Search

Greenhouse gas (GHG) emissions datasets are often incomplete due to inconsistent reporting and poor transparency. Filling the gaps in these datasets allows for more accurate targeting of strategies aiming to accelerate the reduction of GHG emissions. This study evaluates the potential of machine learning methods to automate the completion of GHG datasets. We use three datasets of increasing complexity with 18 different gap‐filling methods and provide a guide to which methods are useful in which circumstances. If few dataset features are available, or the gap consists only of a missing time step in a record, then simple interpolation is often the most accurate method and complex models should be avoided. However, if more features are available and the gap involves non‐reporting emitters, then machine learning methods can be more accurate than simple extrapolation. Furthermore, the secondary output of feature importance from complex models allows for data collection prioritization to accelerate the improvement of datasets. Graph‐based methods are particularly scalable due to the ease of updating predictions given new data and incorporating multimodal data sources. This study can serve as a guide to the community upon which to base ever more integrated frameworks for automated detailed GHG emissions estimations, and implementation guidance is available at https://hackmd.io/@luke‐scot/ML‐for‐GHG‐database‐completion and https://doi.org/10.5281/zenodo.10463104. This article met the requirements for a gold‐gold JIE data openness badge described at http://jie.click/badges. [ABSTRACT FROM AUTHOR]

In this work, the development and application of advanced predictive 0D/1D methodologies to simulate Real Driving Emission (RDE) cycles are described. Firstly, the 1D simulation model is validated on a map of steady state operating points, which allows to use successively the very same model, with its calibration, during an RDE cycle simulation, considering the sequence of varying loads, and rotational speeds. In particular, the validated 1D model is used to simulate a typical RDE transient cycle of approximately 1 h and 45 min. The test case investigated is a modern plug-in hybrid passenger car engine, in which the thermal power unit consists of a 1 L three-cylinder, turbocharged gasoline engine. The experimental and simulated RDE cycle is characterized by a sensibly varying Internal Combustion Engine (ICE) operation, allowing to evaluate engine performance and cylinder out emissions. To speed up the calculation and significantly lower the Central Processing Unit (CPU)/real time ratio a dedicated numerical solver for fast simulation has been implemented and tested, while keeping the fidelity of the results. A predictive 0D, multi-zone model for Spark Ignition (SI) combustion has been applied, together with emission sub-models for the calculation of the main pollutants. Both instantaneous and cumulative emissions have been evaluated. The results of the simulations have been compared to the experimental data of RDE cycles, showing a good predictiveness of the models and the high potential of 0D/1D simulation codes as design tools, in the new scenario of demanding testing procedures. This approach can be applied for any engine configuration operating under any transient condition. [ABSTRACT FROM AUTHOR]

This work is focused on the simulation of a complete hybrid bus vehicle model performing a real-world driving cycle. The simulation framework consists of a coupled co-simulation environment, where all the vehicle sub-system models are linked to achieve a real time exchange of input and output signals. In the vehicle model also the electric devices of the powertrain and accumulation system are included. This co-simulation platform is applied to investigate the hybridization of a 12-m city bus, performing a typical urban driving mission. A comparison between the conventional powertrain is performed against the hybridized version, to highlight the advantages and challenges. In particular, the novelty of this modeling approach is that the IC engine simulation does not rely on pre-processed look-up tables, but exploits a high-fidelity one-dimensional thermo-fluid dynamic model. However, it was necessary to develop a fast simulation methodology to exploit this predictive tool, achieving a low computational cost. The 1D engine model is first validated against the experimental engine map data available, showing a good model predictivity. Then the 1D engine model and the other models of the powertrain are coupled to the vehicle model, in order to follow the prescribed velocity profile of the driving cycle. The complete model is applied under different conditions, to evaluate the impact on performance and emissions and assess the simulation predictivity. [ABSTRACT FROM AUTHOR]

The most common source of information about sea ice conditions is remote sensing data, especially images obtained from synthetic aperture radar (SAR) and passive microwave radiometers (PMR). Here we introduce an adaptive fusion scheme based on Graph Laplacians that allows us to retrieve the most relevant information from satellite images. In a first test case, we explore the potential of sea ice classification employing SAR and PMR separately and simultaneously, in order to evaluate the complementarity of both sensors and to assess the result of a combined use. Our test case illustrates the flexibility and efficiency of the proposed scheme and indicates an advantage of combining AMSR‐2 89 GHz and Sentinel‐1 data for sea ice mapping. Plain Language Summary: The Earth's land and ocean surface is monitored from space using different sensors mounted on various satellite platforms. Each type of sensor has its advantages and limitations. Combining data from different sensors can potentially solve ambiguities in information retrievals associated with the use of only a single sensor. Here, we apply a multi‐sensor fusion scheme that can be used for various data combinations in order to extract relevant information. The main goal of this work is to explore the potential of simultaneously applying two sensors for sea ice mapping and monitoring, namely synthetic aperture radar and passive microwave radiometers, in order to improve the separation of sea ice types. Key Points: We propose an adaptive scheme for the fusion of passive microwave radiometers and synthetic aperture radar data for sea ice classificationWe demonstrate the flexibility and efficiency of the proposed scheme on a test case by evaluating the performance of various data scenariosWe illustrate the advantages and limitations of applying the data of each sensor simultaneously and separately [ABSTRACT FROM AUTHOR]

Urban green space (UGS) is an important component in the urban ecosystem and has great significance to the urban ecological environment. Although the development of remote sensing platforms and deep learning technologies have provided opportunities for UGS mapping from high-resolution images (HRIs), challenges still exist in its large-scale and fine-grained application due to insufficient annotated datasets and specially designed methods for UGS. Moreover, the domain shift between images from different regions is also a problem that must be solved. To address these issues, a general deep learning (DL) framework is proposed for UGS mapping in the large scale, and fine-grained UGS maps of 31 major cities in mainland China are generated (UGS-1m). The DL framework consists of a generator and a discriminator. The generator is a fully convolutional network designed for UGS extraction (UGSNet), which integrates attention mechanisms to improve the discrimination to UGS, and employs a point-rending strategy for edge recovery. The discriminator is a fully connected network aiming to deal with the domain shift between images. To support the model training, an urban green space dataset (UGSet) with a total number of 4544 samples of 512×512 in size is provided. The main steps to obtain UGS-1m can be summarized as follows: (a) first, the UGSNet will be pre-trained on the UGSet in order to obtain a good starting training point for the generator. (b) After pre-training on the UGSet, the discriminator is responsible for adapting the pre-trained UGSNet to different cities through adversarial training. (c) Finally, the UGS results of 31 major cities in China (UGS-1m) are obtained using 2179 Google Earth images with a data frame of 7 ′ 30 ′′ in longitude and 5 ′ 00 ′′ in latitude and a spatial resolution of nearly 1.1 m. An evaluation of the performance of the proposed framework by samples from five different cities shows the validity of the UGS-1m products, with an average overall accuracy (OA) of 87.56 % and an F1 score of 74.86 %. Comparative experiments on UGSet with the existing state-of-the-art (SOTA) DL models proves the effectiveness of UGSNet as the generator, with the highest F1 score of 77.30 %. Furthermore, an ablation study on the discriminator fully reveals the necessity and effectiveness of introducing the discriminator into adversarial learning for domain adaptation. Finally, a comparison with existing products further shows the feasibility of the UGS-1m and the great potential of the proposed DL framework. The UGS-1m can be downloaded from 10.57760/sciencedb.07049. [ABSTRACT FROM AUTHOR]

Urban green space (UGS) is an important component in the urban ecosystem and has great significance to the urban ecological environment. Although the development of remote sensing platforms and deep learning technologies have provided opportunities for UGS mapping from high-resolution images (HRIs), challenges still exist in its large-scale and fine-grained application, due to insufficient annotated datasets and specially designed methods for UGS. Moreover, the domain shift between images from different regions is also a problem that must be solved. To address these issues, a general deep learning (DL) framework is proposed for UGS mapping in the large scale, and the fine-grained UGS maps of 34 major cities/areas in China are generated (UGS-1m). The DL framework consists of a generator and a discriminator. The generator is a fully convolutional network designed for UGS extraction (UGSNet), which integrates attention mechanisms to improve the discrimination to UGS, and employs a point rending strategy for edge recovery. The discriminator is a fully connected network aiming to deal with the domain shift between images. To support the model training, an urban green space dataset (UGSet) with a total number of 4,454 samples of size 512×512 is provided. The main steps to obtain UGS-1m can be summarized as follows: a) Firstly, the UGSNet will be pre-trained on the UGSet in order to get a good starting training point for the generator; b) After pre-training on the UGSet, the discriminator is responsible to adapt the pre-trained UGSNet to different cities/areas through adversarial training; c) Finally, the UGS results of the 34 major cities/areas in China (UGS-1m) are obtained using 2,343 Google Earth images with a data frame of 7'30" in longitude and 5'00" in latitude, and a spatial resolution of nearly 1.1 meters. Evaluating the performance of the proposed approach on samples from Guangzhou city shows the validity of the UGS-1m products, with an overall accuracy of 87.4% and an F1 score of 81.14%. Furthermore, experiments on UGSet with the existing state-of-the-art (SOTA) DL models proves the effectiveness of UGSNet, with the highest F1 of 77.30%. Finally, the comparisons with existing products further shows the feasibility of the UGS-1m and the effectiveness and great potential of the proposed DL framework. The UGS-1m can be downloaded from https://doi.org/10.5281/zenodo.6155516 (Shi et al., 2022). [ABSTRACT FROM AUTHOR]

Change detection (CD) aims to distinguish surface changes based on bitemporal images. Since high-resolution (HR) images cannot be typically acquired continuously over time, bitemporal images with different resolutions are often adopted for CD in practical applications. Traditional subpixel-based methods for CD using images with different resolutions may lead to substantial error accumulation when the HR images are employed, which is because of intraclass heterogeneity and interclass similarity. Therefore, it is necessary to develop a novel method for CD using images with different resolutions that are more suitable for the HR images. To this end, we propose a super-resolution-based change detection network (SRCDNet) with a stacked attention module (SAM). The SRCDNet employs a super-resolution (SR) module containing a generator and a discriminator to directly learn the SR images through adversarial learning and overcome the resolution difference between the bitemporal images. To enhance the useful information in multiscale features, a SAM consisting of five convolutional block attention modules (CBAMs) is integrated to the feature extractor. The final change map is obtained through a metric learning-based change decision module, wherein a distance map between bitemporal features is calculated. Ablation study and comparative experiments on two large datasets, building change detection dataset (BCDD) and season-varying change detection dataset (CDD), and a real-image experiment on the Google dataset fully demonstrate the superiority of the proposed method. The source code of SRCDNet is available at https://github.com/liumency/SRCDNet. [ABSTRACT FROM AUTHOR]

The prediction of internal combustion engine performance and emissions in real driving conditions is getting more and more important due to the upcoming stricter regulations. This work aims at introducing and validating a new transient simulation methodology of an ICE coupled to a hybrid architecture vehicle, getting closer to real-time calculations. A one-dimensional computational fluid dynamic software has been used and suitably coupled to a vehicle dynamics model in a user function framework integrated within a Simulink® environment. A six-cylinder diesel engine has been modeled by means of the 1D tool and cylinder-out emissions have been compared to experimental data. The measurements available have been used also to calibrate the combustion model. The developed 1D engine model has been then used to perform driving cycle simulations considering the vehicle dynamics and the coupling with the energy storage unit in the hybrid mode. The map-based approach along with the vehicle simulation tool has also been used to perform the same simulation and the two results are compared to evaluate the accuracy of each approach. In this framework, to achieve the best simulation performance in terms of computational time over simulated time ratio, the 1D engine model has been used in a configuration with a very coarse mesh. Results have shown that despite the high mesh spacing used the accuracy of the wave dynamics prediction was not affected in a significant way, whereas a remarkable speed-up factor was achieved. This means that a crank angle resolution approach to the vehicle simulation is a viable and accurate strategy to predict the engine emission during any driving cycle with a computation effort compatible with the tight schedule of a design process. [ABSTRACT FROM AUTHOR]

Although multimodal remote sensing data analysis can strongly improve the characterization of physical phenomena on Earth’s surface, nonidealities and estimation imperfections between records and investigation models can limit its actual information extraction ability. In this article, we aim at predicting the maximum information extraction that can be reached when analyzing a given data set. By means of an asymptotic information theory-based approach, we investigate the reliability and accuracy that can be achieved under optimal conditions for multimodal analysis as a function of data statistics and parameters that characterize the multimodal scenario to be addressed. Our approach leads to the definition of two indices that can be easily computed before the actual processing takes place. Moreover, we report in this article how they can be used for operational use in terms of image selection in order to maximize the robustness of the multimodal analysis, as well as to properly design data collection campaigns for understanding and quantifying physical phenomena. Experimental results show the consistency of our approach. [ABSTRACT FROM AUTHOR]

This article examines advances in interferometric synthetic aperture radar (InSAR) satellite measurement technologies to understand their relevance, utilization, and limitations for bridge monitoring. Waterloo Bridge is presented as a case study to explore how InSAR data sets can be combined with traditional measurement techniques including sensors installed on the bridge and automated total stations. A novel approach to InSAR bridge monitoring was adopted by the installation of physical reflectors at key points of structural interest on the bridge, in order to supplement the bridge’s own reflection characteristics and ensure that the InSAR measurements could be directly compared and combined with in situ measurements. The interpretation and integration of InSAR data sets with civil infrastructure data are more than a trivial task, and a discussion of uncertainty of measurement data is presented. Finally, a strategy for combining and interpreting varied data from multiple sources to provide useful insights into each of these methods is presented, outlining the practical applications of this data analysis to support wider monitoring strategies. [ABSTRACT FROM AUTHOR]

This article introduces the Rayleigh autoregressive moving average (RARMA) model, which is useful to interpret multiple different sets of remotely sensed data, from wind measurements to multitemporal synthetic aperture radar (SAR) sequences. The RARMA model is indeed suitable for continuous, asymmetric, and nonnegative signals observed over time. It describes the mean of Rayleigh-distributed discrete-time signals by a dynamic structure including autoregressive (AR) and moving average (MA) terms, a set of regressors, and a link function. After presenting the conditional likelihood inference for the model parameters and the detection theory, in this article, a Monte Carlo simulation is performed to evaluate the finite signal length performance of the conditional likelihood inferences. Finally, the new model is applied first to sequences of wind speed measurements, and then to a multitemporal SAR image stack for land-use classification purposes. The results in these two test cases illustrate the usefulness of this novel dynamic model for remote sensing data interpretation. [ABSTRACT FROM AUTHOR]

Nonlinear unmixing algorithms are playing a key role in modern earth observation analysis thanks to their ability to characterize complex phenomena occurring in the instantaneous field of view. When unmixing hyperspectral images according to nonlinear mixture models by means of state-of-the-art methods, actual abundances of the elements in the scene can be only indirectly estimated. Thus, the reliability of the investigation can be dramatically jeopardized, hence degrading the accuracy of the characterization of the surface composition. In order to overcome this issue, we propose in this paper a nonlinear programming scheme that aims at providing direct estimation of the end members fractions. The method we introduce is based on a structural optimization approach where the abundances are directly assessed, so that no epistemic uncertainties are injected in the framework. Experimental results show that the proposed method is able to deliver accurate and reliable estimates of these quantities in hyperspectral images. [ABSTRACT FROM AUTHOR]

The imbalance between the (often limited) number of available training samples and the high data dimensionality, together with the presence of mixed pixels, often complicates the classification of remotely sensed hyperspectral data. In this paper, we tackle these problems by developing a new method that combines spectral unmixing and classification techniques in a subspace-based approach. The proposed method is developed under the assumption that the spectral signature of a land cover class is associated with a given set of pure spectral signatures (called endmembers in spectral unmixing terminology), which define a low-dimensional subspace with clear physical meaning. We aim to exploit this relationship to learn the class-dependent subspaces and integrate them with a multinomial logistic regression procedure. Experiments on synthetic datasets and real hyperspectral images show that our method is able to obtain competitive performances in comparison with other approaches, particularly when very limited training sets are available. [ABSTRACT FROM AUTHOR]

Spectral unmixing (SU) is a useful tool for hyperspectral remote sensing image analysis. However, due to the interference of spectral variance and non‐linearity caused by photon multiple‐scattering, the result might be an inaccuracy. In addition, the unmixing performance of typically relies on the prior knowledge of endmembers. Although many classical endmember extraction algorithms have been presented, it is hard to obtain accurate endmembers in practical applications. This study presents a bilinear normal mixing model named as BNMM to tackle these issues. In fact, BNMM employs the polynomial post‐non‐linear mixing model to alleviate the effect of non‐linearity and uses a normal distribution model to reduce the influence of endmembers variability. Based on the BNMM, the authors develop a Hamiltonian Monte Carlo algorithm for SU. The experimental results demonstrate that the proposed algorithm outperforms other classical unmixing algorithms in the case of simulated and benchmark datasets. [ABSTRACT FROM AUTHOR]

Accurately estimating the elements in Earth observations is crucial when assessing specific features such as air quality index, water pollution, or urbanization process behavior. Moreover, physical–chemical composition can be retrieved from hyperspectral images when proper spectral unmixing architectures are employed. Specifically, when linear and nonlinear combinations of endmembers (pure spectral components) are accurately characterized, hyperspectral unmixing plays a key role in understanding and quantifying phenomena occurring over the instantaneous field-of-view. Thus, reliable detection of nonlinear reflectance behavior can play a key role in enhancing hyperspectral unmixing performance. In this paper, two new methods for adaptive design of mixture models for hyperspectral unmixing are introduced. One of the methods relies on exploiting geometrical features of hyperspectral signatures in terms of nonorthogonal projections onto the space induced by the endmembers’ spectra. Then, an iterative process aims at understanding the order of local nonlinearity that is displayed by each endmember over every pixel. An improved version of an artificial neural network-based approach for nonlinearity order information is also considered and compared. Experimental results show that the proposed approaches are actually able to retrieve thorough information on the nature of the nonlinear effects over the image, while providing excellent performance in reconstructing the given data sets. [ABSTRACT FROM AUTHOR]

In this letter, a new method for higher order nonlinear hyperspectral unmixing is introduced. The proposed scheme relies on the harmonic description of the endmembers contributions to characterize the interactions among the materials showing up in the given scenes. Moreover, it aims at directly estimating the probability of occurrence of each material in the images, so to provide an accurate quantification of the endmembers also in complex scenarios. Experimental results carried out on synthetic and real data sets show that the proposed method is able to obtain good unmixing performance when compared to other state-of-the-art architectures. [ABSTRACT FROM AUTHOR]

As an unsupervised learning tool, autoencoder has been widely applied in many fields. In this letter, we propose a new robust unmixing algorithm that is based on stacked nonnegative sparse autoencoders (NNSAEs) for hyperspectral data with outliers and low signal-to-noise ratio. The proposed stacked autoencoders network contains two main steps. In the first step, a series of NNSAE is used to detect the outliers in the data. In the second step, a final autoencoder is performed for unmixing to achieve the endmember signatures and abundance fractions. By taking advantage from nonnegative sparse autoencoding, the proposed approach can well tackle problems with outliers and low noise-signal ratio. The effectiveness of the proposed method is evaluated on both synthetic and real hyperspectral data. In comparison with other unmixing methods, the proposed approach demonstrates competitive performance. [ABSTRACT FROM AUTHOR]

To efficiently model high-order nonlinear material mixtures in complex scenery, more and more complex spectral mixing models have been developed, so that over-fitting phenomena more often occur during the unmixing process. Therefore, the accurate and robust inversion of material abundances is a challenging task, especially for low signal-to-noise ratio (SNR) data. In this paper, this task is achieved by inverting the parameters using a hierarchical Bayesian model based on the P-linear mixing model (PLMM). Moreover, spatial information is integrated in the inversion process by considering that similar pixels share the same prior information. Thanks to the fact that PLMM can be translated into a linear model using endmembers and their powers, unmixing is performed by solving a convex optimization problem. Results obtained from synthetic and real data show that the proposed algorithm improves the accuracy of abundance estimation and efficiently reduces over-fitting effects in low SNR data. [ABSTRACT FROM PUBLISHER]

Information theory has recently become an interesting topic in earth observation data management and analysis, since it can provide important information on hidden interactions and correlations among the considered data records. Although several methods have been proposed and implemented to efficiently extract a proper set of features and deliver accurate image investigation, classification, and segmentation, these architectures show drawbacks when the data sets are characterized by complex interactions among the samples. In this paper, a new approach based on information theory for automatic pattern recognition is introduced for accurate classification of remotely sensed data. Experimental results carried out on real data sets show the validity of the proposed approach. [ABSTRACT FROM PUBLISHER]

In order to provide reliable information about the instantaneous field of view considered in hyperspectral images through spectral unmixing, understanding the kind of mixture that occurs over each pixel plays a crucial role. In this paper, in order to detect nonlinear mixtures, a method for fast identification of linear mixtures is introduced. The proposed method does not need statistical information and performs an a priori test on the spectral linearity of each pixel. It uses standard least squares optimization to achieve estimates of the likelihood of occurrence of linear combinations of endmembers by taking advantage of the geometrical properties of hyperspectral signatures. Experimental results on both real and synthetic data sets show that the aforesaid algorithm is actually able to deliver a reliable and thorough assessment of the kind of mixtures present in the pixels of the scene. [ABSTRACT FROM PUBLISHER]

Algorithms allowing the deconvolution of hyperspectral data play a key-role in remotely sensed data processing for mineralogical investigation. Modified Gaussian model (MGM) based methods are of particular interest because they are able to retrieve accurate estimates of minerals abundances and chemistry in surface's rocks. However, MGM-based frameworks deliver high computational complexity and sensitivity to initial parameters for statistical distribution definition. In this paper, a new approach for efficient and robust mineralogical investigation over extraterrestrial bodies is introduced. The proposed framework takes advantage of the solid characterization of remote sensing hyperspectral images by unmixing higher order nonlinear combinations of reflectance features associated with mafic minerals. Experimental results achieved over Mars and Moon hyperspectral images show that the proposed scheme is able to retrieve magmatic mineral abundance maps that are highly correlated to those achieved by means of MGM-based scheme while overcoming the aforesaid issues. Finally, an empirical study allowing to distinguish between clino- and orthopyroxenes by properly processing the outcomes of nonlinear hyperspectral unmixing method is reported. [ABSTRACT FROM PUBLISHER]

Spectral unmixing is an important technique for exploiting hyperspectral data. The presence of nonlinear mixing effects poses an important problem when attempting to provide accurate estimates of the abundance fractions of pure spectral components (endmembers) in a scene. This problem complicates the development of algorithms that can address all types of nonlinear mixtures in the scene. In this paper, we develop a new strategy to simultaneously estimate both the endmember signatures and their corresponding abundances using a biswarm particle swarm optimization (BiPSO) bilinear unmixing technique based on Fan's model. Our main motivation in this paper is to explore the potential of the newly proposed bilinear mixture model based on particle swarm optimization (PSO) for nonlinear spectral unmixing purposes. By taking advantage of the learning mechanism provided by PSO, we embed a multiobjective optimization technique into the algorithm to handle the more complex constraints in simplex volume minimization algorithms for spectral unmixing, thus avoiding limitations due to penalty factors. Our experimental results, conducted using both synthetic and real hyperspectral data, demonstrate that the proposed BiPSO algorithm can outperform other traditional spectral unmixing techniques by accounting for nonlinearities in the mixtures present in the scene. [ABSTRACT FROM PUBLISHER]

Higher order nonlinear material mixtures provide a good model to explain the effects of physical–chemical phenomena on hyperspectral remote sensing measurements. Therefore, inverting nonlinear effects starting from the measured spectral values is a very challenging yet fundamental task to provide a thorough and reliable characterization of the materials in a scene. In this paper, this task is achieved by inverting a new model for nonlinear hyperspectral mixtures. Specifically, we show that it is possible to effectively unmix hyperspectral data by assuming a harmonic description of the higher order nonlinear combination of the endmembers. The rationale for this model is that the harmonic analysis is able to understand and quantify effects that cannot be effectively described by classic polynomial combinations. Although the model is nonlinear, unmixing is performed by solving a linear system thanks to the recently proposed polytope decomposition (POD). Experimental results show that inverting this model leads to improved performances with respect to the state of the art in terms of endmember abundance estimation both over synthetic and real datasets. [ABSTRACT FROM PUBLISHER]

In order to achieve a better knowledge of the effect of the anthropogenic extents over the environment, extracting reliable and effective information by Earth observations (EOs) is crucial to help developing a sound human–environment interaction (HEI) assessment. In this sense, the use of future hyperspectral sensors for wide area characterization leads to the need of hyperspectral unmixing (HSU) architectures to recognize urban materials and structures. Further, as urban settlements are often characterized by geometrically and spectrally complex scenarios, the nonlinear reflectance interplay among the elements that constitute each scene must be very well detailed and described so that a thorough knowledge of the scenes can be carried out. In this paper, properly set higher order nonlinear mixture models are used to perform an accurate characterization of the anthropogenic settlements in several EO scenes acquired in different continents. Moreover, a brand new index for estimation of urban extents is provided. Experimental results show how the proposed approach is able to deliver accurate and reliable characterization of urban materials and extents. [ABSTRACT FROM PUBLISHER]

Mining information in Big Data requires to design a new class of algorithms and methods so that the computational complexity load is acceptable and the informativity loss is avoided. Information theory-based methodologies can represent a valid option in this sense. In this paper, we analyze a recently introduced method, called PROMODE, to efficiently detect local affinity patterns (LAPs) within Big Data sets. This processing framework operates with a computational load lower than what is required by other algorithms in literature, and is flexible enough to be applied to very heterogeneous remotely sensed datasets. Examples for spaceborne SAR and hyperspectral datasets, as well as a dataset involving Earth observations and clinical records are provided to prove this point. [ABSTRACT FROM PUBLISHER]

Nonlinear hyperspectral unmixing (HSU) plays a key-role in understanding and quantifying the physical-chemical phenomena occurring over geometrically complex fields of view. Nonlinear HSU methods that do not rely on prior knowledge of the ground truth to analyze the scene are especially interesting. However, they can be affected either by overfitting or performance degradation provided by inaccurate setting of unmixing parameters. In this paper, we introduce a new nonlinear HSU architecture which aims at taking advantage of the benefit provided by the combination of polytope decomposition (POD) method together with artificial neural network (ANN)-based learning. Specifically, ANN is able to efficiently estimate the order $p$ of the nonlinearity provided by the given scene even without the thorough knowledge of the ground truth. The ANN-based learning is used to feed the POD in order to deliver accurate unmixing based on a $p$-linear polynomial model. Experimental results over simulated and real scenes show promising performance of the proposed framework. [ABSTRACT FROM PUBLISHER]

We explore new and existing convolutional neural network (CNN) architectures for sea ice classification using Sentinel-1 (S1) synthetic aperture radar (SAR) data by investigating two key challenges: binary sea ice versus open-water classification, and a multi-class sea ice type classification. The analysis of sea ice in SAR images is challenging because of the thermal noise effects and ambiguities in the radar backscatter for certain conditions that include the reflection of complex information from sea ice surfaces. We use manually annotated SAR images containing various sea ice types to construct a dataset for our Deep Learning (DL) analysis. To avoid contamination between classes we use a combination of near-simultaneous SAR images from S1 and fine resolution cloud-free optical data from Sentinel-2 (S2). For the classification, we use data augmentation to adjust for the imbalance of sea ice type classes in the training data. The SAR images are divided into small patches which are processed one at a time. We demonstrate that the combination of data augmentation and training of a proposed modified Visual Geometric Group 16-layer (VGG-16) network, trained from scratch, significantly improves the classification performance, compared to the original VGG-16 model and an ad hoc CNN model. The experimental results show both qualitatively and quantitatively that our models produce accurate classification results. [ABSTRACT FROM AUTHOR]

Spectral unmixing (SU) aims at decomposing the mixed pixel into basic components, called endmembers with corresponding abundance fractions. Linear mixing model (LMM) and nonlinear mixing models (NLMMs) are two main classes to solve the SU. This paper proposes a new nonlinear unmixing method base on general bilinear model, which is one of the NLMMs. Since retrieving the endmembers' abundances represents an ill-posed inverse problem, prior knowledge of abundances has been investigated by conceiving regularizations techniques (e.g., sparsity, total variation, group sparsity, and low rankness), so to enhance the ability to restrict the solution space and thus to achieve reliable estimates. All the regularizations mentioned above can be interpreted as denoising of abundance maps. In this paper, instead of investing effort in designing more powerful regularizations of abundances, we use plug-and-play prior technique, that is to use directly a state-of-the-art denoiser, which is conceived to exploit the spatial correlation of abundance maps and nonlinear interaction maps. The numerical results in simulated data and real hyperspectral dataset show that the proposed method can improve the estimation of abundances dramatically compared with state-of-the-art nonlinear unmixing methods. [ABSTRACT FROM AUTHOR]

The magnitude of a random telegraph signal (RTS) in nanoscale floating-gate devices has been experimentally investigated as a function of carrier concentration. Discrete current switching, which is caused by a single trap, has been found to be almost one order of magnitude higher with respect to what was predicted by the classical theory of carrier number and correlated mobility fluctuations. Nevertheless, the trap signature well fits the typical SiO2 trap spectroscopy. In addition, the rigid shift between the transfer curves related to filled- and empty-trap state, together with the normalized current fluctuation dependence on the channel carrier density, suggests that a pure number fluctuation is the correct theoretical interpretative framework. Thus, we propose a possible physical explanation for such a giant RTS on the basis of a quasi-1-D current filamentation. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) have been widely applied in hyperspectral imagery (HSI) classification. However, their classification performance might be limited by the scarcity of labeled data to be used for training and validation. In this paper, we propose a novel lightweight shuffled group convolutional neural network (abbreviated as SG-CNN) to achieve efficient training with a limited training dataset in HSI classification. SG-CNN consists of SG conv units that employ conventional and atrous convolution in different groups, followed by channel shuffle operation and shortcut connection. In this way, SG-CNNs have less trainable parameters, whilst they can still be accurately and efficiently trained with fewer labeled samples. Transfer learning between different HSI datasets is also applied on the SG-CNN to further improve the classification accuracy. To evaluate the effectiveness of SG-CNNs for HSI classification, experiments have been conducted on three public HSI datasets pretrained on HSIs from different sensors. SG-CNNs with different levels of complexity were tested, and their classification results were compared with fine-tuned ShuffleNet2, ResNeXt, and their original counterparts. The experimental results demonstrate that SG-CNNs can achieve competitive classification performance when the amount of labeled data for training is poor, as well as efficiently providing satisfying classification results. [ABSTRACT FROM AUTHOR]

The trade-off between spatial and temporal resolution limits the acquisition of dense time series of Landsat images, and limits the ability to properly monitor land surface dynamics in time. Spatiotemporal image fusion methods provide a cost-efficient alternative to generate dense time series of Landsat-like images for applications that require both high spatial and temporal resolution images. The Spatial and Temporal Reflectance Unmixing Model (STRUM) is a kind of spatial-unmixing-based spatiotemporal image fusion method. The temporal change image derived by STRUM lacks spectral variability and spatial details. This study proposed an improved STRUM (ISTRUM) architecture to tackle the problem by taking spatial heterogeneity of land surface into consideration and integrating the spectral mixture analysis of Landsat images. Sensor difference and applicability with multiple Landsat and coarse-resolution image pairs (L-C pairs) are also considered in ISTRUM. Experimental results indicate the image derived by ISTRUM contains more spectral variability and spatial details when compared with the one derived by STRUM, and the accuracy of fused Landsat-like image is improved. Endmember variability and sliding-window size are factors that influence the accuracy of ISTRUM. The factors were assessed by setting them to different values. Results indicate ISTRUM is robust to endmember variability and the publicly published endmembers (Global SVD) for Landsat images could be applied. Only sliding-window size has strong influence on the accuracy of ISTRUM. In addition, ISTRUM was compared with the Spatial Temporal Data Fusion Approach (STDFA), the Enhanced Spatial and Temporal Adaptive Reflectance Fusion Model (ESTARFM), the Hybrid Color Mapping (HCM) and the Flexible Spatiotemporal DAta Fusion (FSDAF) methods. ISTRUM is superior to STDFA, slightly superior to HCM in cases when the temporal change is significant, comparable with ESTARFM and a little inferior to FSDAF. However, the computational efficiency of ISTRUM is much higher than ESTARFM and FSDAF. ISTRUM can to synthesize Landsat-like images on a global scale. [ABSTRACT FROM AUTHOR]

In this paper, a novel convolutional neural network (CNN)-based architecture, named fine segmentation network (FSN), is proposed for semantic segmentation of high resolution aerial images and light detection and ranging (LiDAR) data. The proposed architecture follows the encoder–decoder paradigm and the multi-sensor fusion is accomplished in the feature-level using multi-layer perceptron (MLP). The encoder consists of two parts: the main encoder based on the convolutional layers of Vgg-16 network for color-infrared images and a lightweight branch for LiDAR data. In the decoder stage, to adaptively upscale the coarse outputs from encoder, the Sub-Pixel convolution layers replace the transposed convolutional layers or other common up-sampling layers. Based on this design, the features from different stages and sensors are integrated for a MLP-based high-level learning. In the training phase, transfer learning is employed to infer the features learned from generic dataset to remote sensing data. The proposed FSN is evaluated by using the International Society for Photogrammetry and Remote Sensing (ISPRS) Potsdam and Vaihingen 2D Semantic Labeling datasets. Experimental results demonstrate that the proposed framework can bring considerable improvement to other related networks. [ABSTRACT FROM AUTHOR]

This work presents an analysis framework enabling the integration of a clinical-administrative dataset of Type 2 Diabetes (T2D) patients with environmental information derived from air quality maps acquired from remote sensing data. The research has been performed within the EU project MOSAIC, which gathers T2D patients' data coming from Fondazione S.Maugeri (FSM) hospital and the Pavia local health care agency (ASL). The proposed analysis is aimed to highlight the complexity of the domain, showing the different perspectives that can be adopted when applying a data-driven approach to large variety of temporal, geo-localized data. We investigated a set of 899 patients, located in the Pavia area, and detected several patterns depicting how clinical facts and air pollution variations may be related. [ABSTRACT FROM AUTHOR]

A very interesting perspective of "big data" in diabetes management stands in the integration of environmental information with data gathered for clinical and administrative purposes, to increase the capability of understanding spatial and temporal patterns of diseases. Within the MOSAIC project, funded by the European Union with the goal to design new diabetes analytics, we have jointly analyzed a clinical-administrative dataset of nearly 1.000 type 2 diabetes patients with environmental information derived from air quality maps acquired from remote sensing (satellite) data. Within this context we have adopted a general analysis framework able to deal with a large variety of temporal, geo-localized data. Thanks to the exploitation of time series analysis and satellite images processing, we studied whether glycemic control showed seasonal variations and if they have a spatiotemporal correlation with air pollution maps. We observed a link between the seasonal trends of glycated hemoglobin and air pollution in some of the considered geographic areas. Such findings will need future investigations for further confirmation. This work shows that it is possible to successfully deal with big data by implementing new analytics and how their exploration may provide new scenarios to better understand clinical phenomena., (© 2015 Diabetes Technology Society.)