Earth Observation Data Analysis Research Articles

Remote sensing data fusion approach for estimating forest degradation: a case study of boreal forests damaged by Polygraphus proximus

In the context of global climate change and rising anthropogenic loads, outbreaks of both endemic and invasive pests, pathogens, and diseases pose an increasing threat to the health, resilience, and productivity of natural forests and forest plantations worldwide. The effective management of such threats depends on the opportunity for early-stage action helping to limit the damage expand, which is difficult to implement for large territories. Recognition technologies based on the analysis of Earth observation data are the basis for effective tools for monitoring the spread of degradation processes, supporting pest population control, forest management, and conservation strategies in general. In this study, we present a machine learning-based approach for recognizing damaged forests using open source remote sensing images of Sentinel-2 supported with Google Earth data on the example of bark beetle, Polygraphus proximus Blandford, polygraph. For the algorithm development, we first investigated and annotated images in channels corresponding to natural color perception—red, green, and blue—available at Google Earth. Deep neural networks were applied in two problem formulations: semantic segmentation and detection. As a result of conducted experiments, we developed a model that is effective for a quantitative assessment of the changes in target objects with high accuracy, achieving 84.56% of F1-score, determining the number of damaged trees and estimating the areas occupied by withered stands. The obtained damage masks were further integrated with medium-resolution Sentinel-2 images and achieved 81.26% of accuracy, which opened the opportunity for operational monitoring systems to recognize damaged forests in the region, making the solution both rapid and cost-effective. Additionally, a unique annotated dataset has been collected to recognize forest areas damaged by the polygraph in the region of study.

Time series (2001/2002–2021) analysis of Earth observation data using Google Earth Engine (GEE) for detecting changes in land use land cover (LULC) with specific reference to forest cover in East Godavari Region, Andhra Pradesh, India

Time series (2001/2002–2021) analysis of Earth observation data using Google Earth Engine (GEE) for detecting changes in land use land cover (LULC) with specific reference to forest cover in East Godavari Region, Andhra Pradesh, India

EOdal: An open-source Python package for large-scale agroecological research using Earth Observation and gridded environmental data

Earth Observation by means of remote sensing imagery and gridded environmental data opens tremendous opportunities for systematic capture, quantification and interpretation of plant–environment interactions through space and time. The acquisition, maintenance and processing of these data sources, however, requires a unified software framework for efficient and scalable integrated spatio-temporal analysis taking away the burden of data and file handling from the user. Existing software products either cover only parts of these requirements, exhibit a high degree of complexity, or are closed-source, which limits reproducibility of research. With the open-source Python library EOdal (Earth Observation Data Analysis Library) we propose a novel software that enables the development of fully reproducible spatial data science chains through the strict use of open-source developments. Thanks to its modular design, EOdal enables advanced data warehousing especially for remote sensing data, sophisticated spatio-temporal analysis and intersection of different data sources, as well as nearly unlimited expandability through application programming interfaces (APIs).

An operational Sentinel-2 based monitoring system for the management and control of direct aids to the farmers in the context of the Common Agricultural Policy (CAP): A case study in mainland Portugal

The European Union (EU) member states are expected to develop new procedures, based on automatic earth observation data analysis, for the management and control of direct aids to the farmers, as part of the Common Agricultural Policy (CAP) reform of 2020. Here, we propose an operational monitoring system based on Sentinel-2 surface reflectance (SR) data and machine learning (ML) algorithms, consisting of a hierarchical approach triggering 3 color-coded warning alerts to distinguish among compliant (green), non-compliant (red), and inconclusive (yellow) parcels comparatively to the farmer’s declaration. A Random Forest (RF) model is applied to a 5-day interpolated SR time series to generate a preliminary crop map, where all the parcels whose predicted and declared crop type match are flagged as compliant. Next, a refinement procedure is adopted to improve the discrimination between temporary and permanent crops. At this stage, VI temporal metrics and texture are used as input to a Support Vector Machine (SVM) classifier trained using only the previous compliant parcels. Through a set of decision rules, SVM crop class predictions are flagged as compliant, non-compliant and inconclusive. The system was tested for a significant area in mainland Portugal, using the 2019 Land Parcel Information System (LPIS) data. The system returned 96.5%, 2.5% and 1% of the parcels as compliant, inconclusive, and non-compliant, respectively. Comparison with field inspections for the subsidy control of 2019 revealed that only 1.1% of the correct declarations were classified by the system as non-compliant (5% as admissible value), while less than 5% of the real non-compliant declarations passed through the system (10–20%).

Editorial of Special Issue “Machine and Deep Learning for Earth Observation Data Analysis”

Earth observation and remote sensing technologies provide ample and comprehensive information regarding the dynamics and complexity of the Earth system [...]

Open Source Framework for Enabling HPC and Cloud Geoprocessing Services

Geoprocessing is a set of tools that can be used to efficiently address several pressing chal-lenges for the global economy ranging from agricultural productivity, the design of transport networks, to the prediction of climate change and natural disasters. This paper describes an Open Source Framework developed, within three European projects, for Ena-bling High-Performance Computing (HPC) and Cloud geoprocessing services applied to agricultural challenges. The main goals of the European Union projects EUXDAT (EUro-pean e-infrastructure for eXtreme Data Analytics in sustainable developmenT), CYBELE (fostering precision agriculture and livestock farming through secure access to large-scale HPC-enabled virtual industrial experimentation environment empowering scalable big data analytics), and EOPEN (opEn interOperable Platform for unified access and analysis of Earth observatioN data) are to enable the use of large HPC systems, as well as big data management, user-friendly access and visualization of results. In addition, these projects focus on the development of software frameworks, and fuse Earth-observation data, such as Copernicus data, with non-Earth-observation data, such as weather, environmental and social media information. In this paper, we describe the agroclimatic-zones pilot used to validate the framework. Finally, performance metrics collected during the execution (up to 182 times speedup with 256 MPI processes) of the pilot are presented.

Understanding an urbanizing planet: Strategic directions for remote sensing

Scientific contributions from remote sensing over the last fifty years have significantly advanced our understanding of urban areas. Key contributions of urban remote sensing include but are not limited to characterization of urban areas, urban land cover changes and thermal remote sensing of urban climates. Today, the proliferation of new sensors, long time series of the satellite record, joint analysis of Earth observation data with ancillary data sets, widespread availability of high-performance computing facilities, and slow but increasing use of remote sensing data and methods in non-remote sensing fields together offer new opportunities to generate scientific knowledge for an urbanizing planet. Simultaneously, the scale and pace of contemporary urbanization require new information about urban areas from both the science and policy communities. This paper examines remote sensing contributions to the scientific understanding of urban areas over the last 50 years until today. Based on this assessment and current needs by user communities, we identify four strategic directions for future urban remote sensing research: high temporal frequency analysis, characterization of urban heterogeneity, characterization of urban form and structure in two and three dimensions, and linking remote sensing with emerging urban data. Advances in these four areas are likely to generate significant new insights that will be useful to both science and policy.

Automated global delineation of human settlements from 40 years of Landsat satellite data archives

ABSTRACTThis paper presents the analysis of Earth Observation data records collected between 1975 and 2014 for assessing the extent and temporal evolution of the built-up surface in the frame of the Global Human Settlement Layer project. The scale of the information produced by the study enables the assessment of the whole continuum of human settlements from rural hamlets to megacities. The study applies enhanced processing methods as compared to the first production of the GHSL baseline data. The major improvements include the use of a more refined learning set on built-up areas derived from Sentinel-1 data which allowed testing the added-value of incremental learning in big data analytics. Herein, the new features of the GHSL built-up grids and the methods are described and compared with the previous ones using a reference set of building footprints for 277 areas of interest. The results show a gradual improvement in the accuracy measures with a gain of 3.6% in the balanced accuracy, between the first production of the GHSL baseline and the latest GHSL multitemporal built-up grids. A validation of the multitemporal component is also conducted at the global scale establishing the reliability of the built-up layer across time.

Segment-before-Detect: Vehicle Detection and Classification through Semantic Segmentation of Aerial Images

Like computer vision before, remote sensing has been radically changed by the introduction of deep learning and, more notably, Convolution Neural Networks. Land cover classification, object detection and scene understanding in aerial images rely more and more on deep networks to achieve new state-of-the-art results. Recent architectures such as Fully Convolutional Networks can even produce pixel level annotations for semantic mapping. In this work, we present a deep-learning based segment-before-detect method for segmentation and subsequent detection and classification of several varieties of wheeled vehicles in high resolution remote sensing images. This allows us to investigate object detection and classification on a complex dataset made up of visually similar classes, and to demonstrate the relevance of such a subclass modeling approach. Especially, we want to show that deep learning is also suitable for object-oriented analysis of Earth Observation data as effective object detection can be obtained as a byproduct of accurate semantic segmentation. First, we train a deep fully convolutional network on the ISPRS Potsdam and the NZAM/ONERA Christchurch datasets and show how the learnt semantic maps can be used to extract precise segmentation of vehicles. Then, we show that those maps are accurate enough to perform vehicle detection by simple connected component extraction. This allows us to study the repartition of vehicles in the city. Finally, we train a Convolutional Neural Network to perform vehicle classification on the VEDAI dataset, and transfer its knowledge to classify the individual vehicle instances that we detected.

A Survey on Gaussian Processes for Earth-Observation Data Analysis: A Comprehensive Investigation

Gaussian processes (GPs) have experienced tremendous success in biogeophysical parameter retrieval in the last few years. GPs constitute a solid Bayesian framework to consistently formulate many function approximation problems. This article reviews the main theoretical GP developments in the field, considering new algorithms that respect signal and noise characteristics, extract knowledge via automatic relevance kernels to yield feature rankings automatically, and allow applicability of associated uncertainty intervals to transport GP models in space and time that can be used to uncover causal relations between variables and can encode physically meaningful prior knowledge via radiative transfer model (RTM) emulation. The important issue of computational efficiency will also be addressed. These developments are illustrated in the field of geosciences and remote sensing at local and global scales through a set of illustrative examples. In particular, important problems for land, ocean, and atmosphere monitoring are considered, from accurately estimating oceanic chlorophyll content and pigments to retrieving vegetation properties from multi- and hyperspectral sensors as well as estimating atmospheric parameters (e.g., temperature, moisture, and ozone) from infrared sounders.

Early detection of biomass production deficit hot-spots in semi-arid environment using FAPAR time series and a probabilistic approach

Early warning monitoring systems in food-insecure countries aim to detect unfavourable crop and pasture conditions as early as possible during the growing season. This manuscript describes a procedure to estimate the probability of experiencing an end-of-season biomass production deficit during the on-going season based on a statistical analysis of Earth Observation data. A 15-year time series of the Fraction of Absorbed Photosynthetically Active Radiation from the SPOT-VEGETATION instrument is used to characterize the climatological development of vegetation, its variability and its current status. Forecasts of overall seasonal performances, expressed in terms of the probability of experiencing a critical deficit at the end of the growing season, are updated regularly whenever a new satellite observation is made available. Results and performances of the method are discussed for croplands and pastures in the Sahel.

A disaster information and monitoring system utilizing earth observation

Purpose – This paper aims to present disaster information and a monitoring system in order to utilize earth observation data in the operative process of early warning, mitigation and management of natural disasters. The system is aimed at integrating earth observation data analysis with modern ICTs including GIS, grid, mobile communication and web technology to support disaster monitoring and to share disaster information during a crisis.Design/methodology/approach – The system development concerned outlining an operative disaster monitoring and management process. The process was derived from actual practices, suggestions and needs of different user groups involved in disaster management. After investigating state‐of‐the‐art ICTs and reviewing the existing tools and databases, a suitable system architecture was designed and a prototype system was implemented, adapting to a proven software development process.Findings – The prototype system implementation demonstrated how satellite‐based data can be used ...

An automated object-based approach for the multiscale image segmentation of forest scenes

Over the last decade the analysis of Earth observation data has evolved from what were predominantly per-pixel multispectral-based approaches, to the development and application of multiscale object-based methods. To empower users with these emerging object-based approaches, methods need to be intuitive, easy to use, require little user intervention, and provide results closely matching those generated by human interpreters. In an attempt to facilitate this, we present multiscale object-specific segmentation (MOSS) as an integrative object-based approach for automatically delineating image-objects (i.e., segments) at multiple scales from a high-spatial resolution remotely sensed forest scene. We further illustrate that these segments cognitively correspond to individual tree crowns, ranging up to forest stands, and describe how such a tool may be used in computer-assisted forest inventory mapping. MOSS is composed of three primary components: object-specific analysis (OSA), object-specific upscaling (OSU), and a new segmentation algorithm referred to as size constrained region merging (SCRM). The rationale for integrating these methods is that the first two provide the third with object-size parameters that otherwise would need to be specified by a user. Analysis is performed on an IKONOS-2 panchromatic image that represents a highly fragmented forested landscape in the Sooke Watershed on southern Vancouver Island, BC, Canada.

Advances in mathematical morphology applied to geoscience and remote sensing

By concentrating on the analysis of the spatial relationships between groups of pixels, mathematical morphology provides us with an image processing strategy complementary to those based on the analysis of the spectral signature of single pixels. A wide variety of morphological transformations are available for extracting structural information in spatial data. Accordingly, a stream of successful applications in geoscience and remote sensing have been reported since the mid-1980s as highlighted in a brief survey. However, recent advances in the theory of mathematical morphology still remain largely unexplored. We show in this paper that they can enhance methodologies for the processing and analysis of Earth observation data for tasks as diverse as filtering, simplification, directional segmentation and crest line extraction. We also address important issues overlooked in the past and concerning the applicability of a given morphological filter to Earth observation data. In particular, we point out that self-dual or even self-complementary filters are required in many applications to produce results independent of the local contrast of the searched image structures.