Search

Machine learning models are used to identify crops in satellite data, which achieve high classification accuracy but do not necessarily have a high degree of transferability to new regions. This paper investigates the use of machine learning models for crop classification using Sentinel-2 imagery. It proposes a new testing methodology that systematically analyzes the quality of the spatial transfer of trained models. In this study, the classification results of Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Stochastic Gradient Descent (SGD), Multilayer Perceptron (MLP), Support Vector Machines (SVM), and a Majority Voting of all models and their spatial transferability are assessed. The proposed testing methodology comprises 18 test scenarios to investigate phenological, temporal, spatial, and quantitative (quantitative regarding available training data) influences. Results show that the model accuracies tend to decrease with increasing time due to the differences in phenological phases in different regions, with a combined F1-score of 82% (XGBoost) when trained on a single day, 72% (XGBoost) when trained on the half-season, and 61% when trained over the entire growing season (Majority Voting). [ABSTRACT FROM AUTHOR]

The Mediterranean ecosystem exhibits a particular geology and climate, which is characterized by mild, rainy winters and long, very hot summers with low precipitation; it has led to the emergence of resilient plant species. Such habitats contain a preponderance of shrubs, and collectively harbor 10% of the Earth's species, thus containing some of the most unique shrubby formations protecting against environmental natural degradation. Due to shrub species diversity, initial phases of forestland, heterogenous grasses, bare ground and stones, the monitoring of such areas is difficult. For this reason, the aim of this paper is to assess semi-automatic classifications of the shrubby formations based on multispectral Sentinel-2 and visible and near infrared (VINR) AISA-EAGLE II hyperspectral airborne images with a support of Canopy High Model (CHM) as a three-dimensional information and field-verified patterns, based on Match-T/DSM and aerial photos. Support Vector Machine (SVM) and Random Forest (RF) classifiers have been tested on a few scenarios featuring different combinations of spectral and Minimum Noise Fraction (MNF) transformed bands and vegetation indices. Referring to the results, the average overall accuracy for the SVM and AISA images (all tested data sets) was 78.23%, and for the RF: 79.85%. In the case of Sentinel-2, the SVM classifier obtained an average value of 83.63%, while RF: 85.32%; however, in the case of the shrubland, we would like to recommend the RF classifier, because the highest mean value of F1-score achieved was 91.86% (SVM offered few-percent-point worse results), and the required training time was quicker than SVM. Commonly available Sentinel-2 data offered higher accuracies for shrubland monitoring than did the airborne VNIR data. [ABSTRACT FROM AUTHOR]

Joint sparse representation classification (JSRC) is a representative spectral–spatial classifier for hyperspectral images (HSIs). However, the JSRC is inappropriate for highly heterogeneous areas due to the spatial information being extracted from a fixed-sized neighborhood block, which is often unable to conform to the naturally irregular structure of land cover. To address this problem, a superpixel-based JSRC with nonlocal weighting, i.e., superpixel-based nonlocal weighted JSRC (SNLW-JSRC), is proposed in this paper. In SNLW-JSRC, the superpixel representation of an HSI is first constructed based on an entropy rate segmentation method. This strategy forms homogeneous neighborhoods with naturally irregular structures and alleviates the inclusion of pixels from different classes in the process of spatial information extraction. Afterwards, the superpixel-based nonlocal weighting (SNLW) scheme is built to weigh the superpixel based on its structural and spectral information. In this way, the weight of one specific neighboring pixel is determined by the local structural similarity between the neighboring pixel and the central test pixel. Then, the obtained local weights are used to generate the weighted mean data for each superpixel. Finally, JSRC is used to produce the superpixel-level classification. This speeds up the sparse representation and makes the spatial content more centralized and compact. To verify the proposed SNLW-JSRC method, we conducted experiments on four benchmark hyperspectral datasets, namely Indian Pines, Pavia University, Salinas, and DFC2013. The experimental results suggest that the SNLW-JSRC can achieve better classification results than the other four SRC-based algorithms and the classical support vector machine algorithm. Moreover, the SNLW-JSRC can also outperform the other SRC-based algorithms, even with a small number of training samples. [ABSTRACT FROM AUTHOR]

Estimating precipitation area is important for weather forecasting as well as real-time application. This paper aims to develop an analytical framework for efficient precipitation area estimation using S-band dual-polarization radar measurements. Several types of factors, such as types of sensors, thresholds, and models, are considered and compared to form a data set. After building the appropriate data set, this paper yields a rigorous comparison of classification methods in statistical (logistic regression and linear discriminant analysis) and machine learning (decision tree, support vector machine, and random forest). To achieve better performance, spatial classification is considered by incorporating latitude and longitude of observation location into classification, compared with non-spatial classification. The data used in this study were collected by rain detector and present weather sensor in a network of automated weather systems (AWS), and an S-band dual-polarimetric weather radar during ten different rainfall events of varying lengths. The mean squared prediction error (MSPE) from leave-one-out cross validation (LOOCV) is computed to assess the performance of the methods. Of the methods, the decision tree and random forest methods result in the lowest MSPE, and spatial classification outperforms non-spatial classification. Particularly, machine-learning-based spatial classification methods accurately estimate the precipitation area in the northern areas of the study region. [ABSTRACT FROM AUTHOR]

Automatic building extraction from satellite images, an open research topic in remote sensing, continues to represent a challenge and has received substantial attention for decades. This paper presents an object-based and machine learning-based approach for automatic house detection from RGB high-resolution images. The images are first segmented by an algorithm combing a thresholding watershed transformation and hierarchical merging, and then shadows and vegetation are eliminated from the initial segmented regions to generate building candidates. Subsequently, the candidate regions are subjected to feature extraction to generate training data. In order to capture the characteristics of house regions well, we propose two kinds of new features, namely edge regularity indices (ERI) and shadow line indices (SLI). Finally, three classifiers, namely AdaBoost, random forests, and Support Vector Machine (SVM), are employed to identify houses from test images and quality assessments are conducted. The experiments show that our method is effective and applicable for house identification. The proposed ERI and SLI features can improve the precision and recall by 5.6% and 11.2%, respectively. [ABSTRACT FROM AUTHOR]

Feature extraction using polarimetric synthetic aperture radar (PolSAR) images is of great interest in SAR classification, no matter if it is applied in an unsupervised approach or a supervised approach. In the supervised classification framework, a major group of methods is based on machine learning. Various machine learning methods have been investigated for PolSAR image classification, including neural network (NN), support vector machine (SVM), and so on. Recently, representation-based classifications have gained increasing attention in hyperspectral imagery, such as the newly-proposed sparse-representation classification (SRC) and nearest-regularized subspace (NRS). These classifiers provide excellent performance that is comparable to or even better than the classic SVM for remotely-sensed image processing. However, rare studies have been found to extend this representation-based NRS classification into PolSAR images. By the use of the NRS approach, a polarimetric feature vector-based PolSAR image classification method is proposed in this paper. The polarimetric SAR feature vector is constructed by the components of different target decomposition algorithms for each pixel, including those scattering components of Freeman, Huynen, Krogager, Yamaguchi decomposition, as well as the eigenvalues, eigenvectors and their consequential parameters such as entropy, anisotropy and mean scattering angle. Furthermore, because all these representation-based methods were originally designed to be pixel-wise classifiers, which only consider the separate pixel signature while ignoring the spatial-contextual information, the Markov random field (MRF) model is also introduced in our scheme. MRF can provide a basis for modeling contextual constraints. Two AIRSAR data in the Flevoland area are used to validate the proposed classification scheme. Experimental results demonstrate that the proposed method can reach an accuracy of around 99% for both AIRSAR data by randomly selecting 300 pixels of each class as the training samples. Under the condition that the training data ratio is more than 4%, it has better performance than the SVM, SVM-MRF and NRS methods. [ABSTRACT FROM AUTHOR]

In this paper, an approach for radar clutter, especially sea and land clutter classification, is considered under the following conditions: the average amplitude levels of the clutter are close to each other, and the distributions of the clutter are unknown. The proposed approach divides the dataset into two parts. The first data sequence from sea and land is used to train the model to compute the parameters of the classifier, and the second data sequence from sea and land under the same conditions is used to test the performance of the algorithm. In order to find the essential structure of the data, a new data representation method based on the graph spectrum is utilized. The method reveals the nondominant correlation implied in the data, and it is quite different from the traditional method. Furthermore, this representation is combined with the support vector machine (SVM) artificial intelligence algorithm to solve the problem of sea and land clutter classification. We compare the proposed graph feature set with nine exciting valid features that have been used to classify sea clutter from the radar in other works, especially when the average amplitude levels of the two types of clutter are very close. The experimental results prove that the proposed extraction can represent the characteristics of the raw data efficiently in this application. [ABSTRACT FROM AUTHOR]

Classification of hyperspectral images always suffers from high dimensionality and very limited labeled samples. Recently, the spectral-spatial classification has attracted considerable attention and can achieve higher classification accuracy and smoother classification maps. In this paper, a novel spectral-spatial classification method for hyperspectral images by using kernel methods is investigated. For a given hyperspectral image, the principle component analysis (PCA) transform is first performed. Then, the first principle component of the input image is segmented into non-overlapping homogeneous regions by using the entropy rate superpixel (ERS) algorithm. Next, the local spectral histogram model is applied to each homogeneous region to obtain the corresponding texture features. Because this step is performed within each homogenous region, instead of within a fixed-size image window, the obtained local texture features in the image are more accurate, which can effectively benefit the improvement of classification accuracy. In the following step, a contextual spectral-texture kernel is constructed by combining spectral information in the image and the extracted texture information using the linearity property of the kernel methods. Finally, the classification map is achieved by the support vector machines (SVM) classifier using the proposed spectral-texture kernel. Experiments on two benchmark airborne hyperspectral datasets demonstrate that our method can effectively improve classification accuracies, even though only a very limited training sample is available. Specifically, our method can achieve from 8.26% to 15.1% higher in terms of overall accuracy than the traditional SVM classifier. The performance of our method was further compared to several state-of-the-art classification methods of hyperspectral images using objective quantitative measures and a visual qualitative evaluation. [ABSTRACT FROM AUTHOR]

Invasive plants are a serious problem in island ecosystems and are the main cause of the extinction of endemic species. Cuba is located within one of the hotspots of global biodiversity, which, coupled with high endemism and the impacts caused by various disturbances, makes it a region particularly sensitive to potential damage by invasive plants like Dichrostachys cinerea (L.) Wight & Arn. (marabú). However, there is a lack of timely information for monitoring this species, as well as about the land use and land cover (LULC) classes most significantly impacted by this invasion in the last few decades and their spatial distribution. The main objective of this study, carried out in Central Cuba, was to detect and monitor the spread of marabú over a 28-year period. The land covers for the years 1994 and 2022 were classified using Landsat 5 TM and 8 OLI images with three different classification algorithms: maximum likelihood (ML), support vector machine (SVM), and random forest (RF). The results obtained showed that RF outperformed the other classifiers, achieving AUC values of 0.92 for 1994 and 0.97 for 2022. It was confirmed that the area covered by marabú increased by 29,555 ha, from 61,977.59 ha in 1994 to 91,533.47 ha in 2022 (by around 48%), affecting key land covers like woodlands, mangroves, and rainfed croplands. These changes in the area covered by marabú were associated, principally, with changes in land uses and tenure and not with other factors, such as rainfall or relief in the province. The use of other free multispectral imagery, such as Sentinel 2 data, with higher temporal and spatial resolution, could further refine the model's accuracy. [ABSTRACT FROM AUTHOR]

Imaging spectroscopy (hyperspectral sensing) is a proven tool for mapping and monitoring the spatial distribution of vegetation species composition. However, there exists a gap when it comes to the availability of high-resolution spatial and spectral imagery for accurate tree species mapping, particularly in complex forest environments, despite the continuous advancements in operational remote sensing and field sensor technologies. Here, we aim to bridge this gap by enhancing our fundamental understanding of imaging spectrometers via complex simulated environments. We used DIRSIG, a physics-based, first-principles simulation approach to model canopy-level reflectance for 3D plant models and species-level leaf reflectance in a synthetic forest scene. We simulated a realistic scene, based on the same species composition, found at Harvard Forest, MA (USA). Our simulation approach allowed us to better understand the interplay between instrument parameters and landscape characteristics, and facilitated comprehensive traceability of error budgets. To enhance our understanding of the impact of sensor design on classification performance, we simulated image samples at different spatial, spectral, and scale resolutions (by modifying the pixel pitch and the total number of pixels in the sensor array, i.e., the focal plane dimension) of the imaging sensor and assessed the performance of a deep learning-based convolutional neural network (CNN) and a traditional machine learning classifier, support vector machines (SVMs), to classify vegetation species. Overall, across all resolutions and species mixtures, the highest classification accuracy varied widely from 50 to 84%, and the number of genus-level species classes identified ranged from 2 to 17, among 24 classes. Harnessing this simulation approach has provided us valuable insights into sensor configurations and the optimization of data collection methodologies to improve the interpretation of spectral signatures for accurate tree species mapping in forest scenes. Note that we used species classification as a proxy for a host of imaging spectroscopy applications. However, this approach can be extended to other ecological scenarios, such as in evaluating the changing ecosystem composition, detecting invasive species, or observing the effects of climate change on ecosystem diversity. [ABSTRACT FROM AUTHOR]

Hyperspectral image classification can be achieved by modeling an energy minimization problem on a graph of image pixels. In this paper, an effective spectral-spatial classification method for hyperspectral images based on joint bilateral filtering (JBF) and graph cut segmentation is proposed. In this method, a novel technique for labeling regions obtained by the spectral-spatial segmentation process is presented. Our method includes the following steps. First, the probabilistic support vector machines (SVM) classifier is used to estimate probabilities belonging to each information class. Second, an extended JBF is employed to perform image smoothing on the probability maps. By using our JBF process, salt-and-pepper classification noise in homogeneous regions can be effectively smoothed out while object boundaries in the original image are better preserved as well. Third, a sequence of modified bi-labeling graph cut models is constructed for each information class to extract the desirable object belonging to the corresponding class from the smoothed probability maps. Finally, a classification map is achieved by merging the segmentation maps obtained in the last step using a simple and effective rule. Experimental results based on three benchmark airborne hyperspectral datasets with different resolutions and contexts demonstrate that our method can achieve 8.56%-13.68% higher overall accuracies than the pixel-wise SVM classifier. The performance of our method was further compared to several classical hyperspectral image classification methods using objective quantitative measures and a visual qualitative evaluation. [ABSTRACT FROM AUTHOR]

This paper proposes a Nested Sliding Window (NSW) method based on the correlation between pixel vectors, which can extract spatial information from the hyperspectral image (HSI) and reconstruct the original data. In the NSW method, the neighbourhood window constructed with the target pixel as the centre contains relevant pixels that are spatially adjacent to the target pixel. In the neighbourhood window, a nested sliding sub-window contains the target pixel and a part of the relevant pixels. The optimal sub-window position is determined according to the average value of the Pearson correlation coefficients of the target pixel and the relevant pixels, and the target pixel can be reconstructed by using the pixels and the corresponding correlation coefficients in the optimal sub-window. By combining NSW with Principal Component Analysis (PCA) and Support Vector Machine (SVM), a classification model, namely NSW-PCA-SVM, is obtained. This paper conducts experiments on three public datasets, and verifies the effectiveness of the proposed model by comparing with two basic models, i.e., SVM and PCA-SVM, and six state-of-the-art models, i.e., CDCT-WF-SVM, CDCT-2DCT-SVM, SDWT-2DWT-SVM, SDWT-WF-SVM, SDWT-2DCT-SVM and Two-Stage. The proposed approach has the following advantages in overall accuracy (OA)—take the experimental results on the Indian Pines dataset as an example: (1) Compared with SVM (OA = 53.29%) and PCA-SVM (OA = 58.44%), NSW-PCA-SVM (OA = 91.40%) effectively utilizes the spatial information of HSI and improves the classification accuracy. (2) The performance of the proposed model is mainly determined by two parameters, i.e., the window size in NSW and the number of principal components in PCA. The two parameters can be adjusted independently, making parameter adjustment more convenient. (3) When the sample size of the training set is small (20 samples per class), the proposed NSW-PCA-SVM approach achieves 2.38–18.40% advantages in OA over the six state-of-the-art models. [ABSTRACT FROM AUTHOR]

Mapping agricultural crops is an important application of remote sensing. However, in many cases it is based either on hyperspectral imagery or on multitemporal coverage, both of which are difficult to scale up to large-scale deployment at high spatial resolution. In the present paper, we evaluate the possibility of crop classification based on single images from very high-resolution (VHR) satellite sensors. The main objective of this work is to expose performance difference between state-of-the-art parcel-based smoothing and purely data-driven conditional random field (CRF) smoothing, which is yet unknown. To fulfill this objective, we perform extensive tests with four different classification methods (Support Vector Machines, Random Forest, Gaussian Mixtures, and Maximum Likelihood) to compute the pixel-wise data term; and we also test two different definitions of the pairwise smoothness term. We have performed a detailed evaluation on different multispectral VHR images (Ikonos, QuickBird, Kompsat-2). The main finding of this study is that pairwise CRF smoothing comes close to the state-of-the-art parcel-based method that requires parcel boundaries (average difference ' 2.5%). Our results indicate that a single multispectral (R, G, B, NIR) image is enough to reach satisfactory classification accuracy for six crop classes (corn, pasture, rice, sugar beet, wheat, and tomato) in Mediterranean climate. Overall, it appears that crop mapping using only one-shot VHR imagery taken at the right time may be a viable alternative, especially since high-resolution multitemporal or hyperspectral coverage as well as parcel boundaries are in practice often not available. [ABSTRACT FROM AUTHOR]

Accurate cotton maps are crucial for monitoring cotton growth and precision management. The paper proposed a county-scale cotton mapping method by using random forest (RF) feature selection algorithm and classifier based on selecting multi-features, including spectral, vegetation indices, and texture features. The contribution of texture features to cotton classification accuracy was also explored in addition to spectral features and vegetation index. In addition, the optimal classification time, feature importance, and the best classifier on the cotton extraction accuracy were evaluated. The results showed that the texture feature named the gray level co-occurrence matrix (GLCM) is effective for improving classification accuracy, ranking second in contribution among all studied spectral, VI, and texture features. Among the three classifiers, the RF showed higher accuracy and better stability than support vector machines (SVM) and artificial neural networks (ANN). The average overall accuracy (OA) of the classification combining multiple features was 93.36%, 7.33% higher than the average OA of the single-time spectrum, and 2.05% higher than the average OA of the multi-time spectrum. The classification accuracy after feature selection by RF can still reach 92.12%, showing high accuracy and efficiency. Combining multiple features and random forest methods may be a promising county-scale cotton classification method. [ABSTRACT FROM AUTHOR]

Lithological classification is a pivotal aspect in the field of geology, and traditional field surveys are inefficient and challenging in certain areas. Remote sensing technology offers advantages such as high efficiency and wide coverage, providing a solution to the aforementioned issues. The aim of this study is to apply remote sensing technology for lithological classification and attempt to enhance the accuracy of classification. Taking a study area in Jixi, Heilongjiang Province, China, as an example, lithological classification is conducted using high-resolution satellite remote sensing data from GF-2 and texture data based on gray-level co-occurrence matrix (GLCM). By comparing the accuracy of lithological classification using different methods, the support vector machine (SVM) method with the highest overall accuracy is selected for further investigation. Subsequently, this study compares the effects of combining GF-2 data with different texture data, and the results indicate that combining textures can effectively improve the accuracy of lithological classification. In particular, the combination of GF-2 and the Dissimilarity index performs the best among single-texture combinations, with an overall accuracy improvement of 7.8630% (increasing from 74.6681% to 82.5311%) compared to using only GF-2 data. In the multi-texture combination dataset, the Mean index is crucial for enhancing classification accuracy. Selecting appropriate textures for combination can effectively improve classification accuracy, but it is important to note that excessive overlaying of textures may lead to a decrease in accuracy. Furthermore, this study employs principal component analysis (PCA) and independent component analysis (ICA) to process the GF-2 data and combines the resulting PCA and ICA datasets with different texture data for lithological classification. The results demonstrate that combining PCA and ICA with texture data further enhances classification accuracy. In conclusion, this study demonstrates the application of remote sensing technology in lithological classification, with a focus on exploring the application value of different combinations of multispectral data, texture data, PCA data, and ICA data. These findings provide valuable insights for future research in this field. [ABSTRACT FROM AUTHOR]

Accurate and reliable crop classification information is a significant data source for agricultural monitoring and food security evaluation research. It is well-known that polarimetric synthetic aperture radar (PolSAR) data provides ample information for crop classification. Moreover, multi-temporal PolSAR data can further increase classification accuracies since the crops show different external forms as they grow up. In this paper, we distinguish the crop types with multi-temporal PolSAR data. First, due to the "dimension disaster" of multi-temporal PolSAR data caused by excessive scattering parameters, a neural network of sparse auto-encoder with non-negativity constraint (NC-SAE) was employed to compress the data, yielding efficient features for accurate classification. Second, a novel crop discrimination network with multi-scale features (MSCDN) was constructed to improve the classification performance, which is proved to be superior to the popular classifiers of convolutional neural networks (CNN) and support vector machine (SVM). The performances of the proposed method were evaluated and compared with the traditional methods by using simulated Sentinel-1 data provided by European Space Agency (ESA). For the final classification results of the proposed method, its overall accuracy and kappa coefficient reaches 99.33% and 99.19%, respectively, which were almost 5% and 6% higher than the CNN method. The classification results indicate that the proposed methodology is promising for practical use in agricultural applications. [ABSTRACT FROM AUTHOR]

Conventional classification algorithms have shown great success in balanced hyperspectral data classification. However, the imbalanced class distribution is a fundamental problem of hyperspectral data, and it is regarded as one of the great challenges in classification tasks. To solve this problem, a non-ANN based deep learning, namely SMOTE-Based Weighted Deep Rotation Forest (SMOTE-WDRoF) is proposed in this paper. First, the neighboring pixels of instances are introduced as the spatial information and balanced datasets are created by using the SMOTE algorithm. Second, these datasets are fed into the WDRoF model that consists of the rotation forest and the multi-level cascaded random forests. Specifically, the rotation forest is used to generate rotation feature vectors, which are input into the subsequent cascade forest. Furthermore, the output probability of each level and the original data are stacked as the dataset of the next level. And the sample weights are automatically adjusted according to the dynamic weight function constructed by the classification results of each level. Compared with the traditional deep learning approaches, the proposed method consumes much less training time. The experimental results on four public hyperspectral data demonstrate that the proposed method can get better performance than support vector machine, random forest, rotation forest, SMOTE combined rotation forest, convolutional neural network, and rotation-based deep forest in multiclass imbalance learning. [ABSTRACT FROM AUTHOR]

Because of the limitations of hardware devices, such as the sensors, processing capacity, and high accuracy altitude control equipment, traditional optical remote sensing (RS) imageries capture information regarding the same scene from mostly one single angle or a very small number of angles. Nowadays, with video satellites coming into service, obtaining imageries of the same scene from a more-or-less continuous array of angles has become a reality. In this paper, we analyze the differences between the traditional RS data and continuous multi-angle remote sensing (CMARS) data, and unravel the characteristics of the CMARS data. We study the advantages of using CMARS data for classification and try to capitalize on the complementarity of multi-angle information and, at the same time, to reduce the embedded redundancy. Our arguments are substantiated by real-life experiments on the employment of CMARS data in order to classify urban land covers while using a support vector machine (SVM) classifier. They show the superiority of CMARS data over the traditional data for classification. The overall accuracy may increase up to about 9% with CMARS data. Furthermore, we investigate the advantages and disadvantages of directly using the CMARS data, and how such data can be better utilized through the extraction of key features that characterize the variations of spectral reflectance along the entire angular array. This research lay the foundation for the use of CMARS data in future research and applications. [ABSTRACT FROM AUTHOR]

In this paper, a novel feature line embedding (FLE) algorithm based on support vector machine (SVM), referred to as SVMFLE, is proposed for dimension reduction (DR) and for improving the performance of the generative adversarial network (GAN) in hyperspectral image (HSI) classification. The GAN has successfully shown high discriminative capability in many applications. However, owing to the traditional linear-based principal component analysis (PCA) the pre-processing step in the GAN cannot effectively obtain nonlinear information; to overcome this problem, feature line embedding based on support vector machine (SVMFLE) was proposed. The proposed SVMFLE DR scheme is implemented through two stages. In the first scatter matrix calculation stage, FLE within-class scatter matrix, FLE between-scatter matrix, and support vector-based FLE between-class scatter matrix are obtained. Then in the second weight determination stage, the training sample dispersion indices versus the weight of SVM-based FLE between-class matrix are calculated to determine the best weight between-scatter matrices and obtain the final transformation matrix. Since the reduced feature space obtained by the SVMFLE scheme is much more representative and discriminative than that obtained using conventional schemes, the performance of the GAN in HSI classification is higher. The effectiveness of the proposed SVMFLE scheme with GAN or nearest neighbor (NN) classifiers was evaluated by comparing them with state-of-the-art methods and using three benchmark datasets. According to the experimental results, the performance of the proposed SVMFLE scheme with GAN or NN classifiers was higher than that of the state-of-the-art schemes in three performance indices. Accuracies of 96.3%, 89.2%, and 87.0% were obtained for the Salinas, Pavia University, and Indian Pines Site datasets, respectively. Similarly, this scheme with the NN classifier also achieves 89.8%, 86.0%, and 76.2% accuracy rates for these three datasets. [ABSTRACT FROM AUTHOR]

This study aims to explore the joint usage of multisource scatterometer measurements in polar sea water and ice discrimination. All radar backscatter measurements from current operating satellite scatterometers are considered, including the C-band ASCAT scatterometer on board the MetOp series satellites, the Ku-band scatterometer on board the HY-2B satellite (HSCAT), and the Ku-band scatterometer on board the CFOSAT satellite (CSCAT). By performing seven experiments that use the same support vector machine (SVM) classifier method but with different input data, we find that the SVM model with all available HSCAT, CSCAT, and ASCAT scatterometer data as inputs gives the best performance. In addition to the SVM outputs, we employ the image erosion/dilation techniques and area growth method to reduce misclassifications of sea water and ice. The sea ice extent obtained in this study shows a good agreement with the National Snow and Ice Data Center (NSIDC) sea ice concentration data from the years 2019 to 2021. More specifically, the sea ice areas are closer to the sea ice areas calculated using 15% as the threshold for NSIDC sea ice concentration data in both Arctic and Antarctic. The sea ice edges acquired by the multisource scatterometer show a close correlation with sea ice edges from the Sentinel-1 Synthetic Aperture Radar (SAR) images. In addition, we found that the coverage of multisource scatterometer data in a half-day is usually above 97%, and more importantly, the sea ice areas obtained on the basis of half-day and daily multisource scatterometer data are very close to each other. The presented work can serve as guidance on the usage of all available scatterometer measurements in sea ice monitoring. [ABSTRACT FROM AUTHOR]

Europe's mountain forests, which are naturally valuable areas due to their high biodiversity and well-preserved natural characteristics, are experiencing major alterations, so an important component of monitoring is obtaining up-to-date information concerning species composition, extent, and location. An important aspect of mapping tree stands is the selection of remote sensing data that vary in temporal, spectral, and spatial resolution, as well as in open and commercial access. For the Tatra Mountains area, which is a unique alpine ecosystem in central Europe, we classified 13 woody species by iterative machine learning methods using random forest (RF) and support vector machine (SVM) algorithms of more than 1000 polygons collected in the field. For this task, we used free Sentinel-2 multitemporal satellite data (10 m pixel size, 12 spectral bands, and 21 acquisition dates), commercial PlanetScope data (3 m pixel size, 8 spectral bands, and 3 acquisitions dates), and airborne HySpex hyperspectral data (2 m pixel size, 430 spectral bands, and a single acquisition) with fusion of the data of topographic derivatives based on Shuttle Radar Topography Mission (SRTM) and airborne laser scanning (ALS) data. The iterative classification method achieved the highest F1-score with HySpex (0.95 RF; 0.92 SVM) imagery, but the multitemporal Sentinel-2 data cube, which consisted of 21 scenes, offered comparable results (0.93 RF; 0.89 SVM). The three images of the high-resolution PlanetScope produced slightly less accurate results (0.89 RF; 0.87 SVM). [ABSTRACT FROM AUTHOR]

Species identification in Quebec, Canada, is usually performed with photo-interpretation at the stand level, and often results in a lack of precision which affects forest management. Very high spatial resolution imagery, such as WorldView-3 and Light Detection and Ranging have the potential to overcome this issue. The main objective of this study is to map 11 tree species at the tree level using an object-based approach. For modeling, 240 variables were derived from WorldView-3 with pixel-based and arithmetic feature calculation techniques. A global approach (11 species) was compared to a hierarchical approach at two levels: (1) tree type (broadleaf/conifer) and (2) individual broadleaf (five) and conifer (six) species. Five different model techniques were compared: support vector machine, classification and regression tree, random forest (RF), k-nearest neighbors, and linear discriminant analysis. Each model was assessed using 16-band or first 8-band derived variables, with the results indicating higher precision for the RF technique. Higher accuracies were found using 16-band instead of 8-band derived variables for the global approach (overall accuracy (OA): 75% vs. 71%, Kappa index of agreement (KIA): 0.72 vs. 0.67) and tree type level (OA: 99% vs. 97%, KIA: 0.97 vs. 0.95). For broadleaf individual species, higher accuracy was found using first 8-band derived variables (OA: 70% vs. 68%, KIA: 0.63 vs. 0.60). No distinction was found for individual conifer species (OA: 94%, KIA: 0.93). This paper demonstrates that a hierarchical classification approach gives better results for conifer species and that using an 8-band WorldView-3 instead of a 16-band is sufficient. [ABSTRACT FROM AUTHOR]

Lack of accurate and up-to-date data associated with irrigated areas and related irrigation amounts is hampering the full implementation and compliance of the Water Framework Directive (WFD). In this paper, we describe the framework that we developed and implemented within the DIANA project to map the actual extent of irrigated areas in the Campania region (Southern Italy) during the 2018 irrigation season. For this purpose, we considered 202 images from the Harmonized Landsat Sentinel-2 (HLS) products (57 images from Landsat 8 and 145 images from Sentinel-2). Such data were preprocessed in order to extract a multitemporal Normalized Difference Vegetation Index (NDVI) map, which was then smoothed through a gap-filling algorithm. We further integrated data coming from high-resolution (4 km) global satellite precipitation Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks (PERSIANN)-Cloud Classification System (CCS) products. We collected an extensive ground truth in the field represented by 2992 data points coming from three main thematic classes: bare soil and rainfed (class 0), herbaceous (class 1), and tree crop (class 2). This information was exploited to generate irrigated area maps by adopting a machine learning classification approach. We compared six different types of classifiers through a cross-validation approach and found that, in general, random forests, support vector machines, and boosted decision trees exhibited the best performances in terms of classification accuracy and robustness to different tested scenarios. We found an overall accuracy close to 90% in discriminating among the three thematic classes, which highlighted promising capabilities in the detection of irrigated areas from HLS products. [ABSTRACT FROM AUTHOR]

Deep learning has attracted extensive attention in the field of hyperspectral images (HSIs) classification. However, supervised deep learning methods heavily rely on a large amount of label information. To address this problem, in this paper, we propose a two-stage deep domain adaptation method for hyperspectral image classification, which can minimize the data shift between two domains and learn a more discriminative deep embedding space with very few labeled target samples. A deep embedding space is first learned by minimizing the distance between the source domain and the target domain based on Maximum Mean Discrepancy (MMD) criterion. The Spatial–Spectral Siamese Network is then exploited to reduce the data shift and learn a more discriminative deep embedding space by minimizing the distance between samples from different domains but the same class label and maximizes the distance between samples from different domains and class labels based on pairwise loss. For the classification task, the softmax layer is replaced with a linear support vector machine, in which learning minimizes a margin-based loss instead of the cross-entropy loss. The experimental results on two sets of hyperspectral remote sensing images show that the proposed method can outperform several state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Deep learning has achieved great success in hyperspectral image classification. However, when processing new hyperspectral images, the existing deep learning models must be retrained from scratch with sufficient samples, which is inefficient and undesirable in practical tasks. This paper aims to explore how to accurately classify new hyperspectral images with only a few labeled samples, i.e., the hyperspectral images few-shot classification. Specifically, we design a new deep classification model based on relational network and train it with the idea of meta-learning. Firstly, the feature learning module and the relation learning module of the model can make full use of the spatial–spectral information in hyperspectral images and carry out relation learning by comparing the similarity between samples. Secondly, the task-based learning strategy can enable the model to continuously enhance its ability to learn how to learn with a large number of tasks randomly generated from different data sets. Benefitting from the above two points, the proposed method has excellent generalization ability and can obtain satisfactory classification results with only a few labeled samples. In order to verify the performance of the proposed method, experiments were carried out on three public data sets. The results indicate that the proposed method can achieve better classification results than the traditional semisupervised support vector machine and semisupervised deep learning models. [ABSTRACT FROM AUTHOR]

Most available studies in lithological mapping using spaceborne multispectral and hyperspectral remote sensing images employ different classification and spectral matching algorithms for performing this task; however, our experiment reveals that no single algorithm renders satisfactory results. Therefore, a new approach based on an ensemble of classifiers is presented for lithological mapping using remote sensing images in this paper, which returns enhanced accuracy. The proposed method uses a weighted pooling approach for lithological mapping at each pixel level using the agreement of the class accuracy, overall accuracy and kappa coefficient from the multi-classifiers of an image. The technique is implemented in four steps; (1) classification images are generated using a variety of classifiers; (2) accuracy assessments are performed for each class, overall classification and estimation of kappa coefficient for every classifier; (3) an overall within-class accuracy index is estimated by weighting class accuracy, overall accuracy and kappa coefficient for each class and every classifier; (4) finally each pixel is assigned to a class for which it has the highest overall within-class accuracy index amongst all classes in all classifiers. To demonstrate the strength of the developed approach, four supervised classifiers (minimum distance (MD), spectral angle mapper (SAM), spectral information divergence (SID), support vector machine (SVM)) are used on one hyperspectral image (Hyperion) and two multispectral images (ASTER, Landsat 8-OLI) for mapping lithological units of the Udaipur area, Rajasthan, western India. The method is found significantly effective in increasing the accuracy in lithological mapping. [ABSTRACT FROM AUTHOR]

Huizhou-style ancient architecture was one of the most important genres of architectural heritage in China. The architecture employed bricks, woods, and stones as raw materials, and timber frames were significant structures. Due to the drawback that the timbers were vulnerable to moisture and atmospheric agents, ancient timber buildings needed frequent protective interventions to maintain its good condition. Such interventions unavoidably disrupted the consistency between the original timber components. Besides this, the modifications brought about difficulty in correctly analysing and judging the state of existing ancient buildings, which, in current preservation practices, mainly rely on the expertise of skilled craftsmen to classify wood species and to identify the building-age of the timber components. Therefore, the industry and the research community urgently need a technique to rapidly and accurately classify wood materials and to discriminate building-age. In the paper, we designed an eye-safe 81-channel hyperspectral LiDAR (HSL) to tackle these issues. The HSL used an acousto-optic tunable filter (AOTF) as a spectral bandpass filter, offering the HSL measurements with 5 nm spectral resolution. Based on the HSL measurements, we analysed the relationship between the surface and cross-section spectral profiles of timber components from different ancient architectures built in the early Qing dynasty (~300 years), late Qing dynasty (~100 years), and nowadays, and confirmed the feasibility of using surface spectra of timber components for classification purpose. We classified building-ages and wood species with multiple Naive Bayes (NB) and support vector machine (SVM) classifiers by the surface spectra of timber components; this also unveiled the possibility of classifying gnawed timber components from its spectra for the first time. The encouraging experimental results supported that the AOTF-HSL is feasible for historic timber building preservation. [ABSTRACT FROM AUTHOR]

Tree species classification at individual tree crowns (ITCs) level, using remote-sensing data, requires the availability of a sufficient number of reliable reference samples (i.e., training samples) to be used in the learning phase of the classifier. The classification performance of the tree species is mainly affected by two main issues: (i) an imbalanced distribution of the tree species classes, and (ii) the presence of unreliable samples due to field collection errors, coordinate misalignments, and ITCs delineation errors. To address these problems, in this paper, we present a weighted Support Vector Machine (wSVM)-based approach for the detection of tree species at ITC level. The proposed approach initially extracts (i) different weights associated to different classes of tree species, to mitigate the effect of the imbalanced distribution of the classes; and (ii) different weights associated to different training samples according to their importance for the classification problem, to reduce the effect of unreliable samples. Then, in order to exploit different weights in the learning phase of the classifier a wSVM algorithm is used. The features to characterize the tree species at ITC level are extracted from both the elevation and intensity of airborne light detection and ranging (LiDAR) data. Experimental results obtained on two study areas located in the Italian Alps show the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

Although many machine learning methods have been successfully applied for the object-based classification of high resolution (HR) remote sensing imagery, current methods are highly dependent on the spectral similarity between segmented objects and have disappointingly poor performance when dealing with different segmented objects that have similar spectra. To overcome this limitation, this study exploited a knowledge graph (KG) that preserved the spatial relationships between segmented objects and has a reasoning capability that can assist in improving the probability of correctly classifying different segmented objects with similar spectra. In addition, to assist the knowledge graph classifications, an image segmentation method generating segmented objects that closely resemble real ground objects in size was used, which improves the integrity of the object classification results. Therefore, a novel HR remote sensing image classification scheme is proposed that involves a knowledge graph and an optimal segmentation algorithm, which takes full advantage of object-based classification and knowledge inference. This method effectively addresses the problems of object classification integrity and misclassification of objects with the same spectrum. In the evaluation experiments, three QuickBird-2 images and over 15 different land cover classes were utilized. The results showed that the classification accuracy of the proposed method is high, with overall accuracies exceeding 0.85. These accuracies are higher than the K Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Tree (DT), and Random Forest (RF) methods. The evaluated results confirmed that the proposed method offers excellent performance in HR remote sensing image classification. [ABSTRACT FROM AUTHOR]

A quantum machine is a human-made device whose collective motion follows the laws of quantum mechanics. Quantum machine learning (QML) is machine learning for quantum computers. The availability of quantum processors has led to practical applications of QML algorithms in the remote sensing field. Quantum machines can learn from fewer data than non-quantum machines, but because of their low processing speed, quantum machines cannot be applied to an image that has hundreds of thousands of pixels. Researchers around the world are exploring applications for QML and in this work, it is applied for pseudo-labelling of samples. Here, a PRISMA (PRecursore IperSpettrale della Missione Applicativa) hyperspectral dataset is prepared by quantum-based pseudo-labelling and 11 different machine learning algorithms viz., support vector machine (SVM), K-nearest neighbour (KNN), random forest (RF), light gradient boosting machine (LGBM), XGBoost, support vector classifier (SVC) + decision tree (DT), RF + SVC, RF + DT, XGBoost + SVC, XGBoost + DT, and XGBoost + RF with this dataset are evaluated. An accuracy of 86% was obtained for the classification of pine trees using the hybrid XGBoost + decision tree technique. [ABSTRACT FROM AUTHOR]

Air quality has a significant influence on the environment and health. Instruments that efficiently and inexpensively detect air quality could be extremely valuable in detecting air quality indices. This study presents a robust deep learning model named AQE-Net, for estimating air quality from mobile images. The algorithm extracts features and patterns from scene photographs collected by the camera device and then classifies the images according to air quality index (AQI) levels. Additionally, an air quality dataset (KARACHI-AQI) of high-quality outdoor images was constructed to enable the model's training and assessment of performance. The sample data were collected from an air quality monitoring station in Karachi City, Pakistan, comprising 1001 hourly datasets, including photographs, PM2.5 levels, and the AQI. This study compares and examines traditional machine learning algorithms, e.g., a support vector machine (SVM), and deep learning models, such as VGG16, InceptionV3, and AQE-Net on the KHI-AQI dataset. The experimental findings demonstrate that, compared to other models, AQE-Net achieved more accurate categorization findings for air quality. AQE-Net achieved 70.1% accuracy, while SVM, VGG16, and InceptionV3 achieved 56.2% and 59.2% accuracy, respectively. In addition, MSE, MAE, and MAPE values were calculated for our model (1.278, 0.542, 0.310), which indicates the remarkable efficacy of our approach. The suggested method shows promise as a fast and accurate way to estimate and classify pollutants from only captured photographs. This flexible and scalable method of assessment has the potential to fill in significant gaps in the air quality data gathered from costly devices around the world. [ABSTRACT FROM AUTHOR]

In this paper, we develop a hyperspectral feature extraction method called sparse and smooth low-rank analysis (SSLRA). First, we propose a new low-rank model for hyperspectral images (HSIs) where we decompose the HSI into smooth and sparse components. Then, these components are simultaneously estimated using a nonconvex constrained penalized cost function (CPCF). The proposed CPCF exploits total variation penalty, ℓ 1 penalty, and an orthogonality constraint. The total variation penalty is used to promote piecewise smoothness, and, therefore, it extracts spatial (local neighborhood) information. The ℓ 1 penalty encourages sparse and spatial structures. Additionally, we show that this new type of decomposition improves the classification of the HSIs. In the experiments, SSLRA was applied on the Houston (urban) and the Trento (rural) datasets. The extracted features were used as an input into a classifier (either support vector machines (SVM) or random forest (RF)) to produce the final classification map. The results confirm improvement in classification accuracy compared to the state-of-the-art feature extraction approaches. [ABSTRACT FROM AUTHOR]

Rain type classification into convective and stratiform is an essential step required to improve quantitative precipitation estimations by remote sensing instruments. Previous studies with Micro Rain Radar (MRR) measurements and subjective rules have been performed to classify rain events. However, automating this process by using machine learning (ML) models provides the advantages of fast and reliable classification with the possibility to classify rain minute by minute. A total of 20,979 min of rain data measured by an MRR at Das in northeast Spain were used to build seven types of ML models for stratiform and convective rain type classification. The proposed classification models use a set of 22 parameters that summarize the reflectivity, the Doppler velocity, and the spectral width (SW) above and below the so-called separation level (SL). This level is defined as the level with the highest increase in Doppler velocity and corresponds with the bright band in stratiform rain. A pre-classification of the rain type for each minute based on the rain microstructure provided by the collocated disdrometer was performed. Our results indicate that complex ML models, particularly tree-based ensembles such as xgboost and random forest which capture the interactions of different features, perform better than simpler models. Applying methods from the field of interpretable ML, we identified reflectivity at the lowest layer and the average spectral width in the layers below SL as the most important features. High reflectivity and low SW values indicate a higher probability of convective rain. [ABSTRACT FROM AUTHOR]

Hyperspectral images often have hundreds of spectral bands of different wavelengths captured by aircraft or satellites that record land coverage. Identifying detailed classes of pixels becomes feasible due to the enhancement in spectral and spatial resolution of hyperspectral images. In this work, we propose a novel framework that utilizes both spatial and spectral information for classifying pixels in hyperspectral images. The method consists of three stages. In the first stage, the pre-processing stage, the Nested Sliding Window algorithm is used to reconstruct the original data by enhancing the consistency of neighboring pixels and then Principal Component Analysis is used to reduce the dimension of data. In the second stage, Support Vector Machines are trained to estimate the pixel-wise probability map of each class using the spectral information from the images. Finally, a smoothed total variation model is applied to ensure spatial connectivity in the classification map by smoothing the class probability tensor. We demonstrate the superiority of our method against three state-of-the-art algorithms on six benchmark hyperspectral datasets with 10 to 50 training labels for each class. The results show that our method gives the overall best performance in accuracy even with a very small set of labeled pixels. Especially, the gain in accuracy with respect to other state-of-the-art algorithms increases when the number of labeled pixels decreases, and, therefore, our method is more advantageous to be applied to problems with a small training set. Hence, it is of great practical significance since expert annotations are often expensive and difficult to collect. [ABSTRACT FROM AUTHOR]

A segmentation-based fully-polarimetric synthetic aperture radar (PolSAR) image classification method that incorporates texture features and color features is designed and implemented. This method is based on the framework that conjunctively uses statistical region merging (SRM) for segmentation and support vector machine (SVM) for classification. In the segmentation step, we propose an improved local binary pattern (LBP) operator named the regional homogeneity local binary pattern (RHLBP) to guarantee the regional homogeneity in PolSAR images. In the classification step, the color features extracted from false color images are applied to improve the classification accuracy. The RHLBP operator and color features can provide discriminative information to separate those pixels and regions with similar polarimetric features, which are from different classes. Extensive experimental comparison results with conventional methods on L-band PolSAR data demonstrate the effectiveness of our proposed method for PolSAR image classification. [ABSTRACT FROM AUTHOR]

Detailed, accurate and frequent land cover mapping is a prerequisite for several important geospatial applications and the fulfilment of current sustainable development goals. This paper introduces a methodology for the classification of annual high-resolution satellite data into several detailed land cover classes. In particular, a nomenclature with 27 different classes was introduced based on CORINE Land Cover (CLC) Level-3 categories and further analysing various crop types. Without employing cloud masks and/or interpolation procedures, we formed experimental datasets of Landsat-8 (L8) images with gradually increased cloud cover in order to assess the influence of cloud presence on the reference data and the resulting classification accuracy. The performance of shallow kernel-based and deep patch-based machine learning classification frameworks was evaluated. Quantitatively, the resulting overall accuracy rates differed within a range of less than 3%; however, maps produced based on Support Vector Machines (SVM) were more accurate across class boundaries and the respective framework was less computationally expensive compared to the applied patch-based deep Convolutional Neural Network (CNN). Further experimental results and analysis indicated that employing all multitemporal images with up to 30% cloud cover delivered relatively higher overall accuracy rates as well as the highest per-class accuracy rates. Moreover, by selecting 70% of the top-ranked features after applying a feature selection strategy, slightly higher accuracy rates were achieved. A detailed discussion of the quantitative and qualitative evaluation outcomes further elaborates on the performance of all considered classes and highlights different aspects of their spectral behaviour and separability. [ABSTRACT FROM AUTHOR]

Unmanned Aerial Vehicles (UAVs) are emerging and promising platforms for carrying different types of cameras for remote sensing. The application of multispectral vegetation indices for ground cover classification has been widely adopted and has proved its reliability. However, the fusion of spectral bands and vegetation indices for machine learning-based land surface investigation has hardly been studied. In this paper, we studied the fusion of spectral bands information from UAV multispectral images and derived vegetation indices for almond plantation classification using several machine learning methods. We acquired multispectral images over an almond plantation using a UAV. First, a multispectral orthoimage was generated from the acquired multispectral images using SfM (Structure from Motion) photogrammetry methods. Eleven types of vegetation indexes were proposed based on the multispectral orthoimage. Then, 593 data points that contained multispectral bands and vegetation indexes were randomly collected and prepared for this study. After comparing six machine learning algorithms (Support Vector Machine, K-Nearest Neighbor, Linear Discrimination Analysis, Decision Tree, Random Forest, and Gradient Boosting), we selected three (SVM, KNN, and LDA) to study the fusion of multi-spectral bands information and derived vegetation index for classification. With the vegetation indexes increased, the model classification accuracy of all three selected machine learning methods gradually increased, then dropped. Our results revealed that that: (1) spectral information from multispectral images can be used for machine learning-based ground classification, and among all methods, SVM had the best performance; (2) combination of multispectral bands and vegetation indexes can improve the classification accuracy comparing to only spectral bands among all three selected methods; (3) among all VIs, NDEGE, NDVIG, and NDVGE had consistent performance in improving classification accuracies, and others may reduce the accuracy. Machine learning methods (SVM, KNN, and LDA) can be used for classifying almond plantation using multispectral orthoimages, and fusion of multispectral bands with vegetation indexes can improve machine learning-based classification accuracy if the vegetation indexes are properly selected. [ABSTRACT FROM AUTHOR]

This study aimed at evaluating the synergistic use of Sentinel-1 and Sentinel-2 data combined with the Support Vector Machines (SVMs) machine learning classifier for mapping land use and land cover (LULC) with emphasis on wetlands. In this context, the added value of spectral information derived from the Principal Component Analysis (PCA), Minimum Noise Fraction (MNF) and Grey Level Co-occurrence Matrix (GLCM) to the classification accuracy was also evaluated. As a case study, the National Park of Koronia and Volvi Lakes (NPKV) located in Greece was selected. LULC accuracy assessment was based on the computation of the classification error statistics and kappa coefficient. Findings of our study exemplified the appropriateness of the spatial and spectral resolution of Sentinel data in obtaining a rapid and cost-effective LULC cartography, and for wetlands in particular. The most accurate classification results were obtained when the additional spectral information was included to assist the classification implementation, increasing overall accuracy from 90.83% to 93.85% and kappa from 0.894 to 0.928. A post-classification correction (PCC) using knowledge-based logic rules further improved the overall accuracy to 94.82% and kappa to 0.936. This study provides further supporting evidence on the suitability of the Sentinels 1 and 2 data for improving our ability to map a complex area containing wetland and non-wetland LULC classes. [ABSTRACT FROM AUTHOR]

Supervised classification systems used for land cover mapping require accurate reference databases. These reference data come generally from different sources such as field measurements, thematic maps, or aerial photographs. Due to misregistration, update delay, or land cover complexity, they may contain class label noise, i.e., a wrong label assignment. This study aims at evaluating the impact of mislabeled training data on classification performances for land cover mapping. Particularly, it addresses the random and systematic label noise problem for the classification of high resolution satellite image time series. Experiments are carried out on synthetic and real datasets with two traditional classifiers: Support Vector Machines (SVM) and Random Forests (RF). A synthetic dataset has been designed for this study, simulating vegetation profiles over one year. The real dataset is composed of Landsat-8 and SPOT-4 images acquired during one year in the south of France. The results show that both classifiers are little influenced for low random noise levels up to 25%-30%, but their performances drop down for higher noise levels. Different classification configurations are tested by increasing the number of classes, using different input feature vectors, and changing the number of training instances. Algorithm complexities are also analyzed. The RF classifier achieves high robustness to random and systematic label noise for all the tested configurations; whereas the SVM classifier is more sensitive to the kernel choice and to the input feature vectors. Finally, this work reveals that the cross-validation procedure is impacted by the presence of class label noise. [ABSTRACT FROM AUTHOR]

Accurate regional and global information on land cover and its changes over time is crucial for environmental monitoring, land management, and planning. In this study, we selected Fengning County, in China's Hebei Province, as a case study area. Using satellite data, we generated fused normalized-difference vegetation index (NDVI) data with high spatial and temporal resolution by utilizing the STARFM algorithm to produce a fused GF-1 and MODIS NDVI dataset. We extracted seven phenological parameters (including the start, end, and length of the growing season, base value, mid-season date, maximum NDVI, seasonal NDVI amplitude) from a fused NDVI time-series after reconstruction using the TIMESAT software. We developed four classification scenarios based on different combinations of GF-1 spectral features, the fused NDVI time-series, and the phenological parameters. We then classified the land cover using a support vector machine and analyzed the classification accuracies. We found that the proposed method achieved satisfactory classification results, and that the combination of the fused NDVI data with the extracted phenological parameters significantly improved classification accuracy. The classification accuracy based on the composited GF-1 multi-spectral bands combined with the phenological parameters was the highest among the four scenarios, with an overall classification accuracy of 88.8% and a Kappa coefficient of 0.8714, which represent increases of 9.3 percentage points and 0.1073, respectively, compared with GF-1 spectral data alone. The producer's and user's accuracy for different land cover types improved, with a few exceptions, and cropland and broadleaf forest had the largest increase. [ABSTRACT FROM AUTHOR]

Detailed land cover information is valuable for mapping complex urban environments. Recent enhancements to satellite sensor technology promise fit-for-purpose data, particularly when processed using contemporary classification approaches. We evaluate this promise by comparing the influence of spatial resolution, spectral band set and classification approach for mapping detailed urban land cover in Nottingham, UK. A WorldView-2 image provides the basis for a set of 12 images with varying spatial and spectral characteristics, and these are classified using three different approaches (maximum likelihood (ML), support vector machine (SVM) and object-based image analysis (OBIA)) to yield 36 output land cover maps. Classification accuracy is evaluated independently and McNemar tests are conducted between all paired outputs (630 pairs in total) to determine which classifications are significantly different. Overall accuracy varied between 35% for ML classification of 30 m spatial resolution, 4-band imagery and 91% for OBIA classification of 2 m spatial resolution, 8-band imagery. The results demonstrate that spatial resolution is clearly the most influential factor when mapping complex urban environments, and modern "very high resolution" or VHR sensors offer great advantage here. However, the advanced spectral capabilities provided by some recent sensors, coupled with contemporary classification approaches (especially SVMs and OBIA), can also lead to significant gains in mapping accuracy. Ongoing development in instrumentation and methodology offer huge potential here and imply that urban mapping opportunities will continue to grow. [ABSTRACT FROM AUTHOR]

The optimal parameters of polarimetric scattering decomposition are critical to classify the pixels in polarimetric synthetic aperture radar (PolSAR) images by utilizing the method of machine learning. Therefore, span-based mutual information (Sp-MI) is proposed to lighten the dependence on labeling information, and then a heuristic representative learning scheme is also given by artificial neural network (ANN) to classify parameters separately with the increasing sequence according to the values of Sp-MI. Furthermore, an innovative method of using the sine function is presented to map the parameters of angular, and a min-max scaling method is applied to complete the procedure of normalization. Except for the support vector machine, three ANN-based classifiers are implemented to verify the rationality and effectiveness of the proposed representative learning and normalization scheme. Meanwhile, the classification method is compared with four similar comparison methods on three real PolSAR images. Finally, the classification results show the effectiveness of the proposed Sp-MI and the validation of the representative learning scheme in the aspect of classification overall accuracy and visual effect. [ABSTRACT FROM AUTHOR]

Remote sensing techniques, developed over the past four decades, have enabled large-scale forest inventory. Light Detection and Ranging (LiDAR), as an active remote sensing technology, allows for the acquisition of three-dimensional point clouds of scanned areas, as well as a range of features allowing for increased performance of object extraction and classification approaches. As many publications have shown, multiple LiDAR-derived metrics, with the assistance of classification algorithms, contribute to the high accuracy of tree species discrimination based on data obtained by laser scanning. The aim of this article is to review studies in the species classification literature which used data collected by Airborne Laser Scanning. We analyzed these studies to figure out the most efficient group of LiDAR-derived features in species discrimination. We also identified the most powerful classification algorithm, which maximizes the advantages of the derived metrics to increase species discrimination performance. We conclude that features extracted from full-waveform data lead to the highest overall accuracy. Radiometric features with height information are also promising, generating high species classification accuracies. Using random forest and support vector machine as classifiers gave the best species discrimination results in the reviewed publications. [ABSTRACT FROM AUTHOR]

Hyperspectral image processing techniques, with their ability to provide information about the chemical compositions of materials, have great potential for pavement condition assessment. This study introduces a novel age-based pavement assessment method, employing an integrated algorithm with artificial neural network (ANN) and spectral angle mapping (SAM) on hyperspectral images. In the proposed method, the resulting ANN prediction outputs are used to make a new prediction along with the results from SAM scores. Tests are performed on hyperspectral images that have 360 spectral bands between 400 and 900 nm, collected by a specifically designed vehicular system for proximal image acquisition. The acquired images have eight classes, including three different pavement classes (good (5-year), medium (10-year), and poor (25-year)), yellow dye, white dye, soil, paving stone, and shadow. Several experiments are performed to evaluate the robustness of the followed methodology with limited learning data that include 5, 10, 25, and 50 samples per class, selected randomly from our independent spectral database. For a fair comparison, the individual ANN, SAM, support vector machine (SVM), and stacked auto-encoders (SAE) algorithms are also evaluated. The classification performances of individual ANN and SAM are significantly increased with their joint use, demonstrating a 1.2% to 21% classification accuracy improvement in relation to the training sample size. The study proves that the proposed approach is quite robust in cases wherein few training data are available, while SAE and standard ANN algorithms are more successful in cases wherein more learning data are present. [ABSTRACT FROM AUTHOR]

Southern Corn Rust (SCR) is one of the most destructive diseases in corn production, significantly affecting corn quality and yields globally. Field-based fast, nondestructive diagnosis of SCR is critical for smart agriculture applications to reduce pesticide use and ensure food safety. The development of spectral disease indices (SDIs), based on in situ leaf reflectance spectra, has proven to be an effective method in detecting plant diseases in the field. However, little is known about leaf spectral signatures that can assist in the accurate diagnosis of SCR, and no SDIs-based model has been reported for the field-based SCR monitoring. Here, to address those issues, we developed SDIs-based monitoring models to detect SCR-infected leaves and classify SCR damage severity. In detail, we first collected in situ leaf reflectance spectra (350–2500 nm) of healthy and infected corn plants with three severity levels (light, medium, and severe) using a portable spectrometer. Then, the RELIEF-F algorithm was performed to select the most discriminative features (wavelengths) and two band normalized differences for developing SDIs (i.e., health index and severity index) in SCR detection and severity classification, respectively. The leaf reflectance spectra, most sensitive to SCR detection and severity classification, were found in the 572 nm, 766 nm, and 1445 nm wavelength and 575 nm, 640 nm, and 1670 nm wavelength, respectively. These spectral features were associated with leaf pigment and leaf water content. Finally, by employing a support vector machine (SVM), the performances of developed SCR-SDIs were assessed and compared with 38 stress-related vegetation indices (VIs) identified in the literature. The SDIs-based models developed in this study achieved an overall accuracy of 87% and 70% in SCR detection and severity classification, 1.1% and 8.3% higher than the other best VIs-based model under study, respectively. Our results thus suggest that the SCR-SDIs is a promising tool for fast, nondestructive diagnosis of SCR in the field over large areas. To our knowledge, this study represents one of the first few efforts to provide a theoretical basis for remote sensing of SCR at field and larger scales. With the increasing use of unmanned aerial vehicles (UAVs) with hyperspectral measurement capability, more studies should be conducted to expand our developed SCR-SDIs for SCR monitoring at different study sites and growing stages in the future. [ABSTRACT FROM AUTHOR]

The purpose of this work is to perform the joint design of a classification system including both a radar sensor and an image processing software. Experimental data were generated with a three-dimensional scanner. The criterion which rules the design is the false recognition rate, which should be as small as possible. The classifier involved is support vector machines, combined with an error correcting code. We apply the proposed method to optimize security check. For this purpose we retain eight relevant parameters which impact the recognition performances. To estimate the best parameters, we adapt our adaptive mixed grey wolf algorithm. This is a computational technique inspired by nature to minimize a criterion. Our adaptive mixed grey wolf algorithmwas found to outperform comparative methods in terms of computational load on simulations and with real-world data. [ABSTRACT FROM AUTHOR]

Foam is often present in satellite images of coastal areas and can lead to serious errors in the detection of shorelines especially when processing high spatial resolution images (<20 m). This study focuses on shoreline extraction and shoreline evolution using high spatial resolution satellite images in the presence of foam. A multispectral supervised classification technique is selected, namely the Support Vector Machine (SVM) and applied with three classes which are land, foam and water. The merging of water and foam classes followed by a segmentation procedure enables the separation of land and ocean pixels. The performance of the method is evaluated using a validation dataset acquired on two study areas (south and north of the bay of Sendaï—Japan). On each site, WorldView-2 multispectral images (eight bands, 2 m resolution) were acquired before and after the Fukushima tsunami generated by the Tohoku earthquake in 2011. The consideration of the foam class enables the false negative error to be reduced by a factor of three. The SVM method is also compared with four other classification methods, namely Euclidian Distance, Spectral Angle Mapper, Maximum Likelihood, and Neuronal Network. The SVM method appears to be the most efficient to determine the erosion and the accretion resulting from the tsunami, which are societal issues for littoral management purposes. [ABSTRACT FROM AUTHOR]

This research investigated the performance of four different machine learning supervised image classifiers: artificial neural network (ANN), decision tree (DT), random forest (RF), and support vector machine (SVM) using SPOT-7 and Sentinel-1 images to classify mangrove age and species in 2019 in a Red River estuary, typical of others found in northern Viet Nam. The four classifiers were chosen because they are considered to have high accuracy, however, their use in mangrove age and species classifications has thus far been limited. A time-series of Landsat images from 1975 to 2019 was used to map mangrove extent changes using the unsupervised classification method of iterative self-organizing data analysis technique (ISODATA) and a comparison with accuracy of K-means classification, which found that mangrove extent has increased, despite a fall in the 1980s, indicating the success of mangrove plantation and forest protection efforts by local people in the study area. To evaluate the supervised image classifiers, 183 in situ training plots were assessed, 70% of them were used to train the supervised algorithms, with 30% of them employed to validate the results. In order to improve mangrove species separations, Gram–Schmidt and principal component analysis image fusion techniques were applied to generate better quality images. All supervised and unsupervised (2019) results of mangrove age, species, and extent were mapped and accuracy was evaluated. Confusion matrices were calculated showing that the classified layers agreed with the ground-truth data where most producer and user accuracies were greater than 80%. The overall accuracy and Kappa coefficients (around 0.9) indicated that the image classifications were very good. The test showed that SVM was the most accurate, followed by DT, ANN, and RF in this case study. The changes in mangrove extent identified in this study and the methods tested for using remotely sensed data will be valuable to monitoring and evaluation assessments of mangrove plantation projects. [ABSTRACT FROM AUTHOR]

The advancement in satellite remote sensing technology has revolutionised the approaches to monitoring the Earth's surface. The development of the Copernicus Programme by the European Space Agency (ESA) and the European Union (EU) has contributed to the effective monitoring of the Earth's surface by producing the Sentinel-2 multispectral products. Sentinel-2 satellites are the second constellation of the ESA Sentinel missions and carry onboard multispectral scanners. The primary objective of the Sentinel-2 mission is to provide high resolution satellite data for land cover/use monitoring, climate change and disaster monitoring, as well as complementing the other satellite missions such as Landsat. Since the launch of Sentinel-2 multispectral instruments in 2015, there have been many studies on land cover/use classification which use Sentinel-2 images. However, no review studies have been dedicated to the application of ESA Sentinel-2 land cover/use monitoring. Therefore, this review focuses on two aspects: (1) assessing the contribution of ESA Sentinel-2 to land cover/use classification, and (2) exploring the performance of Sentinel-2 data in different applications (e.g., forest, urban area and natural hazard monitoring). The present review shows that Sentinel-2 has a positive impact on land cover/use monitoring, specifically in monitoring of crop, forests, urban areas, and water resources. The contemporary high adoption and application of Sentinel-2 can be attributed to the higher spatial resolution (10 m) than other medium spatial resolution images, the high temporal resolution of 5 days and the availability of the red-edge bands with multiple applications. The ability to integrate Sentinel-2 data with other remotely sensed data, as part of data analysis, improves the overall accuracy (OA) when working with Sentinel-2 images. The free access policy drives the increasing use of Sentinel-2 data, especially in developing countries where financial resources for the acquisition of remotely sensed data are limited. The literature also shows that the use of Sentinel-2 data produces high accuracies (>80%) with machine-learning classifiers such as support vector machine (SVM) and Random forest (RF). However, other classifiers such as maximum likelihood analysis are also common. Although Sentinel-2 offers many opportunities for land cover/use classification, there are challenges which include mismatching with Landsat OLI-8 data, a lack of thermal bands, and the differences in spatial resolution among the bands of Sentinel-2. Sentinel-2 data show promise and have the potential to contribute significantly towards land cover/use monitoring. [ABSTRACT FROM AUTHOR]

To investigate the performance of extreme gradient boosting (XGBoost) in remote sensing image classification tasks, XGBoost was first introduced and comparatively investigated for the spectral-spatial classification of hyperspectral imagery using the extended maximally stable extreme-region-guided morphological profiles (EMSER_MPs) proposed in this study. To overcome the potential issues of XGBoost, meta-XGBoost was proposed as an ensemble XGBoost method with classification and regression tree (CART), dropout-introduced multiple additive regression tree (DART), elastic net regression and parallel coordinate descent-based linear regression (linear) and random forest (RaF) boosters. Moreover, to evaluate the performance of the introduced XGBoost approach with different boosters, meta-XGBoost and EMSER_MPs, well-known and widely accepted classifiers, including support vector machine (SVM), bagging, adaptive boosting (AdaBoost), multi class AdaBoost (MultiBoost), extremely randomized decision trees (ExtraTrees), RaF, classification via random forest regression (CVRFR) and ensemble of nested dichotomies with extremely randomized decision tree (END-ERDT) methods, were considered in terms of the classification accuracy and computational efficiency. The experimental results based on two benchmark hyperspectral data sets confirm the superior performance of EMSER_MPs and EMSER_MPs with mean pixel values within region (EMSER_MPsM) compared to that for morphological profiles (MPs), morphological profile with partial reconstruction (MPPR), extended MPs (EMPs), extended MPPR (EMPPR), maximally stable extreme-region-guided morphological profiles (MSER_MPs) and MSER_MPs with mean pixel values within region (MSER_MPsM) features. The proposed meta-XGBoost algorithm is capable of obtaining better results than XGBoost with the CART, DART, linear and RaF boosters, and it could be an alternative to the other considered classifiers in terms of the classification of hyperspectral images using advanced spectral-spatial features, especially from generalized classification accuracy and model training efficiency perspectives. [ABSTRACT FROM AUTHOR]