Data available at multiple spatial / spectral / temporal scales pose numerous challenges to the data scientists. Of late researchers paid wide attention to handle such data acquired through various sensing mechanisms to address intertwined topics—like pattern retrieval, pattern analysis, quantitative reasoning, and simulation and modelling—for better understanding spatiotemporal behaviours of several terrestrial phenomena and processes. Various original algorithms and techniques that are mainly based on mathematical morphology (Matheron 1975, Serra 1982, Soille 2010, Sagar 2010, 2013) have been developed and demonstrated. This course that presents fundamentals of mathematical morphology and their involvement in interpolations and extrapolations with applications in geosciences and geoinformatics would be useful for those with research interests in image processing and analysis, remote sensing and geosciences, geographical information sciences, spatial statistics and mathematical morphology, mapping of earth-like planetary surfaces, etc. This course will be offered in two parts. In the morning shift all the fundamental morphological transformations would be covered. The applications of those transformations, covered in the first shift, to understand the morphological interpolations and extrapolations would be covered with several case studies in the second shift.
Despite the wide and often successful application of machine learning techniques to analyse and interpret remotely sensed data, the complexity, special requirements, as well as selective applicability of these methods often hinders to use them to their full potential. The gap between sensor- and application-specific expertise on the one hand, and a deep insight and understanding of existing machine learning methods often leads to suboptimal results, unnecessary or even harmful optimizations, and biased evaluations. The aim of this tutorial is twofold: First, spread good practices for data preparation: Inform about common mistakes and how to avoid them (e.g. dataset bias, non-iid samples), provide recommendations about proper preprocessing and initialization (e.g. data normalization), and state available sources of data and benchmarks. Second, present efficient and advanced machine learning tools: Give an overview of standard machine learning techniques and when to use them (e.g. standard regression and classification techniques, clustering, etc.), as well as introducing the most modern methods (such as random fields, ensemble learning, and deep learning).
The tutorial is designed to provide a complete introduction to the physics, phenomenology and exploitation techniques of imaging spectroscopy. The course covers sensor types using a model that can be applied to either dispersive or interferometric imaging spectrometers with the primary focus upon the currently dominant forms, calibration, atmospheric effects and compensation, processing and analytic techniques in multiple examples covering reflective and emissive wavelength regimes. The course is structures with an Introduction; Sensors-Data Collection-Calibration; Signatures and atmospheric compensation techniques, and Exploitation and mathematical techniques for hyperspectral data.
Although originally designed for navigation, signals from the Global Navigation Satellite System (GNSS), ie., GPS, GLONASS, Galileo and COMPASS, exhibit strong reflections from the Earth and ocean surface. Effects of rough surface scattering modify the properties of reflected signals. Several methods have been developed for inverting these effects to retrieve geophysical data such as ocean surface roughness (winds) and soil moisture. GNSS reflectometry (GNSS-R) methods enable the use of small, low power, passive instruments. The power and mass of GNSS-R instruments can be made low enough to enable deployment on small satellites, balloons and UAV’s.
Extensive sets of airborne GNSS-R measurements have been collected over the past 15 years. Flight campaigns have included penetration of hurricanes with winds up to 60 m/s and flights over agricultural fields with calibrated soil moisture measurements. Fixed, tower-based GNSS-R experiments have been conducted to make measurements of sea state, sea level, soil moisture, ice and snow as well as inter-comparisons with microwave radiometry. Early research sets of satellite-based GNSS-R data were first collected by the UK-DMC satellite, launched in 2003. This was followed by Tech Demo Sat-1 in 2014. CYGNSS, an 8-satellite constellation funded by NASA, is expected to be launched in November 2016 to observe tropical storm development with high spatial and temporal resolution. GEROS-ISS (GNSS ReEflectometry, Radio-Occultation and Scatterometry) is a planned ESA experiment aboard the International Space Station (ISS) to demonstrate GNSS-R altimetry. Secondary goals of GEROS-ISS are scatterometry, land applications, and radio-occultation. The ³Cat-2 micro satellite, carrying the PYCARO GNSS-R receiver, was launched in August 2016. This 6-U (30 cm x 20 cm) cubesat, developed at the Universitat Politècnica de Catalunya-Barcelona Tech (UPC), Spain and funded as a European Commission project (E-GEM), will test semi-codeless and dual-polarimetric reflectometry.
Availability of spaceborne GNSS-R data and the development of new applications from these measurements, is expected to increase significantly following launch of these new satellite missions.
This all-day tutorial will summarize the current state of the art in physical modeling, signal processing and application of GNSS-R measurements from fixed, airborne and satellite-based platforms.
The National Ecological Observatory Network (NEON) is a continental scale ecological platform designed to collect and disseminate data that contributes to understanding and forecasting the impacts of climate change, land use change, and invasive species on ecology. The observatory plans to reach full initial operational capacity by January 1, 2018 and will collect observations for 30 years thereafter. Once operational, the NEON Airborne Observation Platform (AOP) will annually collect airborne remote sensing observations across 81 sites in 20 distinct eco-climatic domains within the continental United States, Alaska, Hawaii, and Puerto Rico. Data collected by the AOP are intended to support observations from complementary observation systems within NEON, and provide a bridge which supports spatial and temporal scaling between localized point scale observations, regional data sets, and continental scale satellite observations. The AOP will operate three payloads that include a discrete and full-waveform LiDAR, hyperspectral imaging spectrometer, and high resolution RGB camera. In addition, the AOP team collects relevant field spectra to support calibration activities and other NEON data products. When operational, NEON will provide ~180 data products, with 23 being derived from the AOP observations. All NEON data products, protocols, procedures, and designs will be freely available to any researchers in the world. The AOP flight campaign in 2017 marks the first year the AOP will attempt to collect observations at all but one (Hawaii excluded) of the NEON domains; this campaign will include Alaska and Puerto Rico. The campaign will be carried out with two identical sensor payloads collecting measurements simultaneously between March and October, 2017. Payload-1 will primarily cover the eastern domain regions while Payload-2 will primarily cover western regions. This campaign will be the first to demonstrate the operational capabilities of the NEON AOP.
This tutorial will include several speakers who will detail the design, implementation and lessons learned in reaching operational capacity of the AOP to support the NEON observatory. Talks will focus on 1) overview of the NEON project and the synergy of the AOP observations with other ecological observations acquired by NEON, 2) introduction to the NEON sensors and payload, 3) mission planning and flight design with emphasis on coordinating flights to observe all sites during peak greenness and in fair weather, as well as site-level flight plan design considerations, 4) calibration of the imaging spectrometer to provide consistent repeatable observations across differing payloads and yearly campaigns, 5) the algorithms and workflows selected for producing remote sensing data products which will support the mission of NEON, 6) quantification of data product uncertainty introduced by the sensors, flight acquisition parameters, and algorithmic choices, 7) file formats used to distribute the data, and 8) how NEON data from all parts of the observatory can be accessed by the public to support research endeavors. Participants will gain a fundamental understanding of the NEON mission, details on technical aspects of the AOP, familiarity with NEON AOP products, and potential research avenues for furthering ecological applications of remote sensing data.
The one-day tutorial includes a wide overview of spaceborne Synthetic Aperture Radar (SAR) systems covering the theory, technology and applications. This tutorial is based on the lectures of Prof. Moreira held at the Karlsruhe Institute of Technology (KIT), Germany, as well as at national and international radar courses. The tutorial is fully interdisciplinary and well suited for participants interested in learning different aspects of the entire end-to-end system of spaceborne SAR systems.
The deluge of Erath Observation (EO) data counting hundreds of Terabytes per day needs to be converted into meaningful information, largely impacting the socio-economic-environmental triangle. Multispectral and microwave EO sensor are unceasingly streaming millions of samples per second, which must be interpreted to mine physical parameters to understand Earth patterns and phenomena. Many alternative heterogeneous information sources, as in-situ observations, maps or multimedia information, social networks, are contributing to the overall understanding.
The challenge is the exploration of these data for spatio-temporal patterns, relevant information and knowledge, for timely and perpetual global understanding of the phenomena governing the Earth and impacting processes as environmental, socio-economic, etc..
Data Science, specifically for Earth Observation imagery, besides to the prevalent 3Vs, is postulating additional challenges emerging from its very particular nature: data sources are sensors and instruments as multispectral or Synthetic Aperture Radar (SAR), information is spatio-temporal, meaning is quantitative as physical parameters and qualitative as semantic descriptors, understanding is contextual in synergy with multi-sensor, in-situ, geoinformation and other sources of information.
Therefore, the goal of the tutorial is the presentation of specific leading edge concepts, methods and algorithms for information content exploration and intelligence extraction from Big Data provided by EO sensors and other related sources. The tutorial offers an cross-disciplinary view of methods in signal processing, machine learning, deep learning, visualization and data mining also addressing the meaning extraction and semantic representations. Looking to the near future technologies, basic elements of quantum information processing will be also presented.
Thanks to the capability of providing direct physical measurements, synthetic aperture radar (SAR) Interferometry allowing generation of topographic maps, accurate localization of ground scatterers, and monitoring of possible displacements to a mm/year order, is one of the techniques that have most pushed the applications of SAR to a wide range of scientific, institutional and commercial areas, and it has provided significant returns to our society in terms of improvements in the risk monitoring.
SAR images relative to a same scene and suitable for interferometric processing are today available for most of the Earth, and their number is exponentially growing. Archives associated to SAR spaceborne sensors are filled by data collected with time and observation angle diversity (multipass-multibaseline data); moreover, current system trends in the SAR field involve clusters of cooperative formation-flying satellites with capability of multiple simultaneous acquisitions (bistatic and multistatic tandem SAR systems), airborne systems with multibaseline acquisition capability in a single pass are also available, and unmanned air vehicles with capability of differential monitoring of rapid phenomena are being experimented. In parallel, developments are underway of processing techniques, evolutions of the powerful SAR Interferometry, aimed at fully exploiting the information lying in such huge amount of multipass-multibaseline data, to produce new and/or more accurate measuring functionalities.
Focus of this tutorial is on processing methods that, by coherently combining multiple SAR images at the complex (phase and amplitude) data level, differently from phase-only Interferometry, allow improved or extended imaging and differential monitoring capabilities, in terms of accuracy and unambiguous interpretation of the measurements.
The tutorial will cover interrelated techniques that have been shaping in the recent years an emerging branch of SAR interferometric remote sensing, that can be termed Tomographic SAR Imaging, which is playing an important role in the development of next generation of SAR products and will enhance the application spectrum of SAR systems in Earth observation.
Patches are small image parts that capture both texture and local structure information. Though being crude low-level features compared to higher level descriptors, they have led to very powerful approaches in a wide range of image processing tasks such as deblurring, inpainting or classification. They form a core component of most current image restoration techniques.
In the past few years, several extensions of patch-based processing have been developed specifically for remote sensing, in particular for hyperspectral and SAR imaging. Strong fluctuations due to speckle indeed prevent from direct analysis and interpretation of radiometric, polarimetric or interferometric information from SAR images. Robust estimation procedures are thus essential to the successful use of SAR imaging. Given the efforts devoted to producing very high-resolution imaging systems, estimation of radar properties must preserve at best the spatial resolution and combine information from all available channels (interferometric, polarimetric, multi-date, multi-angle). Patch-based methods are among the most promising approaches to reach these goals.
This tutorial offers a review of the concept of patch-based image processing, from the basics of non-local denoising to more advanced concepts like dictionary learning and sparse coding, or local selection of optimal filtering parameters. It describes several applications of patch-based processing in remote sensing with a special focus on SAR imaging.