ESA title

Category: Philab

Research fellow call: AI and EO for Climate

Posted on by nchimonides

Artificial Intelligence (AI) has the power to accelerate the global response to climate change and is the focus of a new research fellowship position call with the European Space Agency.

AI algorithms can systematically organise petabytes of data, uncover new insights and train models that predict change. This makes their application across the fields of Earth observation and climate research increasingly attractive, especially when the need to slow and adapt to negative future consequences is becoming ever more urgent.

The new two-year fellowship is a joint collaboration between two parts of ESA’s Directorate of Earth Observation Programme – the Climate Office, which oversees the development of key global climate satellite datasets (part of its Climate Change Initiative) and informs both the UNFCCC and the wider science community and the innovation-focussed Φ-lab, which connects partners from industry, national and international organisations and the third sector through its AI4EO initiative.

Read the full article on climate.esa.int.

ESA Φ-lab at ESRIN and Thales Alenia Space to work jointly on Earth observation innovation

Posted on by nchimonides

The ESA Director of Earth Observation has signed a letter of intent with Thales Alenia Space Italy, with the aim of collaborating on disruptive solutions for Earth observation (EO). Cognitive SAR, federated learning, hybrid computing for Artificial Intelligence (AI) at scale and the use of AI and EO in immersive reality are the core elements of the collaboration.

With its mission to accelerate the future of Earth observation through transformational innovation, Φ-lab continues to reinforce Europe’s global lead in the space science and commercial sectors. Partnerships are a key element of innovation, and Φ-lab has a strong track record of collaboration with a broad range of organisations.

Artificial Intelligence and new computing paradigms like neuromorphic, quantum, and edge computing, applied to both optical and radar EO data, are a strategic area of interest for both Φ-lab and Thales Alenia Space in Italy. Specific topics include end-to-end learning for SAR data, physically-based AI for extracting information from SAR data and enabling object detection, recognition and classification, collective intelligence and federated learning at the edge, and the use of AI and EO in immersive-reality scenarios such as AR/VR for satellite data and management.

The aim of the cooperation between Φ-lab and Thales Alenia Space Italy is to jointly explore such innovative technologies and their application to uses cases of significant interest to both entities. The expectation is that this will help ESA Φ-lab to focus on research that seeks to boost the innovation capabilities of the European EO industry, enabling the sector to gain an unrivalled competitive advantage in the face of fierce worldwide competition.

Massimo Comparini is SEVP of Observation, Exploration and Navigation at Thales Alenia Space: “There are both significant opportunities and sizeable challenges in harnessing the power of cutting-edge AI paradigms for Earth observation. We believe that Thales Alenia Space’s extensive industry experience, in combination with ESA Φ-lab’s unparalleled reputation for research, will create a platform for developing practical solutions to real-world problems in EO data handling.”

“With this agreement, ESA Φ-lab is creating another strategic partnership that will push the boundaries of Earth observation innovation, strengthening Europe’s unique competitive advantage through ground-breaking innovation,” added Giuseppe Borghi, the Head of Φ-lab and the main ESA contact for the collaboration. “We are extremely happy that an EO world leader like Thales Alenia Space has proactively identified synergies with ESA that will drive the success of this mutually beneficial initiative on transformative technologies.”

In commenting on the signing of the letter of intent, ESA’s Director of Earth Observation Programmes Simonetta Cheli emphasised the symbiotic nature of the undertaking: “Partnering with Thales Alenia Space in game-changing Earth observation research is yet another example of ESA advancing the European space sector through collaborative innovation. Our joint efforts will pool the know-how of both parties to yield what I’m certain will be remarkable breakthroughs in AI-driven information processing.”

To know more: ESA Φ-lab, Thales Alenia Space Italy

HiVE microsatellite constellation to provide early crop-health monitoring

Posted on by nchimonides

At a ceremony today at ESA’s ESRIN establishment, German company constellr signed a contract extension to design, develop and customer-validate its HiVE solution with ESA InCubed technical and financial support. Through the development of a microsatellite with an innovative Thermal Infrared (TIR) payload, HiVE will place advanced-warning data on crop stress at the fingertips of agribusiness companies, smart-farm operators and government policy makers.

Traditional approaches to measuring crop water-stress conditions include monitoring irrigation systems, indirect measurement of field temperatures, or aerial remote sensing of temperature via drones, all of which have drawbacks. Satellite remote sensing is available, but generally relies on optical imaging of leaf colour changes, meaning that at the time of detection irreversible crop damage has probably already occurred. Thermal infrared satellite measurements, which eliminate these drawbacks, are however becoming increasingly available.

constellr GmbH, a New Space start-up with offices in Freiburg and Brussels, saw an opportunity to provide immediate monitoring of crop health through specifically created TIR Earth observation satellites. By directly measuring leaf temperature from space, changes in plant transpiration can be spotted so that farmers can take remedial action days or weeks before critical crop deterioration ensues. constellr’s HiVE (High-resolution VEgetation monitoring) system will encompass a constellation of microsatellites with miniaturised TIR sensors in combination with a global ground-station-as-a-service infrastructure and cloud-based data platform. HiVE’s toolset will give both commercial and institutional customers actionable insights on crop conditions, helping to reduce the risk of crop loss and improve yield predictions.

The HiVE development is technically supported and partially funded by the ESA InCubed programme. At the contract extension signing today, constellr CTO Marius Bierdel commented on the significance of the investment: “Supported by the technical expertise and funding of InCubed, constellr is able to expedite the development of its first commercially operational satellite. This is a critical early part of our rapid infrastructure development cycle – a major driver for our competitiveness in the market and the key to bringing us a step closer to being a successful player in the space ecosystem.”

The German National Delegation to ESA was also represented at the meeting. “HiVE is the largest investment that we have made so far within InCubed,” explained Michael Nyenhuis, InCubed Programme Coordinator at the German Space Agency at DLR. “Given the current global issues of drought and food shortages, today’s launch of this development initiative is particularly timely, and we are sure that the final product will have a decisive role in optimising future irrigation management and biomass output.”

“This is a great example of how ESA can aid private-sector advances on solutions to climate problems and support a promising business initiative relevant to the agribusiness sector,” added ESA Director of Earth Observation Programmes Simonetta Cheli. “The technical support and business advice from ESA will undoubtedly provide an essential springboard for constellr in its journey to mission readiness and ultimately the delivery of this crucially important service.”

To know more: constellr, ESA InCubed, DLR

Strengthening InCubed’s role in commercial Earth observation

Posted on by nchimonides

Commercialisation is universally recognised as essential for the future prosperity of all aspects of the European space sector, and Earth observation is no exception. The ESA InCubed programme, a co-funding initiative that helps entrepreneurs bring their innovative ideas to market, has enjoyed enormous success since the launch of its first activity in 2018 and continues to make a prodigious contribution to commercial Earth observation. The InCubed portfolio includes around 60 activities, with an impressive €63 million invested so far.

At the upcoming ESA Council at Ministerial Level, Member States will have the possibility to further empower InCubed in its far-reaching efforts to foster commercial innovation. The programme proposal makes the case for a wider remit, including a set of new ‘Invest Actions’ designed to help boost the European Earth observation economy and reinforce relationships with the private investor community.

Read the full article on www.esa.int.

Φ-lab@ESRIN extends its AI innovation push through collaboration with Leonardo Labs

Posted on by nchimonides

The ESA Director of Earth Observation has signed a letter of intent with the Space Technologies Leonardo Lab (represented by Leonardo, Telespazio and e-GEOS) with a view to jointly developing space-based solutions for Earth observation (EO). After exploring areas of common interest, ESA Φ-lab and the Space Technologies Leonardo Lab will work together on projects that seek to boost the impact on the space sector of transformative technologies such as Artificial Intelligence, High-Performance Computing (HPC), quantum computing and Big Data.

The mission of Φ-lab@ESRIN is to accelerate the future of Earth observation through transformational innovation, thereby strengthening Europe’s world-leading competitiveness in the space sector. Partnerships are an essential building block of that mission, and Φ-lab has concluded a number of agreements with organisations, including venture capitalists, large and small companies and research centres, in order to increase the breadth and reach of its activities.

Two of the principal focus areas of innovation at Φ-lab are Artificial Intelligence (AI) and new computing paradigms like quantum, neuromorphic and edge computing, areas which are also central to the remit of a network of research laboratories set up by Italian company Leonardo. These Leonardo Labs include a Space Technologies research centre in Rome, run by Leonardo together with affiliates e-GEOS and Telespazio.

With such a degree of common interest between Φ-lab and the Space Technologies Leonardo Lab, the idea of a collaborative venture seemed like a natural fit. Leonardo Chief Technology and Innovation Officer Franco Ongaro explains: “The Leonardo Group has a consolidated relationship with ESA, further strengthened by the agreement signed with Φ-lab. The agreement with ESA allows us to pool our skills in areas such as AI, Big Data and quantum computing, combined with the computational capabilities of Leonardo’s HPC infrastructure, davinci-1, to increase the application of innovative methodologies in Earth observation and in the wider space context. The agreement is an expression of the vision of the company, which aims to strengthen the research activities carried out through the Leonardo Labs network – the company’s network of laboratories aimed at the digital sphere – and the consolidation of the open innovation activities that both represent determined factors of growth and competitiveness.”

“ESA Φ-lab is committed to pushing the boundaries of Earth Observation and how it is conceived, designed and implemented,” adds Simonetta Cheli, ESA Director of Earth observation. “The ultimate goal is to boost the innovation element of EO and thereby strengthen Europe’s world-leading competitiveness from both a scientific and commercial point of view. When we started interactions with what are now the Leonardo Labs, we immediately recognised synergies and complementarities that could greatly benefit this vision. We’re very pleased to have now reinforced our relationship with these major industry partners on topics of collaboration that are at the core of what we see as the future of EO.”

Details of the collaboration, which will also be able to draw on the wider Leonardo Labs network, are to be fleshed out as the parties continue their discussions. Nevertheless, a number of exciting topics of interest have already emerged. Neuromorphic Nets for example are AI architectures that better mimic the human brain and its neural networks in order to increase information processing efficiency and speed. Frugal Learning and Neural Ordinary Differential Equations are both types of AI model that are aimed at balancing computational performance and resources. All three of these areas potentially feed into the fourth topic, Onboard/Edge AI, which concerns the recent addition of AI processors to satellite payloads and the associated requirement for low-power/high performance computation. Last but certainly not least, Explainable/Trusted AI deals with the need to improve trust in Machine Learning models through predictability, robustness and explainability.

“The themes that we’ve jointly identified represent some of the most interesting development areas for the future of Earth observation,” comments Giuseppe Borghi, the Head of Φ-lab and the main ESA point of contact for the collaboration. “In exploring these transformative innovation areas together, Φ-lab and the Space Technologies Leonardo Lab intend to enhance the positive impact of such innovations on EO use cases. We expect the results of the partnership to then strengthen the growth of European EO, an ecosystem that is already generating world-leading solutions.”

Pierre Philippe Mathieu, the Head of the Φ-lab Explore Office, highlights the significance of the Leonardo Lab’s namesake: “AI is going through a global renaissance, and Leonardo Da Vinci was certainly one of the biggest icons of the Renaissance, bringing together as he did so many diverse fields of art and science with his creativity. This partnership between Leonardo Lab and ESA will strive to bring some of this Renaissance mindset to the inspiring world of AI4EO, gathering cross-disciplinary teams to develop innovative EO solutions which capitalise on the latest developments in AI techniques.”

To know more: ESA Φ-lab, Leonardo, Telespazio, e-GEOS

InCubed initiatives focus on data quality improvement and change monitoring

Posted on by nchimonides

Three activities launched under co-funding from the ESA InCubed programme respond to customer needs for improved information quality and precise measurement of trends and variations by exploiting Earth observation (EO) assets. Targeted sectors include agri-food, environmental protection, mining and oil and gas.

NEO (NL): SINERGI service

Earth observation data from optical and Synthetic Aperture Radar (SAR) sensors provides a wealth of information for an ever-increasing number of business applications, but there is often a lack of verification of such data from other sources. Dutch company NEO is developing SINERGI, a novel service that improves reliability by combining EO-derived change detection with crowd-sourced data and publicly available information.

NEO Chief Operating Officer Jan Erik Wien explains: “SINERGI represents a major step forward in the fusion of satellite and non-space data. It uses semantic integration technologies to add validation and additional context to EO-based information services, enabling customers to make informed and data-driven decisions in their operations and helping them to meet their ESG [Environmental, Social and Governance] commitments. Typical Big Data pools feeding into SINERGI might include local government records, planning permission documents or even social media posts.”

The intended customer segments for the service vary from governing authorities in areas such as construction, forestry law enforcement and environmental inspection, to private-sector businesses like insurance companies. SINERGI has now completed its main development and is being piloted with customers in the fields of building-related information and invasive plant species in waterways.

ABACO (IT): FIbEO product

Another example of fusing EO and ground-based data is FIbEO, a product conceived by the ABACO group and aimed at the food production industry. “We recognised a gap in the market in terms of information availability for guaranteeing food quality,” says ABACO Project Manager Marco Bonfigli. “For a given crop, agricultural players need to understand current biomass status, have access to intelligent yield estimates and be able to cross-check compliance with specifications. The FIbEO platform will provide such aggregated insight through ML [Machine Learning] algorithms that draw on both satellite imagery and historical data, ultimately helping growers, consortia and control bodies to create trustworthy food supply chains.”

The first target segment for FIbEO is viniculture, with collaboration currently ongoing with growers in Italy’s Chianti region. The first release of the platform will enable wineries not only to predict output but also to identify dead vines in the field in near-real time.

TRE Altamira (IT): BulletInSAR service

Turning once again to the topic of change detection through SAR sensing, Copernicus Sentinel-1 and other radar imaging constellations enable mm-accurate displacements of the Earth’s surface to be measured from space, providing invaluable information to operators in sectors such as mining, energy, civil engineering and civil protection agencies. TRE Altamira already provides customers with remote sensing ground-deformation information on their assets of interest, but the satellite data stream currently requires significant human processing in order to produce actionable end-user reports.

Feedback from TRE Altamira’s clients identified the requirement for faster response times, greater capacity for monitoring multiple assets and supplementary details on measurement reliability. BulletInSAR is the company’s solution, a tool that will deliver timely, scalable deformation reports by adopting an ML-based unsupervised process to cut out the human bottleneck.

Alessandro Ferretti is the company’s CEO: “Innovation and pushing the technology envelope have always been key elements of TRE Altamira’s identity, and BulletInSAR is no exception. As development gets underway, we’re really pitching for a superior user experience, a solution that will deliver fully automated reports using a cloud-hosted interface with tailored results screening. Co-funding from InCubed is of course a powerful enabler for TRE Altamira, helping to propel us forward as we take market-driven SAR ground-displacement reporting to the next level.”

ESA InCubed Officer Piera di Vito continues the theme: “All three of these activities are a perfect fit for InCubed’s DNA: supporting innovative ideas that spot a commercial need for AI-driven, EO-sourced data and insight. We are proud to see and help sustain such a competitive and dynamic ecosystem in the Earth observation domain, and the fact that SINERGI, FIbEO and BulletInSAR are at different stages in their development amply demonstrates the end-to-end nurturing that InCubed provides, from concept through to market readiness.”

To know more: SINERGI, FIbEO, BulletInSAR

Copernicus Sentinel-1A image courtesy of ESA/DLR Microwaves and Radar Institute/GFZ/e-GEOS/INGV–ESA SEOM INSARAP study, CC BY-SA 3.0 IGO

ESA team achievement prize awarded to Φ-sat-1 team

Posted on by nchimonides

The Φ-sat-1 team has been recognised in a major award that the Agency grants for achievements promoting the success and public reputation of ESA with the involvement of multiple Directorates. The team, which includes several researchers from Φ-lab, conceived, designed and built the Φ-sat-1 experiment to demonstrate Artificial Intelligence (AI) data processing capabilities onboard satellites.

Φ-sat-1 is the first ESA experiment exploring the potential of AI to improve the efficiency of sensor information streaming from Earth observation (EO) satellites. By filtering out clouds from optical imagery on the satellite itself, only the useful data is downlinked to ground stations, leading to significant bandwidth savings. The concept paves the way for a revolution in EO, as onboard AI processors will enable new services to be deployed quickly and cheaply by uploading applications directly to satellites.

The Peer Review Board for the ESA Team Achievement Award were impressed that the Φ-sat-1 team had transformed an idea into a completely new approach to onboard data processing in a very short time and under tight cost constraints, thanks to the combined efforts of members working across multiple ESA sites and Directorates.

“It was a stimulating experience for our researchers to be part of Φ-sat-1 and its pioneering development of AI-enabled EO satellites,” commented Pierre Philippe Mathieu, Head of the Explore Office. “Working fast in collaborative, interdisciplinary teams is part of our modus operandi at Φ-lab, and so it’s particularly pleasing that the review board recognised these aspects of the project.”

To know more: Φ-lab and Φ-sat

Irish minister commends InCubed contribution to entrepreneurial space sector

Posted on by nchimonides

During a visit yesterday to ESA’s ESRIN establishment, the Irish National Delegation to ESA took a tour of Φ-lab and discussed the importance of the ESA InCubed programme. The day’s schedule also included the signing of a contract for the InCubed-supported PROTELUM activity.

The Irish Delegation was received yesterday at ESRIN by Simonetta Cheli, Director of Earth Observation Programmes and head of the establishment. The visitors were given a tour of the site’s facilities and participated in a number of sessions covering ESA’s Earth observation (EO) programmes, Ireland’s space policy and technical discussions with the Earth Observation Directorate management team.

The tour featured a visit to Φ-lab, where Division Head Giuseppe Borghi explained the lab’s mission and highlighted some of its flagship programmes. Φ-lab’s focus on transformational innovation in commercial EO was a key theme of the day, with a number of managers from Irish space-sector businesses among the guests. Several of these companies have benefited directly from Φ-lab support with the co-funding of development activities through InCubed.

“Ireland has a strong tradition of entrepreneurship in many sectors and, as our industry representatives showed during the visit to ESRIN, New Space is no exception,” commented Damien English TD, Irish Minister of State for Business, Employment and Retail. “We continue to be impressed by the work that Φ-lab and its InCubed programme are doing in nurturing private-sector Research and Development in Earth observation. It is enabling Irish companies to realise their potential by accelerating the commercialisation of their products and services, which is a key deliverable highlighted in Ireland’s National Space Strategy for Enterprise.”

One such InCubed initiative is the PROTELUM activity, which was launched yesterday at a signing ceremony during the visit. Developed by Dublin-based Davra, PROTELUM is a management tool for the ongoing compliance assessment and monitoring of mining sites. The platform will cover the entire mining life cycle and will enable operators and regulators to continually identify safety risks, both underground and at the surface. The solution will apply analytical methods to data from sources such as industrial Internet of Things (IoT) sensors, EO satellites and drones in order to provide actionable insights and predictive modelling.

County Cork’s Treemetrics also attended the event and gave a brief overview of its Satforcert product in one of the technical sessions. Satforcert uses EO-derived data in combination with Global Navigation Satellite Systems (GNSS) to create more efficient and transparent processes for sustainable forest management certification. Currently enjoying its second stint of InCubed co-funding, the product has successfully completed end-user validation and is now being expanded to include features related to forest carbon storage and credits.

Other InCubed-supported companies present during the visit included mBryonics, Skytek, TechWorks Marine and Icon Geo.

Simonetta Cheli added: “It has been a pleasure to welcome the Irish Delegation today in what has been an extremely fruitful exchange of ideas on the current status and future direction of European Earth observation. The contribution from industry partners has been particularly stimulating, with for example Davra and Treemetrics both demonstrating how commercial EO can contribute to sustainable development by providing vital monitoring tools. We are therefore delighted to support the PROTELUM and Satforcert initiatives through the ESA InCubed programme.”

To know more: ESA InCubed, Davra, Treemetrics, mBryonics, Skytek, TechWorks Marine, Icon Geo

InCubed to be represented at ESA’s Industry Space Days 2022

Posted on by gaiamaggi

Michele Castorina, Head of the Φ-lab Invest Office, will talk about EO Market trends and present an overview of the ESA InCubed programme at the Industry Space Days (ISD) event, taking place on 28–29 September at ESA’s ESTEC establishment.

The ISD is an annual event organised by the ESA SME Office of the Directorate of Commercialisation, Industry and Procurement. Aimed at fostering cooperation between actors in the space sector, the gathering is free of charge and open to entities and investors from ESA Member States, Associate States, Cooperating States and the European Union. Participants can register here.

This year, Φ-lab’s Michele Castorina will be at the ISD to give attendees a flavour of the mission and activities of InCubed, including how companies, innovators and entrepreneurs can apply for co-funding of product/service development and commercialisation initiatives in the Earth observation sector. Michele will also be on hand for informal discussions with interested entities.

To know more: ISD 2022, ESA SME Office, InCubed

The AI effect: high-performing Sentinel-2 cloud mask goes global

Posted on by esaphilabincubed@2020_admin

After releasing its free and open-source cloud mask for Copernicus Sentinel-2 data, Estonian company KappaZeta is now working on enlarging the model from the Northern European summer season to year-round global coverage. Developed in conjunction with ESA Φ-lab, KappaMask is already outperforming similar approaches and uses Artificial Intelligence (AI) and active learning techniques to optimise automatic data labelling.

Although well established as a gold-standard provider of Earth observation (EO) insight, the data from Sentinel-2, like all optical satellite imagery, needs to have cloud and cloud-shadow areas identified and filtered out. Creating a cloud mask, effectively a stencil that removes unwanted data, is an essential step for virtually any EO application, and as ESA has shown with the Φ-sat-1 experiment, masking can be done effectively at source through onboard processing on the satellite. For Sentinel-2 users however, free, accurate and user-friendly cloud masks are currently few and far between. While masking is relatively simple when studying small areas, large stacks of imagery require automated pre-processing in order to provide timely, valid data to the user.

KappaZeta set out to provide an AI-powered, free-of-charge solution for Sentinel-2 data users worldwide. In an initiative funded by ESA Φ-lab, development commenced in 2020, with Phase 1 focused on Northern European summer-season conditions. Refining the mask was aided by the adoption of active learning, an approach which selects the highest impact samples for labelling. “We needed a reference dataset to train and test our model,” explains KappaZeta CEO Kaupo Voormansik. “Manual labelling of satellite imagery is a slow and expensive process, but as interest has grown in Deep Learning, the active learning methodology has proven to be a powerful tool for efficiently creating high-variety reference cloud masks using limited resources.”

Phase 1 was completed in August 2021, with the outcome published in a research paper and the initial version of KappaMask released to the public. The European model proved to be highly accurate and in fact performed better than comparable products, with particularly noteworthy results in the detection of cloud shadows and small fragmented clouds – a problematic area for some previous cloud masks.

The successful release of the Northern European summertime mask was followed by Phase 2, which aims to extend the model to the rest of the world over all seasons. This entails both improving the Phase-1 model architecture and obtaining a global reference dataset. For the latter, KappaZeta has used a combination of existing labelled datasets and its own labelling, the plan being to add 5000 newly segmented sub-tiles (each consisting of a 512 by 512 pixel area) to improve model accuracy. With an eye once again on efficient working, the team has picked the sub-tile locations based on Sentinel-2 data download statistics, thereby selecting according to user interest rather than aiming for a blanket global coverage.

Nicolas Longépé, Φ-lab data scientist and one of the ESA supervisors for KappaMask, recognises the effectiveness of the company’s research paradigm: “KappaZeta has used a smart approach for developing its cloud mask, with active learning and demand-based coverage helping to achieve the right trade-offs in terms of precision versus effort. Indeed the Phase-1 results have already shown KappaMask to be one of the most accurate free-to-use cloud masks, and once complete we fully expect the product to significantly enrich the analysis toolbox of Sentinel-2 data users.”

“We are also happy to support the project to see how KappaMask compares with other available solutions,” added Valentina Boccia of the ESA EO Ground Segment Department. “KappaZeta’s work convincingly illustrates how innovative AI techniques could be integrated into the mainstay of Sentinel-2 data processing.”

KappaMask is scheduled for release as a cloud-masking web service later this year. The reference dataset and source code will be freely available, and details of the model and the accuracy validation will be published in a forthcoming paper.

To know more: Sentinel-2, KappaZeta, Φ-lab Explore Office