An overview of the self-organizing map algorithm, on which the papers in this issue are based, is presented in this article.

The Self-Organizing Map

This paper introduces the use of single layer and deep convolutional networks for remote sensing data analysis. Direct application to multi- and hyper-spectral imagery of supervised (shallow or deep) convolutional networks is very challenging given the high input data dimensionality and the relatively small amount of available labeled data. Therefore, we propose the use of greedy layer-wise unsupervised pre-training coupled with a highly efficient algorithm for unsupervised learning of sparse features. The algorithm is rooted on sparse representations and enforces both population and lifetime sparsity of the extracted features, simultaneously. We successfully illustrate the expressive power of the extracted representations in several scenarios: classification of aerial scenes, as well as land-use classification in very high resolution (VHR), or land-cover classification from multi- and hyper-spectral images. The proposed algorithm clearly outperforms standard Principal Component Analysis (PCA) and its kernel counterpart (kPCA), as well as current state-of-the-art algorithms of aerial classification, while being extremely computationally efficient at learning representations of data. Results show that single layer convolutional networks can extract powerful discriminative features only when the receptive field accounts for neighboring pixels, and are preferred when the classification requires high resolution and detailed results. However, deep architectures significantly outperform single layers variants, capturing increasing levels of abstraction and complexity throughout the feature hierarchy.

Unsupervised Deep Feature Extraction for Remote Sensing Image Classification

Accurate correction of the corrupting effects of the atmosphere and the water’s surface are essential in order to obtain the optical, biological and biogeochemical properties of the water from satellite-based multi- and hyper-spectral sensors. The major challenges now for atmospheric correction are the conditions of turbid coastal and inland waters and areas in which there are strongly-absorbing aerosols. Here, we outline how these issues can be addressed, with a focus on the potential of new sensor technologies and the opportunities for the development of novel algorithms and aerosol models. We review hardware developments, which will provide qualitative and quantitative increases in spectral, spatial, radiometric and temporal data of the Earth, as well as measurements from other sources, such as the Aerosol Robotic Network for Ocean Color (AERONET-OC) stations, bio-optical sensors on Argo (Bio–Argo) floats and polarimeters. We provide an overview of the state of the art in atmospheric correction algorithms, highlight recent advances and discuss the possible potential for hyperspectral data to address the current challenges.

Sensor capability and atmospheric correction in ocean colour remote sensing

This paper introduces the use of single-layer and deep convolutional networks for remote sensing data analysis. Direct application to multi- and hyperspectral imagery of supervised (shallow or deep) convolutional networks is very challenging given the high input data dimensionality and the relatively small amount of available labeled data. Therefore, we propose the use of greedy layerwise unsupervised pretraining coupled with a highly efficient algorithm for unsupervised learning of sparse features. The algorithm is rooted on sparse representations and enforces both population and lifetime sparsity of the extracted features, simultaneously. We successfully illustrate the expressive power of the extracted representations in several scenarios: classification of aerial scenes, as well as land-use classification in very high resolution or land-cover classification from multi- and hyperspectral images. The proposed algorithm clearly outperforms standard principal component analysis (PCA) and its kernel counterpart (kPCA), as well as current state-of-the-art algorithms of aerial classification, while being extremely computationally efficient at learning representations of data. Results show that single-layer convolutional networks can extract powerful discriminative features only when the receptive field accounts for neighboring pixels and are preferred when the classification requires high resolution and detailed results. However, deep architectures significantly outperform single-layer variants, capturing increasing levels of abstraction and complexity throughout the feature hierarchy.

The Self-Organizing Map (SOM) algorithm has attracted a great deal of interest among researches and practitioners in a wide variety of fields. The SOM has been analyzed extensively, a number of variants have been developed and, perhaps most notably, it has been applied extensively within fields ranging from engineering sciences to medicine, biology, and economics. We have collected a comprehensive list of 5384 scientific papers that use the algorithms, have benefited from them, or contain analyses of them. The list is intended to serve as a source for literature surveys. The present addendum contains 2092 new articles, mainly from the years 1998-2002. We have provided a keyword index to help finding articles of interest, and additionally a modern automatically constructed variant of a thematic index: a WEBSOM interface to the whole article collection of years 1981-2000. The SOM of SOMs is available at http://websom.hut.fi/websom/somref/search.cgi for browsing and searching the collection.

Bibliography of Self-Organizing Map SOM) Papers: 1998-2001 Addendum

The problem of cloud data classification from satellite imagery using neural networks is considered. Several image transformations such as singular value decomposition (SVD) and wavelet packet (WP) were used to extract the salient spectral and textural features attributed to satellite cloud data in both visible and infrared (IR) channels. In addition, the well-known gray-level cooccurrence matrix (GLCM) method and spectral features were examined for the sake of comparison. Two different neural-network paradigms namely probability neural network (PNN) and unsupervised Kohonen self-organized feature map (SOM) were examined and their performance were also benchmarked on the geostationary operational environmental satellite (GOES) 8 data. Additionally, a postprocessing scheme was developed which utilizes the contextual information in the satellite images to improve the final classification accuracy. Overall, the performance of the PNN when used in conjunction with these feature extraction and postprocessing schemes showed the potential of this neural-network-based cloud classification system.

/pdf/a-study-of-cloud-classification-with-neural-networks-using-1dwodnze26.pdf

A study of cloud classification with neural networks using spectral and textural features

In cloud classification from satellite imagery, temporal change in the images is one of the main factors that causes degradation in the classifier performance. In this paper, a novel temporal updating approach is developed for probabilistic neural network (PNN) classifiers that can be used to track temporal changes in a sequence of images. This is done by utilizing the temporal contextual information and adjusting the PNN to adapt to such changes. Whenever a new set of images arrives, an initial classification is first performed using the PNN updated up to the last frame while at the same time, a prediction using Markov chain models is also made based on the classification results of the previous frame. The results of both the old PNN and the predictor are then compared. Depending on the outcome, either a supervised or an unsupervised updating scheme is used to update the PNN classifier. Maximum likelihood (ML) criterion is adopted in both the training and updating schemes. The proposed scheme is examined on both a simulated data set and the Geostationary Operational Environmental Satellite (GOES) 8 satellite cloud imagery data. These results indicate the improvements in the classification accuracy when the proposed scheme is used.

/pdf/temporal-updating-scheme-for-probabilistic-neural-network-bl3i3leyxl.pdf

Temporal updating scheme for probabilistic neural network with application to satellite cloud classification

An efficient and robust neural network-based scheme is introduced in this paper to perform automatic cloud detection and classification. An unsupervised Kohonen neutral network was used to classify, the cloud contents of a 8/spl times/8 blocks in an image into ten different cloud classes. Inputs to the network consisted of textural features of each block obtained using an efficient feature extraction scheme namely, the wavelet transform (WT). This scheme not only reduces the dimensionality of the data but also extracts useful features of the data. To improve the detection rate and reduce the false positive rate, especially for low clouds and thin high clouds, a multi-channel fusion system was constructed to combine the results of different optical bands. All alternative approach for automatic cloud detection/classification based on multi-spectral features was also studied to analyze and compare the effectiveness of multi-spectral-based scheme vs textural-based scheme. The results using high resolution GOES 8 data show the promise of the Kohonen neural network when used in conjunction with WT as feature extractor for cloud detection/classification.

Neural network-based cloud detection/classification using textural and spectral features

Automatic cloud classification of satellite imagery can be of great help to meteorological studies. A neural network-based cloud classification system is developed and introduced. Several image transformation schemes such as wavelet transform (WT) and singular value decomposition (SVD) are used to extract the salient textural feature of the data and is then compared with those of the well-known gray-level co-occurrence matrix (GLCM) approach. Two different neural network paradigms namely the probability neural network (PNN) and the unsupervised Kohonen (1990) self-organized feature map (SOM) are chosen and examined. The performance of the proposed cloud classification system is benchmarked on the Geostationary Operational Environmental Satellite (GOES) 8 data set and promising results have been achieved.

Neural network-based cloud classification on satellite imagery using textural features

Presents a training algorithm for probabilistic neural networks (PNN) using the minimum classification error (MCE) criterion. A comparison is made between the MCE training scheme and the widely used maximum likelihood (ML) learning on a cloud classification problem using satellite imagery data.

/pdf/comparison-of-two-different-pnn-training-approaches-for-1lm8jdaor0.pdf

Bin Tian

Papers

A study of cloud classification with neural networks using spectral and textural features

Temporal updating scheme for probabilistic neural network with application to satellite cloud classification

Neural network-based cloud detection/classification using textural and spectral features

Neural network-based cloud classification on satellite imagery using textural features

Comparison of two different PNN training approaches for satellite cloud data classification