Soil moisture (SM) dynamics regulate the exchange of water, energy, and biochemical fluxes between land and atmosphere. Consolidated earth observation SM products are available at low resolution (e.g., 3-40 km) globally, but higher resolutions are still under research. Surface heterogeneity in soil properties, land use, and vegetation cover can hinder SM retrieval. This paper aims to illustrate the effects of surface roughness anisotropy, canopy structure, vegetation water content, and precipitation patterns on SAR and optical observations at a resolution of approximately 100 m. Case studies and strategies to improve high-resolution SM retrieval will be discussed.
Most of the current SAR systems aquire fully polarimetric data where the obtained scattering information can
be represented by various coherent and incoherent parameters. In previous contributions we reviewed these
parameters in terms of their "utility" for landcover classification, here, we investigate their impact on several
classification algoritms. Three classifiers: the minimum-distance classifier, a multi-layer perceptron (MLP) and
one based on logistic regression (LR) were applied on an L-Band scene acquired by the E-SAR sensor. MLP
and LR were chosen because they are robust w.r.t. the data statistics. An interesting result is that MLP gives
better results on the coherent parameters while LR gives better results on the incoherent parameters.
In this contribution, we present a study on a series of representations of polarimetric synthetic aperture radar (SAR) data, testing and comparing them with respect to their utility for land cover classification. Different classification algorithms are also compared. Part of this work is dedicated to the study of the dependence of the classification results on the varying size of averaging windows of pixels. Such an analysis will permit to prove if the polarimetric parameters under consideration describe only point-like physical properties of the targets or if they also contain "extended" local information. The final goal is to provide an objective estimate of the usefulness of these parameters.
The objective of this paper is to investigate and compare two model-based methods for the soil moisture retrieval from SAR data. The overall accuracy of model-based methods in estimating geophysical parameters mostly depends both on the performances of the exploited direct model and on the intrinsic ambiguity of SAR data. The ambiguity is due to the complexity of the relationship between the geophysical parameters, such as soil moisture and soil roughness, and the backscattering values that makes 'ill posed' the inverse problem of the parameter retrieval. Moreover, the accuracy of soil moisture estimates depends also on the retrieval algorithm and on its robustness to the noise. In this study, the methods under investigation perform a probabilistic estimation of the parameters, finding solutions representative of an unknown distribution such as the mean or the most probable solutions. The model-based methods considered are a Neural Network algorithm, to explicit invert the direct model, and a Mixture Model algorithm, to approximate the parameter distribution function. The theoretical direct model adopted to tune the inversion algorithms is the Integral Equation Method (IEM) model. A comparison of the characteristics of the two algorithms is shown, and same evaluations of the accuracy in predicting soil moisture content from SAR data are performed. In particular, evaluations refers to ERS and ENVISAT ASAR data simulated by means of the IEM model.
In recent years it has been proved that combined analysis of SAR intensity and interferometric correlation images is a valuable tool in classification tasks where traditional techniques such as crisp thresholding schemes and classical maximum likelihood classifiers have been employed. In this work, developed in the framework of the ESA AO3-320 project titled Application of ERS data to landslide activity monitoring in southern Apennines, Italy, our goal is to investigate: (1) usefulness of SAR interferometric correlation information in mapping areas with diffuse erosional activity, including landslides; and (2) effectiveness of soft computing techniques in the combined analysis of SAR intensity and interferometric correlation images. Two neural classifiers are selected from the literature. The first classifier is a one- stage error-driven Multilayer Perceptron (MLP) and the second classifier is a Two-Stage Hybrid (TSH) learning system, consisting of a sequence of an unsupervised data-driven first stage with a supervised error-driven second stage. The TSH unsupervised first stage is implemented as either: (1) the on- line learning, dynamic-sizing, dynamic-linking Fully Self Organizing Simplified Adaptive Resonance Theory (FOSART) clustering model; (2) the batch-learning, static-sizing, no- linking Fuzzy Learning Vector Quantization (FLVQ) algorithm; or (3) the on-line learning, static-sizing, static-linking Self-Organizing Map (SOM). The input data set consists of three SAR ERS-1/ERS-2 tandem pair images depicting an area featuring slope instability phenomena in the Campanian Apennines of Southern Italy. From each tandem pair, four pixel-based features are extracted: the backscattering mean intensity, the interferometric coherence, the backscattering intensity texture and the backscattering intensity change. Our classification task is focused on the discrimination of land cover types useful for hazard evaluation, i.e., evaluation of areas affected by erosion. Classification results show that class erosion can be discriminated from other land cover classes when SAR mean intensity images are combined with coherence and texture information. In addition, our results demonstrate that soft computing techniques provide useful tools for the combined analysis of SAR intensity and coherence images. In particular, the TSH classifier employing the FOSART clustering algorithm shows: (1) an overall accuracy comparable with that of the other classification schemes under testing; (2) a training cost significantly lower than that of MLP and lower than that of TSH employing either FLVQ or SOM as its first stage; and (3) a capability of discriminating class erosion superior to that of the other classification schemes under testing.
In the last years, both local and global analysis techniques for the effective processing of interferometric SAR data have been proposed. We developed two local approaches to eliminate inconsistencies in the measured (wrapped) phase field, based on the local configurations of phase gradients in finite windows. The first technique adopts a fixed search strategy which 'cures' isolated residue couples by an appropriate series of corrections determined a priori. A second strategy uses the generalization capabilities of a neural network, trained on a suitable number of simulated target phase fields, to add 2 - (pi) cycles to the proper locations of the interferogram. These approaches, in spite of the high dimensionality of this problem, are able to correctly remove more than half the original number of pointlike inconsistencies on real noisy interferograms. This stems from the observation that phase unwrapping is an ill-posed problem, which has to be solved globally. Hence, a global stochastic method has been implemented, based on the minimization of a functional measuring the regularity of the phase field. The optimization tool used is simulated annealing with constraints. This methodology gives excellent results also in difficult conditions. We will present some of the recent results which aim at integrating the above-mentioned methodologies into powerful processing chains optimized for operating on large IFSAR datasets from real scenes. The effectiveness of such phase retrieving methods allows the application of sophisticated and innovative remote sensing techniques, such as differential interferometry.
We consider the problem of classification of remote sensed data from LANDSAT Thematic Mapper images. The data have been acquired in July 1986 on an area locate din South Italy. We compare the performance obtained by feed-forward neural networks designed by a parallel genetic algorithm to determine their topology with the ones obtained by means of a multi-layer perceptron trained with Back Propagation learning rule. The parallel genetic algorithm, implemented on the APE100/Quadrics platform, is based on the coding scheme recently proposed by Sternieri and Anelli and exploits a recently proposed environment for genetic algorithms on Quadrics, called AGAPE. The SASIMD architecture of Quadrics forces the chromosome representation. The coding scheme provides that the connections weights of the neural network are organized as a floating point string. The parallelization scheme adopted is the elitistic coarse grained stepping stone model, with migration occurring only towards neighboring processors. The fitness function depends on the mean square error.After fixing the total number of individuals and running the algorithm on Quadrics architectures with different number of processors, the proposed parallel genetic algorithm displayed a superlinear speedup. We report results obtained on a data set made of 1400 patterns.
2D phase unwrapping, a problem common to signal processing, optics, and interferometric radar topographic applications, consists in retrieving an absolute phase field from principal, noisy measurements. In this paper, we analyze the application of neural networks to this complex mathematical problem, formulating it as a learning-by-examples strategy, by training a multilayer perceptron to associate a proper correction pattern to the principal phase gradient configuration on local window. In spite of the high dimensionality of this problem the proposed MLP, trained on examples from simulated phase surfaces, shows to be able to correctly remove more than half the original number of pointlike inconsistencies on real noisy interferograms. Better efficiencies could be achieved by enlarging the processing window size, so as to exploit a greater amount of information. By pushing further this change of perspective, one passes from a local to a global point of view; problems of this kind are more effectively solved, rather than through learning strategies, by minimization procedures, for which we prose a powerful algorithm, based on a stochastic approach.
Phase unwrapping is one of the toughest problems in interferometric SAR processing. The main difficulties arise from the presence of point-like error sources, called residues, which occur mainly in close couples due to phase noise. We present an assessment of a local approach to the resolution of these problems by means of a neural network. Using a multi-layer perceptron, trained with the back- propagation scheme on a series of simulated phase images, fashion the best pairing strategies for close residue couples. Results show that god efficiencies and accuracies can have been obtained, provided a sufficient number of training examples are supplied. Results show that good efficiencies and accuracies can be obtained, provided a sufficient number of training examples are supplied. The technique is tested also on real SAR ERS-1/2 tandem interferometric images of the Matera test site, showing a good reduction of the residue density. The better results obtained by use of the neural network as far as local criteria are adopted appear justified given the probabilistic nature of the noise process on SAR interferometric phase fields and allows to outline a specifically tailored implementation of the neural network approach as a very fast pre-processing step intended to decrease the residue density and give sufficiently clean images to be processed further by more conventional techniques.
This paper deals with the application of a new competitive, on-line, neuro-fuzzy architecture, the fully self-organizing simplified adaptive resonance theory (FOSART), to the analysis of remote sensed Antarctic data, in a classification experiment. FOSART employs fuzzy set memberships in the weights updating rule; it applies an ART-based vigilance test to control neuron proliferation and takes advantage of the fact that it employs a new version of the competitive Hebbian Rule to dynamically generate and remove synaptic links between neurons, as well as neurons. As a consequence, FOSART can develop disjointed subnets. The results obtained with FOSART have been compared with those obtained with other neuro-fuzzy unsupervised architecture: FuzzySART, FLVQ, SOM. The finding suggests that FOSART performances are lower, at convergence, than those of FLVQ and SOM, even if it shows a faster adaptivity to the input data structure, due to its topological and on-line characteristics.
KEYWORDS: Classification systems, Fuzzy logic, Neural networks, Neurons, Data processing, Feature extraction, Data acquisition, Data modeling, Information operations, Radon
In this work the effectiveness of the fuzzy Kohonen clustering network (FKCN) has been explored in two classification experiments of remote sensed data. The FKCN has been introduced in a multi-modular neural classification system for feature extraction before labeling. The unsupervised module is connected in cascade with the next supervised module, based on the backpropagation learning rule. The performance of the FKCN has been evaluated in comparison with those of a conventional Kohonen self organizing map (SOM) neural network. Experimental results have proved that the fuzzy clustering network can be used for complex data pre-processing.
This study investigates the applicability of a multimodular neuro-fuzzy system in the multispectral analysis of magnetic resonance (MR) images of the human brain. The system consists of two components: an unsupervised neural module for image segmentation in tissue regions and a supervised module for tissue labeling. The former is the fuzzy Kohonen clustering network (FKCN). The latter is a feed-forward network based on the back-propagation learning rule. The results obtained with the FKCN have been compared with those extracted by a self organizing map (SOM). The system has been used to analyze the multispectral MR brain images of a healthy volunteer. The data set included the proton density (PD), T2, T1 weighted spin-echo (SE) bands and a new T1- weighted three dimensional sequence, i.e. the magnetization- prepared rapid gradient echo (MP-RAGE). One of the main objectives of this study has been to evaluate the usefulness of brain imaging with the MP-RAGE sequence in view of automatic tissue classification. To this purpose, a quantitative evaluation has been provided on the base of some labeled areas selected interactively by a neuro- radiologist from the input raw images. Quantitative results seem to indicate that the MP-RAGE sequence may provide higher tissue separability than the T1-weighted SE sequence.
In the cosmic ray space experiments, the separation of the signal from background is a hard task. Due to the well-known critical conditions that characterize this class of experiments, some changes of the detector performances can be observed during the data taking. As a consequence, differences between the test and real data are found as systematic errors in the classification phase. In this paper, a modular classification system based on neural networks is proposed for the signal/background discrimination task in cosmic ray space experiments, without a priori knowledge of the discriminating feature distributions. The system is composed by two neural modules. The first one is a self organizing map (SOM) that both clusters the real data space in suitable classes of similarity and builds a prototype for each of them; a skilled inspection of the prototypes defines the signal and background. The second one, a multi layer perceptron (MLP) with a single hidden layer, adapts the classification model based on training/test data to the real experimental conditions. The MLP synaptic weights adaptive formation takes into account the labelled real data set as defined in the first system-phase. The modular neural system has been applied in the context of TRAMP-Si experiment, performed on the NASA Balloon-Borne Magnet Facility, for the positron/proton discrimination.
In this paper a modular neural network architecture is proposed for classification of Remote Sensed data. The neural network learning task of the supervised Multi Layer Perceptron (MLP) Classifier has been made more efficient by pre-processing the input with an unsupervised feature discovery neural module. Two classification experiments have been carried for coping with two different situations, very usual in real remote sensing applications: the availability of complex data, such as high dimensional and multisourced data, and on the contrary, the case of imperfect low dimensional data set, with a limited number of samples. In the first experiment on a multitemporal data set, the Linear Propagation Network (LPN) has been introduced to evaluate the effectiveness of neural data compression stage before classification. In the second experiment on a poor data set, the Kohonen Self Organising Feature Map (SOM) Network has been introduced for clustering data before labelling. In the paper is also illustrated the criterion for the selection of an optimal number of cluster centres to be used as node number of the output SOM layer. The results of the two experiments have confirmed that modular learning performs better than the non-modular one in learning quality and speed.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.