Explore the vast range of titles available.

Coastal development and urban planning are facing different issues including natural disasters and extreme storm events. The ability to track and forecast the evolution of the physical characteristics of coastal areas over time is an important factor in coastal development, risk mitigation and overall coastal zone management. Traditional bathymetry measurements are obtained using echo-sounding techniques which are considered expensive and not always possible due to various complexities. Remote sensing tools such as satellite imagery can be used to estimate bathymetry using incident wave signatures and inversion models such as physical models of waves. In this work, we present two novel approaches to bathymetry estimation using deep learning and we compare the two proposed methods in terms of accuracy, computational costs, and applicability to real data. We show that deep learning is capable of accurately estimating ocean depth in a variety of simulated cases which offers a new approach for bathymetry estimation and a novel application for deep learning.

The development of semi-supervised learning techniques is essential to enhance the generalization capacities of machine learning algorithms. Indeed, raw image data are abundant while labels are scarce, therefore it is crucial to leverage unlabeled inputs to build better models. The availability of large databases have been key for the development of learning algorithms with high level performance. Despite the major role of machine learning in Earth Observation to derive products such as land cover maps, datasets in the field are still limited, either because of modest surface coverage, lack of variety of scenes or restricted classes to identify. We introduce a novel large-scale dataset for semi-supervised semantic segmentation in Earth Observation, the MiniFrance suite. MiniFrance has several unprecedented properties: it is large-scale, containing over 2000 very high resolution aerial images, accounting for more than 200 billions samples (pixels); it is varied, covering 16 conurbations in France, with various climates, different landscapes, and urban as well as countryside scenes; and it is challenging, considering land use classes with high-level semantics. Nevertheless, the most distinctive quality of MiniFrance is being the only dataset in the field especially designed for semi-supervised learning: it contains labeled and unlabeled images in its training partition, which reproduces a life-like scenario. Along with this dataset, we present tools for data representativeness analysis in terms of appearance similarity and a thorough study of MiniFrance data, demonstrating that it is suitable for learning and generalizes well in a semi-supervised setting. Finally, we present semi-supervised deep architectures based on multi-task learning and the first experiments on MiniFrance. These results will serve as baselines for future work on semi-supervised learning over the MiniFrance dataset. The Minifrance suite and related semi-supervised networks will be publicly available to promote semi-supervised works in Earth Observation.

Stray light is a critical aspect for high performance optical instruments. When stray light control by design is insufficient to reach the performance requirement, correction by post-processing must be considered. This situation is encountered, for example, in the case of the Earth observation instrument 3MI, whose stray light properties are complex due to the presence of many ghosts distributed on the detector array. We implement an iterative correction method and discuss its convergence properties. Spatial and field binning can be employed to reduce the computation time but at the cost of a decreased performance. Interpolation of the stray light properties is required to achieve high performance correction. For that, two methods are proposed and tested. The first interpolate the stray light in the field domain while the second applies a scaling operation based on a local symmetry assumption. Ultimately, the scaling method is selected and a stray light reduction by a factor of 58 is obtained at 2σ (129 at 1σ) for an extended scene illumination.

Unprecedented amounts of analysis‐ready Earth Observation (EO) data, combined with increasing computational power and new algorithms, offer novel opportunities for analysing ecosystem dynamics across large geographic extents, and to support conservation planning and action. Much research effort has gone into developing global EO‐based land‐cover and land‐use datasets, including tree cover, crop types, and surface water dynamics. Yet there are inherent trade‐offs between regional and global EO products pertaining to class legends, availability of training/validation data, and accuracy. Acknowledging and understanding these trade‐offs is paramount for both developing EO products and for answering science questions relevant for ecology or conservation studies based on these data. Here we provide context on the development of global EO‐based land‐cover and land‐use datasets, and outline advantages and disadvantages of both regional and global datasets. We argue that both types of EO‐derived land‐cover datasets can be preferable, with regional data providing the context‐specificity that is often required for policy making and implementation (e.g., land‐use and management, conservation planning, payment schemes for ecosystem services), making use of regional knowledge, particularly important when moving from land cover to actors. Ensuring that global and regional land‐cover and land‐use products derived based on EO data are compatible and nested, both in terms of class legends and accuracy assessment, should be a key consideration when developing such data. Open access high‐quality training and validation data derived as part of such efforts are of utmost importance. Likewise, global efforts to generate sets of essential variables for climate change, biodiversity, or eventually land use, which often require land‐cover maps as inputs, should consider regionalized, hierarchical approaches to not sacrifice regional context. Global change impacts manifest in regions, and so must the policy and planning responses to these challenges. EO data should embrace that regions matter, perhaps more than ever, in an age of global data availability and processing.

This paper presents a map of Africa's rainforests for 2005. Derived from moderate resolution imaging spectroradiometer data at a spatial resolution of 250 m and with an overall accuracy of 84%, this map provides new levels of spatial and thematic detail. The map is accompanied by measurements of deforestation between 1990, 2000 and 2010 for West Africa, Central Africa and Madagascar derived from a systematic sample of Landsat images—imagery from equivalent platforms is used to fill gaps in the Landsat record. Net deforestation is estimated at 0.28% yr−1 for the period 1990–2000 and 0.14% yr−1 for the period 2000–2010. West Africa and Madagascar exhibit a much higher deforestation rate than the Congo Basin, for example, three times higher for West Africa and nine times higher for Madagascar. Analysis of variance over the Congo Basin is then used to show that expanding agriculture and increasing fuelwood demands are key drivers of deforestation in the region, whereas well-controlled timber exploitation programmes have little or no direct influence on forest-cover reduction at present. Rural and urban population concentrations and fluxes are also identified as strong underlying causes of deforestation in this study.

Land cover maps are a vital input variable to many types of environmental research and management. While they can be produced automatically by machine learning techniques, these techniques require substantial training data to achieve high levels of accuracy, which are not always available. One technique researchers use when labelled training data are scarce is domain adaptation (DA)—where data from an alternate region, known as the source domain, are used to train a classifier and this model is adapted to map the study region, or target domain. The scenario we address in this paper is known as semi-supervised DA, where some labelled samples are available in the target domain. In this paper we present Sourcerer, a Bayesian-inspired, deep learning-based, semi-supervised DA technique for producing land cover maps from satellite image time series (SITS) data. The technique takes a convolutional neural network trained on a source domain and then trains further on the available target domain with a novel regularizer applied to the model weights. The regularizer adjusts the degree to which the model is modified to fit the target data, limiting the degree of change when the target data are few in number and increasing it as target data quantity increases. Our experiments on Sentinel-2 time series images compare Sourcerer with two state-of-the-art semi-supervised domain adaptation techniques and four baseline models. We show that on two different source-target domain pairings Sourcerer outperforms all other methods for any quantity of labelled target data available. In fact, the results on the more difficult target domain show that the starting accuracy of Sourcerer (when no labelled target data are available), 74.2%, is greater than the next-best state-of-the-art method trained on 20,000 labelled target instances.

The Google Earth Engine (GEE) portal provides enhanced opportunities for undertaking earth observation studies. Established towards the end of 2010, it provides access to satellite and other ancillary data, cloud computing, and algorithms for processing large amounts of data with relative ease. However, the uptake and usage of the opportunity remains varied and unclear. This study was undertaken to investigate the usage patterns of the Google Earth Engine platform and whether researchers in developing countries were making use of the opportunity. Analysis of published literature showed that a total of 300 journal papers were published between 2011 and June 2017 that used GEE in their research, spread across 158 journals. The highest number of papers were in the journal Remote Sensing, followed by Remote Sensing of Environment. There were also a number of papers in premium journals such as Nature and Science. The application areas were quite varied, ranging from forest and vegetation studies to medical fields such as malaria. Landsat was the most widely used dataset; it is the biggest component of the GEE data portal, with data from the first to the current Landsat series available for use and download. Examination of data also showed that the usage was dominated by institutions based in developed nations, with study sites mainly in developed nations. There were very few studies originating from institutions based in less developed nations and those that targeted less developed nations, particularly in the African continent.

China's Earth Observation(EO) System has undergone significant development since the 1970s, as China has dedicated substantial efforts to advancing remote sensing technology. With fifty years of development, China has successfully narrowed the remote sensing technology gap with foreign countries through collaborative endeavors of the government and enterprises. At present, China has constructed a comprehensive EO system that has been proven indispensable for driving economic growth and facilitating sustainable development. This paper provides an overview of the development, missions, andapplications of China's EO system, while also exploring future directions and technical trends of China's EO system.

Although satellite‐based variables have for long been expected to be key components to a unified and global biodiversity monitoring strategy, a definitive and agreed list of these variables still remains elusive. The growth of interest in biodiversity variables observable from space has been partly underpinned by the development of the essential biodiversity variable (EBV) framework by the Group on Earth Observations – Biodiversity Observation Network, which itself was guided by the process of identifying essential climate variables. This contribution aims to advance the development of a global biodiversity monitoring strategy by updating the previously published definition of EBV, providing a definition of satellite remote sensing (SRS) EBVs and introducing a set of principles that are believed to be necessary if ecologists and space agencies are to agree on a list of EBVs that can be routinely monitored from space. Progress toward the identification of SRS‐EBVs will require a clear understanding of what makes a biodiversity variable essential, as well as agreement on who the users of the SRS‐EBVs are. Technological and algorithmic developments are rapidly expanding the set of opportunities for SRS in monitoring biodiversity, and so the list of SRS‐EBVs is likely to evolve over time. This means that a clear and common platform for data providers, ecologists, environmental managers, policy makers and remote sensing experts to interact and share ideas needs to be identified to support long‐term coordinated actions. This contribution introduces a set of definitions and principles that are believed to be necessary if ecologists and space agencies are to agree on a list of essential biodiversity variables that can be routinely monitored from space. In particular, it argues that progress toward the identification of satellite remote sensing EBVs (SRS‐EBVs) will require a clear understanding of what makes a biodiversity variable essential, as well as agreement on who the users of the SRS‐EBVs are.

Imaging spectrometry from aerial or spaceborne platforms, also known as hyperspectral remote sensing, provides dense sampled and fine structured spectral information for each image pixel, allowing the user to identify and characterize Earth surface materials such as minerals in rocks and soils, vegetation types and stress indicators, and water constituents. The recently launched DLR Earth Sensing Imaging Spectrometer (DESIS) installed on the International Space Station (ISS) closes the long-term gap of sparsely available spaceborne imaging spectrometry data and will be part of the upcoming fleet of such new instruments in orbit. DESIS measures in the spectral range from 400 and 1000 nm with a spectral sampling distance of 2.55 nm and a Full Width Half Maximum (FWHM) of about 3.5 nm. The ground sample distance is 30 m with 1024 pixels across track. In this article, a detailed review is given on the applicability of DESIS data based on the specifics of the instrument, the characteristics of the ISS orbit, and the methods applied to generate products. The various DESIS data products available for users are described with the focus on specific processing steps. The results of the data quality and product validation studies show that top-of-atmosphere radiance, geometrically corrected, and bottom-of-atmosphere reflectance products meet the mission requirements. The limitations of the DESIS data products are also subject to a critical examination.