Wildfires, hurricanes, floods and droughts we are now observing are direct consequences of global warming caused by unwise actions and negligence, and they are becoming a new normal for more and more communities. By organising the contest, CloudFerro would like to attract our attention to the alarming situation to motivate all the citizens to unite and take a better care  of our planet.

How to take part?

You need to submit an image of your choice generated on one of the platforms developed and operated by CloudFerro – CREODIAS, WEkEO or CODE-DE. The images should demonstrate the changes in natural environment as captured by satellites in recent years, such as wildfires, floods, droughts, deforestation, ice melting.

Not sure how to generate a beautiful image?

See a tutorial on visualizing EO data or join a free webinar on October 26^th where an expert will show you step by step how to do it using free software. Register for the webinar here.

The organizers are waiting for your works until 31 October 2021.

Go to the contest page for more details: https://bit.ly/2Y0Snkr

The post International CloudFerro contest “Seize the beauty of our planet” appeared first on EARSC.

The Sustainable Development Goals (SDGs) were adopted by the United Nations, with the aim of monitoring progress, informing policies and ensuring accountability. Earth Observation can support several targets and indicators in the UN SDG framework by providing accurate and reliable data on the state of natural resources, biodiversity, atmosphere, oceans, etc. This actionable information helps on the SDGs implementation role, monitoring, reporting and the facilitation and shaping of reporting methods, policy and tools.

Within the EARSC portal, we present a section identifying EO services from private sector providers that help support goals and targets and ultimately with the monitoring and reporting of the SDGs.

The eowiki/SDGs highlights cases where EO technologies are contributing to a set of current targets covering the social and economic dimensions of sustainable development where companies provide EO derived data and services and can make an important contribution towards the Agenda 2030 showing the potential of EO across the span of the social, economic, and environmental goals.

Want to know more how industry is responding to the SDGs targets covering the social and economic dimensions of sustainable development? Visit eowiki/SDGs

The post EO Services Industry Supporting the UN Agenda 2030 appeared first on EARSC.

Thursday 21 October 2021, 16h00-17h00 CEST

The System of Environmental Economic Accounting (SEEA) is the accepted international standard for environmental-economic accounting, providing a framework for statistics on the environment and its relationship with the economy. It brings together economic and environmental information in an internationally agreed set of standard concepts, definitions, classifications, accounting rules and tables to produce internationally comparable statistics.

In March 2021 the United Nations Statistical Commission adopted the SEEA Ecosystem Accounting (SEEA EA) as a new international statistical standard to integrate ecosystems and their services into national accounting, and to account for biodiversity and ecosystems in national economic planning and policy decision-making. This new international statistical framework brings a new paradigm shift in the appreciation and valuation of natural resources, allowing countries worldwide to use a common set of rules and methods to track changes in ecosystem assets (e.g. ecosystem extent and conditions) and related flow of services (i.e. ecosystem services), and to link ecosystem information to economic and development activities. The concept of Ecosystem Accounting provides also a new policy framework underpinning the development of ecosystem-related indicators from other international agreements including the CBD post-2020 global biodiversity framework.

The EU Biodiversity Strategy for 2030 recognises the value of ecosystem accounting and has plans to include natural capital accounting into European legislations.

Earth Observations is widely recognized as a major source of information to monitor the extent, condition and services of their ecosystems. The advent of dense EO data streams at appropriate scales combined with the emergence of digital technologies offer unprecedented opportunities for countries to efficiently monitor the extent and conditions of their ecosystems and implement their ecosystem accounting.

The webinar will provide an opportunity to meet three experts on the field:

• Representative from the United Nations presenting the System of Environmental Economic Accounting (SEEA) framework
• Representative from the European Environment Agency (EEA) to emphasise the green deal and the importance of natural capital accounting as one of the tools that needs to be developed to integrate biodiversity considerations into public and business decision making.
• Representative from the European Space Agency bridging the discussion on how earth observation is an enabling factor for ecosystem accounting and showcasing examples of ecosystem accounts including the changes in stocks of environmental assets.

In this EOcafe our host, Geoff SAWYER (EARSC’s Strategic Advisor and former Secretary General) together with our guests,

• Alessandra ALFIERI, United Nations Statistics Division (UNSD), Head of Environmental Economic Accounts Section.
• Jan Erik PETERSEN & Eva IVITS,European Environment Agency.
• Marc PAGANINI, European Space Agency (ESA), Directorate of Earth Observation Programmes.

will discuss the following:

• Earth Observation could help to assess the impacts on the state of the environment and on specific sectors of the economy. How can geospatial data and Earth Observation contribute to ecosystem accounting? What should be the kind of information needed to complement the ecosystem accounting?
• How in your opinion the “ecosystem accounting” supports the objectives of the Green Deal? how does impact into the EU Biodiversity Strategy for 2030?
• How does “ecosystem accounting” differ from the generic “ecosystem monitoring”?
• How do you see the way to engage with the private sector industry on this topic? How could industry partner with governments to create standardized accounting systems?
• “Natural capital accounting”, what does really means?
• What types of thematic topics are covered within the ecosystem accounting? And what kind of information does the “ecosystem accounting is looking for in for example air emissions, land accounts, agriculture?
• How can the EO service companies be involved in this business? What should EARSC do next to explore these opportunities?
• …

Registration: The webinar is open to ALL but priority will be given to EARSC members. Registration is free but compulsory. Please click on the following link to register.

Registration link

Please note this is a virtual event!

EOcafe is part of a series of EARSC meetings that offer timely, relevant, and practical information on a broad variety of topics related to the EO sector. Join us every two weeks to discuss and network while enjoying a cup of coffee with friends.

IMPORTANT NOTES!!!

• The use of a video camera is not mandatory but encouraged to facilitate better interaction among the attendees and the guest speaker(s).
• The EOcafe will stay open after 17:00 in case our guests want to continue the discussion.
• By registering for this event, you accept the terms and conditions (https://earsc.org/wp-content/uploads/2021/03/EARSC_Events_GDPR.pdf).

If you have any questions, and/or you want to know more about the EOcafe, and/or you want to share an idea about a future EOcafe, please contact Delphine (Delphine.Miramont@earsc.org).

The post EOcafe: Ecosystem Accounting, one step further to achieve the Green Deal objectives appeared first on EARSC.

ESA WorldCereal’s challenging task is to build an open-source classification system for seasonal crop mapping at the global scale. For every 10 m X 10 m pixel on Earth we need to be able to tell if this pixel is being cultivated or not and if yes, if it was irrigated and if in one of the main agricultural seasons wheat or maize was grown on that pixel.

Given the amount of potential approaches to tackle these tasks, a thorough benchmarking exercise was paramount. This exercise should provide objective arguments allowing us to define what works and what doesn’t and which ultimately should lead to what we believe is the best tradeoff between a scientifically sound yet technically feasible WorldCereal classification module. Here’s what we found.

MATCHING OUR NEEDS WITH THE AVAILABLE APPROACHES

If you are familiar with classification tasks based on remote sensing data, you for sure know how many different approaches are described in scientific literature. Some approaches like robust random forest classifiers have been around for a few decades, while others such as deep convolutional and recurrent neural networks have only come around more recently. And this only covers the classification algorithm itself, while many other choices need to be made as well. It was therefore important to define some specific questions that needed an answer first, in order to be able to develop a robust WorldCereal classification system later on. The most important ones are:

• Do we work with pixel-based or patch-based classifiers?
• Do we compute expert-derived input features or do we directly feed the original time series to the classifiers?
• Are we pursuing one global model or many regional models?
• How detailed can our classification nomenclature be without jeopardizing accuracy?

The table below outlines the algorithms that we tested, ranging from pixel-based random forest classifiers to patch-based convolutional-recurrent neural network.

Classification algorithms that were tested in the WorldCereal benchmarking exercise

CROP CALENDARS, AGRO-ECOLOGICAL ZONES AND BINARY CLASSIFIERS

Before benchmarking could start, some prerequisites were needed. The seasonal nature of the WorldCereal products requires a careful assessment of global crop calendars for wheat and maize. A major task has been the creation of such global pixel-based crop calendars covering all possible wheat and maize seasons, and combining the results in grouped agro-ecological zones (see figures below), thereby leveraging as much as possible existing sources of information, such as GEOGLAM Crop Monitor, FAO crop calendars and JRC-ASAP. Based on this information, the WorldCereal system exactly knows when to process which area to generate end-of-season crop type maps for our crops of interest.

Global pixel-based crop calendars for winter and summer cereals (SOS = start of season; EOS = end of season)

Agro-ecological zone groups, where grouping is based among others on the similarity of wheat and maize crop calendars

Next to the concepts of crop calendars and agro-ecological zones, we also decided to exclusively focus on binary classifiers in a hierarchical context. This means that the algorithms are trained to detect one class against all others. This ensures the algorithms can focus well on one particular task and avoids them being susceptible to complex classification nomenclatures that need to reflect the highly diverse global agricultural landscape.

The hierarchical nature of the WorldCereal classifiers

BENCHMARKING CRITERIA

In order to come up with the best possible approach to generate the WorldCereal products at global scale, we need objective criteria to compare different algorithms. These criteria can be organized in three general categories:

• Quality-related (e.g. how accurate are the results?)
• Performance-related (e.g. what computational resources are needed?)
• Requirements-related (e.g. how much and what kind of training data is required?)

A careful tradeoff needs to be made, as for example the theoretically ‘best’ algorithm might require an amount of training data that is not everywhere available. While assessing the above criteria, we keep constant track of robustness and transferability of the algorithms because only generalizable workflows will be capable of providing consistent results at the global scale, thereby mitigating the numerous blind spots where no training data is available.

REFERENCE DATA & INPUTS

WorldCereal’s reference data repository contains a growing collection of labeled points, polygons and maps, all derived from existing data sources yet harmonized to one common legend. This reference database forms an integral part of the WorldCereal system and will be opened up for exploitation and contributions from third parties.

The benchmarking results described here were conducted on >  100,000 reference samples. For each sample, a spatio-temporal input datastack of 640 m X 640 m covering 1,5 years of input data was extracted and stored for Sentinel-1 backscatter data, Sentinel-2 L2A reflectance values and ancillary data such as AgERA5 meteo inputs and the Copernicus 30 m DEM.

PIXEL-BASED LSTM ON INPUT TIME SERIES

Nowadays convolutional neural networks working on input patches taking into account spatial context seem to take the lead in scientific literature related to classification. According to our findings, however, there’s still quite some adverse effects of these kinds of algorithms especially in regions with few and only point-based training data. While the validation score was similar for both pixel-based as well as patch-based algorithms (F1 ~0.9 for cropland), large-scale tests clearly showed visual artefacts in some regions when using patch-based approaches. Moreover, pixel-based classifiers seemed to be better capable of capturing small borders between parcels which easily get smeared out in patch-based convolutional nets (see figure below). Our default approach is therefore to work on individual pixels, focusing on the rich temporal dimension. The modular nature of the system however allows us to switch to the convolutional architecture whenever we want, for example in the European context where LPIS datasets led to excellent results using convolutional nets.

Comparison of patch-based versus pixel-based neural networks for annual cropland detection. The arrows point to parcel borders being more correctly identified in the pixel-based approach.

Interestingly, we also found in general a slight advantage of using a LSTM network on input time series over the expert computation of derived input features followed by a random forest algorithm. This suggests that for a global approach – provided that sufficient amount of reference data are available – a deep neural network is able to find some important features in the temporal domain that our expert-derived manual feature computation might have overlooked.

GLOBALLY TRAINED, REGIONALLY FINETUNED

The grouping of agro-ecological zones according to their crop calendars led to a significant reduction of regions without any useful reference data. However, still many regions with limited to no data remained. This introduces a difficult challenge: training one globally applicable model would lead to too many compromises. Training many regional models on the other hand leaves many agro-ecological zones without a model due to lack of reference data and it also could lead to artefacts at the zone borders.

We decided to go for the best of two worlds and setup a hierarchical model approach. We train a global base model on all available reference data and progressively finetune the model in regional zones if sufficient reference data is available. This leaves us with at least a base model that can be applied anywhere, while having potentially locally finetuned models that inherit from the base model but are better adapted to local conditions. Another advantage of this approach is that the regional finetuning needs much less training data, as lower-level features have already been learned in the global base model which could benefit from all reference data.

Hierarchical model approach with one global base model and several locally finetuned AEZ models.

CROP TYPE DETECTORS

With wheat and maize being the focus crops during the WorldCereal project, we benchmarked the ability to train wheat and maize detectors. For maize, up to two seasons can take place but we did not find the need to train season-specific maize detectors. One generic maize detector can be applied to any potential maize season and we found a mean F1 score over all AEZ of 0.75.

The situation is very different for wheat. Depending on the seasonality in a region, either winter wheat, spring wheat or both can be grown. Especially aided by the concept of growing degree days which we use to normalize the input time series, winter cereals can more easily be distinguished from summer cereals. Hence we found that a generic wheat detector for both winter and summer seasons performed significantly worse than season-specific wheat detectors.

Furthermore, we benchmarked the ability to distinguish wheat from barley and rye. While it is often suggested that from a remote sensing perspective (and even in the field) these crops are hard to separate, we did find to our surprise that this was in fact possible to a reasonable degree. A combined winter cereals detector (wheat, barley and rye) for example reached a F1 score of 0.87, while a focused winter wheat detector still reached a F1 of 0.86. A large-scale validation is however planned to verify whether these findings hold or that they are attributed to some degree of inevitable overfitting. The results for the current spring wheat detector are somewhat inconclusive due to the low amount of reference data that is currently present in our data repository.

CONCLUSIONS

The global nature of the WorldCereal products revealed some interesting benchmarking results that were not always fully in line with the most recent scientific literature. We argue that the concepts of many excellent publications are not always sufficiently developed yet to be upscaled from a specialized study to an operational global mapping approach. We therefore need to make smart and well-informed design and algorithm choices to maximize our chances of success.

As usual, no one size fits all. Compromises need to be made, careful tradeoffs need to be chosen. But thanks to the rigorous benchmarking experiments that we carried out, we were able to settle down on quite a few long-standing crop mapping questions. Thanks to the modular nature of the WorldCereal system, all currently tested methods but also any future methods can be easily plugged in by the user.

And best of all? All our algorithms and methods are going to be open-sourced! We hope that this will stimulate the community to build upon our findings, and further improve our ability to map crops at a global scale. Meanwhile we’re gradually moving towards the global demonstration, where we’ll actually put our algorithms to work and generate global cropland, wheat and maize maps. Stay tuned!

The post VITO: MAPPING CROPS AT A GLOBAL SCALE! WHAT WORKS AND WHAT DOESN’T? appeared first on EARSC.

About a year ago, we introduced you to the H2020 e-shape project. Based on user need analysis, we started updating and developing agricultural services to monitor and improve sustainable agriculture in Europe. These services were demonstrated to and tested by end users over the past agricultural growing season. As we promised you more details on the outcomes, here’s already a story about crop calendar monitoring, one of the GEOGLAM initiatives to monitor the crop condition at a global scale.

THE IMPORTANCE OF CROP CALENDARS

Annual cropping systems are very dynamic by nature, where changes may occur in a very short time span. Obtaining these crop calendars at the parcel level is receiving more and more attention, and has now also been identified as an Essential Agricultural Variable by GEOGLAM, the Global Agricultural Monitoring Initiative.
This information can be used in a wide array of applications. Yield prediction models, for example, depend on the exact definition of the phenological stage of the crop, in order to properly assess for example the impact of a drought on the expected yield. Governmental bodies, as another example, want to use this information to derive if a cover crop was planted and how long it was present on the field. 
To this end, developing crop calendar extraction workflows has been a focal point within the e-shape project, in order to provide this information at the parcel level. Not only was the focus on the methodological developments, but also on how to make these service available on-demand, at the global scale. 

EXPLOITING THE ADVANTAGE OF TIME SERIES

High-resolution satellites like Sentinel-1 and Sentinel-2 offer a tremendous wealth of data, with their frequent overpass allowing to asses the current state of the agricultural fields at a sub-weekly scale. These time series offer a big potential for monitoring and detecting what is happening on the field. 

Specific phenological stadia or field actions can be picked-up by these time series. Crop calendar events such as crop harvest or emergence, can result in an abrupt change of the spectral signature (Fig. 1). Although you could guess when such a specific event roughly took place, just by looking at the evolution in time, it is difficult to pin-point an exact date on it. 
So, how can we turn these satellite time series into useful information to allow an accurate determination of a crop calendar event?

Well, let’s take a look at how it can be done with a concrete example, namely the determination of the harvest date.
As the harvest can be manifested in many different forms, it was defined in this case as the removal of above-ground biomass for annual crops. The first step is to find suitable satellite variables that are strongly impacted by the harvest. 
In this case, a combination of both the fAPAR derived from Sentinel-2 and the VH/VV backscatter ratio of Sentinel-1 was selected (Fig. 1). 
Both variables are found to be sensitive to crop harvest events in a different way. 
The optical based fAPAR can give some info on the biophysical change of the crop, while the SAR-based VH/VV is sensitive to the crop structural change at harvest.
Furthermore, the VH/VV is not impeded by clouds and can give valid data at a regular basis. In the case of the fAPAR, the problem of clouds was resolved since the CropSAR algorithm was used to fill the cloud-induced gaps.

Fig. 1: Time series of used indices for harvest detection for a sugar beet field in Italy. for the VH/VV ratio time series for both the ascending orbit (ro117) as for the descending orbit are illustrated (ro95). The red line shows the actual harvest of the crop. As can be notices both the VH/VV and fAPAR time series show some specific temporal behavior around harvest.

In order to go from the time series of the indices to an exact harvest data, the use of some innovative technologies like neural networks come into play. A neural network was trained in such a way that it provides the probability of a harvest event occurring in a window of 5 consecutive observations. These probabilities are used to make the final harvest date estimation.
Figure 2 illustrates an example of the harvest probabilities resulting from the field on Figure 1.
As can be noticed, the harvest probability is nearly zero outside the harvest period and rises clearly around the harvest period. Furthermore, the model is also able to recognize small harvest events for some catch crops outside the main growing season. 

Fig. 2: Time series of the harvest probabilities obtained for the field on Figure 1. The harvest probabilities are predicted at a 5-daily frequency for both VH/VV backscatter data originating from an ascending (ro117) and descending orbit (ro95) and by using the corresponding fAPAR values at the same dates.

But how accurate can we actually predict the crop harvest date?
Based on some additional validation efforts on fields in Belgium, Italy and Greece, the harvest date could generally be estimated within 5-6 days from the actual harvest date. 
A more extensive validation will be conducted across different agricultural areas and crop types to further check the prediction accuracy and to assess its robustness. 

Fig. 3:  Left: Predicted crop harvest dates in 2020 for the main growing season for a region in Belgium.
Right: The corresponding crop types that were analyzed. Despite different crop types that were cultivated in this area, the harvest prediction matches quite good with the normal harvest period for the different crop types. 

ENABLING A GLOBAL SERVICE

Developing a method to accurately determine the harvest date is one thing, making sure that this method is available as a service to the wider community is another. To this end, additional efforts were undertaken, ensuring a robust and global service. 

Many different aspects need to be considered in this exercise, from how to host the service, to where to get the right EO-data from. As pre-calculating the harvest dates on a global scale would be too much of a task, an on-demand web service is most appropriate. For this purpose, we use openEO, which provides a standard API to simplify big EO data processing. On top, a Jupyter Notebook was created to ensure an easy use of the service, even for the non-experts.

Next on the agenda: the expansion of the number of crop calendar events (crop emergence, bare soil exposure) available as a service, as well as the evaluation of the usefulness of these services for a number of user groups.
We’ll keep you posted!

The post VITO: WHAT HAPPENS ON THE FIELDS? MONITORING THE CROP CALENDARS appeared first on EARSC.

The Earth Observation Downstream services industry is a cutting-edge and fast moving sector for which innovation is key to provide new products and services. As a result, research is very important for the development of the business and its competitiveness.

Horizon Europe is the European Union research and innovation framework programme with a value of €95, 5 billion for the period 2021-2027. Renewed every seven years, the programme was previously known as “Horizon 2020”. Aligned with the ambitious objectives of the European Green Deal, Horizon Europe will contribute to achieve a more sustainable and digital Europe. On 15th June 2021, the European Commission adopted the main work programme of Horizon Europe for the period 2021-2022[1]. The Commission is currently working on the first drafting phase of Work Programme 2023-2024.

A good understanding of the structure of Horizon Europe is necessary to foresee the opportunities for the EO sector. First, it should be recalled that Horizon Europe has three main pillars: Excellent science (Pillar 1), Global challenges and European Industrial Competitiveness (Pillar 2) and Innovative Europe (Pillar 3). Missions areas are actions across pillars intented to “achieve a bold and inspirational and measurable goal” in a certain timeframe with an impact for society and policy making. These missions are the following: Conquering cancer; Adaptation to climate change, including societal transformation; Healthy oceans, seas, coastal and inland waters; Climate-neutral and smart cities and Soil, health and food.

Under Pillar 2, the focus is on tackling global challenges and boosting the EU’s industrial competitiveness. This Pillar is composed of six clusters that are broken down into individual expected impacts:

• Health
• Culture, Creativity and Inclusive Society
• Civil Security for Society
• Digital, Industry and Space
• Climate, Energy and Mobility
• Food, Bioeconomy, Natural resources, Agriculture and Environment

Each cluster aims to deliver in different objectives, through a series of “Destinations” (technology sectors) described in the Work Programme. It is recommended to read the Destination’s description and visit the Tender’s portal to know more about the funding opportunities, the eligibility criteria and conditions.

During our EOafe dedicated to Horizon Europe, our speakers presented the funding opportunities offered by Cluster 4 (Digital, Industry and Space) and Cluster 6 (Food, Bioeconomy, Natural resources, Angriculture and Environment) more specifically.

Marjan Van Meerloo, Policy Officer at DG RTD, stressed that environmental observation (data and information) is of great value in assessing the state of the planet and delivering crucial information for the Green Deal. Environmental observation is cross cutting over many destinations and is complementary to other clusters, specifically Cluster 4. Destination 7 of Cluster 6 aims to ensure (better) accessible, interoperable, deployable or exploitable information, including decreasing in-situ gaps and ensuring availability. Also, the integration of earth/environmental information coming from different sources (space-based, airborne including drones, in-situ and citizens observations) with other relevant data to deliver input is necessary for shaping Cluster 6 policies. In this context, there is a strong link between this cluster and Copernicus, ESA’s Earth observation programme, GEO/EuroGEO and GEOSS.

In the Work Programme 2022 (Opening 28th October 2021 with a Deadline on 15th February 2022), the following calls will be of great interest for the EO downstream services industry:

• HORIZON-CL6-2022-GOVERNANCE-01-07: New technologies for acquiring in-situ observation datasets to address climate change effects (Innovation Actions –€20 million)
• HORIZON-CL6-2022-GOVERNANCE-01-08: Uptake and validation of citizen observations to complement authoritative measurement within the urban environment and boost related citizen engagement (Innovation Actions –€14 million)
• HORIZON-CL6-2022-GOVERNANCE-01-09: Environmental observations solutions contributing to meeting “One Health” challenges (Research and Innovation Actions -€10 million)

It is also worth adding that an “Infoday” session will be held at the end of October 2021 and more information is accessible by consulting the European Commission Factsheet on the Earth and Environmental observation.

Martina Sindelar, Policy Officer at DG DEFIS, thendeveloped the opportunities under Cluster 4 “Digital, Industry and Space”, which focuses more specifically on the EU approach to technology development. She recalled that for the first time in the EU Research and Innovation programmes, the use of Copernicus and EGNSS is at the core of Horizon Europe and many calls offer funding to reinforce EU capacity to access and use space. In more than 100 calls across all clusters, the mandatory use of Copernicus and EGNSS is foreseen “if projects use satellite-based earth observation, positioning, navigation and/or related timing data and services”.

Cluster 4 aims at leveraging on Copernicus and EGNSS to bring benefits for companies and citizens while fostering synergies between the two flagship programmes and supporting the Green Deal’s objectives. There are many calls under Cluster 4 where Earth observation plays a significant role. Here are a few examples:

• HORIZON-EUSPA-2022-SPACE-02-52

Public sector as Galileo and/or Copernicus user

• HORIZON-EUSPA-2022-SPACE-02-54

Copernicus downstream applications and the European Data Economy

• HORIZON-EUSPA-2022-SPACE-02-55

             Large-scale Copernicus data uptake with AI and HPC  

• HORIZON-EUSPA-2022-SPACE-02-56

             Designing space-based downstream applications with international partners

Furthermore, there are opportunities under the CASSINI initiative. Many tools offer support for companies developing applications using Copernicus and/or Galileo data by giving access to investment (Cassini Seed and Growth Funding Activity/ Matchmaking instruments) and supporting the development of the business (Cassini Business Accelerator, Cassini prizes).

Our discussion during the EOcafe emphasized the many opportunities across the different Clusters of Horizon Europe. There is no doubt that the Earth Observation Downstream services industry can benefit from the EU research and innovation programme, especially with calls under Cluster 4 and 6. We will look closely at the upcoming Horizon Europe calls to guide the companies and support them in their application.

[1] You can find here a previous EARSC Policy Blog about Horizon Europe Work Programme 2021-2022.

The post Geoff’s Blog: Horizon Europe – Opportunities for the EO downstream services sector appeared first on EARSC.

Thursday 7^th October 2021, 16:00-16:45 CEST

The Group on Earth Observations (GEO) is a partnership of governments and organizations envisioning a future whereby decisions for human-kind will be informed by timely, reliable, openly shared science-based environmental information underpinned by systematic Earth observations. GEO gathers together over 113 countries and their delegates are national representatives interested in Earth Observation and geospatial technologies.

GEO plays an important role in connecting the demand for sound and timely environmental information with the supply of data collected and made available by the GEO community. In doing so, GEO is working to build the Global Earth Observation System of Systems (GEOSS), a set of “coordinated, independent Earth observation, information and processing systems that interact and provide access to diverse information for a broad range of users in both public and private sectors”. GEOSS was designed to deliver the data and information necessary to increase our understanding of the Earth and improve global policy and decision-making abilities. 

As stated in the GEO Strategic Plan 2016-2025, GEO is a “flexible and agile forum” gathering many actors, such as governments, public sector agencies, UN bodies, academia and the private sector. EARSC is a participating member of GEO and works closely with the secretariat on various topics, but especially those connected with private sector engagement. In order to implement the Canberra Declaration’s elements related to the private sector, a Private Sector subgroup[1] is intented to engage with private sector’s stakeholders with a special focus on creating opportunities for small, medium and micro sized enterprises.

In the context of a rich global policy agenda in 2021 including the UN Framework Convention on Climate Change COP26, the Convention on Biological Diversity COP15, the UN Decade of Ocean Science for Sustainable Development and the UN Decade of Ecosystem Restoration, the GEO Week 2021 will present multidisciplinary activities of the GEO Work Programme. As it is highlighted in the GEO Strategic Plan, “Earth Observations are an indispensable component to measure and monitor our progress towards addressing societal challenges”. In that regard, the GEO Week will highlight how the use of Earth Observations contributes to these efforts.

On July 1st 2021, Ms Yana Gevorgyan was appointed as the new GEO Secretariat Director. According to previous declarations, her vision for GEO includes strengthening GEO’s core membership participation in the organization’s mission, the connections with GEO’s regional structures and multisectoral partnerships.

Our EOcafe will be a good opportunity to discuss further about the future of GEO, the involvement with the private sector and EARSC’s collaboration within the GEO community.

Join us in the EOcafe to hear more about the vision for the Group on Earth Observations and more specifically the relations with the private sector!

Our host Geoff Sawyer (EARSC Strategic Advisor and former Secretary General) will discuss with Ms Yana Gevorgyan, (GEO Secretariat Director)

Topics which could be addressed during this EOcafe include the following:

• What is the vision for GEO in the long-term?
• What will be the key missions of GEO in the upcoming years?
• How will GEO connect more with private stakeholders in the future?
• What tools will GEO use to create more opportunities for the small, medium and micro-sized companies?
• How can EARSC support GEO’s activities and missions?

Registration: The webinar is open to ALL but priority will be given to EARSC members. Registration is free but compulsory. Please click on the following link to register.

Registration link

Please note this is a virtual event!

EOcafe is part of a series of EARSC meetings that offer timely, relevant, and practical information on a broad variety of topics related to the EO sector. Join us every two weeks to discuss and network while enjoying a cup of coffee with friends.

IMPORTANT NOTES!!!

• The use of a video camera is not mandatory but encouraged to facilitate better interaction among the attendees and the guest speaker(s).
• The EOcafe will stay open after 17:00 in case our guests want to continue the discussion.
• By registering for this event, you accept the terms and conditions (https://earsc.org/wp-content/uploads/2021/03/EARSC_Events_GDPR.pdf).

If you have any questions, and/or you want to know more about the EOcafe, and/or you want to share an idea about a future EOcafe, please contact Delphine (Delphine.Miramont@earsc.org).

[1] https://earthobservations.org/documents/pb/me_202101/PB-19-13_Draft%20PS-SG%20Work%20Plan.pdf

The post EOcafe: The Group on Earth Observations (GEO) appeared first on EARSC.

Registration now open

A new six-week online course on Artificial Intelligence and Earth monitoring is now open for registration. The course showcases the wealth of Copernicus data that is now available and introduces new ways of working with this data using AI and machine learning techniques.  

Artificial intelligence (AI) is playing an increasingly important part in our daily lives, whether it is providing our personalised social media feeds, online shopping or streaming movie suggestions, or even the mapping apps that route us around traffic jams. On a bigger scale, AI is already having a major impact on healthcare, finance, farming and many other sectors and its influence is predicted to expand rapidly in the coming years. 

One area where there is considerable untapped potential for AI is in the field of Earth observation, where it can be used to help manage large datasets, find new insights in data  and generate new products and services. 

With this in mind, EUMETSAT, ECMWF, Mercator Ocean International and the EEA have joined up to develop a new massive open online course (MOOC) on AI and Earth monitoring. 

The idea for the course is to introduce participants to the wealth of Copernicus Earth observation data and the AI and machine learning techniques that can be used to work with it. 

The course provides a round-up of the latest developments in AI and Earth observation, and will help participants bridge the gap between Earth observation data and AI techniques and aims to drive innovative new uses of Copernicus data. 

What does the MOOC cover?

The MOOC will introduce participants to the Copernicus Programme and AI and machine learning (a subset of AI) with hands-on practical examples with ocean, atmosphere, terrestrial and climate data. Practical examples are hosted on the WEkEO online platform that provides easy access to all Copernicus environmental data.  

The course is structured across six weeks but it can be followed at the learners’ own pace. The first week will be an introduction to Copernicus data and services and the WEkEO platform. Then there will be a week on AI/machine learning techniques and this will then be followed by four themed weeks covering oceans, atmosphere, terrestrial and climate data. 

MOOC content will be hosted on the FutureLearn platform and consists of short interviews with leading machine learning  and science experts, and companies using machine learning techniques with Copernicus data. 

With more than 40 contributors, the course will give participants a new and timely overview of the latest advances and techniques in machine learning and Earth observation/monitoring.

Practical work – WEkEO and Jupyter notebooks

As well as video content there is also a strong hands-on element with the inclusion of a series of specially-developed Jupyter notebooks that will guide people through the process of working with Copernicus data and new and exciting machine learning algorithms. 

The notebooks are put together using Python and give examples of the different types of Copernicus data (ocean, atmosphere, land and climate) and machine learning algorithms.

To make it easier to follow the notebooks, they are accompanied by dedicated video tutorials that have been produced to explain the content of the notebooks. 

Caption: The WEkEO data viewer. The WEkEO online platform was developed by EUMETSAT, ECMWF, Mercator Ocean International and the EEA in support of the Copernicus Programme.

The notebooks and accompanying tutorials are hosted on the Copernicus WEkEO platform (www.wekeo.eu), which provides free access to all Copernicus environmental data. WEkEO is the EU Copernicus DIAS reference service for environmental data, virtual processing environments and skilled user support. 

Participants will register on WEkEO to get a free user account to run the notebooks online.  

Who has organised the MOOC?

The MOOC is funded by the Copernicus Programme and has been developed as a joint project with EUMETSAT, ECMWF, Mercator Ocean International and the EEA. These organisations also operate the Copernicus WEkEO platform.

Register for the course

Access WEkEO

Access the WEkEO data viewer

The post Artificial Intelligence for Earth Monitoring MOOC appeared first on EARSC.

GAF, the German Aerospace Center (DLR) in Neustrelitz and Antrix Corporation have a successful cooperation stretching back 25 years. In 1996, they signed agreements for the purpose of receiving Indian Earth observation data and distributing the data to European customers on an exclusive basis. That was the starting point for 25 years of successful cooperation and the acquisition of millions of scenes so far – and on into the future.

Neustrelitz, Germany, 28 September 2021

The cooperation between the GAF subsidiary Euromap GmbH, DLR and Antrix began in 1996 with the signing of various agreements. The purpose: to receive Indian Earth observation data and distribute this data to European customers on an exclusive basis. In order to handle the processing, storage and provision of the data, GAF formed the wholly owned subsidiary Euromap GmbH on the DLR campus in Neustrelitz. GAF and Euromap merged in 2014.

“We are very proud of the now already 25 years of successful cooperation with our long-standing partners, the German Aerospace Center (DLR) and Antrix Corporation of the Indian Space Research Organisation (ISRO),” emphasised Dr. Sebastian Carl (Managing Director of GAF) during a meeting with Holger Maass, Department Head of the National Ground Segment of DLR at the DLR campus in Neustrelitz, Mecklenburg-Vorpommern.

Using the antennas and the operational experience at the DLR national satellite data receiving ground facility in Neustrelitz, the partners started with the reception of data from the Indian IRS-1C remote sensing satellite, which was launched in 1995. So far, the partnership has included six satellite missions. Thanks to both the ambitious Indian EO programme and the common understanding reached between Antrix and GAF, the partnership is also set to be expanded further. It has paved the way for the first commercial provision of remote sensing data in Europe for mapping, state planning and ecological research.

To date, GAF has acquired and archived more than 1.4 million scenes covering almost 40 billion square kilometres with medium, high or very-high resolution IRS optical satellite raw data. Furthermore, GAF has acquired roughly 26,000 scenes covering 38 billion square kilometres with low resolution data from the Oceansat-2 Ocean Colour Monitor. GAF has provided data products and related services to, for example, the Joint Research Center (JRC) of the European Commission and the European Space Agency (ESA) for the Copernicus and Earthnet programmes.

Holger Maass concludes, “GAF and DLR share spatial proximity and a professional alliance in Neustrelitz. It is an excellent example of a partnership between a scientific organisation and a private company. Over the 25 years of our cooperation, our technical progress has accelerated and the speed of the rollout of our remote sensing services has increased.”

Antrix Corporation expresses its deep appreciation regarding the way this partnership has been taken forward by GAF AG. Antrix is looking forward to continuing its association with GAF and DLR and wishes all the stakeholders a successful future.

This Press Release has about 3.167 characters.

About Antrix – India:

Antrix Corporation Limited (ACL), incorporated on 28 September 1992 (under the Companies Act, 1956) is a wholly owned Government of India company, under the administrative control of the Department of Space (DOS). Antrix is the commercial arm of Indian Space Research Organisation (ISRO) and is responsible for the promotion and commercial exploitation of the products and services resulting from the Indian Space Programme. The Company was awarded ‘MINIRATNA’ status in 2008.

About DLR – Germany:

The German Remote Sensing Data Center (DFD) is an institute of the German Aerospace Center (DLR). Together with the centre’s Remote Sensing Technology Institute (IMF), it comprises DLR’s Earth Observation Center (EOC), which coordinates DLR’s activities relating to Earth observation data from satellites and aircraft. DFD focuses on the reception, archiving, distribution and utilisation of data.

In addition to applied research, DFD has expertise in the development and operation of satellite ground systems.

About GAF AG – Germany:

GAF AG is an e-GEOS (Telespazio/ASI) company located in Munich and Neustrelitz, Germany. It is a leading geo-information company with an international reputation as a skilled provider of data, products and services in the fields of geo-information, spatial IT and consulting for private and public clients. As a result of a merger with its former subsidiary Euromap GmbH, GAF has become the exclusive supplier in Europe of optical Indian Remote Sensing data from several missions. The company’s archives contain systematic coverage of Europe and northern Africa from 1996 and onwards, and include satellite raw data from the high and medium resolution IRS missions IRS 1C, IRS-1D, Resourcesat-1, Resourcesat-2 and Cartosat-1. GAF is also specialised in the production of orthoimage mosaics and digital elevation models from various high and very-high resolution satellite missions.

To obtain more information, please contact:

The post GAF AG: 25 years of successful cooperation between GAF AG, DLR and Antrix appeared first on EARSC.

Every year, The Icon Group has a Student Essay Competitionwhere we reward students for an essay related to Earth Observation (EO) and a specific theme that is very close to The Icon Group’s values. This year’s topic was “Looking at the Environment”. This year’s winners have demonstrated strong knowledge of EO systems and showcase how the technology helps in real life situations.

Emmet McHugh Director of the Icon Group stated: “It is our second year organising this competition and we are thrilled about the increased interest from students in the competition. We created this competition to find talent to showcase it and we have accomplished just that. It is wonderful to see so many people care about the environment and be on the same mission to save it. We are also very happy with the interest from other organisations showing support for the competition such as Geoawesomeness and CAPIGI. We hope next year even more international students will apply!”

Our first place winner is Heather Needham from the University of Oxford. She will receive a 1000 euros prize for her Essay Forests as a causality of peace: The consequences of conflict cessation on forest loss within Colombia and protected areas. You find the full Essay here.

“I am delighted that my essay was selected to win the Icon Group Student Essay Competition 2021. I am looking forward to seeing my essay published in Geoawesomeness, and I would like to thank the Icon Group for the very generous prize“, said Heather.

Tessa Buckley from University of Reading is our Runner-up. She will receive 500 euros for her Essay, Looking at the Environment: Climate Change Impacts on the Barisal River Delta Mangroves, Bangladesh, 1988 to 2010. You can read her full essay here.

Tessa stated “It excites me that the recognition of my essay opens doors for starting more research, moving towards my aspiration of utilising looking at the environment remote sensing techniques as a crucial tool for climate education.”

You can learn more about our competition and this year’s winners at our upcoming webinar with CAPIGI: The Challenges of IO/GIS Skills; the case of The Icon Group

DATE: Thursday 4th of November

TIME: 15.30 (CET) – 17.00 / Dublin time 14.30 – 16.00 (UTC+1)

Register here

You can also contact us at media@icon.ie and get the latest news from us on Twitter and LinkedIn.

The post The Icon Group: Winners of the Icon Group Student Essay Competition 2021 appeared first on EARSC.