Skip to content

Sinergise has recently released eo-learn, an open-source framework to quickly and easily build Earth Observation (EO) applications. The framework allows to prototype and automate the processing of entire EO pipelines for large areas in few lines of Python code. Given the availability of large amounts of open data, machine learning (ML) algorithms can be seamlessly embedded into the processing pipeline to extract actionable information. The aim of eo-learn is to facilitate entry to the EO field for small and medium-size enterprises and research centres through exploitation of open-access satellite data.

Source: @peter_neff on Twitter
The availability of open EO data through the Copernicus and Landsat programs represents an unprecedented resource for many EO applications, ranging from land use and land cover (LULC) monitoring, crop monitoring and yield prediction, to disaster control, emergency services and humanitarian relief.

Given the large amount of high spatial resolution data at high revisit frequency, frameworks able to automatically extract complex patterns in such spatio-temporal data are required. In order to fully exploit the intrinsic information available in remote sensing data, Sinergise has built a set of tools to make prototyping of complex EO workflows as easy, fast, and accessible as possible. This set of tools is called eo-learn, an open-source Python framework which has been recently released and presented at the International Conference on Knowledge Discovery and Data Mining.

eo-learn acts as a bridge between Earth Observation/Remote Sensing and Python ecosystem for data science and ML. On one hand, its aim is to make entry to the field of remote sensing for non-experts easier. On the other, to bring the state-of-the-art tools for computer vision, ML, and deep learning existing in Python ecosystem to remote sensing experts.

Example of eo-learn pipeline of a global monitoring system for water-level of dams, reservoirs and lakes. Python code to build and run such pipeline has been open-sourced by Sinergise.

eo-learn is easy to use, its design modular, and encourages collaboration — sharing and reusing of specific tasks in a typical EO-value-extraction workflow, such as cloud masking, image co-registration, feature extraction, classification, etc. Everyone is free to use any of the available tasks and is encouraged to improve upon them, develop new ones and share them with the rest of the community. The library is shared under MIT license so it can be used for research and commercial purposes. Sinergise believes that there is so much of untapped potential in remote sensing, and tools to fully exploit such potential should be made available to anyone. Who knows, perhaps someone will save the Planet with it. Everyone wins. That being said, as an open-source project, contributions from the community are essential to its success, as well as the success of remote sensing and EO applications.

In a nutshell
eo-learn is available on the Python package manager and on Sentinel -Hub’s GitHub repository. The main advantage of eo-learn is the possibility of dealing with areas-of-interest (AOI) of any given size, e.g. at a country or continental level. The framework allows splitting the AOI into smaller patches that can be processed with limited computational resources and allows automation of the processing pipeline. eo-learn handles multi-temporal and multi-source remote sensing data, both in raster and vector format. A pipeline in eo-learn is defined as a connected acyclic graph of well-specified tasks to be performed on the data. Example tasks include data retrieval and rasterization, cloud and snow masking, co-registration, interpolation, feature manipulation, and geometric sampling. Tasks are modular and allow users to easily implement their own. The Python environment allows to use the many available packages for data analysis and ML, and quickly prototype and test EO applications. eo-learn supports parallelization of operations, such that the same workflow (e.g. data preparation for land cover classification) can be run in parallel for the smaller patches constituting the AOI. Logging and reporting allow to monitor and debug the execution of the processing pipeline.

Example applications
eo-learn was designed to provide the most common operations to process spatio-temporal data that would allow building of complete remote sensing applications. Examples of such applications developed by Sinergise include land use and land cover classification at a country level using ML, and the creation of a complete service for automatic global water-level monitoring, both using eo-learn and the Copernicus data. These examples are also available as open-source to inspire the development of new applications.

Example of a land cover classification pipeline using ML and deep learning algorithms using eo-learn. Python code to build and run such pipeline has been open-sourced by Sinergise.

Community
A key resource for the success of eo-learn is, of course, the community, both of remote sensing and ML experts. Anyone with interests in developing large-scale remote sensing applications using spatio-temporal satellite imagery is therefore warmly invited to test eo-learn, provide feedback, and possibly, contribute to it. Users all over the world have already contributed to the project with custom processing tasks and valuable feedback. The future of EO is looking as bright as ever.

“The development of eo-learn was funded by the Perceptive Sentinel European project. The project has received funding from European Union’s Horizon 2020 Research and Innovation Programme under the Grant Agreement 776115.”

Namibia is the most arid country in sub-Saharan Africa. Due to the high variability in rainfall there is widely fluctuating forage production from year-to-year.
Local farmers need to provide fodder for their herd till the next rainy season. Planning pro-actively is essential to be able to take necessary actions as soon as possible when conditions are deteriorating.
Here remote sensing comes into play; learn more about Remote Sensing for livestock management in Namibia!

An example of the 4 year NDVI anomaly product for the 1 to 10 May 2018 period for the Erongo region in Namibia. The green areas on the map indicate above-normal greenness and the red below-normal greenness values and support stakeholders in critical decision making. Infrastructure such as roads, towns and farm and conservancy boundaries are included in the regional products to aid users to identify their area of interest.

DATA TO SUPPORT CRITICAL DECISIONS

Most of Namibia’s rangelands know a short rainy season followed by a 6-9 month long dry season. Poor or postponed management actions are likely to result in animal losses, missed marketing opportunities and eventually lead to rangeland degradation such as the loss of desirable, perennial grazing plants and accelerated soil erosion.

Farmers, support agencies and policy makers need a system to provide reliable, accurate and timely information about the health of rangelands in order to support decision making with regards to animal production and rangeland management.
It gives the ability to work pro-actively, more efficiently and to intervene at critical times when for example a forage shortage threatens to occur.

ACQUIRE, ANALYSE & ACT
The Rangeland early warning and monitoring system makes use of satellite technology. Earth observation satellites like PROBA-V monitor the activity (greenness) of our planet’s vegetation every day. Thanks to this data we can obtain information about the current growing season and provide easy to interpret action maps to our land users, farmers and other stakeholders.

The information maps are made available through bi-weekly email service as well as an online portal, www.namibiarangelands.com.

Based on this information, land managers can easily keep track of the state and productivity of their rangelands which makes them more resilient to adverse climate change impacts such as severe droughts. They can:

follow how the season progresses timely notice if the trajectory is above or below normal act pro-actively improve decision making

SERVING OUR STAKEHOLDERS

If below normal greenness occurs for prolonged periods during the late growing season, low forage production are to be expected and farmers are forewarned to take timely action.

Current users of the data include:
- livestock and game farmers,
- communal conservancy support agencies
- agricultural bank of Namibia.

Currently the early warning system produces greenness (NDVI) anomaly maps in near real time on a decadal basis during the rainy season. The product range includes various anomaly products, as well as Vegetation Condition Index products.

Since 2018, three products were based on PROBA-V 333 m NDVI data, namely:

- Four year NDVI anomaly (this product was requested by farmers)
- One year NDVI anomaly
- Previous decad NDVI anomaly

On-going research developments include the modelling of annual herbaceous production (making use of PROBA-V data) and use of other earth observation approaches to monitor rangeland conditions, as well as the development of a mobile phone application for land users to assist with dry season fodder flow planning for their specific situation (Rangeland Fodder Flow App available on Play Store (Android) and App Store (iOS)) .

Source

We are excited to share this interesting case study that demonstrates how the European Earth Observation Programme “Copernicus” can trigger operational projects, which in turn can increase safety and provide useful information to decision makers and citizens.

Regional monitoring of Toscana
The case involves a collaboration of three different entities: the Regione Toscana, the University of Florence, and TRE ALTAMIRA, our EO value-added service company. The group is working together to make surface deformation data that is gathered from space, into a unique and reliable data source for a decision-support system for civil protection at regional scale.

The service. In 2016, TRE ALTAMIRA and The Earth Science Department (DST) of the University of Florence were requested by the Regional Government of Toscana (Italy) to provide a risk mapping service over the entire region using satellite radar data that would be updated on a regular basis. DST is an “expertise centre” for the Italian Civil Protection Department, having extensive experience in landslide mapping and monitoring, as well as in civil protection procedures.

The service takes advantage of Sentinel-1 imagery, provided by ESA, in the framework of the Copernicus programme. Sentinel-1 A and B are two twin satellite platforms mounting synthetic aperture radar (SAR) sensors specifically designed for ground deformation monitoring over large areas by means of interferometric data processing (InSAR).

By applying SqueeSAR™ – TRE ALTAMIRA’s proprietary InSAR algorithm – to Sentinel-1 archive images, our engineers have identified millions of measurement points over Tuscany, which are now used as a “virtual geodetic network” for measuring any surface displacement. The displacement time-series describing the motion of these “radar benchmarks” are regularly updated with every new satellite acquisition. InSAR bulletins highlighting areas affected by accelerations or, more generally, abrupt trend variations are then delivered to all regional municipalities. To this end, a new algorithm, designed specifically for this application, can automatically select all points exhibiting any anomalous behaviour. Finally, DST staff integrates InSAR data with other information layers (e.g. high resolution DTM, geological maps, landslide inventory data, etc.), and provides recommendations for risk mitigation.

GISAT teams up with crowd-sourcing experts to explore synergies with Earth Observation.

Recent years have brought tremendous advancements in the area of automated information extraction from Earth Observation (EO) imagery. Still, even the most advanced state-of-the-art algorithms often do not provide a satisfactory solution when based on imagery alone. The GAME.EO project explores the potential of the crowd-sourcing and gaming approaches to exploit distributed human intelligence networks for reference information gathering, in particular in areas where standard on-site collection campaigns are impossible or expensive. In the frame of the project, mobile-based tools will be developed and tested to mobilize volunteers to feed EO-based information workflows in a timely and accurate manner. The approach will be exemplified on the dedicated use case for informal settlements monitoring to demonstrate added-value and synergies with current machine-learning algorithms for the identification, delineation and further characterization of these areas. The developed framework and tools will be evaluated in cooperation with the World Bank Group users and stakeholders.

The GAME.EO project is funded by the European Space Agency (ESA) under the EO Science for Society Call. The project is led by GISAT, teaming with the International Institute for Applied Systems Analysis (IIASA) and Spatial Focus company, both from Austria, as subcontractors.

About GISAT:

GISAT is the geoinformation services company, providing actionable information based on Earth Observation technology. It focuses on integrated operational EO application in various expert domains supported by web-based exploration platforms for information analysis and assessment.
“web:“http://www.gisat.cz
email: gisat@gisat.cz
phone: +420 271741935

The first forum of the GMES & Africa Support Programme is a communication platform that encourages and promotes the exchanging of views among Earth Ob­servation service providers and end-users at the grass­roots level in Africa. The first forum is being co-organised by the African Union Commission and the Government of Gabon and will be held from 19th to 23rd November 2018 in Libreville, Ga­bon.

The theme of the first GMES and Africa Forum is “Unlock­ing the potential of Earth Observation as a key driver of Africa’s sustainable development”. Satellites are collecting huge volumes of high resolution images in real and/or near real time from space, and these have great potential to be utilised for different applications in the day-to-day activities of people in various sectors.

Hence, the forum addresses how to unlock the potential of Earth Observation data in order to support socio-eco­nomic transformation and the achievement of the Africa We Want, as articulated in Agenda 2063. It also dis­cusses what the GMES and Africa Support Programme delivers to user communities in Africa. About 250 representatives from Earth Observation service and data providers, academia, the private sector and research institutions, including grassroots level users and decision mak­ers, from 55 beneficiary African Countries and all over the world, are expected to attend the five-day event.

The GMES and Africa Programme is an Earth Observation Programme co-financed by the African Union Commission and the European Commission.

GAF AG has been providing consultancy services to the Programme since 2017 in the form of a technical assistance team consisting of long-term and short term experts.

For more information, click here.

Shortfalls in personnel and equipment can be eased by utlising the most efficient monitoring methods.

Abandoned cars at the Syria-Turley Border | Captured with WorldView-2
Europe faces intense migratory pressure and the European Commission recognises that it is unlikely to ease, even in the long term.

In fact, there is every chance the situation will get worse – there is no resolution in sight for many protracted conflicts in Africa and the Middle East, and the threat of climate change induced-displacement is growing. Affected populations might have decades in which to plan their retreat from rising sea levels, or just hours to flee a natural disaster, and the EU must be prepared for either situation.

We have emerged from the challenge of the 2015 migration wave having learnt some hard lessons. And now it’s time to move on from crisis mode, and the associated inefficiencies, to prepare our institutions for properly managing future human movements.

Currently there are persistent and significant gaps in the personnel and equipment available to the agencies mandated with managing the EU’s external borders – to the point that the European Commission believes they must be doubled in order to meet their current operational needs.
It is no surprise really. The external borders of the EU are vast and complicated. They traverse oceans, mountains, and rivers. But boats, trucks, and personnel will always leave gaps, and effective management requires the ability to monitor and react to action at any geographical location, which is why the European Border Surveillance System (EUROSUR) was created.

“EUROSUR fuses different streams of data in order to visualise the situation along the border, even where there are no resources on the ground,” says Dr. Melanie Rankl, Account Manager at European Space Imaging. “The aim is to prevent crime, irregular migration, and protect the lives of migrants.”
“Very high resolution optical satellite imagery is an especially powerful data stream for EUROSUR because relatively small objects such as cars and boats can be clearly identified. The satellites have the capacity to image even the most remote areas in near real-time – enabling the prompt gathering of new information and the verification of other intelligence sources.”

Satellite monitoring delivers cost-effective insights that enable resources to be deployed to the areas where they are most needed, maximizing operational efficiency.
“Particularly in emergency situations, satellite data can prove to be very valuable information” comments Sonia Antunes, Project Office at European Maritime Safety Agency (EMSA).
Compared to imagery from planes or drones, satellites offer logistical simplicity by cutting out the need for permits, air traffic control, equipment, and pilots. This is especially important when the area of the interest is in a crisis or conflict zone.
European Space Imaging has been reliably supplying very high resolution satellite imagery to EU earth observation programmes such as the Integrated Maritime Services (IMS) and COPERNICUS for over a decade, and is proud to offer a service that helps keep our borders secure and our citizens safe, all while protecting the lives of vulnerable people.

About European Space Imaging
European Space Imaging, a Munich based company has been downloading, processing, analysing and selling earth observation data since 2002. They are only European provider of true 30 cm resolution data and to own and operate their own multi mission ground station. With more than 15 years experience, European Space Imaging has developed a reputation for expert and personalised customer service and an unbeatable track record for supplying innovative solutions to meet the diverse projects and requirements of their customers.

The integration of natural hazard risk assessment into the urban development planning is demonstrated by IABG, in cooperation with the United Nations University. Monastir, Tunisia serves as a pilot city in this EU-funded project. The study contributes to the mitigation of future damages caused by urban flash floods and leads towards a sustainable urban planning.

(Web-based information platform for sustainable urban planning (Source: IABG)
Global megatrends such as increasing urbanization and the associated socio-economic change as well as climate change lead to an increased disaster risk worldwide. Recent heavy rainfall events with severe flooding in Tunisia and Mallorca in October 2018 dramatically bear witness to this trend. Loss of life and damages amounting to millions are the consequences. According to the latest figures published by the African-Arab Platform for Disaster Risk Reduction (DRR), annual losses only in Tunisia are estimated at up to 140 million USD. In particular, natural disasters such as drought, flooding and storms are increasing in frequency and intensity. Therefore, the assessment of current and future disaster risk is essential to support risk-based and preventive urban planning in order to strengthen the resilience of cities against flash floods and other natural hazards. The project “Urban Disaster Resilience Through Risk Assessment and Sustainable Planning (UD-RASP)”, which is carried out in Tunisia, aimed to improve urban resilience against multi-hazards as part of disaster prevention. A methodology was developed to integrate the results of a risk assessment into sustainable urban planning and thus reduce the urban disaster risk (DRR) and support the implementation of the UN Sendai Framework for Disaster Risk Reduction (2015-2030) as well as the UN Sustainable Development Goals 9 and 11. A process that can be applied locally, regionally and nationally, especially in North Africa, was developed in the project.

The project was carried out by the project partners IABG (project management and focus on remote sensing / geoinformatics / modelling), United Nations University – Institute EHS (scientific partner with focus on risk analysis and assessment, scenario analysis) and the city of Monastir (Tunisia) as a pilot city in the period January 2017 – October 2018, and co-financed by the European Commission / DG Echo.
The main objective of the project was to create the technical and methodological prerequisites for integrating risk assessment facing natural hazards and capacity building in risk management into the future urban planning process. For this purpose, a web-based platform was created which will be centrally accessible to stakeholders for the respective subject-related decision-making and will present all information relevant for planning purposes in a spatial context. Through a continuous participation of stakeholders and decision-makers of the Monastir region and higher authorities, the sustainable application and acceptance of the project was ensured by means of workshops and interviews. Due to the inhomogeneous and incomplete data situation, especially of digital, spatial data, an extensive data collection was carried out. Missing information was supplemented and processed with remote sensing methods. Based on a standardized geo-database, which also integrates the land use and development plan (Plan d’ Aménagement) obligatory for North Africa, further evaluations and analyses were realized: identification and localization of hazard prone areas (focus on urban flash floods and coastal erosion), analysis of exposure (population, infrastructure) as well as vulnerability in the affected urban areas. In the subsequent risk analysis, affected zones were identified and evaluated. To support sustainability in urban planning, a scenario analysis was applied to identify and visualize potential urban risk areas urban flash floods up to the year 2030. This task required a retrospective analysis to simulate future urban development (urban growth modelling). In addition to the simulation of precipitation events (e.g. 100-year flood event HQ100) to locate exposed areas, socio-economic data for the modelling of vulnerability were considered and included in the risk assessment as well as further local specific parameters, which could significantly influence future urban development (e.g. economic data, legal situation).

In the course of the project, all participants were sensitized to the complex issues of remote sensing and risk analysis and their possible applications in sustainable urban planning. Extensive workshops and training courses for municipal staff will ensure the practical application of the project results in the future.
Source

Deimos Imaging and its parent company UrtheCast announced that they have been awarded a multi-million Euro contract through a consortium led by Airbus Defence and Space – and also including Planet, IGN-France and space4environment – to provide a very large set of Earth Observation products and services to the European Commission and the European Space Agency (ESA), July 13.

The contract, known as VHR IMAGE 2018, involves the collection, processing and supply of cloud-free, seamless, very-high resolution imagery of six million square kilometers over 39 European countries. The data will feed the geo-information services with which European institutions and governments implement their environmental, land and crisis management policies. This dataset will be available to institutional users on European and national levels, and will serve a large range of applications such as the monitoring of biodiversity in riparian zones, coastal areas, risk and protected areas, and the update of Land Parcel Identification Systems.

Deimos Imaging provides market-leading quality control processes, technical knowledge and significant expertise to the consortium. Additionally, Deimos Imaging’s worldwide network of federated missions provides an exceptional capability to acquire very high-quality imagery with 1-meter or better resolution. Three of Deimos Imaging’s core partners, Beijing Space View Ltd., SI Imaging Service and Twenty First Century Aerospace Technology Co. Ltd., signed exclusive distribution agreements to contribute to this project through Deimos Imaging, providing significantly increased collection capabilities.

Donald Osborne, CEO of UrtheCast, commented, “We are pleased to enter into this contract as part of a consortium of world leaders in the field of Earth Observation. This serves not only as affirmation of the best-in-class nature of UrtheCast’s Earth Observation technologies, but also as an important transitional step as we continue to advance our ground-breaking UrtheDaily Constellation following our recent success in securing financing. The contract is one of the largest ever awarded to Deimos demonstrating that UrtheCast is in an excellent position to cement our role as clear leaders in the next generation of geospatial and geoanalytics technology and services.”

The VHR IMAGE 2018 dataset is part of the Copernicus Space Component Data Access (CSC-DA) service, financed by the European Union and operated by ESA, with the goal of granting to institutional users on a European and national level harmonised access to data for a large number of application domains such as land administration, forestry and environment, and security and public safety.
Source

On 8 and 9 October, the conference on “European land monitoring at its crossroads – opportunities and challenges”, organised under the auspices of the Austrian Presidency of the Council of the European Union, took place in Innsbruck

During the conference high-level representatives and decision makers from the European Environment Agency (EEA), the European Environment Information and Observation Network (EIONET), the European Space Agency (ESA), as well as international experts from the science domain and industry discussed the current state of the European public, scientific and industrial land monitoring capacities in face of increasing international competition.

Overall, the participants confirmed that the Copernicus Land Monitoring Service (CLMS) is providing essential information for effective environment and climate change related policy-making and planning by European, national, regional and municipal actors across the EU. The Copernicus programme is perceived worldwide as the most advanced Earth observation monitoring programme, creating leverage through a full systemic approach encompassing space and in situ dimensions and core information services as well as user uptake and commercialisation initiatives. Further, the full, free and open access to Copernicus services, and their long-term continuity over decades, ensure that European citizens, businesses and public authorities have guaranteed access to up-to-date, high-quality, authenticated information on the status, change, and trends in land cover and land use in their neighbourhood. In this context, the European land monitoring information products and services are triggering many national-level initiatives, and stimulating activities to assemble more complete, consistent and timely land monitoring information at all scales across Europe. To further strengthen the application capacity at regional level, it was considered important that EO space industry, amongst other via the instruments offered by the H2020 programme continues to get the opportunity to participate in the design and definition of future land monitoring service products. From a generic perspective, it was acknowledged that co-design and co-production, as is today the case via EEA’s Eionet network involvement in CLMS, is key to ensure trust in the produced geospatial information.
We again thank everyone who attended to the conference. Your participation and contribution was greatly appreciated and helped us provide a valuable event for all.

Please download post event resources here

Canberra, 27 September 2018 – Airbus and the Australian Space Agency (ASA) have signed a statement of intent confirming the European manufacturer’s commitment towards enhancing the capability and competitiveness of the country’s space sector.

The statement of intent, which is the first to be signed by the agency with an industry partner, includes Airbus’ support for space discovery, technology development and connectivity, and Science, Technology, Engineering and Mathematics (STEM) education in Australia.

Pierre Jaffre, President Asia-Pacific Airbus said: “Airbus aims to support projects and partnerships that contribute to growth and jobs in Australia, with a special focus on innovation and skills. We look forward to working with the Australian Space Agency, as well as the country’s academia, SMEs and start-ups, to develop Australia’s space sovereign capability. This includes nurturing and developing areas of strategic priority and technologies identified by an expert reference group panel.”

Dr Megan Clark AC, Head of the Australian Space Agency, said: “The Australian Space Agency is committed to a transparent and significant engagement with industry. Our purpose is to transform and grow the Australian space sector, and the broader use of space across the country’s economy, to inspire and deliver benefit to all Australians. We welcome Airbus’ choice of Australia for the world’s first operations of the Zephyr and Skynet 5 platforms. We also welcome Airbus’ efforts to actively support STEM education and training opportunities in Australia and internationally.”

Airbus and the Australian Space Agency have a shared interest in enhancing the competitiveness and capability of the Australian space industry. This includes the growing importance of commercialisation at every point along the space value-added chain, from research and development to high-tech manufacturing, transportation, satellite operations and consumer services based on satellite signals and data.

Airbus Defence and Space has a major presence in Australia. In 2011, the Royal Australian Air Force became the launch operator of the A330 Multi Role Tanker Transport (MRTT) which it designates locally as the KC-30A. Airbus has also been supplying earth observation satellite imagery to the Australian market for over 25 years, and the company’s fully integrated optical and radar satellite constellation enables daily acquisitions at high resolutions.

In 2016, a brand new purpose built satellite ground station was established in Adelaide to land Airbus Defence and Space’s Skynet secure military satellite communications. In June 2018, Airbus selected Wyndham airfield in Western Australia as the first flight base for its pioneering Zephyr solar-powered unmanned aircraft.

Airbus’ Space Systems business line designs, develops and operates major space systems around the world. Globally, commercial and institutional customers rely on the company’s leading space and technology solutions. This covers everything from the smallest electronic parts to the full in-orbit delivery of satellites, from very-high-resolution Earth observation instruments to unprecedented deep-space exploration missions, and from today’s most reliable telecommunication satellites to unfailing International Space Station operations.

Souce