scholarly journals A Season Independent U-net Model for Robust Mapping of Solar Arrays Using Sentinel-2 Imagery

2021 ◽  
Author(s):  
Michael Evans ◽  
Taylor Minich ◽  
Rachel Soobitsky ◽  
Kumar Mainali
Keyword(s):  
North Carolina ◽  
Learning Technologies ◽  
Observation Data ◽  
Validation Data ◽  
Chesapeake Bay Watershed ◽  
Solar Arrays ◽  
Minimal Data ◽  
Temporal And Spatial ◽  
Earth Observation Data ◽  
Sentinel 2

We have an unprecedented ability to map the Earth’s surface as deep learning technologies are applied to an abundance of high-frequency Earth observation data. Simple, free, and effective methods are needed to enable a variety of stakeholders to use these tools to improve scientific knowledge and decision making. Here we present a trained U-Net model that can map and delineate ground mounted solar arrays using publicly available Sentinel-2 imagery, and that requires minimal data pre-processing and no feature engineering. By using label overloading and image augmentation during training, the model is robust to temporal and spatial variation in imagery. The trained model achieved a precision and recall of 91.5% each and an intersection over union of 84.3% on independent validation data from two distinct geographies. This generalizability in space and time makes the model useful for repeatedly mapping solar arrays. We use this model to delineate all ground mounted solar arrays in North Carolina and the Chesapeake Bay watershed to illustrate how these methods can be used to quickly and easily produce accurate maps of solar infrastructure.

scholarly journals Effective, Low-cost Methods of Applying Computer Vision to Public Earth Observation Data

2020 ◽  
Author(s):  
Michael Evans ◽  
Taylor Minich
Keyword(s):  
Wildlife Conservation ◽  
Low Cost ◽  
Ground Truth ◽  
Google Earth ◽  
Earth Observation ◽  
Learning Technologies ◽  
Observation Data ◽  
Solar Arrays ◽  
Observation Systems ◽  
Earth Observation Data

We have an unprecedented ability to analyze and map the Earth’s surface, as deep learning technologies are applied to an abundance of Earth observation systems collecting images of the planet daily. In order to realize the potential of these data to improve conservation outcomes, simple, free, and effective methods are needed to enable a wide variety of stakeholders to derive actionable insights from these tools. In this paper we demonstrate simple methods and workflows using free, open computing resources to train well-studied convolutional neural networks and use these to delineate objects of interest in publicly available Earth observation images. With limited training datasets (<1000 observations), we used Google Earth Engine and Tensorflow to process Sentinel-2 and National Agricultural Imaging Program data, and use these to train U-Net and DeepLab models that delineate ground mounted solar arrays and parking lots in satellite imagery. The trained models achieved 81.5% intersection over union between predictions and ground-truth observations in validation images. These images were generated at different times and from different places from those upon which they were trained, indicating the ability of models to generalize outside of data on which they were trained. The two case studies we present illustrate how these methods can be used to inform and improve the development of renewable energy in a manner that is consistent with wildlife conservation.

scholarly journals A Possible Role of Copernicus Sentinel-2 Data to Support Common Agricultural Policy Controls in Agriculture

Agronomy ◽  
2021 ◽  
Vol 11 (1) ◽  
pp. 110
Author(s):  
Filippo Sarvia ◽  
Elena Xausa ◽  
Samuele De Petris ◽  
Gianluca Cantamessa ◽  
Enrico Borgogno-Mondino
Keyword(s):  
Agricultural Policy ◽  
Common Agricultural Policy ◽  
Observation Data ◽  
Key Factor ◽  
Ndvi Time Series ◽  
Earth Observation Data ◽  
Four Levels ◽  
Nw Italy ◽  
Sentinel 2

Farmers that intend to access Common Agricultural Policy (CAP) contributions must submit an application to the territorially competent Paying Agencies (PA). Agencies are called to verify consistency of CAP contributions requirements through ground campaigns. Recently, EU regulation (N. 746/2018) proposed an alternative methodology to control CAP applications based on Earth Observation data. Accordingly, this work was aimed at designing and implementing a prototype of service based on Copernicus Sentinel-2 (S2) data for the classification of soybean, corn, wheat, rice, and meadow crops. The approach relies on the classification of S2 NDVI time-series (TS) by “user-friendly” supervised classification algorithms: Minimum Distance (MD) and Random Forest (RF). The study area was located in the Vercelli province (NW Italy), which represents a strategic agricultural area in the Piemonte region. Crop classes separability proved to be a key factor during the classification process. Confusion matrices were generated with respect to ground checks (GCs); they showed a high Overall Accuracy (>80%) for both MD and RF approaches. With respect to MD and RF, a new raster layer was generated (hereinafter called Controls Map layer), mapping four levels of classification occurrences, useful for administrative procedures required by PA. The Control Map layer highlighted that only the eight percent of CAP 2019 applications appeared to be critical in terms of consistency between farmers’ declarations and classification results. Only for these ones, a GC was warmly suggested, while the 12% must be desirable and the 80% was not required. This information alone suggested that the proposed methodology is able to optimize GCs, making possible to focus ground checks on a limited number of fields, thus determining an economic saving for PA and/or a more effective strategy of controls.

scholarly journals A Sentinel-2 Dataset for Uganda

Data ◽  
2021 ◽  
Vol 6 (4) ◽  
pp. 35
Author(s):  
Jonas Ardö
Keyword(s):  
Environmental Monitoring ◽  
Input Data ◽  
Vegetation Indices ◽  
Earth Observation ◽  
Observation Data ◽  
Output Data ◽  
Radiometric Correction ◽  
Clear Sky ◽  
Earth Observation Data ◽  
Sentinel 2

Earth observation data provide useful information for the monitoring and management of vegetation- and land-related resources. The Framework for Operational Radiometric Correction for Environmental monitoring (FORCE) was used to download, process and composite Sentinel-2 data from 2018–2020 for Uganda. Over 16,500 Sentinel-2 data granules were downloaded and processed from top of the atmosphere reflectance to bottom of the atmosphere reflectance and higher-level products, totalling > 9 TB of input data. The output data include the number of clear sky observations per year, the best available pixel composite per year and vegetation indices (mean of EVI and NDVI) per quarter. The study intention was to provide analysis-ready data for all of Uganda from Sentinel-2 at 10 m spatial resolution, allowing users to bypass some basic processing and, hence, facilitate environmental monitoring.

scholarly journals Evaluation of the Potential of Convolutional Neural Networks and Random Forests for Multi-Class Segmentation of Sentinel-2 Imagery

2019 ◽  
Vol 11 (8) ◽  
pp. 907 ◽  
Author(s):  
Vasileios Syrris ◽  
Paul Hasenohr ◽  
Blagoj Delipetrev ◽  
Alexander Kotsev ◽  
Pieter Kempeneers ◽  
...  
Keyword(s):  
Random Forests ◽  
Computational Models ◽  
Earth Observation ◽  
Data Sets ◽  
Observation Data ◽  
Computational Aspects ◽  
Learning Set ◽  
Earth Observation Data ◽  
Class Segmentation ◽  
Sentinel 2

Motivated by the increasing availability of open and free Earth observation data through the Copernicus Sentinel missions, this study investigates the capacity of advanced computational models to automatically generate thematic layers, which in turn contribute to and facilitate the creation of land cover products. In concrete terms, we assess the practical and computational aspects of multi-class Sentinel-2 image segmentation based on a convolutional neural network and random forest approaches. The annotated learning set derives from data that is made available as result of the implementation of European Union’s INSPIRE Directive. Since this network of data sets remains incomplete in regard to some geographic areas, another objective of this work was to provide consistent and reproducible ways for machine-driven mapping of these gaps and a potential update of the existing ones. Finally, the performance analysis identifies the most important hyper-parameters, and provides hints on the models’ deployment and their transferability.

scholarly journals Fast Unsupervised Multi-Scale Characterization of Urban Landscapes Based on Earth Observation Data

2021 ◽  
Vol 13 (12) ◽  
pp. 2398
Author(s):  
Claire Teillet ◽  
Benjamin Pillot ◽  
Thibault Catry ◽  
Laurent Demagistri ◽  
Dominique Lyszczarz ◽  
...  
Keyword(s):  
Urban Areas ◽  
Urban Landscapes ◽  
Observation Data ◽  
Validation Data ◽  
Multi Scale ◽  
Macro Scale ◽  
Neighborhood Scale ◽  
Urban Footprint ◽  
Sentinel 2

Most remote sensing studies of urban areas focus on a single scale, using supervised methodologies and very few analyses focus on the “neighborhood” scale. The lack of multi-scale analysis, together with the scarcity of training and validation datasets in many countries lead us to propose a single fast unsupervised method for the characterization of urban areas. With the FOTOTEX algorithm, this paper introduces a texture-based method to characterize urban areas at three nested scales: macro-scale (urban footprint), meso-scale (“neighbourhoods”) and micro-scale (objects). FOTOTEX combines a Fast Fourier Transform and a Principal Component Analysis to convert texture into frequency signal. Several parameters were tested over Sentinel-2 and Pleiades imagery on Bouake and Brasilia. Results showed that a single Sentinel-2 image better assesses the urban footprint than the global products. Pleiades images allowed discriminating neighbourhoods and urban objects using texture, which is correlated with metrics such as building density, built-up and vegetation proportions. The best configurations for each scale of analysis were determined and recommendations provided to users. The open FOTOTEX algorithm demonstrated a strong potential to characterize the three nested scales of urban areas, especially when training and validation data are scarce, and computing resources limited.

scholarly journals INTEGRATION OF SENTINEL-2 AND LANDSAT-8 DATA FOR SURFACE REFLECTANCE TIME-SERIES ANALYSIS

2019 ◽  
Vol XLII-4/W18 ◽  
pp. 205-210 ◽  
Author(s):  
G. Berdou ◽  
S. Shrestha ◽  
M. Hahn
Keyword(s):  
Atmospheric Correction ◽  
Surface Characteristics ◽  
Global Scale ◽  
Landsat 8 ◽  
Observation Data ◽  
Common Reference ◽  
Key Factor ◽  
Land Covers ◽  
Earth Observation Data ◽  
Sentinel 2

Abstract. Integration of Sentinel-2 and Landsat-8 imagery is a key factor to provide earth observation data at a global scale with higher temporal resolution. Integration of data from two sensors is possible with the consistent harmonized data framed in common reference and processing, which can be used for comparing geophysical surface characteristics. This study focuses on the analysis of the atmospheric correction methods available for both Landsat-8 and Sentinel-2 products to convert the top of the atmosphere to the bottom of atmosphere reflectance. Other investigations (De Keukelaere, 2018) carried out similar analyses focusing on data acquired over water, while this study emphasises the analyses over land covers. Two processing algorithms iCOR and Sen2COR are utilized to perform atmospheric corrections, and results are statistically and visually compared. Comparisons based on same images processed with different algorithms show very strong correlation for some classes (urban: 0.99), while correlation values around 0.85 were achieved between images from different sensors.

The Sen2Cube.at national semantic Earth observation data cube for Austria 

2021 ◽  
Author(s):  
Martin Sudmanns ◽  
Hannah Augustin ◽  
Lucas van der Meer ◽  
Andrea Baraldi ◽  
Dirk Tiede
Keyword(s):  
Inference Engine ◽  
Earth Observation ◽  
Data Cube ◽  
Observation Data ◽  
Semantic Enrichment ◽  
Area Of Interest ◽  
Information Layer ◽  
Semantic Models ◽  
Earth Observation Data ◽  
Sentinel 2

<div> <p>The Sen2Cube.at is a Sentinel-2 semantic Earth observation (EO) data and information cube that combines an EO data cube with an AI-based inference engine by integrating a computer-vision approach to infer new information. Our approach uses semantic enrichment of optical images and makes the data and information directly available and accessible for further use within an EO data cube. The architecture is based on an expert system, in which domain-knowledge can be encoded in semantic models (knowledgebase) and applied to the Sentinel-2 data as well as semantically enriched, data-derived information (factbase).  </p> </div><div> <p>The initial semantic enrichment in the Sen2Cube.at system is general-purpose, user- and application-independent, derived directly from optical EO images as an initial step towards a scene classification map. These information layers are automatically generated from Sentinel-2 images with the SIAM software (Satellite Image Automated Mapper). SIAM is a knowledge-based and physical-model-based decision tree that produces a set of information layers in a fully automated process that is applicable worldwide and does not require any samples. A graphical inference engine allows application-specific Web-based semantic querying based on the generic information layer as a replicable and explainable approach to produce information. The graphical inference engine is a new Browser-based graphical user interface (GUI) developed in-house with a semantic querying language. Users formulate semantic models in a graphical way and can execute them on any area-of-interest and time interval, which will be evaluated by the core of the inference engine attached to the data cube. This also enables non-expert users to formulate analyses without requiring programming skills.  </p> </div><div> <p>While the methodology is software-independent, the prototype is based on the Open Data Cube and additional in-house developed components in the Python programming language. Scaling is possible depending on the available infrastructure resources due to the system’s Docker-based container architecture. Through its fully automated semantic enrichment, innovative graphical querying language in the GUI for semantic querying and analysis as well as the implementation as a scalable infrastructure, this approach is suited for big data analysis of Earth observation data. It was successfully scaled to a national data cube for Austria, containing all available Sentinel-2 images from the platforms A and B. </p> </div>

Potential of Sentinel and high resolution EO data for monitoring nature protection in cities – the SeMoNa22 project

2021 ◽  
Author(s):  
Anna Iglseder ◽  
Markus Immitzer ◽  
Christoph Bauerhansl ◽  
Hannes Hoffert-Hösl ◽  
Klaus Kramer ◽  
...  
Keyword(s):  
Time Series ◽  
Nature Conservation ◽  
High Resolution ◽  
Satellite Data ◽  
Laser Scanning ◽  
Object Oriented ◽  
Earth Observation ◽  
Observation Data ◽  
Earth Observation Data ◽  
Sentinel 2

<p><span><span>At the end of the 1980s the Municipal Department for Environmental Protection of Vienna - MA 22 initiated a detailed biotope mapping on the basis of the Viennese nature conservation law. Approximately 40 % of Vienna’s city area were covered, however only 2 % of the densely populated areas. This biotope mapping was the basis for the biotope types mapping (2005-2011) and of </span></span><span><span>the</span></span><span><span> green areas monitoring (2005). An update of these surveys has been planned in order to meet the various requirements of urban nature conservation and the national and international, respectively, legal monitoring and reporting obligations.</span></span></p><p><span><span>Since the 1970s the municipality of Vienna has built up a comprehensive database and uses state-of-the-art methods for collecting geodata carrying out services for surveying, airborne imaging and laser-scanning. Currently systems for mobile mapping, oblique aerial photos and a surveying flight with a single photon LiDAR system are being implemented or prepared. Because of the numerous high-resolution data available within the municipality and limitations mainly in spatial resolution of satellite data, the City of Vienna saw no need or benefit in integrating satellite images until now.</span></span></p><p><span><span>However, satellite data are now available within the European Copernicus program, which have considerable potential for monitoring green spaces and biotope types due to their high temporal resolution and the large number of spectral channels and SAR data. For the first time, the Sentinel-1 mission offers a combination of high spatial resolution in Interferometric Wide Swath (IW) recording mode and high temporal coverage of up to four shots every 12 days in cross-polarization in the C-band. The Sentinel-2 satellites deliver multispectral data in 10 channels every 5 days with spatial resolutions of 10 or 20 m.</span></span></p><p><span><span>Within the SeMoNa22 project, various indicators are derived for the Vienna urban area (2015-2020) and used for object-oriented mapping and classification of biotope types and characterization of the green space:</span></span></p><ul><li> <p><span><span>Sentinel-1 data (→ time series on the annual cycles in the backscattering properties of the vegetation, phenology),</span></span></p> </li> <li> <p><span><span>Sentinel-2 data (→ multispectral time series via parameters for habitat classification / vegetation indices),</span></span></p> </li> <li> <p><span><span>High-resolution earth observation data (airborne laser scanning (ALS), image matching, orthophoto → various parameter describing the horizontal and vertical vegetation structure).</span></span></p> </li> </ul><p><span><span>The main goals of SeMoNa22 is to explore efficient and effective ways of knowing if, how and to what extent the data collected can form the basis and become an integrative part of urban conservation monitoring. For this purpose, combinations of different earth observation data (satellite- and aircraft- supported or terrestrial sensors) and existing structured fieldwork data collections (species mapping, soil parameters, meteorology) are examined by means of pixel- and object-oriented methods of remote sensing and image processing. The study is done for several test sites in Vienna covering different ecosystems. In this contribution the ongoing SeMoNa22 project will be presented and first results will be shown and discussed.</span></span></p>

scholarly journals Advances and limitations of using satellites to monitor cyanobacterial harmful algal blooms

2019 ◽  
Vol 31 ◽  
Author(s):  
Igor Ogashawara
Keyword(s):  
United States Of America ◽  
Harmful Algal Blooms ◽  
Algal Blooms ◽  
The United States ◽  
Observation Data ◽  
The Usa ◽  
Temporal And Spatial ◽  
Earth Observation Data ◽  
Remote Sensing Techniques ◽  
Cyanobacterial Harmful Algal Blooms

Abstract The use of satellites for monitoring forests is common and well-known practice. However, the operational remote monitoring of water quality from space is still under development. In the United States of America (USA), the use of this type of data is just now being applied to operationally monitor cyanobacterial harmful algal blooms (CHABs). This powerful tool can be used to generate temporal and spatial assessments of CHABs, however the validation of the retrieved information is still a challenge - especially in tropical and equatorial countries. This commentary discusses the advantages and challenges of current initiatives that use Earth Observation data for managing CHABs such as “Lake Erie’s HAB Bulletin” and “Project CYAN” - both in the USA. Additionally, it was also discussed the application of remote sensing techniques to monitor CHABs in Brazilian inland waters.

Sign in / Sign up

Export Citation Format

Share Document