We present TerraMind, the first any-to-any generative, multimodal foundation model for Earth observation (EO). Unlike other multimodal models, TerraMind is pretrained on dual-scale representations combining both token-level and pixel-level data across modalities. On a token level, TerraMind encodes high-level contextual information to learn cross-modal relationships, while on a pixel level, TerraMind leverages fine-grained representations to capture critical spatial nuances. We pretrained TerraMind on nine geospatial modalities of a global, large-scale dataset. In this paper, we demonstrate that (i) TerraMind's dual-scale early fusion approach unlocks a range of zero-shot and few-shot applications for Earth observation, (ii) TerraMind introduces "Thinking-in-Modalities" (TiM) -- the capability of generating additional artificial data during finetuning and inference to improve the model output -- and (iii) TerraMind achieves beyond state-of-the-art performance in community-standard benchmarks for EO like PANGAEA. The pretraining dataset, the model weights, and our code are open-sourced under a permissive license.

In this article, we explore the potential of quantum machine learning for subsurface feature extractions from radar sounder signals. We propose a hybrid quantum-classical learning paradigm that leverages parameterized quantum circuits to generate probability amplitudes based on quantum properties such as superposition and entanglement. These amplitudes are synergistically integrated with the classical deep neural networks that are efficient in learning high-dimension contextual features for downstream prediction tasks. The present research work is structured around two objectives. First, we investigate the role of quantum circuits in the latent space for transferring back-and-forth rich discriminative spatial context from the encoder to the decoder for segmentation. Second, we investigate how the probabilistic amplitudes derived from quantum circuits are significant in integrating into the classical models to provide new insights for radar sounder signals segmentation. The performance of the hybrid architectures has been studied in small-scale settings by simulating the expected behaviour of the quantum circuits on a classical machine. The experimental results have demonstrated the viability of quantum machine learning frameworks on MCoRDS-1 and MCoRDS-3 datasets for radar sounder signal segmentation. Qualitatively, they are capable of delineating the spatial extent of the bedrock from noise. Additionally, we conduct a comparative analysis between theQiskit Aer Simulatorand theIBM FakeBackend Simulatorto highlight the computational trade-offs and validate fidelity of two simulators for scalable experimentation. Therefore, our work opens up new avenues of research for future radar sounder data analysis leading to more precise and efficient subsurface target segmentation.

The trend of building larger and more complex imaging satellite constellations leads to the challenge in managing multiple acquisition requests of the Earth surface. Optimally planning these acquisitions is an intractable optimization problem, and heuristic algorithms are used today for finding sub-optimal solutions. Recently, quantum algorithms have been considered for this purpose, due to the potential breakthroughs that they can bring in optimization, expecting either a speedup or an increase in the solution quality. Hybrid quantum-classical methods have been considered as a short-term solution for taking advantage of small quantum machines. In this paper, we propose reverse quantum annealing as a method for improving the acquisition plan obtained by a classical optimizer. We investigate the benefits of the method with different annealing schedules and different problem sizes. The obtained results provide guidelines on designing a larger hybrid quantum-classical framework based on reverse quantum annealing for this application.

This article presents a hybrid quantum-classical framework by incorporating quantum feature maps regulated classical Convolutional Neural Network (CNN) architecture in the context of detecting different subsurface targets in the radar sounder signal. The quantum feature maps are generated by quantum circuits to utilize spatially-bound input information from the input training samples. The associated spectral probabilistic amplitudes of the feature maps are further fed as an input to the classical CNN-based network to classify the subsurface targets in the radargram. Experimental results on the MCoRDS and MCoRDS3 dataset demonstrated the capability of contextualizing the classical architecture through quantum feature maps for characterizing the radar sounder data.

The increasing availability of high-resolution, open-access satellite data facilitates the production of global Land Cover (LC) maps, an essential source of information for managing and monitoring natural and human-induced processes. However, the accuracy of the obtained LC maps can be affected by the discrepancy between the spatial resolution of the satellite images and the extent of the LC present in the scene. Indeed, several pixels may be misclassified because of their mixed spectral signatures, i.e., more than two LC classes are present in the pixel. To solve this problem, this paper proposes an approach that explores the possibility of using simple but effective unmixing approaches to enhance the classification accuracy of the mixed spectral pixels. The results showed that several pixels, including buildings and grassland LC, are typically classified as cropland. By unmixing their spectral content, it is possible to extract the most prevalent class within the area of each pixel to update the classification map, thus sharply increasing the map accuracy. These promising preliminary results indicate the potential for broader applicability and efficiency in global LC mapping.

Seismic Imaging (SI) survey design for onshore applications faces challenges such as accessibility and poor data quality due to unexpected (near-)surface conditions. In this paper, we explore the correlation between the surface conditions provided by Land-Cover (LC) maps generated using Remote Sensing (RS) data and different settings of Seismic Processing (SP) parameters. The study involves a 2D seismic line related to geothermal exploration from the Netherlands.

The amount of data needed to effectively train modern deep neural architectures has grown significantly, leading to increased computational requirements. These intensive computations are tackled by the combination of last generation computing resources, such as accelerators, or classic processing units. Nevertheless, gradient communication remains as the major bottleneck, hindering the efficiency notwithstanding the improvements in runtimes obtained through data parallelism strategies. Data parallelism involves all processes in a global exchange of potentially high amount of data, which may impede the achievement of the desired speedup and the elimination of noticeable delays or bottlenecks. As a result, communication latency issues pose a significant challenge that profoundly impacts the performance on distributed platforms. This research presents node-based optimization steps to significantly reduce the gradient exchange between model replicas whilst ensuring model convergence. The proposal serves as a versatile communication scheme, suitable for integration into a wide range of general-purpose deep neural network (DNN) algorithms. The optimization takes into consideration the specific location of each replica within the platform. To demonstrate the effectiveness, different neural network approaches and datasets with disjoint properties are used. In addition, multiple types of applications are considered to demonstrate the robustness and versatility of our proposal. The experimental results show a global training time reduction whilst slightly improving accuracy. Code: https://github.com/mhaut/eDNNcomm.

Kernel methods are class of Machine Learning (ML) models that have been widely employed in the literature for Earth Observation (EO) applications. The increasing development of quantum computing hardware motivates further research to improve the capabilities and the performances of data analysis algorithms. In this manuscript an implementation of Adiabatic Quantum Kitchen Sinks (AQKS) kernel estimation algorithm integrated with parallel quantum annealing is presented. Such combination with the concept of parallel quantum annealing allows for the solving of multiple problem instances in the same annealing cycle, thus reducing the number of rquired calls to the quantum annealing solver. The proposed workflow is then implemented using a D-Wave Advantage system and tested on a regression problem on a real Remote Sensing (RS) dataset. The obtained results are then analyzed and compared with those obtained by a classical kernel approximation algorithm based on Random Fourier Features.

The continuous stream of high spatial resolution satellite data offers the opportunity to regularly produce land cover (LC) maps. To this end, Transformer deep learning (DL) models have recently proven their effectiveness in accurately classifying long time series (TS) of satellite images. The continual generation of regularly updated LC maps can be used to analyze dynamic phenomena and extract multi-temporal information. However, several challenges need to be addressed. Our paper aims to study how the performance of a Transformer model changes when classifying TS of satellite images acquired in years later than those in the training set. In particular, the behavior of the attention in the Transformer model is analyzed to determine when the information provided by the initial training set needs to be updated to keep generating accurate LC products. Preliminary results show that: (i) the selection of the positional encoding strategy used in the Transformer has a significant impact on the classification accuracy obtained with multi-year TS, and (ii) the most affected classes are the seasonal ones.

Earth Observation (EO) data processing faces challenges due to large volumes, multiple sources, and diverse formats. To address this issue, this paper presents a scalable and parallelizable workflow using Apache Airflow, capable of integrating Machine Learning (ML) and Deep Learning (DL) models with Modular Supercomputing Architecture (MSA) systems. To test the workflow, we considered the production of large-scale Land-Cover (LC) maps as a case study. The workflow manager, Airflow, offers scalability, extensibility, and programmable task definition in Python. It allows us to execute different steps of the workflow in different High-Performance Computing (HPC) systems. The workflow is demonstrated on the Dynamical Exascale Entry Platform (DEEP) and Jülich Research on Exascale Cluster Architectures (JURECA) hosted at the Jülich Supercomputing Centre (JSC), a platform that incorporates heterogeneous JSC systems.

Land cover maps generated by the classification of remote sensing data allow for monitoring Earth processes and the dynamics of objects and phenomena. For accurate land cover variability quantification in environmental monitoring, maps need to be spatiotemporally consistent, continually updated, and indicate permanent changes. However, producing frequent and spatiotemporally consistent land cover maps is challenging because it involves balancing the need for temporal consistency with the risk of missing real changes. In this work, we propose a scalable and semi-automatic method for generating annual land cover maps with labels that are consistently applied from one year to the next. It uses a Transformer deep learning model as a classifier, which is trained on satellite time series of images using High Performance Computing (HPC). The trained model can generate stable maps by shifting the prediction window along the temporal direction. The effectiveness of the proposed approach is tested qualitatively and quantitatively on a multi-annual Sentinel-2 dataset acquired over a three-year period in a study area located in the southern Italian Alps.

In the last decade, deep learning (DL) has significantly impacted industry and science. Initially largely motivated by computer vision tasks in 2-D imagery, the focus has shifted toward 3-D data analysis. In particular, 3-D surface reconstruction, i.e., reconstructing a 3-D shape from sparse input, is of great interest to a large variety of application fields. DL-based approaches show promising quantitative and qualitative surface reconstruction performance compared to traditional computer vision and geometric algorithms. This survey provides a comprehensive overview of these DL-based methods for 3-D surface reconstruction. To this end, we will first discuss input data modalities, such as volumetric data, point clouds, and RGB, single-view, multiview, and depth images, along with corresponding acquisition technologies and common benchmark datasets. For practical purposes, we also discuss evaluation metrics enabling us to judge the reconstructive performance of different methods. The main part of the document will introduce a methodological taxonomy ranging from point-and mesh-based techniques to volumetric and implicit neural approaches. Recent research trends, both methodological and for applications, are highlighted, pointing toward future developments.

Deep Learning models have proven necessary in dealing with the challenges posed by the continuous growth of data volume acquired from satellites and the increasing complexity of new Remote Sensing applications. To obtain the best performance from such models, it is necessary to fine-tune their hyperparameters. Since the models might have massive amounts of parameters that need to be tuned, this process requires many computational resources. In this work, a method to accelerate hyperparameter optimization on a High-Performance Computing system is proposed. The data batch size is increased during the training, leading to a more efficient execution on Graphics Processing Units. The experimental results confirm that this method reduces the runtime of the hyperparameter optimization step by a factor of 3 while achieving the same validation accuracy as a standard training procedure with a fixed batch size.

The implementation of scalable processing workflows is essential to improve the access to and analysis of the vast amount of high-resolution and multi-source Remote Sensing (RS) data and to provide decision-makers with timely and valuable information. The Modular Supercomputing Architecture (MSA) systems that are operated by the Jülich Supercomputing Centre (JSC) are a concrete solution for data-intensive RS applications that rely on big data storage and processing capabilities. To meet the requirements of applications with more complex computational tasks, JSC plans to connect the High Performance Computing (HPC) systems of its MSA environment to different quantum computers via the Jülich UNified Infrastructure for Quantum computing (JUNIQ). The paper describes this unique computing environment and highlights its potential to address real RS application scenarios through high-performance and hybrid quantum-classical processing workflows.

Applications from Remote Sensing (RS) unveiled unique challenges to Deep Learning (DL) due to the high volume and complexity of their data. On the one hand, deep neural network architectures have the capability to automatically ex-tract informative features from RS data. On the other hand, these models have massive amounts of tunable parameters, re-quiring high computational capabilities. Distributed DL with data parallelism on High-Performance Computing (HPC) sys-tems have proved necessary in dealing with the demands of DL models. Nevertheless, a single HPC system can be al-ready highly heterogeneous and include different computing resources with uneven processing power. In this context, a standard data parallelism strategy does not partition the data efficiently according to the available computing resources. This paper proposes an alternative approach to compute the gradient, which guarantees that the contribution to the gradi-ent calculation is proportional to the processing speed of each DL model's replica. The experimental results are obtained in a heterogeneous HPC system with RS data and demon-strate that the proposed approach provides a significant training speed up and gain in the global accuracy compared to one of the state-of-the-art distributed DL framework.

Regression analysis has a crucial role in many Earth Ob-servation (EO) applications. The increasing availability and recent development of new computing technologies moti-vate further research to expand the capabilities and enhance the performance of data analysis algorithms. In this paper, the biophysical variable estimation problem is addressed. A novel approach is proposed, which consists in a reformulated Support Vector Regression (SVR) and leverages Quantum Annealing (QA). In particular, the SVR optimization prob-lem is reframed to a Quadratic Unconstrained Binary Opti-mization (QUBO) problem. The algorithm is then tested on the D-Wave Advantage quantum annealer. The experiments presented in this paper show good results, despite current hardware limitations, suggesting that this approach is viable and has great potential.

This paper presents an approach that aims to produce a Time-Series (TS) of consistent Land-Cover (LC) maps, typically needed to perform environmental monitoring. First, it creates an annual training set for each TS to be classified, leveraging on publicly available thematic products. These annual training sets are then used to generate a set of preliminary LC maps that allow for the identification of the unchanged areas, i.e., the stable temporal component. Such areas can be used to define an informative and reliable multi-year training set, by selecting samples belonging to the different years for all the classes. The multi-year training set is finally employed to train a unique multi-year Long Short Term Mem-ory (LSTM) model, which enhances the consistency of the annual LC maps. The preliminary results carried out on three TSs of Sentinel 2 images acquired in Italy in 2018,2019 and 2020 demonstrates the capability of the method to improve the consistency of the annual LC maps. The agreement of the obtained maps is$\approx 78{\%}$, compared to the$\approx 74{\%}$achieved by the LSTM models trained separately.

In Remote Sensing (RS) classification, generalization ability is one of the measure that characterizes the success of Machine Learning (ML) models, but is often impeded by the scarse availability of annotated training data. Annotated RS samples are expensive to obtain and can present large disparities when produced by different annotators. In this paper, we utilize Few-Shot Learning (FSL) with meta-learning to address the challenge of generalization using limited amount of training information. The data used in this paper is leveraged from different datasets that have diverse distributions, that means distinct feature spaces. We tested our approach on publicly available RS benchmark datasets to perform few-shot RS image classification using meta-learning. The results of the experiments suggest that our approach is able to generalize well on the unseen data even with limited number of training samples and reasonable training time.

Land-cover classification methods are based on the processing of large image volumes to accurately extract representative features. Particularly, convolutional models provide notable characterization properties for image classification tasks. Distributed learning mechanisms on high performance computing platforms have been proposed to speed up the processing, whilst achieving an efficient feature extraction. High performance computing platforms are commonly composed of a combination of CPUs and GPUs, with different computational capabilities. As a result, current homogeneous workload distribution techniques for deep learning become obsolete due to their inefficient use of computational resources. To address this, new computational balancing proposals, such as heterogeneous data parallelism, have been implemented. Nevertheless, these techniques should be improved to handle the peculiarities of working with heterogeneous data workloads in the training of distributed deep learning models. The objective of handling heterogeneous workloads for current platforms motivates the development of this work. This paper proposes an innovative heterogeneous gradient calculation applied to land-cover classification tasks through convolutional models, considering the data amount assigned to each device in the platform whilst maintaining the acceleration. Extensive experimentation has been conducted on multiple datasets, considering different deep models on heterogeneous platforms to demonstrate the performance of the proposed methodology.

The increasing availability of quantum computers motivates researching their potential capabilities in enhancing the performance of data analysis algorithms. Similarly, as in other research communities, also in Remote Sensing (RS) it is not yet defined how its applications can benefit from the usage of quantum computing. This paper proposes a formulation of the Support Vector Regression (SVR) algorithm that can be executed by D-Wave quantum computers. Specifically, the SVR is mapped to a Quadratic Unconstrained Binary Optimization (QUBO) problem that is solved with Quantum Annealing (QA). The algorithm is tested on two different types of computing environments offered by D-Wave: The Advantage system, which directly embeds the problem into the Quantum Processing Unit (QPU), and a Hybrid solver that employs both classical and quantum computing resources. For the evaluation, we considered a biophysical variable estimation problem with RS data. The experimental results show that the proposed quantum SVR implementation can achieve comparable or in some cases better results than the classical implementation. This work is one of the first attempts to provide insight into how QA could be exploited and integrated in future RS workflows based on Machine Learning (ML) algorithms.

Recent developments in Quantum Computing (QC) have paved the way for an enhancement of computing capabilities. Quantum Machine Learning (QML) aims at developing Machine Learning (ML) models specifically designed for quantum computers. The availability of the first quantum processors enabled further research, in particular the exploration of possible practical applications of QML algorithms. In this work, quantum formulations of the Support Vector Machine (SVM) are presented. Then, their implementation using existing quantum technologies is discussed and Remote Sensing (RS) image classification is considered for evaluation.

Using computationally efficient techniques for transforming the massive amount of Remote Sensing (RS) data into scientific understanding is critical for Earth science. The utilization of efficient techniques through innovative computing systems in RS applications has become more widespread in recent years. The continuously increased use of Deep Learning (DL) as a specific type of Machine Learning (ML) for data-intensive problems (i.e., ‘big data’) requires powerful computing resources with equally increasing performance. This paper reviews recent advances in High-Performance Computing (HPC), Cloud Computing (CC), and Quantum Computing (QC) applied to RS problems. It thus represents a snapshot of the state-of-the-art in ML in the context of the most recent developments in those computing areas, including our lessons learned over the last years. Our paper also includes some recent challenges and good experiences by using Europeans fastest supercomputer for hyper-spectral and multi-spectral image analysis with state-of-the-art data analysis tools. It offers a thoughtful perspective of the potential and emerging challenges of applying innovative computing paradigms to RS problems.

A wide variety of Remote Sensing (RS) missions are continuously acquiring a large volume of data every day. The availability of large datasets has propelled Deep Learning (DL) methods also in the RS domain. Convolutional Neural Networks (CNNs) have become the state of the art when tackling the classification of images, however the process of training is time consuming. In this work we exploit the Layer-wise Adaptive Moments optimizer for Batch training (LAMB) optimizer to use large batch size training on High-Performance Computing (HPC) systems. With the use of LAMB combined with learning rate scheduling and warm-up strategies, the experimental results on RS data classification demonstrate that a ResNet50 can be trained faster with batch sizes up to 32K.

Support Vector Machine (SVM) is a popular supervised Machine Learning (ML) method that is widely used for classification and regression problems. Recently, a method to train SVMs on a D-Wave 2000Q Quantum Annealer (QA) was proposed for binary classification of some biological data. First, ensembles of weak quantum SVMs are generated by training each classifier on a disjoint training subset that can be fit into the QA. Then, the computed weak solutions are fused for making predictions on unseen data. In this work, the classification of Remote Sensing (RS) multispectral images with SVMs trained on a QA is discussed. Furthermore, an open code repository is released to facilitate an early entry into the practical application of QA, a new disruptive compute technology.

Similarly to other scientific domains, Deep Learning (DL) holds great promises to fulfil the challenging needs of Remote Sensing (RS) applications. However, the increase in volume, variety and complexity of acquisitions that are carried out on a daily basis by Earth Observation (EO) missions generates new processing and storage challenges within operational processing pipelines. The aim of this work is to show that High-Performance Computing (HPC) systems can speed up the training time of Convolutional Neural Networks (CNNs). Particular attention is put on the monitoring of the classification accuracy that usually degrades when using large batch sizes. The experimental results of this work show that the training of the model scales up to a batch size of 8,000, obtaining classification performances in terms of accuracy in line with those using smaller batch sizes.

This work proposes a novel distributed deep learning model for Remote Sensing (RS) images super-resolution. High Performance Computing (HPC) systems with GPUs are used to accelerate the learning of the unknown low to high resolution mapping from large volumes of Sentinel-2 data. The proposed deep learning model is based on self-attention mechanism and residual learning. The results demonstrate that state-of-the-art performance can be achieved by keeping the size of the model relatively small. Synchronous data parallelism is applied to scale up the training process without severe performance loss. Distributed training is thus shown to speed up learning substantially while keeping performance intact.

The classification of land-cover classes in remote sensing images can suit a variety of interdisciplinary applications such as the interpretation of natural and man-made processes on the Earth surface. The Convolutional Support Vector Machine (CSVM) network was recently proposed as binary classifier for the detection of objects in Unmanned Aerial Vehicle (UAV) images. The training phase of the CSVM is based on convolutional layers that learn the kernel weights via a set of linear Support Vector Machines (SVMs). This paper proposes the Multi-scale Convolutional Support Vector Machine (MCSVM) network, that is an ensemble of CSVM classifiers which process patches of different spatial sizes and can deal with multi-class classification problems. The experiments are carried out on the EuroSAT Sentinel-2 dataset and the results are compared to the one obtained with recent transfer learning approaches based on pre-trained Convolutional Neural Networks (CNNs).

The implementation of efficient remote sensing workflows is essential to improve the access to and analysis of the vast amount of sensed data and to provide decision-makers with clear, timely, and useful information. The Dynamical Exascale Entry Platform (DEEP) is an European pre-exascale platform that incorporates heterogeneous High-Performance Computing (HPC) systems, i.e., hardware modules which include specialised accelerators. This paper demonstrates the potential of such diverse modules for the deployment of remote sensing data workflows that include diverse processing tasks. Particular focus is put on pipelines which can use the Network Attached Memory (NAM), which is a novel supercomputer module that allows near processing and/or fast shared storage of big remote sensing datasets.

Advances in remote sensing hardware have led to a significantly increased capability for high-quality data acquisition, which allows the collection of remotely sensed images with very high spatial, spectral, and radiometric resolution. This trend calls for the development of new techniques to enhance the way that such unprecedented volumes of data are stored, processed, and analyzed. An important approach to deal with massive volumes of information is data compression, related to how data are compressed before their storage or transmission. For instance, hyperspectral images (HSIs) are characterized by hundreds of spectral bands. In this sense, high-performance computing (HPC) and high-throughput computing (HTC) offer interesting alternatives. Particularly, distributed solutions based on cloud computing can manage and store huge amounts of data in fault-tolerant environments, by interconnecting distributed computing nodes so that no specialized hardware is needed. This strategy greatly reduces the processing costs, making the processing of high volumes of remotely sensed data a natural and even cheap solution. In this paper, we present a new cloud-based technique for spectral analysis and compression of HSIs. Specifically, we develop a cloud implementation of a popular deep neural network for non-linear data compression, known as autoencoder (AE). Apache Spark serves as the backbone of our cloud computing environment by connecting the available processing nodes using a master-slave architecture. Our newly developed approach has been tested using two widely available HSI data sets. Experimental results indicate that cloud computing architectures offer an adequate solution for managing big remotely sensed data sets.

Progress in sensor technology leads to an ever-increasing amount of remote sensing data which needs to be classified in order to extract information. This big amount of data requires parallel processing by running parallel implementations of classification algorithms, such as Support Vector Machines (SVMs), on High-Performance Computing (HPC) clusters. Tomorrow's supercomputers will be able to provide exascale computing performance by using specialised hardware accelerators. However, existing software processing chains need to be adapted to make use of the best fitting accelerators. To address this problem, a mapping of an SVM remote sensing classification chain to the Dynamical Exascale Entry Platform (DEEP), a European pre-exascale platform, is presented. It will allow to scale SVM-based classifications on tomorrow's hardware towards exascale performance.

Supervised image classification is one of the essential techniques for generating semantic maps from remotely sensed images. The lack of labeled ground truth datasets, due to the inherent time effort and cost involved in collecting training samples, has led to the practice of training and validating new classifiers within a single image. In line with that, the dominant approach for the division of the available ground truth into disjoint training and test sets is random sampling. This paper discusses the problems that arise when this strategy is adopted in conjunction with spectral-spatial and pixel-wise classifiers such as 3D Convolutional Neural Networks (3D CNN). It is shown that a random sampling scheme leads to a violation of the independence assumption and to the illusion that global knowledge is extracted from the training set. To tackle this issue, two improved sampling strategies based on the Density-Based Clustering Algorithm (DBSCAN) are proposed. They minimize the violation of the train and test samples independence assumption and thus ensure an honest estimation of the generalization capabilities of the classifier.

The progress of remote sensing technologies leads to increased supply of high-resolution image data. However, solutions for processing large volumes of data are lagging behind: desktop computers cannot cope anymore with the requirements of macro-scale remote sensing applications; therefore, parallel methods running in High-Performance Computing (HPC) environments are essential. Managing an HPC processing pipeline is non-trivial for a scientist, especially when the computing environment is heterogeneous and the set of tasks has complex dependencies. This paper proposes an end-to-end scientific workflow approach based on the UNICORE workflow management system for automating the full chain of Support Vector Machine (SVM)-based classification of remotely sensed images. The high-level nature of UNICORE workflows allows to deal with heterogeneity of HPC computing environments and offers powerful workflow operations such as needed for parameter sweeps. As a result, the remote sensing workflow of SVM-based classification becomes re-usable across different computing environments, thus increasing usability and reducing efforts for a scientist.

Component trees are region-based representations that encode the inclusion relationship of the threshold sets of an image. These representations are one of the most promising strategies for the analysis and the interpretation of spatial information of complex scenes as they allow the simple and efficient implementation of connected filters. This work proposes a new efficient hybrid algorithm for the parallel computation of two particular component trees-the max- and min-tree-in shared and distributed memory environments. For the node-local computation a modified version of the flooding-based algorithm of Salembier is employed. A novel tuple-based merging scheme allows to merge the acquired partial images into a globally correct view. Using the proposed approach a speed-up of up to 44.88 using 128 processing cores on eight-bit gray-scale images could be achieved. This is more than a five-fold increase over the state-of-the-art shared-memory algorithm, while also requiring only one-thirty-second of the memory.

Self-Dual Attribute Profiles (SDAPs) have proven to be an effective method for extracting spatial features able to improve scene classification of remote sensing images with very high spatial resolution. An SDAP is a multilevel decomposition of an image obtained with a sequence of transformations performed by attribute filters over the Tree of Shapes (ToS). One of the main issues with this technique is the identification of the filter thresholds generating a SDAP composed of features that should be relevant for the classification problem. This paper proposes a tree-based supervised feature extraction strategy, which is based on Fisher's linear discriminant analysis relying on the available class information. The exploitation of the ToS structure in the threshold selection procedure allows one to avoid any prior full image filtering, as in other related techniques. Furthermore, the ToS automates and optimizes the whole process by decreasing the computational time and overcoming the conventional selection procedure based on trial and error attempts. The proposed automatic spatial feature extraction technique has been tested in the classification of a very high resolution image proving its effectiveness with respect to a conventional selection strategy.

Classification of remote sensing images often use Support Vector Machines (SVMs) that require an n-fold cross-validation phase in order to do model selection. This phase is characterized by sweeping through a wide set of parameter combinations of SVM kernel and cost parameters. As a consequence this process is computationally expensive but represents a principled way of tuning a model for better accuracy and to prevent overfitting together with regularization that is in SVMs inherently solved in the optimization. Since the cross-validation technique is done in a principled way also known as `gridsearch', we aim at supporting remote sensing scientists in two ways. Firstly by reducing the time-to-solution of the cross-validation by applying state-of-the-art parallel processing methods because the sweep of parameters and cross-validation runs itself can be nicely parallelized. Secondly by reducing manual labour by automating the parallel submission processes since manually performing cross-validation is very time consuming, unintuitive, and error-prone especially in large-scale cluster or supercomputing environments (e.g., batch job scripts, node/core/task parameters, etc.).

Morphological attribute profiles are multilevel decompositions of images obtained with a sequence of transformations performed by connected operators. They have been extensively employed in performing multi-scale and region-based analysis in a large number of applications. One main, still unresolved, issue is the selection of filter parameters able to provide representative and non-redundant threshold decomposition of the image. This paper presents a framework for the automatic selection of filter thresholds based on Granulometric Characteristic Functions (GCFs). GCFs describe the way that non-linear morphological filters simplify a scene according to a given measure. Since attribute filters rely on a hierarchical representation of an image (e.g., the Tree of Shapes) for their implementation, GCFs can be efficiently computed by taking advantage of the tree representation. Eventually, the study of the GCFs allows the identification of a meaningful set of thresholds. Therefore, a trial and error approach is not necessary for the threshold selection, automating the process and in turn decreasing the computational time. It is shown that the redundant information is reduced within the resulting profiles (a problem of high occurrence, as regards manual selection). The proposed approach is tested on two real remote sensing data sets, and the classification results are compared with strategies present in the literature.

Satellite image classification is a key task used in remote sensing for the automatic interpretation of a large amount of information. Today there exist many types of classification algorithms using advanced image processing methods enhancing the classification accuracy rate. One of the best state-of-the-art methods which improves significantly the classification of complex scenes relies on Self-Dual Attribute Profiles (SDAPs). In this approach, the underlying representation of an image is the Tree of Shapes, which encodes the inclusion of connected components of the image. The SDAP computes for each pixel a vector of attributes providing a local multiscale representation of the information and hence leading to a fine description of the local structures of the image. Instead of performing a pixel-wise classification on features extracted from the Tree of Shapes, it is proposed to directly classify its nodes. Extending a specific interactive segmentation algorithm enables it to deal with the multi-class classification problem. The method does not involve any statistical learning and it is based entirely on morphological information related to the tree. Consequently, a very simple and effective region-based classifier relying on basic attributes is presented.

A novel unsupervised change detection approach for multi-spectral remote sensing data based on morphological transformation is presented. Profiles obtained by attribute filters can provide a rich multi-level analysis of the contextual information. The proposed method is based on the assumption that pixels belonging to changed areas exhibit profiles with significant differences due to a variation in their geometry, whereas pixels within unchanged areas result in similar profiles due to their similar spatial characteristics. The extension to the multi-spectral scenario is performed by applying the morphological analysis on the available bands that compose a given data set. In such scenario radiometric normalization results mandatory in order to minimize the effect due to different acquisition's conditions. To this purpose, IR-MAD is performed as pre-processing. In the paper, preliminary results obtained considering a multi-temporal Landsat ETM+ data set acquired over an agriculture area are shown.

Remotely sensed images with very high spatial resolution provide a detailed representation of the surveyed scene with a geometrical resolution that, at the present, can be up to 30 cm (WorldView-3). A set of powerful image processing operators have been defined in the mathematical morphology framework. Among those, connected operators [e.g., attribute filters (AFs)] have proven their effectiveness in processing very high resolution images. AFs are based on attributes which can be efficiently implemented on tree-based image representations. In this paper, we considered the definition of min, max, direct, and subtractive filter rules for the computation of AFs over the tree-of-shapes representation. We study their performance on the classification of remotely sensed images. We compare the classification results over the tree of shapes with the results obtained when the same rules are applied on the component trees. The random forest is used as a baseline classifier, and the experiments are conducted using multispectral data sets acquired by QuickBird and IKONOS sensors over urban areas.

Attribute profiles (APs) have increasingly been receiving more attention over the last years, as they are able to extract and model spatial information that is useful for the analysis of remote sensing images of very high spatial resolution (VHR). However, one of the major issues in employing APs is the choice of a proper range of thresholds, able to provide a representative and non-redundant multi-level image decomposition. This paper presents a novel method for the automatic selection of adequate thresholds to compute the AP. A new concept of cumulative function, which can be seen as an extension of the basic notion of granulometry, is introduced. In particular, different information on the spatial context is achieved according to the measure used for computing the cumulative function, which is computed on the AP composed by considering all possible values of the attribute. The proposed approach aims at selecting the set of thresholds that provides the best approximation of the resulting cumulative function based on the chosen measure. Experimental analysis carried out on a very high resolution image shows the effectiveness of the presented strategy in providing a set of thresholds able to retain the salient spatial structures in the scene.

Big Data Analytics methods take advantage of techniques from the fields of data mining, machine learning, or statistics with a focus on analysing large quantities of data (aka `big datasets') with modern technologies. Big data sets appear in remote sensing in the sense of large volumes, but also in the sense of an ever increasing amount of spectral bands (i.e., high-dimensional data). The remote sensing has traditionally used the above described techniques for a wide variety of application such as classification (e.g., land cover analysis using different spectral bands from satellite data), but more recently scalability challenges occur when using traditional (often serial) methods. This paper addresses observed scalability limits when using support vector machines (SVMs) for classification and discusses scalable and parallel developments used in concrete application areas of remote sensing. Different approaches that are based on massively parallel methods are discussed as well as recent developments in parallel methods.

With respect to the exponential increase in the number of available remote sensors in recent years, the possibility of having different types of data captured over the same scene, has resulted in many research works related to the joint use of passive and active sensors for the accurate classification of different materials. However, until now, there is a small number of research works related to the integration of highly valuable information obtained from the joint use of LiDAR and hyperspectral data. This paper proposes an efficient classification approach in terms of accuracies and demanded CPU processing time for integrating big data sets (e.g., LiDAR and hyperspectral) to provide land cover mapping capabilities at a range of spatial scales. In addition, the proposed approach is fully automatic and is able to efficiently handle big data containing a huge number of features with very limited number of training samples in few seconds.

In this letter, we explore the use of self-dual attribute profiles (SDAPs) for the classification of hyperspectral images. The hyperspectral data are reduced into a set of components by nonparametric weighted feature extraction (NWFE), and a morphological processing is then performed by the SDAPs separately on each of the extracted components. Since the spatial information extracted by SDAPs results in a high number of features, the NWFE is applied a second time in order to extract a fixed number of features, which are finally classified. The experiments are carried out on two hyperspectral images, and the support vector machines and random forest are used as classifiers. The effectiveness of SDAPs is assessed by comparing its results against those obtained by an approach based on extended APs.

In this paper we compare features obtained by different filtering strategies for morphological attribute filters by considering non-increasing attributes. The Attribute profiles (APs) and Self Dual Attribute Profiles (SDAPs) are obtained by sequentially applying attribute filters on tree-based image representations, such as Min- or Max-trees and Inclusion tree, respectively. This work aims to study the effects of using the filtering rules max, min, direct and subtractive, when considering the non-increasing attributes moment of inertia and standard deviation. A very high spatial resolution data set is used in the experiments, and the extracted information obtained by the profiles is analyzed. This is done by studying the effects on the classification accuracy by using the profiles as additional input features to a Random Forest classifier.

The big data analytics approach emerged that can be interpreted as extracting information from large quantities of scientific data in a systematic way. In order to have a more concrete understanding of this term we refer to its refinement as smart data analytics in order to examine large quantities of scientific data to uncover hidden patterns, unknown correlations, or to extract information in cases where there is no exact formula (e.g. known physical laws). Our concrete big data problem is the classification of classes of land cover types in image-based datasets that have been created using remote sensing technologies, because the resolution can be high (i.e. large volumes) and there are various types such as panchromatic or different used bands like red, green, blue, and nearly infrared (i.e. large variety). We investigate various smart data analytics methods that take advantage of machine learning algorithms (i.e. support vector machines) and state-of-the-art parallelization approaches in order to overcome limitations of big data processing using non-scalable serial approaches.

UNLABELLED: Metals are essential for the structure and function of many proteins and nucleic acids. The geometrical arrangement of the atoms that coordinate a metal in a biological macromolecule is an important determinant of the specificity and role of that metal. At present, however, this information can be retrieved only from the literature, which sometimes contains an improper or incorrect description of the geometry, and often lacks it altogether. Thus, we developed FindGeo to quickly and easily determine the coordination geometry of selected, or all, metals in a given structure. FindGeo works by superimposing the metal-coordinating atoms in the input structure to a library of templates with alternative ideal geometries, which are ranked by RMSD to identify the best geometry assignment. AVAILABILITY: FindGeo is freely available as a web service and as a stand-alone program at http://metalweb.cerm.unifi.it/tools/findgeo/.

SUMMARY: Metal-MACiE is a new publicly available web-based database, held in MySQL, which aims to organize the available information on the properties and the roles of metals in the context of the catalytic mechanisms of metalloenzymes. Metal-MACiE, which currently covers 75% of metal-dependent enzyme commission (EC) sub-sub-classes and is continuously growing, exploits the existing MACiE database for the annotation of the reaction mechanisms. The two databases constitute complementary sources of information for enzymology, biochemistry and molecular pharmacology studies. AVAILABILITY: http://www.ebi.ac.uk/thornton-srv/databases/Metal_MACiE/home.html.