ESA Φ-lab and World Food Programme launch joint innovation initiative

The EO & AI for SDGs Innovation Programme is now open for submissions. Launched by Φ-lab together with the World Food Programme Innovation Accelerator, the initiative aims to find Earth observation and Artificial Intelligence-based solutions to global hunger issues.

In a world where we produce enough food to feed everyone, there are 811 million people – or 10% of the global population – that still go to bed hungry every night. The COVID-19 pandemic, climate change and the complex social-economic landscape only serve to make the situation more dire, but as a counterpoint to this daunting backdrop, advances in space, satellite and Artificial Intelligence (AI) technologies have radically transformed humanity’s ability to observe and model the Earth’s systems.

This then begs the question of how Earth observation (EO) and AI can help solve global food crises. To find an answer, Φ-lab and the World Food Programme (WFP) Innovation Accelerator are joining forces to launch the EO & AI for SDGs Innovation Programme. The initiative will seek out cutting-edge innovations that use EO and AI technologies to address the challenges that WFP faces in its operations, while striving for business viability and industry leadership.

Read the full article at wfpinnovation

InCubed and SENER Aeroespacial’s EO-DDL development continues apace

Eight months after kick off, the EO-DDL payload data transmission system is currently undergoing prototype construction. Designed to meet the downlink requirements of tomorrow’s Earth observation satellites, the InCubed co-funded activity is well on the way to reaching a key Technology Readiness Level milestone.

With the rapid transformation of the Earth observation sector, satellites are increasingly being launched in large constellations with payloads of next-generation sensors producing considerable volumes of data. This presents significant challenges for data transmission, as the growth in spacecraft numbers leads to congestion of frequency bands and current hardware struggles to keep up with payload data-rate requirements.

ESA has proposed to alleviate the problem of overcrowded airwaves by moving the frequency range for sensor data from the X-band (8.025-8.4 GHz) to the K-band (25.5-27 GHz). While the K-band has the advantage of a greater bandwidth, it does bring its own challenges, such as requiring highly directional beams and complex signal modulation to cope with the infamous ‘rain fade’ effect.

Responding to these trends and technical requirements, SENER Aeroespacial is developing a bespoke, future-proof solution for satellite-to-ground-station data transmission: the Earth Observation Data DownLink system (EO-DDL). The EO-DDL consists of a Payload Data Transmitter (PDT) unit in tandem with a Dual Band Steerable Antenna (DBSA) assembly. The system can transmit in both X and K-band and will handle data rates of over 2.6 Gb/s per channel.

Building on a feasibility study it previously carried out for ESA, SENER is now working under an InCubed contract to develop the product further. “Collaborating on this InCubed activity is an exciting opportunity for SENER, as it will enable us to meet the increasing demands for high-throughput LEO-to-ground communication in institutional and commercial EO markets. We’re very happy to contribute to cross-fertilisation within ESA by extending the experience we’ve gained in the Science Programme to Earth observation. We’re also hoping to agree strategic partnerships as a result of the development, with several satellite manufacturers already showing interest in the proposed product line,” commented Jose Antonio Gomez, SENER Project Manager for the EO-DDL.

Andrea Modenini, ESA Technical Officer, was also keen to underline the importance of the activity: “Developing the EO-DDL represents a major step forward in satellite communication architecture. The dual-band capabilities will provide unprecedented flexibility, while the data-rate capacity of multiple gigabits per second will ensure that the data transmission module can tackle the expected traffic from big-data payloads.”

Since signing the contract in March of this year, product development has been progressing steadily. Following the definition and design phase, the team successfully passed the Preliminary Design Review and will hold the all-important Critical Design Review within the next few weeks. Meanwhile the prototype components are being produced and assembled in preparation for functional testing, with the activity expected to meet its final objective of achieving a significant level of technology readiness (TRL 6) during the second quarter of 2022.

To know more: SENER Aeroespacial, ESA Technology Readiness Levels, Satellite frequency bands

Sat4Flood completes InCubed activity to monitor levees and is now in commercialisation phase

Miramap, SkyGeo and 52impact have successfully completed the Sat4Flood activity as part of the InCubed programme, demonstrating the ability to estimate and visualise the risks of levee failure using Earth observation data. Sat4Flood is now rolling out the product to water safety organisations and has started to generate revenue.

Sat4Flood provides organisations responsible for water safety with a cost effective tool to better understand and manage levee failure risks globally. Dutch activity partners Miramap, SkyGeo and 52impact developed the Sat4Flood monitoring service by combining satellite high-resolution soil moisture data with Interferometric SAR deformation data and other Earth observation data sources.

Since completing the InCubed activity, the Sat4Flood activity partners have started engaging with potential customers and rolling out the product commercially, beginning with water authorities and international engineering companies. As a result Sat4Flood is expected to soon join the ranks of former InCubed activities that are generating revenue.

Sat4Flood Project Manager Yvette Pluijmers from Miramap said: ‘’By combining our companies’ extensive experience in monitoring levees, we have been able to develop state-of-the-art technologies that can identify and monitor levee failures. The consequences of levee failure are huge and so Sat4Flood provides users with a much-needed product to help prevent the devastating impacts of levee failures.’’

Sea level rise, extreme weather such as hurricanes, storms and drought events around the world continue to cause levee failures. This can lead to critical flood defence failures resulting in tragic losses of life and the devastation of large areas. Sat4Flood service helps water safety organisations to prevent such failures by providing continuous and reliable monitoring of levees. The Sat4Flood service web portal provides information in a user-friendly way and potential levee hazard alerts are pushed to service users in order to proactively mitigate the risk.

ESA’s InCubed programme supported the development, validation and commercial viability of Sat4Flood. This included identifying key target customers, gathering their feedbacks on levee failures identification and visualisation to validate the product, up to engaging with three potential customers in a proof of concept validation. The proof of concept was a great success, the engaged customers received three months of fully operational service, to which they provided very useful feedback to further fine-tune the product.

Amanda Regan, Head of the Φ-lab Invest Office and InCubed Programme Manager, said: ‘’Sat4Flood provides water safety organisations with an invaluable product to monitor levee failures. The InCubed team have enjoyed working with Miramap, SkyGeo and 52impact to develop Sat4Flood and we wish them all the best in their commercial roll-out.’’

The Sat4Flood InCubed activity commenced in September 2019 and was successfully concluded during the final review in March 2021. A major finding of the activity was a clear confirmation of the benefits that satellite based systems like Sat4Flood can provide to users with customisable levee monitoring information.

To know more: Sat4Flood InCubed activity, Sat4Flood website, Sat4Flood video pitch

HubCAP kicked-off as a new InCubed activity

HubCAP is a newly launched product developed by the Irish Icon Group with the support of ESA InCubed programme. This Open Source “Hands-Free Monitoring” platform for integration with existing workflows will answer the emerging needs from ELMS/CAP (environmental land management system/common agriculture policy), which represent a deep interest for the Icon Group.

HubCAP will be a highly flexible Application Platform for the agriculture and environmental sectors, based on Copernicus data and the SEN4CAP (Sentinels for Common Agriculture Policy) toolkit. It is developed by the Icon Group, a European leader in Earth imaging services and Ireland’s largest processor of imagery data.

The objective of this newly developed product is to align with a new paradigm in Land Cover and Use Determination using satellite imagery that has been enabled by the move from an artisanal process to an automated workflow-based provision of information. This will free up trained and capable technicians to provide analysis and information, rather than just simple image-based products, making the end user experience easier and more tailor-made.

The HubCAP service is conceived as three modules, each with a different starting point:

  1. IACS Module (integrated administration and control system)  – this will be the Paying Agency existing interface for CAP users, which they will customise to obtain HubCAP information
  2. EO Module – based upon results of other activities (SEN4CAP, DIAS (Data and Information Access Services))
  3. Bureau Module – based on a validated user concept and other activities (IACS)

The system is simple – because it includes a comprehensive API (Application Programming Interface) for monitoring via direct integration with existing administration systems, wide, verified, fully supported and very customer focused. It is wide thanks to an advanced dashboard for conducting bespoke ad-hoc local analyses, and it is verified since it offers and supports integrated ‘geo-photos’ and other forms of verification, where required.

Also, each classification ‘transaction’ is fully recorded and certified, showing the algorithm version and image sets used.

Elaine Doyle, Icon Group Product Manager said: “HubCAP is a robust and simple platform through which Government Agencies (especially CAP, non-CAP Paying Agencies and Environmental Agencies), and commercial users will be able to access the benefits of Sentinel data in a fully supported, legally recorded and compliant manner. We are very happy to count on ESA InCubed programme support to develop and commercialise it”.

Patrick Griffith, ESA Technical Officer, added: “The market of EO based CAP monitoring service capabilities is now really taking up pace. HubCAP comes with some innovative concepts and will lead to the enrichment and diversification of this key market for EO services.”

To know more: HubCAP Activity page, Icon Group, ESA InCubed programme

Φ-lab visiting professor advances the application of quantum computing in EO

Prof. Mihai Datcu, Visiting Professor at Φ-lab, has recently published a paper on the use of Quantum Computing in hyperspectral imaging, a compelling and topical area which is very much in line with the QC4EO initiative. The paper is included in the prestigious IEEE J-STARS journal and describes the first application of a quantum annealer in EO data analysis.

Quantum technologies are constantly evolving, with Quantum Computing (QC) enjoying fast-track development and considerable investment within the ICT industry. The Quantum Computing for Earth Observation (QC4EO) initiative is one of Φ-lab’s flagship programmes, aimed at exploring new computing paradigms to solve previously intractable data-analysis problems in EO.

Initially created as a collaborative venture between ESA and CERN, QC4EO now has a number of partners including DLR, ECMWF, ELLIS, LRZ and TUM. The initiative seeks to leverage the increasing power of quantum computers to explore new EO applications. Some of the potential of QC4EO lies in the intersection of EO problems with QC’s capabilities for optimising large-scale systems and Quantum Machine Learning (QML).

One of the most interesting applications is the processing of images from hyperspectral satellite sensors. The substantial volumes of data from the HYP image sensors are organised in a number of spectral bands, but not all the bands have the same information value for the classification of features such as land cover types. Prof. Datcu explains: “Selecting the most informative and trustworthy bands for each land-cover class is an important analysis step for high-accuracy classification tasks and saving internal storage space. Although there are conventional computational tools for this selection process, known as annealers, we knew from theoretical studies that quantum technologies have the potential to carry out the optimisation more efficiently. Until now though, there hasn’t been any real-world research in this area.”

Prof. Datcu’s work involved comparing the performance of quantum and traditional computational techniques in processing the hyperspectral data. First, a D-Wave Quantum Annealer (D-Wave QA) was benchmarked against a conventional annealer for the task of band selection. Next, the D-Wave QA-selected bands were split into the respective land-cover classes with both quantum and conventional classifiers.

The results were encouraging: “In the first part of the study, we proved that the D-Wave QA selected the appropriate bands and that the quantum methodology reduced both storage space and computational load,” Prof. Datcu comments. “In the case of the classifiers, the quantum versions even outperformed their conventional counterparts in most instances.”

Leading on from the success of the study, Prof. Datcu’s future work at QC4EO will develop the concept of a hybrid quantum-classical network for EO datasets, creating a tool that can operate across a range of dataset types and sizes.

When asked about this and other collaborative research he is working on at ESA, Prof. Datcu is decidedly enthusiastic: “Φ-lab is a fantastic opportunity to study interdisciplinary, highly complex EO activities such as mission design, remote sensing, environmental parameter retrieval and the interpretation of calibrated results. I see my job as putting together a new vision of AI4EO [Artificial Intelligence for Earth Observation], and inevitably the promising resources of quantum computing will play a major part in that.”

The full paper, A Quantum Annealer for Subset Feature Selection and the Classification of Hyperspectral Images by Soronzonbold Otgonbaatar and Mihai Datcu, can be found here. Other recent papers co-authored by Prof. Datcu include:

  • S. Otgonbaatar and M. Datcu, Natural Embedding of the Stokes Parameters of Polarimetric Synthetic Aperture Radar Images in a Gate-Based Quantum Computer, in IEEE Transactions on Geoscience and Remote Sensing, DOI: 10.1109/TGRS.2021.3110056, downloadable here
  • S. Otgonbaatar and M. Datcu, Classification of Remote Sensing Images With Parameterised Quantum Gates, in IEEE Geoscience and Remote Sensing Letters, DOI: 10.1109/LGRS.2021.3108014

To know more: QC4EOΦ-lab Flagship Programmes

Living Planet Symposium 2022: time for abstracts

ESA’s next Living Planet Symposium is set to take place on 23–27 May 2022 in Bonn, Germany. In gearing up for this prestigious event, it’s now time to submit abstracts to ensure a much sought-after slot to present topics such as the latest scientific findings on our planet, novel Earth observing technologies and new opportunities emerging in the rapidly changing sector of Earth observation.

The deadline for abstract submission is 26 November 2021.

The Living Planet Symposia bring together scientists and researchers from all over the world to present and discuss the latest findings on Earth science and advances in Earth observation technologies. Moreover, these extraordinary events also offer unique forums for decision-makers to be better equipped with information, for partnerships to be forged and formalised, for space industries to join the conversation, for students to learn, and for all to explore the concepts of New Space such as the digital transformation and commercialisation.

Read the full article on www.esa.int

Deep Property by Ticinum Aerospace: InCubed support boosts an innovative AI-based service

Under the ESA InCubed programme, the Italian company Ticinum Aerospace will develop an innovative solution in the various areas of the insurance business (e.g. underwriting, risk modelling, etc.) by leveraging Deep Property. This AI-based service is capable to provide high-quality property data derived from geospatial sources in a cloud-based environment.

Ticinum Aerospace is a spinoff company from the University of Pavia, Italy, founded in 2014 by PhD students and PostDocs at the FabSpace Lab. Their expertise is in Artificial Intelligence (AI), machine learning, computer vision techniques and geospatial data processing.

Ticinum Aerospace aims to scale up a service called Deep Property using an AI-based approach to identify and record risk-relevant characteristics of individual buildings, such as the number of floors, the year of construction, the materials used, etc. This technology leverages big data derived from satellites, Earth observation techniques and other hi-tech sources (e.g. street-level images, smartphone pictures, etc.) to generate information layers that will reduce uncertainty in large-scale risk scenario evaluations.

The use of high-quality property data, generated in near-real-time, will enable insurance and risk modelling companies to enable their clients to improve risk mapping and more efficient property risk management. This will result in reduced losses and, at the same time, increasing competitiveness on the market. This concept originated in the risk estimation context, the generated property data, is coveted in other businesses, like real estate, energy, and smart cities.

The Deep Property development was kicked off in June 2021. All companies supported by the European Space Agency’s Investing in Industrial Innovation (InCubed) programme receive co-funding, technical and strategic support to further develop the service. Before the end of InCubed support in December 2022, Ticinum Aerospace primarily aims to develop new satellite data-based models, improving speed performances, and enlarging the pool of customers by better understanding their needs. During the development, Deep Property will be supported by two leading companies in the insurance context: Generali Global Corporate and Commercial, and Willis Tower Watson.

Gianni Cristian Iannelli, Ticinum Aerospace CEO and Head of Deep Property development team, said: “We are so glad for the opportunity InCubed programme is giving us, and we will do our best to meet the expectation that Deep Property is set to achieve success at global scale. For us as a group of engineers, ESA has always been a source of inspiration, and we are all excited to get their support in our next actions. Deep Property‘s mission is cutting the cost of risk uncertainties, especially against the effect of climate change. ESA will be a valuable partner in reaching our mission on making cities more resilient to natural disasters”.

Michele Castorina, ESA Technical Officer, also added: “More and more data from commercial Earth observation satellites is becoming available at prices that allows downstream market to flourish. Deep Property is exploiting the availability of this data through innovative machine learning algorithms for the insurance market, bringing value and innovation in a sector that is actively seeking to meet the challenges brought by the digital transformation. As ESA InCubed programme, we are more than happy to support this process. ”

To know more: Deep Property, Ticinum Aerospace, Willis Tower Watson, Willis Tower Watson Press Release, Generali, Generali Press Release

Φ-week 2021: looking back and looking ahead

With thousands of online participants and more key sessions than ever before, Φ-week 2021 has proven to be a great success. As the curtain comes down on the event, now is a good time to reflect on its significance, take a quick tour of some of the hugely rich content, and think about outcomes and aspirations.

“Φ-week has established itself as the essential barometer for gauging the current status and future direction of EO innovation – and the 2021 edition is no exception. The coming together of industry, academia, private investors and major institutions fosters a unique exchange of ideas that invigorates our sector and propels us forward” – Giuseppe Borghi, Head of the Φ-lab and member of the Φ-week organising committee.

This year’s Φ-week got off to a tantalising start, with ESA Director General Josef Aschbacher announcing a competition – promising funding worth a total combined value of €1 million – in the areas of cognitive cloud computing in space. Innovators, researchers and entrepreneurs looking to submit their proposals for the competition will have found a great deal to stir the imagination from the 17 main sessions and around 190 supplementary items throughout the week. Indeed Artificial Intelligence (AI) and advanced computing paradigms were frequently recurring topics, with dedicated key sessions and a number of side events devoted to the application of this area to EO.

There were over 3,800 registered attendees from 91 countries at Φ-week 2021. For Ville Meskus, another organising committee member, the gathering provides a vital stimulus for the sector: “Φ-week gives our growing community a unique opportunity to get a very quick, yet comprehensive, snapshot of the latest developments in space and digital technologies, along with their potential and strengths and weaknesses. From my conversations with participants, I know they benefit hugely from the discussions and diversity of material presented, leaving them brimming with inspiration.”

The event this year, now in its fourth edition, was focused on EO New Space, and the theme was covered comprehensively over the course of the five days. Key sessions took up the subjects of enabling technologies, European access to space and accelerating New Space uptake. Smallsats were also discussed in detail, including both ESA SCOUT and other EO missions based on CubeSat platforms.

Many of the side events were hosted by external organisations. Running throughout the week, these specialised sessions delved into an extremely broad range of EO-related subjects, including the Space App Camp, Rapid Action on COVID19 with EO (RACE), data quality, intellectual property and AI for InsurTech, to name but a few.

The e-exhibitions and e-posters mirrored the themes of the key sessions, with around 150 organisations displaying their wares to the virtual audience. Attendees expressed their appreciation at the chance to network, chat via instant messaging and even organise individual video calls with exhibitors.

Looking to the future, Head of the Φ-lab Explore Office Pierre Philippe Mathieu hopes that Φ-week will also attract some new players to the scene, both in terms of careers and the funding competition: “As we’ve seen this week, space is an enthralling and promising career option, and in fact we have positions open in Φ-lab for Research Fellows to explore areas such as AI, the Internet of Things and Quantum Computing for EO. The competition announcement, which is particularly close to our hearts in Φ-lab, will undoubtedly engender a host of fresh ideas for exploring how cognitive cloud computing in space can help shape the new generation of software-defined missions. By next year’s Φ-week, we’ll know who has risen to the Director General’s challenge and whose concepts have won the sought-after funding.”

To know more: Φ-week, ideas.esa.int, jobs.esa.int, Contact Φ-lab

Calling all Sentinel-2 data users: volunteers required for product optimisation

As part of its InCubed co-funded MSCM initiative, Aerospacelab is currently looking for input from users of Sentinel-2 products in order to respond to market needs and improve downstream solutions.

The Multispectral Companion Mission (MSCM) is a constellation currently under development and aimed at supplementing Copernicus Earth observation products with small multispectral satellites, giving rise to high-quality, daily-coverage data sets which are strongly complementary to Sentinel-2 data. Belgian company Aerospacelab is developing and deploying an In-Orbit Demonstrator (IOD) for MSCM in an activity launched in February of this year and supported by ESA’s InCubed programme. The new data products emerging from MSCM, mainly characterised by a high temporal sampling rate, will allow current Sentinel-2-based models to be enhanced and will also unlock new use cases in the fields of precision agriculture, food security and environmental monitoring.

To ensure that its product planning is suitably matched to the needs of the user community, Aerospacelab is seeking collaboration from Sentinel-2 users. Participating entities will be asked to complete short surveys and tests covering topics such as image quality requirements and data access. The respondents will then have access to the resulting report, which will summarise current end-user market trends.

Taking part in this market information exercise will give organisations the opportunity to shape the path of the development activity, as the MSCM constellation will be tailored to the input received from key users. Participants will also have free access to data acquired during the Beta in-orbit testing phase.

To take part in the user group activities, please contact cecile.renaud@aerospacelab.be.

To know more: Aerospacelab, Sentinel-2

Φ-week 2021: artificial intelligence and quantum computing

In three key sessions today, the Φ-week event dealt with the real nitty-gritty of advanced computational methods in Earth observation. Contributors discussed Artificial Intelligence for Earth Observation and Science (AI4EO and AI4SCIENCE), along with the emerging potential of quantum computing.

This morning’s session was entitled ‘AI4EO – Learning from Earth Observation Data to Understand Our Planet’. In summing up the role of Artificial Intelligence (AI), session co-chair Pierre Philippe Mathieu (Head of the Φ-lab Explore Office) gave a simple definition: “When AI meets Big Data from space – that’s where the magic happens.” He went on to describe just why AI is becoming such an essential tool: “Classical methods for information retrieval are now reaching their limits as a result of the volume and variety of data generated. AI offers a completely new view of acquired data, but also automates and accelerates data insight. One of the main aims of the session is to illustrate how to deliver the maximum value from the marriage of AI and EO data, while highlighting the limitations of the technology.”

Adopting AI methods is not without its challenges, and Φ-lab visiting professor Begüm Demir kicked off the session with a talk on the issues surrounding label noise in the training of Deep Learning algorithms. The presentation included proposals for identifying and reducing the impact of noisy image labels in land-cover annotations. The question of uncertainty was also taken up in talks on Machine Learning (ML) in climate change prediction and spatial mapping, while human development featured strongly in presentations on slum improvements, urban settlement and food security.

A feature of AI4EO which is central to the aims of the Φ-sat-1 experiment is filtering data directly on the satellite. A talk from Frontier Development Lab presented research on ML-driven unsupervised novelty detection which has, as Postdoctoral Research Fellow Valentina Zantedeschi from INRIA and University College London explained, already produced some promising results: “We’ve shown that unsupervised ML techniques improve the detection of relevant change while being less susceptible to noise than standard differencing methods. They also promise to reduce compute and memory requirements in terms of data processing and storage.”

“The broad range of talks has given an invaluable insight into the possibilities and hurdles associated with AI in EO,” commented the session’s other chair, ESA Research Fellow Rochelle Schneider. “I was particularly impressed by the diversity of our speakers and their shared passion for both innovation and pushing the boundaries of EO information processing.”

First up after lunch was the related topic of AI4SCIENCE. The session was chaired by ESA Open Science Platform Engineer Anca Anghelea: “AI is now showing enormous potential in helping us answer some fundamental geoscience questions. Machine Learning in particular can play a major role in rapid knowledge discovery by learning patterns and models from data.” With contributions from NASA and Microsoft as well as academia, the talks covered explainable AI and causal discovery, big Earth systems science, sustainability and seasonal forecasting.

Recent advances in quantum computing are expected to unleash unprecedented computing power in the near future for processing and analysing EO data, for example from Synthetic-Aperture Radar (SAR), multispectral and hyperspectral imaging. Following the launch of ESA QC4EO at last year’s Φ-week, the final session of the group showcased some of the work carried out in this field in the last twelve months. CERN presented both the status of its research in quantum computing and the associated shared experiences for EO and particle physics. Other institutions taking part included ECMWF and Oxford University, with the latter’s Timothy Palmer presenting the imaginatively titled ‘Quantum Computing for Earth Observations: the Good, the Bad and the Noisy’.

“Quantum computing and artificial intelligence are new digital technologies that can be combined to get better EO products, and get them faster,” said ESA Digital Technologies Engineer and session facilitator Bertrand Le Saux. “We need to develop and harness the power of Quantum Machine Learning for EO Big Data analytics and, as today’s speakers have shown, we’re now establishing the groundwork for exploring how the unique potency of quantum computing can be used for extracting information from EO data.”

To know more: Φ-week, ESA AI4EO, ESA QC4EO


Photo Copyright: IBM Research