remotesensing-logo

Journal Browser

Journal Browser

Advanced Machine Learning Approaches for Hyperspectral Data Analysis

A special issue of Remote Sensing (ISSN 2072-4292).

Deadline for manuscript submissions: closed (31 March 2021) | Viewed by 43659

Special Issue Editors

Earthquake Engineering and Disaster Management Institute, Istanbul Technical University, Maslak, 34469 Istanbul, Turkey
Interests: hyperspectral remote sensing; earthquake damage assessment; machine learning; meta-modeling; sensitivity analysis

Special Issue Information

Dear Colleagues,

In the last decade, hyperspectral data have become more widely available due to the development and implementation of new sensors on spaceborne, airborne, and unmanned aerial vehicle platforms, as well as on proximal systems. Such advancements have also been supported by the development of appropriate methodologies and computational approaches for data analysis. Although substantial progress has been made in this direction, multiple challenges are still open due to the high dimensionality nature of the data, which is further increased by growing spatial and spectral resolutions.

In this Special Issue, we welcome methodological contributions in terms of novel machine learning algorithms as well as the application of innovative techniques to relevant scenarios from hyperspectral data. We invite you to submit the most recent advancements in the following, and related, topics:

  • Spectral data pre-processing
  • Feature extraction and selection from high-dimensional data
  • Machine learning and data mining methodologies for hyperspectral data analysis
  • Deep, transfer, manifold, metric, and active learning
  • Large-scale hyperspectral data analysis
  • Methods for image segmentation and classification, change and target detection, multi-temporal analysis, hyperspectral unmixing
  • Real-time processing
  • Multi-modal data fusion between hyperspectral imagery with other data sources
  • Advanced techniques for characterization of natural ecosystems, coastal systems, agricultural, or urban areas

Dr. Edoardo Pasolli
Dr. Gulsen Taskin
Dr. Zhou Zhang
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Remote sensing
  • Hyperspectral data
  • Machine learning
  • Data pre-processing
  • Dimensionality reduction
  • Image classification
  • Data fusion
  • Spatial information
  • Deep learning

Published Papers (10 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

23 pages, 7566 KiB  
Article
Identify Informative Bands for Hyperspectral Target Detection Using the Third-Order Statistic
by Xiurui Geng, Lei Wang and Luyan Ji
Remote Sens. 2021, 13(9), 1776; https://0-doi-org.brum.beds.ac.uk/10.3390/rs13091776 - 02 May 2021
Cited by 1 | Viewed by 1727
Abstract
Constrained energy minimization (CEM) has been proposed and widely researched in the field of hyperspectral target detection. Generally, it selects one of the target spectra as the representative and then keeps its output constant while minimizing the average filter output energy of the [...] Read more.
Constrained energy minimization (CEM) has been proposed and widely researched in the field of hyperspectral target detection. Generally, it selects one of the target spectra as the representative and then keeps its output constant while minimizing the average filter output energy of the data. However, it has been proven that as the number of bands (L) increases, CEM will gradually lower the average filter output energy when keeping the representative’s output constant. Unavoidably, due to the inherent spatial and temporal variation of the spectra, this will lead to an unreasonable phenomenon, i.e., if L is particularly large, when adding more bands, CEM will suppress more and more pixels, even including the target pixels. This means that the optimal solution of CEM may not correspond to the target detection result that we desire. To deal with this, in this paper, we introduce the third-order statistic (skewness) of the CEM model, served as an auxiliary index to determine whether a band is beneficial to target detection or not. Theoretically, we prove that the skewness index can always exclude the noisy bands with Gaussian distribution. In addition, experiments on several widely used remote sensing data indicate that the index can also efficiently identify informative bands for a better target detection performance. Full article
(This article belongs to the Special Issue Advanced Machine Learning Approaches for Hyperspectral Data Analysis)
Show Figures

Graphical abstract

25 pages, 703 KiB  
Article
Improving Land Cover Classification Using Genetic Programming for Feature Construction
by João E. Batista, Ana I. R. Cabral, Maria J. P. Vasconcelos, Leonardo Vanneschi and Sara Silva
Remote Sens. 2021, 13(9), 1623; https://0-doi-org.brum.beds.ac.uk/10.3390/rs13091623 - 21 Apr 2021
Cited by 10 | Viewed by 2470
Abstract
Genetic programming (GP) is a powerful machine learning (ML) algorithm that can produce readable white-box models. Although successfully used for solving an array of problems in different scientific areas, GP is still not well known in the field of remote sensing. The M3GP [...] Read more.
Genetic programming (GP) is a powerful machine learning (ML) algorithm that can produce readable white-box models. Although successfully used for solving an array of problems in different scientific areas, GP is still not well known in the field of remote sensing. The M3GP algorithm, a variant of the standard GP algorithm, performs feature construction by evolving hyperfeatures from the original ones. In this work, we use the M3GP algorithm on several sets of satellite images over different countries to create hyperfeatures from satellite bands to improve the classification of land cover types. We add the evolved hyperfeatures to the reference datasets and observe a significant improvement of the performance of three state-of-the-art ML algorithms (decision trees, random forests, and XGBoost) on multiclass classifications and no significant effect on the binary classifications. We show that adding the M3GP hyperfeatures to the reference datasets brings better results than adding the well-known spectral indices NDVI, NDWI, and NBR. We also compare the performance of the M3GP hyperfeatures in the binary classification problems with those created by other feature construction methods such as FFX and EFS. Full article
(This article belongs to the Special Issue Advanced Machine Learning Approaches for Hyperspectral Data Analysis)
Show Figures

Graphical abstract

20 pages, 7000 KiB  
Article
Integrating MNF and HHT Transformations into Artificial Neural Networks for Hyperspectral Image Classification
by Ming-Der Yang, Kai-Hsiang Huang and Hui-Ping Tsai
Remote Sens. 2020, 12(14), 2327; https://0-doi-org.brum.beds.ac.uk/10.3390/rs12142327 - 20 Jul 2020
Cited by 10 | Viewed by 2995
Abstract
The critical issue facing hyperspectral image (HSI) classification is the imbalance between dimensionality and the number of available training samples. This study attempted to solve the issue by proposing an integrating method using minimum noise fractions (MNF) and Hilbert–Huang transform (HHT) transformations into [...] Read more.
The critical issue facing hyperspectral image (HSI) classification is the imbalance between dimensionality and the number of available training samples. This study attempted to solve the issue by proposing an integrating method using minimum noise fractions (MNF) and Hilbert–Huang transform (HHT) transformations into artificial neural networks (ANNs) for HSI classification tasks. MNF and HHT function as a feature extractor and image decomposer, respectively, to minimize influences of noises and dimensionality and to maximize training sample efficiency. Experimental results using two benchmark datasets, Indian Pine (IP) and Pavia University (PaviaU) hyperspectral images, are presented. With the intention of optimizing the number of essential neurons and training samples in the ANN, 1 to 1000 neurons and four proportions of training sample were tested, and the associated classification accuracies were evaluated. For the IP dataset, the results showed a remarkable classification accuracy of 99.81% with a 30% training sample from the MNF1–14+HHT-transformed image set using 500 neurons. Additionally, a high accuracy of 97.62% using only a 5% training sample was achieved for the MNF1–14+HHT-transformed images. For the PaviaU dataset, the highest classification accuracy was 98.70% with a 30% training sample from the MNF1–14+HHT-transformed image using 800 neurons. In general, the accuracy increased as the neurons increased, and as the training samples increased. However, the accuracy improvement curve became relatively flat when more than 200 neurons were used, which revealed that using more discriminative information from transformed images can reduce the number of neurons needed to adequately describe the data as well as reducing the complexity of the ANN model. Overall, the proposed method opens new avenues in the use of MNF and HHT transformations for HSI classification with outstanding accuracy performance using an ANN. Full article
(This article belongs to the Special Issue Advanced Machine Learning Approaches for Hyperspectral Data Analysis)
Show Figures

Graphical abstract

21 pages, 4930 KiB  
Article
A GA-Based Multi-View, Multi-Learner Active Learning Framework for Hyperspectral Image Classification
by Nasehe Jamshidpour, Abdolreza Safari and Saeid Homayouni
Remote Sens. 2020, 12(2), 297; https://0-doi-org.brum.beds.ac.uk/10.3390/rs12020297 - 16 Jan 2020
Cited by 14 | Viewed by 3486
Abstract
This paper introduces a novel multi-view multi-learner (MVML) active learning method, in which the different views are generated by a genetic algorithm (GA). The GA-based view generation method attempts to construct diverse, sufficient, and independent views by considering both inter- and intra-view confidences. [...] Read more.
This paper introduces a novel multi-view multi-learner (MVML) active learning method, in which the different views are generated by a genetic algorithm (GA). The GA-based view generation method attempts to construct diverse, sufficient, and independent views by considering both inter- and intra-view confidences. Hyperspectral data inherently owns high dimensionality, which makes it suitable for multi-view learning algorithms. Furthermore, by employing multiple learners at each view, a more accurate estimation of the underlying data distribution can be obtained. We also implemented a spectral-spatial graph-based semi-supervised learning (SSL) method as the classifier, which improved the performance of the classification task in comparison with supervised learning. The evaluation of the proposed method was based on three different benchmark hyperspectral data sets. The results were also compared with other state-of-the-art AL-SSL methods. The experimental results demonstrated the efficiency and statistically significant superiority of the proposed method. The GA-MVML AL method improved the classification performances by 16.68%, 18.37%, and 15.1% for different data sets after 40 iterations. Full article
(This article belongs to the Special Issue Advanced Machine Learning Approaches for Hyperspectral Data Analysis)
Show Figures

Graphical abstract

25 pages, 23155 KiB  
Article
The t-SNE Algorithm as a Tool to Improve the Quality of Reference Data Used in Accurate Mapping of Heterogeneous Non-Forest Vegetation
by Anna Halladin-Dąbrowska, Adam Kania and Dominik Kopeć
Remote Sens. 2020, 12(1), 39; https://0-doi-org.brum.beds.ac.uk/10.3390/rs12010039 - 20 Dec 2019
Cited by 15 | Viewed by 4557
Abstract
Supervised classification methods, used for many applications, including vegetation mapping require accurate “ground truth” to be effective. Nevertheless, it is common for the quality of this data to be poorly verified prior to it being used for the training and validation of classification [...] Read more.
Supervised classification methods, used for many applications, including vegetation mapping require accurate “ground truth” to be effective. Nevertheless, it is common for the quality of this data to be poorly verified prior to it being used for the training and validation of classification models. The fact that noisy or erroneous parts of the reference dataset are not removed is usually explained by the relatively high resistance of some algorithms to errors. The objective of this study was to demonstrate the rationale for cleaning the reference dataset used for the classification of heterogeneous non-forest vegetation, and to present a workflow based on the t-distributed stochastic neighbor embedding (t-SNE) algorithm for the better integration of reference data with remote sensing data in order to improve outcomes. The proposed analysis is a new application of the t-SNE algorithm. The effectiveness of this workflow was tested by classifying three heterogeneous non-forest Natura 2000 habitats: Molinia meadows (Molinion caeruleae; code 6410), species-rich Nardus grassland (code 6230) and dry heaths (code 4030), employing two commonly used algorithms: random forest (RF) and AdaBoost (AB), which, according to the literature, differ in their resistance to errors in reference datasets. Polygons collected in the field (on-ground reference data) in 2016 and 2017, containing no intentional errors, were used as the on-ground reference dataset. The remote sensing data used in the classification were obtained in 2017 during the peak growing season by a HySpex sensor consisting of two imaging spectrometers covering spectral ranges of 0.4–0.9 μm (VNIR-1800) and 0.9–2.5 μm (SWIR-384). The on-ground reference dataset was gradually cleaned by verifying candidate polygons selected by visual interpretation of t-SNE plots. Around 40–50% of candidate polygons were ultimately found to contain errors. Altogether, 15% of reference polygons were removed. As a result, the quality of the final map, as assessed by the Kappa and F1 accuracy measures as well as by visual evaluation, was significantly improved. The global map accuracy increased by about 6% (in Kappa coefficient), relative to the baseline classification obtained using random removal of the same number of reference polygons. Full article
(This article belongs to the Special Issue Advanced Machine Learning Approaches for Hyperspectral Data Analysis)
Show Figures

Graphical abstract

23 pages, 1071 KiB  
Article
Supervised and Semi-Supervised Self-Organizing Maps for Regression and Classification Focusing on Hyperspectral Data
by Felix M. Riese, Sina Keller and Stefan Hinz
Remote Sens. 2020, 12(1), 7; https://0-doi-org.brum.beds.ac.uk/10.3390/rs12010007 - 18 Dec 2019
Cited by 67 | Viewed by 11152
Abstract
Machine learning approaches are valuable methods in hyperspectral remote sensing, especially for the classification of land cover or for the regression of physical parameters. While the recording of hyperspectral data has become affordable with innovative technologies, the acquisition of reference data (ground truth) [...] Read more.
Machine learning approaches are valuable methods in hyperspectral remote sensing, especially for the classification of land cover or for the regression of physical parameters. While the recording of hyperspectral data has become affordable with innovative technologies, the acquisition of reference data (ground truth) has remained expensive and time-consuming. There is a need for methodological approaches that can handle datasets with significantly more hyperspectral input data than reference data. We introduce the Supervised Self-organizing Maps (SuSi) framework, which can perform unsupervised, supervised and semi-supervised classification as well as regression on high-dimensional data. The methodology of the SuSi framework is presented and compared to other frameworks. Its different parts are evaluated on two hyperspectral datasets. The results of the evaluations can be summarized in four major findings: (1) The supervised and semi-Supervised Self-organizing Maps (SOM) outperform random forest in the regression of soil moisture. (2) In the classification of land cover, the supervised and semi-supervised SOM reveal great potential. (3) The unsupervised SOM is a valuable tool to understand the data. (4) The SuSi framework is versatile, flexible, and easy to use. The SuSi framework is provided as an open-source Python package on GitHub. Full article
(This article belongs to the Special Issue Advanced Machine Learning Approaches for Hyperspectral Data Analysis)
Show Figures

Graphical abstract

21 pages, 5983 KiB  
Article
Active Semi-Supervised Random Forest for Hyperspectral Image Classification
by Youqiang Zhang, Guo Cao, Xuesong Li, Bisheng Wang and Peng Fu
Remote Sens. 2019, 11(24), 2974; https://0-doi-org.brum.beds.ac.uk/10.3390/rs11242974 - 11 Dec 2019
Cited by 39 | Viewed by 3695
Abstract
Random forest (RF) has obtained great success in hyperspectral image (HSI) classification. However, RF cannot leverage its full potential in the case of limited labeled samples. To address this issue, we propose a unified framework that embeds active learning (AL) and semi-supervised learning [...] Read more.
Random forest (RF) has obtained great success in hyperspectral image (HSI) classification. However, RF cannot leverage its full potential in the case of limited labeled samples. To address this issue, we propose a unified framework that embeds active learning (AL) and semi-supervised learning (SSL) into RF (ASSRF). Our aim is to utilize AL and SSL simultaneously to improve the performance of RF. The objective of the proposed method is to use a small number of manually labeled samples to train classifiers with relative high classification accuracy. To achieve this goal, a new query function is designed to query the most informative samples for manual labeling, and a new pseudolabeling strategy is introduced to select some samples for pseudolabeling. Compared with other AL- and SSL-based methods, the proposed method has several advantages. First, ASSRF utilizes the spatial information to construct a query function for AL, which can select more informative samples. Second, in addition to providing more labeled samples for SSL, the proposed pseudolabeling method avoids bias caused by AL-labeled samples. Finally, the proposed model retains the advantages of RF. To demonstrate the effectiveness of ASSRF, we conducted experiments on three real hyperspectral data sets. The experimental results have shown that our proposed method outperforms other state-of-the-art methods. Full article
(This article belongs to the Special Issue Advanced Machine Learning Approaches for Hyperspectral Data Analysis)
Show Figures

Graphical abstract

21 pages, 7506 KiB  
Article
A Novel Hyperspectral Image Classification Pattern Using Random Patches Convolution and Local Covariance
by Yangjie Sun, Zhongliang Fu and Liang Fan
Remote Sens. 2019, 11(16), 1954; https://0-doi-org.brum.beds.ac.uk/10.3390/rs11161954 - 20 Aug 2019
Cited by 7 | Viewed by 3550
Abstract
Today, more and more deep learning frameworks are being applied to hyperspectral image classification tasks and have achieved great results. However, such approaches are still hampered by long training times. Traditional spectral–spatial hyperspectral image classification only utilizes spectral features at the pixel level, [...] Read more.
Today, more and more deep learning frameworks are being applied to hyperspectral image classification tasks and have achieved great results. However, such approaches are still hampered by long training times. Traditional spectral–spatial hyperspectral image classification only utilizes spectral features at the pixel level, without considering the correlation between local spectral signatures. Our article has tested a novel hyperspectral image classification pattern, using random-patches convolution and local covariance (RPCC). The RPCC is an effective two-branch method that, on the one hand, obtains a specified number of convolution kernels from the image space through a random strategy and, on the other hand, constructs a covariance matrix between different spectral bands by clustering local neighboring pixels. In our method, the spatial features come from multi-scale and multi-level convolutional layers. The spectral features represent the correlations between different bands. We use the support vector machine as well as spectral and spatial fusion matrices to obtain classification results. Through experiments, RPCC is tested with five excellent methods on three public data-sets. Quantitative and qualitative evaluation indicators indicate that the accuracy of our RPCC method can match or exceed the current state-of-the-art methods. Full article
(This article belongs to the Special Issue Advanced Machine Learning Approaches for Hyperspectral Data Analysis)
Show Figures

Graphical abstract

20 pages, 3769 KiB  
Article
Ensemble-Based Cascaded Constrained Energy Minimization for Hyperspectral Target Detection
by Rui Zhao, Zhenwei Shi, Zhengxia Zou and Zhou Zhang
Remote Sens. 2019, 11(11), 1310; https://0-doi-org.brum.beds.ac.uk/10.3390/rs11111310 - 01 Jun 2019
Cited by 74 | Viewed by 4989
Abstract
Ensemble learning is an important group of machine learning techniques that aim to enhance the nonlinearity and generalization ability of a learning system by aggregating multiple learners. We found that ensemble techniques show great potential for improving the performance of traditional hyperspectral target [...] Read more.
Ensemble learning is an important group of machine learning techniques that aim to enhance the nonlinearity and generalization ability of a learning system by aggregating multiple learners. We found that ensemble techniques show great potential for improving the performance of traditional hyperspectral target detection algorithms, while at present, there are few previous works have been done on this topic. To this end, we propose an Ensemble based Constrained Energy Minimization (E-CEM) detector for hyperspectral image target detection. Classical hyperspectral image target detection algorithms like Constrained Energy Minimization (CEM), matched filter (MF) and adaptive coherence/cosine estimator (ACE) are usually designed based on constrained least square regression methods or hypothesis testing methods with Gaussian distribution assumption. However, remote sensing hyperspectral data captured in a real-world environment usually shows strong nonlinearity and non-Gaussianity, which will lead to performance degradation of these classical detection algorithms. Although some hierarchical detection models are able to learn strong nonlinear discrimination of spectral data, due to the spectrum changes, these models usually suffer from the instability in detection tasks. The proposed E-CEM is designed based on the classical CEM detection algorithm. To improve both of the detection nonlinearity and generalization ability, the strategies of “cascaded detection”, “random averaging” and “multi-scale scanning” are specifically designed. Experiments on one synthetic hyperspectral image and two real hyperspectral images demonstrate the effectiveness of our method. E-CEM outperforms the traditional CEM detector and other state-of-the-art detection algorithms. Our code will be made publicly available. Full article
(This article belongs to the Special Issue Advanced Machine Learning Approaches for Hyperspectral Data Analysis)
Show Figures

Figure 1

19 pages, 2906 KiB  
Article
Dimensionality Reduction of Hyperspectral Image Using Spatial-Spectral Regularized Sparse Hypergraph Embedding
by Hong Huang, Meili Chen and Yule Duan
Remote Sens. 2019, 11(9), 1039; https://0-doi-org.brum.beds.ac.uk/10.3390/rs11091039 - 01 May 2019
Cited by 18 | Viewed by 3684
Abstract
Many graph embedding methods are developed for dimensionality reduction (DR) of hyperspectral image (HSI), which only use spectral features to reflect a point-to-point intrinsic relation and ignore complex spatial-spectral structure in HSI. A new DR method termed spatial-spectral regularized sparse hypergraph embedding (SSRHE) [...] Read more.
Many graph embedding methods are developed for dimensionality reduction (DR) of hyperspectral image (HSI), which only use spectral features to reflect a point-to-point intrinsic relation and ignore complex spatial-spectral structure in HSI. A new DR method termed spatial-spectral regularized sparse hypergraph embedding (SSRHE) is proposed for the HSI classification. SSRHE explores sparse coefficients to adaptively select neighbors for constructing the dual sparse hypergraph. Based on the spatial coherence property of HSI, a local spatial neighborhood scatter is computed to preserve local structure, and a total scatter is computed to represent the global structure of HSI. Then, an optimal discriminant projection is obtained by possessing better intraclass compactness and interclass separability, which is beneficial for classification. Experiments on Indian Pines and PaviaU hyperspectral datasets illustrated that SSRHE effectively develops a better classification performance compared with the traditional spectral DR algorithms. Full article
(This article belongs to the Special Issue Advanced Machine Learning Approaches for Hyperspectral Data Analysis)
Show Figures

Graphical abstract

Back to TopTop