Spectral observations along the spectrum in many narrow spectral bands through hyperspectral imaging provides valuable information towards material and object recognition, which can be consider as a classification task. Most of the existing studies and research efforts are following the conventional pattern recognition paradigm, which is based on the construction of complex handcrafted features. However, it is rarely known which features are important for the problem at hand. In contrast to these approaches, we propose a deep learning based classification method that hierarchically constructs high-level features in an automated way. Our method exploits a Convolutional Neural Network to encode pixels' spectral and spatial information and a Multi-Layer Perceptron to conduct the classification task. Experimental results and quantitative validation on widely used datasets showcasing the potential of the developed approach for accurate hyperspectral data classification.

The automated man-made object detection and building extraction from single satellite images is, still, one of the most challenging tasks for various urban planning and monitoring engineering applications. To this end, in this paper we propose an automated building detection framework from very high resolution remote sensing data based on deep convolutional neural networks. The core of the developed method is based on a supervised classification procedure employing a very large training dataset. An MRF model is then responsible for obtaining the optimal labels regarding the detection of scene buildings. The experimental results and the performed quantitative validation indicate the quite promising potentials of the developed approach.

In this article, we present a deep multitask learning framework able to couple semantic segmentation and change detection using fully convolutional long short-term memory (LSTM) networks. In particular, we present a UNet-like architecture (L-UNet) that models the temporal relationship of spatial feature representations using integrated fully convolutional LSTM blocks on top of every encoding level. In this way, the network is able to capture the temporal relationship of spatial feature vectors in all encoding levels without the need to downsample or flatten them, forming an end-to-end trainable framework. Moreover, we further enrich the L-UNet architecture with an additional decoding branch that performs semantic segmentation on the available semantic categories that are presented in the different input dates, forming a multitask framework. Different loss quantities are also defined and combined together in a circular way to boost the overall performance. The developed methodology has been evaluated on three different data sets, i.e., the challenging bitemporal high-resolution Office National d'Etudes et de Recherches Aérospatiales (ONERA) Satellite Change Detection (OSCD) Sentinel-2 data set, the very high-resolution (VHR) multitemporal data set of the East Prefecture of Attica, Greece, and finally, the multitemporal VHR SpaceNet7 data set. Promising quantitative and qualitative results demonstrated that the synergy among the tasks can boost up the achieved performances. In particular, the proposed multitask framework contributed to a significant decrease in false-positive detections, with the F1 rate outperforming other state-of-the-art methods by at least 2.1% and 4.9% in the Attica VHR and SpaceNet7 data set cases, respectively. Our models and code can be found at https://github.com/mpapadomanolaki/multi-task-L-UNet.

Marine litter is one of the most relevant pollution problems that our oceans are facing today. Marine litter in our oceans is a major threat to a sustainable planet. Here, we provide a comprehensive analysis of cutting-edge solutions developed globally to prevent, monitor and clean marine litter. Prevention in this research includes only innovative solutions to prevent litter entering oceans and seas rather than interventions such as waste reduction and recycling. On the basis of extensive search and data compilation, our analysis reveals that information is dispersed across platforms and is not easily accessible. In total, 177 solutions—the equivalent to <0.9% of the search hits—fulfilled our validation criteria and were evaluated. Most solutions (n = 106, 60%) primarily address monitoring and were developed during the past 3 years, with the scientific community being the key driver. Few solutions reached mature technical readiness and market availability, while none were validated for efficiency and environmental impact. Looking ahead, we elaborate on the limitations of the existing solutions, the challenges of developing new solutions, and provide recommendations for funding schemes and policy instruments to prevent, monitor and clean marine litter globally. In doing so, we encourage researchers, innovators and policy-makers worldwide to act towards achieving and sustaining a cleaner ocean for future generations.

Plastic debris in the global ocean is considered an important issue with severe implications for human health and marine ecosystems. Here, we exploited high-resolution multispectral satellite observations over the Bay Islands and Gulf of Honduras, for the period 2014-2019, to investigate the capability of satellite sensors in detecting marine plastic debris. We verified findings with in situ data, recorded the spectral characteristics of floating plastic litter, and identified plastic debris trajectories and sources. The results showed that plastic debris originating from Guatemala’s and Honduras’ rivers (such as Motagua, Ulua, Cangrejal, Tinto and Aguan) ends up in the Caribbean Sea, mainly during the period of August to March, which includes the main rainfall season. The detected spatial trajectories indicated that floating plastic debris travels with an average speed of 6 km d⁻¹, following primarily a southwest (SW) to northeast (NE) direction, driven by the prevailing sea surface currents. Based on several satellite observations, there is no indication of a specific accumulation point, since plastic debris is dispersed by the dynamic circulation in the broader region. Our findings provide evidence that satellite remote sensing is a valuable, cost-effective tool for monitoring the sources and pathways of plastic debris in marine ecosystems, and thus could eventually support management strategies in the global ocean.