据反演其变化量,提出将被动微波遥感数据与热红外遥感数据在模型级别协同反演大范围地表土壤水分的方法,这样每天可输出1 km×1 km的升、降轨土壤水分反演结果.以新疆为研究区,对上述方法进行了土壤水分协同反演实验,以地面实测数据为参考的验证结果表明,所提模型得到的土壤水分值与地面实测值之间相关性较高,均方根误差较小,优于单一传感器数据的反演结果,可更好地满足新疆土壤水分监测的需求.     

基于Radarsat2与Landsat8协同反演植被覆盖地表土壤水分的一种新方法

主动微波遥感与被动光学遥感在反演地表土壤水分方面分别具有各自的优缺点,为了将这两者的优势结合弥补缺点,提出了一种基于Radarsat 2与Landsat 8数据协同反演植被覆盖地表土壤水分的半经验耦合模型.该模型基于水云模型,将光学遥感反演得到的植被冠层含水量作为水云模型的关键输入参数,并同时考虑植被冠层与土壤以及其之间的部分对雷达后向散射系数的影响,以此来去除雷达回波中的植被部分.最后选用内蒙古呼伦贝尔市额尔古纳市大兴安岭西侧研究区的Radarsat 2与Landsat 8遥感数据,利用新的耦合模型反演得到植被覆盖区土壤水分含量,并利用地面测量数据对模型进行验证.结果表明:利用Landsat 8数据反演植被含水量算法精度较高(R2=0.89),论文提出的耦合模型反演植被覆盖地表土壤水分精度比之前算法也有了较大的提高,其中HH极化效果最好,R2由0.27提高至0.65.这表明该耦合模型具有较好的反演精度,可以应用于植被覆盖区土壤水分含量的反演.     

基于混沌免疫遗传算法的神经网络及应用

借助混沌随机序列构造初始种群,将免疫机制引入传统遗传进化过程,有效克服传统遗传算法种群“退化”和“早熟”的不足,保持种群多样性,构造得到混沌免疫遗传优化算法.进而将混沌免疫遗传优化算法与BP神经网络相结合,分别用混沌免疫遗传优化算法和自适应BP算法对网络权值进行全局优化和局部二次优化,建立基于混沌免疫遗传算法的神经网络...     

基于混沌免疫遗传算法的神经网络及应用

借助混沌随机序列构造初始种群,将免疫机制引入传统遗传进化过程,有效克服传统遗传算法种群“退化”和“早熟”的不足,保持种群多样性,构造得到混沌免疫遗传优化算法。进而将混沌免疫遗传优化算法与BP神经网络相结合,分别用混沌免疫遗传优化算法和自适应BP算法对网络权值进行全局优化和局部二次优化,建立基于混沌免疫遗传算法的神经网络模型。利用所建立的混合神经网络模型对渤海某海域年极值冰厚进行训练预测,并将模型预测结果与实际数据以及动态拓扑预测的结果进行对比,表日周基于混沌免疫遗传算法的神经网络模型具有很高的预测精度和工程适用性。     

基于微波与光学遥感的石漠化地区土壤剖面含水率反演模型研究

土壤水是全球生态系统的重要组成部分,定量遥感估测喀斯特石漠化地区土壤含水率,可为石漠化治理和生态恢复工作提供基础数据和理论支撑.通过Sentinel-1A和Landsat 8影像数据,运用水云模型提取灌木林地和疏林地的土壤后向散射系数,并计算旱地与有林地的TVDI.并结合实测数据,利用拟合分析对不同深度土壤含水率进行建模,从而对土壤含水率进行反演.结果表明VH极化二次曲线模型和VH极化三次曲线模型分别适用于灌木林地0~5 cm和5~10 cm深度的土壤含水率反演,其R~2和RMSE分别为0.87、0.87和4.57%、4.29%.疏林地0~5 cm和5~10 cm深度土壤含水率反演宜选用VH极化指数回归模型和VH极化下的线性回归模型,各模型的R~2与RMSE分别为0.736、0.72和9.77%、11.28%.三次曲线模型和Logistic回归模型分别适用于旱地和有林地的土壤含水率的反演,各模型的R~2与RMSE在0~5 cm深度分别为0.85、0.69和2.88%、4.02%,在5~10 cm分别为0.76、0.23和3.5%、6.37%.     

基于形态学的多时相SAR洪水监测方法研究

洪涝灾害严重危害人类的生命和财产安全,且发生频繁,危害范围大,因此洪涝灾害的监测至关重要。文章基于灾前/中Sentinel-1A双极化SAR数据,首先分别利用VV和VH极化强度信息构造峡山水库洪涝灾害发生前后差异图,并采用Otsu法初步提取洪水范围,然后,为进一步减弱斑噪影响,引入形态学算法以获得更准确的洪水分布图,最后,将精确提取的VV和VH洪水受灾区域进行叠加整合,得到最终洪灾面积为28.82km2。与光学影像对比分析后得到检测精度为80.260%,高于不加入形态学算法和传统Otsu法的检测精度(77.125%和74.830%),因此本文方法精度更高,准确性更好。     

基于遗传算法优化神经网络的藻类繁殖状态软测量方法

为了提高BP神经网络模型对海洋藻类生长状态软测量的准确性,提出了一种基于遗传优化算法优化BP神经网络的软测量方法.利用遗传算法优化BP神经网络的权值和阈值,然后训练BP神经网络预测模型以求得最优解,再将该预测结果与传统BP网络预测模型的预测结果进行对比.对仿真结果进行有效性验证后,结果表明,通过这种软测量方法,经遗传算法优化后的BP神经网络可以在更短的时间里创造更高的预测准确性,大大提高了对海洋藻类生长状态预测的效率.     

基于GA改进BP神经网络网络异常检测方法

考虑到常规BP神经网络算法容易陷入局部最优解,所建立的网络遗传流量检测模型检测效率低,准确率不高等问题,提出一种改进型GA优化BP神经网络算法,并使用其建立网络遗传流量检测模型。常规遗传算法在搜索过程中,往往会由于出现影响生产适应度高的个体而对遗传算法搜索过程产生影响的现象发生,因此需要对常规遗传算法进行改进。使用的方法是通过混合编码方式进行改进,同时对交叉算子、变异算子、交叉概率以及变异概率等参数进行优化修正。使用KDD CUP99数据库中的网络异常流量数据进行实验研究,研究结果表明,所提出方法的检测性能要明显优于常规算法,其对BP神经网络的结构、权值以及阈值进行同步优化,避免了盲目选择BP神经网络结构参数带来的问题,避免了常规BP神经网络容易陷入局部最优解的问题。     

Derivation of surface soil moisture from ENVISAT ASAR wide swath and image mode data in agricultural areas

Water and energy fluxes at the interface between the land surface and atmosphere are strongly dependent on surface soil moisture content, which is highly variable in space and time. It has been shown in numerous studies that microwave remote sensing can provide spatially distributed patterns of surface soil moisture. In order to use remote-sensing-derived soil moisture information for practical applications as, for example, flood forecasting and water balance modeling in mesoscale areas, frequent large-area coverage is a prerequisite. New sensor generations such as ENVISAT Advanced Synthetic Aperture Radar (ASAR) or RADARSAT allow for image acquisitions in different imaging modes and geometries. Imaging modes with the capability of large-area coverage, such as the Wide Swath Mode of ENVISAT ASAR, are of special interest for practical applications in this context. This paper presents a semiempirical soil moisture inversion scheme for ENVISAT ASAR data. Different land cover types as well as mixed-image pixels are taken into account in the soil moisture retrieval process. The inversion results are validated against in situ measurements, and a sensitivity analysis of the model is conducted.     

微波遥感技术监测土壤湿度的研究

土壤湿度在全球气候环境变化中具有重要的作用,微波遥感技术具有监测这一参数的诸多优势。其原理是基于土壤水分在一定范围内和土壤介电常数密切相关。该文从主动微波遥感及被动微波遥感的算法、应用和存在问题等方面分别阐述了当前微波遥感在土壤湿度反演中的研究进展,其中重点介绍了应用较广泛的主动微波遥感中的合成孔径雷达(SAR)和被动微波遥感中的高级微波扫描仪(AMSR)。主动微波遥感中,如何减少或摆脱对地面参数测定特别是粗糙度的依赖、如何采用有效的植被散射模型去除植被影响等问题是未来关注的热点和难点。被动微波遥感中对模型的机理研究还很欠缺,需要结合辐射传输机理及波动论等加强对机理的探讨。另外主被动结合的微波遥感中,对尺度转换、数据同化等技术的研究将是未来关注的重要方向。     

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     

Neural network approach to land cover mapping

A pattern classification method is proposed for remote sensing data using neural networks. First, the authors apply the error backpropagation (BP) algorithm to classify the remote sensing data. In this case, the classification performance depends on a training data set. In order to get stable and precise classification results, the training data set is selected based on geographical information and Kohonen's self-organizing feature map. Using the training data set and the error backpropagation algorithm, a layered neural network is trained such that the training patterns are classified with a specified accuracy. After training the neural network, some pixels are deleted from the original training data set if they are incorrectly classified and a new training data set is built up. Once training is complete, a testing data set is classified by using the trained neural network. The classification results of LANDSAT TM data show that this approach produces excellent results which are more realistic and noiseless compared with a conventional Bayesian method     

Using a priori information to improve soil moisture retrieval from ENVISAT ASAR AP data in semiarid regions

This paper presents a retrieval algorithm that estimates spatial and temporal distribution of volumetric soil moisture content, at an approximate depth of 5 cm, using multitemporal ENVISAT Advanced Synthetic Aperture Radar (ASAR) alternating polarization images, acquired at low incidence angles (i.e., from 15/spl deg/ to 31/spl deg/). The algorithm appropriately assimilates a priori information on soil moisture content and surface roughness in order to constrain the inversion of theoretical direct models, such as the integral equation method model and the geometric optics model. The a priori information on soil moisture content is obtained through simple lumped water balance models, whereas that on soil roughness is derived by means of an empirical approach. To update prior estimates of surface parameters, when no reliable a priori information is available, a technique based solely on the use of multitemporal SAR information is proposed. The developed retrieval algorithm is assessed on the Matera site (Italy) where multitemporal ground and ASAR data were simultaneously acquired in 2003. Simulated and experimental results indicate the possibility of attaining an accuracy of approximately 5% in the retrieved volumetric soil moisture content, provided that sufficiently accurate a priori information on surface parameters (i.e., within 20% of their whole variability range) is available. As an example, multitemporal soil moisture maps at watershed scale, characterized by a spatial resolution of approximately 150 m, are derived and illustrated in the paper.     

Retrieval of snow parameters by iterative inversion of a neuralnetwork

The inversion of snow parameters from passive microwave remote sensing measurements is performed, using an iterative inversion of a neural network (NN) trained with a dense-media multiple-scattering model. Inversion of four parameters is performed based on five brightness temperatures. The four parameters are mean grain size of ice particles in snow, snow density, snow temperature, and snow depth. Iterative inversion of a data-driven forward NN model is justified on a theoretical and methodological basis. An error analysis is performed, comparing iterative inversion of a forward model with the use of an explicit inverse for the retrieval of independent snow parameters from their corresponding measurements. The NN iterative inversion algorithm is further illustrated by reconstructing a synthetic terrain of snow parameters from their corresponding measurements, inverting all four parameters simultaneously. The reconstructed parameter contours are in good agreement with the original synthetic parameter contours     

A dynamic learning neural network for remote sensing applications

The neural network learning process is to adjust the network weights to adapt the selected training data. Based on the polynomial basis function (PBF) modeled neural network that is a modified multilayer perceptrons (MLP) network, a dynamic learning algorithm (DL) is proposed. The presented learning algorithm makes use of the Kalman filtering technique to update the network weights, in the sense that the stochastic characteristics of incoming data sets are implicitly incorporated into the network. The Kalman gains which represent the learning rates of the network weights updating are calculated by using the U-D factorization. By concatenating all of the network weights at each layer to form a long vector such that it can be updated without propagating back, the proposed algorithm improves the performance of convergence to which the backpropagation (BP) learning algorithm often suffers. Numerical illustrations are carried out using two categories of problems: multispectral imagery classification and surface parameters inversion. Results indicates the use of Kalman filtering algorithm not only substantially increases the convergence rate in the learning stage, but also enhances the separability for highly nonlinear boundaries problems, as compared to BP algorithm, suggesting that the proposed DL neural network provides a practical and potential tool for remote sensing applications     

基于自适应波段聚类主成分分析和反向传播神经网络的高光谱图像压缩

高光谱遥感图像具有丰富的光谱信息,数据量大。为了能够有效地利用高光谱图像数据,促进高光谱遥感技术的发展,该文提出一种基于自适应波段聚类主成分分析(PCA)与反向传播(BP)神经网络相结合的高光谱图像压缩算法。算法利用近邻传播(AP)聚类算法对波段进行自适应聚类,对聚类后的各个分组分别进行PCA运算,最后利用BP神经网络对所有主成分进行编码压缩。该文的创新点在于BP神经网络压缩图像时,在训练步骤过程中,误差反向传播是用原图与输出作差值,再反向调整各层的权值、阈值。对高光谱图像进行波段聚类,不仅能够有效地利用谱间相关性,提高压缩性能,还可以降低PCA的运算量。实验结果表明,该文算法与其它现有算法比较,在相同压缩比下,其光谱角更小,信噪比更高。