Skip to content

The ESA program called EO - Science for Society sponsors projects to support the implementation of Earth Observations (EO) in a variety of industry sectors, by providing a roadmap to a best practice. Industry sectors so far covered by the ESA program include oil and gas (EO4OG), agro-insurance (EO4I), the mining of raw materials (EO4RM) and the currently ongoing Earth Observation for Arctic and Baltic shipping (EO4BAS).

During the execution of EO4BAS, maritime advisors, EO specialists and platform designers/developers from DNV, CGI and e-Geos will work closely with stakeholders in the shipping sector operating in the Baltic and Artic region to make EO user-friendly. EO4BAS aims to: 

  1. Map the needs in the shipping sector operating in the Baltic and Artic, for which the current and near future satellite technology and Earth observation products can provide a fit to purpose information.
  2. Define a roadmap to best practice usage of EO information products.
  3. Demonstrate accessibility and usability of fit to purpose EO information products through a DEMO platform. 

As of the end of April EO4BAS is nearing the completion of work package 1 (WP1), by identifying and consolidating the industry’s challenges, geoinformation requirements and needs. This was accomplished through stakeholder interviews, literature review and a workshop (held on the 22nd of March 2023, at the DNV headquarters in Høvik, Norway in a hybrid form).

With the approaching completion of WP 1, EO4BAS will soon enter work package 2 (WP2), which aims to identify mature EO-based information products responding to the identified challenges, needs and requirements of the industry. WP 2 will be led by DNV Barbara V. Scarnato, team lead and Principal Consultant/EO specialist. 

Further, WP3 will include a service mock-up, with development led by CGI and WP4 will include the development of a high-level best practice roadmap for the shipping industry sector, led by DNV. 


Keep an eye out on the EARSC best practice site where a project page for EO4BAS soon will be established, hosting the project's findings, updates, and news!

Barcelona, 13 December 2023

Original link: https://www.isardsat.cat/news/irrigation 

A new study by isardSAT and IRTA provides for the first time a method to classify irrigation systems (flood, sprinkler, drip) and not irrigated fields using remote sensing. This methodology, replicable to several agricultural areas, has mapped in Lleida (Spain) the ongoing modernization of the irrigation systems, which remained unseen within the available databases.

The study Classification of Different Irrigation Systems at Field Scale Using Time-Series of Remote Sensing Data offers a new approach that employs machine learning models (ML) that use time-series of remote sensing data in the Catalan region of Lleida (Spain). This methodology is replicable to other agricultural areas, and provides relevant information that can improve irrigation water management in the analysed sector. Such models have been able to distinguish different irrigation systems regardless of the crop types present in each field.

Map comparation of the irrigation systems declared by SIGPAC-DUN and isardSAT’s ResNet prediction. The ResNet results, in comparison to the SIGPAC-DUN data, show the current modernisation of the irrigation system (from flood irrigation to sprinkler) and the expansion of the drip irrigation in areas that were not irrigated before. IMAGE: isardSAT.

Different machine-learning algorithm models have been used for the study, along with remote sensing products from SMOS/SMAP, Sentinel-2 and Sentinel-3 satellites concerning evapotranspiration and soil mosture data. From the results obtained, maps of irrigation systems were created, delivering detailed information on the status and evolution of irrigation practices in an intensively cultivated region in Catalunya, Spain.

This machine-learning models have been trained with ground truth data from more than 300 fields across the area, collected during a field campaign in 2020. When compared to the field data, results from the ResNet model used show a high precision, and reveal some changes that were not registered in the official databases.

Results from the ResNet processing show a great precision compared to the field data. IMAGE: ResNet results (isardSAT).

Information about irrigation systems in use is difficult to gather, and it appears frequently outdated in the databases – when available. However, it is essential for irrigation districts in order to manage its water resources. Especially in the Mediterranean area, where climate change has extended and worsened drought periods.

Article citation:

G. Paolini, M. J. Escorihuela, O. Merlin, M. P. Sans and J. Bellvert, “Classification of Different Irrigation Systems at Field Scale Using Time-Series of Remote Sensing Data,” in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 15, pp. 10055-10072, 2022, doi: 10.1109/JSTARS.2022.3222884.

For further information, please contact: 

Lluís Bassa Tomàs 
Science CommunicatorisardSAT

Parc Tecnològic
Marie Curie, 8-14
08042 Barcelona, Catalunya
+34 93 350 55 08

 

Since Open Cosmos was founded, its mission has been clear - to simplify access to space in order to solve some of the world's biggest challenges. Today, the company is one of the fastest-growing space infrastructure providers in the sector, providing fully managed satellite missions which incorporate design, build, launch and operations. 

Reliable, cost effective and fast, Open Cosmos is making it easier than ever for customers to access data and insights from space to make better, more informed decisions on Earth.

Their end-to-end space mission capability can be used for all domains, including IoT technology, Earth Observation, Telecommunications and PNT (Positioning, Navigation, Timing).

January 3rd 2023 saw the successful launch of Menut, the second satellite of the Catalan NewSpace strategy. Menut is a 6U form factor satellite featuring a high resolution multispectral imager. The earth observation payload monitors seven bands, from RGB to 3 red edges plus Near InfraRed with a 4.75 Ground Sampling Distance (GSD at 500 km) and a 19.5km swath. The data received from Menut will help to improve spatial planning and allow the data users to better understand the effects of the climate crisis worldwide.

In the following 12 months, Open Cosmos plans to launch and operate another 5 satellites in the form factor range between 6U to 16U.

Combining satellite imagery and next gen AI

Some of the most significant developments for Open Cosmos have been their work on edge computing and AI applications - all of which are designed to automate the process of data collection and dissemination. The upcoming Phisat-2 mission with ESA, for example, will include six different AI applications ranging from sat to map to automatic vessel detection. Combining earth observation imagery with onboard applications means real time decision making can take place within the platform, removing the process of manual decision making on the ground and delivering only the valuable insights that the customer requires.

Similarly MANTIS (Mission and Agile Nanosatellite for Terrestrial Imagery Services) a compact 12U satellite which is due to be launched in October this year, will provide remote sensing capabilities for the monitoring of natural resources. MANTIS is particularly suitable for energy and mining applications which are predominantly found in remote and hostile regions.

MANTIS will use a high-resolution optical payload with onboard recognition and change detection algorithms to enable the processing of data on the ground using the latest machine learning techniques.

DataCosmos - turning data into actionable intelligence

Critical to driving the sector forward is the ability to see more than simply what the image on screen is telling us, by advancing the technologies which allow advanced insights to be drawn from data.

Open Cosmos’ innovative data platform, DataCosmos, is a powerful interface which brings together different types of satellite imagery, data from complementary sources, results from algorithms and a roster of applications to make satellite imagery useful and valuable. Among numerous other applications, DataCosmos offers tools allowing customers to monitor the direction of travel of lava flow after a volcanic eruption, identify dangerous oil spills near desalination plants or even detect algal bloom locations.

All DataCosmos functionalities are available through APIs and can be embedded into automated decision making workflows, with DataCosmos applications running in the background as soon as new data becomes available. This ensures customers are always working from the latest information, by integrating timely, actionable and scalable insights into their business-critical processes.

Open Constellation  - launching the world’s biggest mutualised constellation 

Despite advancements in both upstream satellite infrastructure development and downstream technology, there is often a bottleneck between the two. Either the budget needed to fund an entire constellation is cost prohibitive, or the data generated from one or two satellites cannot provide the revisit times needed to form a rich picture. A solution was required that allowed institutions, organisations and governments to benefit from increased regularity of data without the need to invest in complex satellite infrastructure. OpenConstellation, the flagship offering from Open Cosmos,  is a mutualised satellite infrastructure, comprising 25 earth observation satellites. Using this shared capacity reduces overall costs and increases access to better quality, more frequent data. With more satellites in orbit, more areas can be covered more frequently, giving partners of the OpenConstellation a greater global coverage.

Open Orbit - End to end mission management

Open Cosmos truly is a one-stop shop for every single aspect of satellite missions. Their extensive experience in managing entire missions, from concept design through to manufacture, test and launch allows customers to focus on mission output. Alongside this, they work collaboratively with customers to develop tailored payloads, customised to the needs of the mission requirement. 

High performance, reliable satellite infrastructure can be developed in months, tested and manufactured on site, launched from a host of global locations and operated by experienced engineers to deliver the data and insights that make a difference to those organisations looking to solve global challenges.

If you have an idea you’d like to get into orbit simply, quickly and cost effectively - contact Open Cosmos today.

E-mail: sales@open-cosmos.com

www.open-cosmos.com 

https://www.linkedin.com/company/opencosmos

Wasat has launched Irriget (www.irriget.com) – the EO service that provides growers with precise information on current crop water requirements. Based on the analysis of Sentinel-2, Sentinel-3 and meteorological data, it generates intuitive charts and maps facilitating the optimal irrigation decision-making.
A fusion of satellite thermal and optical data, and application of precise parameters for individual crops enables monitoring of plant water needs. Algorithms based on machine learning produce maps presenting the current condition of crops, actual evapotranspiration and water balance with 20 m resolution. For calculation of potential evapotranspiration, local meteorological data are merged with forecasts and modelled data, and all the processed data are resampled to a higher accuracy. The resulting information determine the optimal irrigation strategy. Irriget allows to indicate proper dates of irrigation and water doses that ensure optimal plant development. Farmers can check on a graph the right water dose that should be applied on a field with specific crop. There is a possibility to divide a field into narrow zones related to the actual operation of a reel irrigation system and to treat each strip independently. Farmers can save time and take full advantage of their irrigation equipment by watering crops with doses calculated on the basis of actual evapotranspiration and water balance. The choice of water quantities and periods of irrigation allows for the optimal coverage of plant needs and has a positive
impact on quantity and quality of yield.

Development of the service has been co-funded by the European Space Agency. Irriget has quickly received positive feedback from Polish growers who irrigate potatoes and other field crops. In January 2023 the organizers of Polagra Premiery International Agricultural Fair in Poznań awarded Irriget with the Gold Medal – the prize which goes to products that are distinguished by a high level of innovation and are appreciated by farmers and agronomists. Growers usually start with free testing of Irriget and most of them subsequently subscribe to the service. As of today, the complete set of functions is available only in Poland, but the work is underway to expand the geographic coverage of the service.

An IoT sensor is great for collecting data on the state of air quality from the moment it is deployed but that data tells us nothing about what happened previously to create the current environmental conditions. If data is to truly help us build more sustainable, safer, healthier and greener cities, we need technologies that enable us to understand what has happened in the past and predict how a situation might evolve in the future. It isn’t a lack of datasets standing in the way of doing this but rather knowing how to use the ones that already exist.
In Europe and around the world, initiatives such as the EU’s Climate-Neutral & Smart Cities mission, the Race to Zero and the Covenant of Mayors Climate-Adapt are helping to galvanise climate action but nobody is under-estimating the scale of the challenge. What these initiatives have in common is the need for constant monitoring of a city’s territory and environment to assess the current situation and check progress. Moreover, this monitoring needs to be put in context with information from decades past to gain the necessary deeper understanding.
This was the aim when developing the climate change adaptation and mitigation platform Latitudo 40, that allows cities to be constantly monitored. It uses raw data generated by earth observation satellites, combined with artificial intelligence (AI), to understand how the earth’s systems have changed and predict how they will evolve in the future. It is designed to provide a more sustainable and resilient approach to urban climate action. In our specialist field of satellite remote sensing, we see a lot of valuable data available, but cities are using only a small portion of it to support key decision-making. To change this, we combine data from satellites with data produced within the city and, through a fusion of the two, create information models that help inform urban planners where to invest money and resources when it comes to protecting and futureproofing their cities. A typical example is our dataset for estimating urban thermal comfort, which brings together information on urban heat island areas, tree canopy (or lack of it) and the age distribution of the resident population. A digital representation of a city can be created in a matter of hours
that quickly highlights and offers insight into key climate and sustainability issues.
Satellite technologies are now several decades old but, due to their complexity, have never reached a mainstream level of usage in the market. Image search and image processing requires specific skills and complex processing systems that aren’t typically available within cities. To make the best possible use of the information potential of these images, we have developed what we call “complexity simplification,” a cloud-based processing workflow that automates image search, analysis, and interpretation. Computer vision and AI algorithms complete the process by extracting the parameters of greatest interest to cities and presenting a simple representation of the evolution of the urban scenarios over time. 

Crucially, unlike the aforementioned IoT sensor, satellite imagery allows for a historical representation of the city, almost a time machine that facilitates an understanding of the starting- and end-point and what happened in between, as well as continuous and frequent monitoring into the future. 
Thanks to satellite imagery, we can easily understand whether there has been land
consumption and how much the relationship between green areas and urbanisation has changed; the state of urban green spaces and how they contribute to mitigating environmental phenomena; and what phenomena have triggered a specific event, such as a flood or the failure of urban infrastructure in the past, and activate the best monitoring systems to prevent them occurring in the future.
It’s one thing having the data and tools, though, and quite another ensuring they are
accessible to those who need them. If they are to be truly effective, they need to be embedded in the daily operations of urban planners and decision-makers just like spreadsheets and email.
This thinking underpinned the development of Latitudo 40, which we describe as “a digital information factory in the cloud”. It can be accessed by a standard web browser and the processing made available through APIs that allow easy integration with existing spatial information systems. No special knowledge of data processing and geospatial analysis technologies is required and analyses provide a representation of the city with an easy-to-understand map, graphs and automated reports. 
From this information, cities can set specific sustainability goals such as increasing green space per inhabitant, reducing the incidence of urban heat islands per inhabitant, and improving climate comfort in metropolitan suburbs. Every city can verify these goals and achievements via monitoring.
Our experience has made us realise that when it comes to data collection and reporting, city managers often allocate high-end budgets for consulting services that can stop with the creation of a static product. What’s needed going forward is a more agile approach facilitated by business models such as software-as-a-service (SaaS) and backed by real-time, accessible data and services. Only then will we be able to turn data into actionable information and use it to build more sustainable, resilient safer, healthier and greener cities.

Can you tell us a bit more about your company? 
 
Mallon Technology is a leading company in the field of Earth Observation (EO) and Geospatial application, providing innovative solutions to clients since its establishment in 1995. Our headquarters are in Cookstown (Northern Ireland) and Dublin, with additional customer sites located throughout Ireland. We pride ourselves on being industry experts in EO business process solutions, offering a range of services that improve the analysis, visualization, management, and dissemination of geospatial information. 

Our Team consists of over one hundred highly skilled professionals, with a proven record of accomplishment in EO and GI consulting services. At Mallon, we strive to offer the best-fit solution for our clients, supported by exceptional service. Our approach to ensuring continuity of service is to hire strong industry professionals and invest in their professional development. 

Mallon prides itself on quality assurance and the ongoing security of sensitive customer data. Mallon is certified to quality standard ISO 9001:2015 and information security standard ISO 27001:2013. We are aware of our responsibilities to the health and well-being of our colleagues and the environment and have active measures in place to improve employee welfare and our impact on the climate. 

Mallon is a member of European Association of Remote Sensing Companies (EARSC) and European Umbrella Organisation for Geographic Information (EUROGI) and is actively involved in its AI and Geospatial and Women in GI Focus Groups. 

What makes your services and products unique? 

One of the company’s key strengths is its ability to collaborate closely with clients to understand their unique needs and tailor solutions to meet those needs. This client-driven approach has enabled Mallon to build strong, long-term relationships with our clients and establish a reputation for excellence in the industry. 

Mallon services and products are unique and competitive due to continuous upskilling of our workforce, allowing us to undertake advanced EO projects that require skills in EO-based environmental monitoring applications using artificial intelligence and machine learning. Our motivated team members and satisfied clients have positioned us at the forefront of technological advancement in the EO community. 

Our client base includes Irish central government and research agencies that are seeking innovative services to facilitate a better understanding of environmental changes. In collaboration with our industry partners, we have also responded to clients with accelerated delivery schedules as part of ESA (European Space Agency) EO Clinic, a collaborative framework targeted towards EO solutions in particularly underserved parts of the world. 

What are your future plans for the company and your products? 

Moving forward, we plan to expand our footprint to the wider European markets, increasing collaboration with other European partners. We are actively participating at events to increase our visibility and build networks. Our goal is to offer complementing solutions in fields such as agricultural monitoring, biodiversity conservation, climate change, natural disaster mapping, and mitigation. We will leverage the vast EO resources available for various environmental monitoring applications in land, agriculture, vegetation, urban, water and beyond. 

In summary, Mallon is a trusted and innovative player in the EO industry, delivering exceptional service, quality, and results to our clients. 

With the aim to expand our network and presence, representatives from Mallon will be attending the EXPANDEO 2023 and we look forward to getting to know you and your organization. 

For further Information: 

Mallon Technology Website: 

https://www.mallontechnology.com/

LinkedIn:  
https://www.linkedin.com/company/mallon-technology/ 

Twitter: 

 Acquisition will allow customers to more easily extract insights from Earth Observation data

SAN FRANCISCO, California and LJUBLJANA, Slovenia – March 29 –  Planet Labs PBC (NYSE: PL), a leading provider of daily data and insights about Earth today announced it has signed an agreement to acquire the business of Holding Sinergise d.o.o. (“Sinergise”), a leading developer platform for earth observation (EO) data. By reducing the complexity of analysis and insights extraction, as well as the cost of EO data storage, Planet aims to continue expanding into new vertical markets with products and applications where EO data is highly relevant such as agriculture, civil government, insurance, financial markets, and sustainable supply chain management. 

Sinergise’s technology powers the European Union-backed Sentinel Hub, an advanced API-driven, cloud streaming platform that allows customers to access multi-source EO data for processing, analysis, and insight extraction. Planet and Sinergise have been partners since 2016 and this acquisition reinforces that making EO data more accessible and actionable to decision makers is critical to businesses and governments. 

“The technology at Sinergise is first class,” said Will Marshall, CEO and co-founder of Planet. “Our integration with Sentinel Hub will meaningfully accelerate our Earth Data Platform plans, in particular by lowering barriers to access for EO data expanding the market, and by allowing partners to quickly and easily build applications, lowers the time to  value creation. Furthermore, this acquisition underscores our strong commitment to investing in Europe, and building and enabling the downstream market ecosystem there.”

Planet expects this acquisition to lower the barriers for current and new Planet customers to access and act on EO data. The addition of Sinergise’s platform capabilities is expected to further enable customers to more easily extract insights from various sources of satellite data and partners to build their own applications on top of Planet’s platform to gain additional value from EO data. 

“We are thrilled to integrate our technologies to together build a powerful Earth Data Platform to unlock the full potential for EO data,” says Grega Milcinski, co-founder of Sinergise. “Partnering with Planet over the years has inspired us to accelerate the adoption of EO driven applications at scale.”

Sinergise’s Sentinel Hub enables businesses, governments, and farmers to transform their management practices and report their sustainable impact. These data sources and distribution services allow governments and agricultural companies to visualize and analyze a variety of data products at an unprecedented speed. The European Space Agency (ESA) recognizes the importance of innovative technologies and awareness of EO-based services, and has facilitated easy access to Planet data in Sentinel Hub.

The transaction is expected to close during Q2 of Planet’s current fiscal year and is subject to certain closing conditions. This will be Planet’s sixth acquisition (BlackBridge group of companies in 2015, Terra Bella business from Google in 2017, Boundless Spatial, Inc. in 2019, VanderSat B.V. in 2021, and Salo Sciences, Inc. in 2023). 

Forward-looking Statements

Except for the historical information contained herein, the matters set forth in this press release are forward-looking statements within the meaning of the "safe harbor" provisions of the Private Securities Litigation Reform Act of 1995, including, but not limited to, implied and express statements regarding: the Company’s ability to capture market opportunity; whether and when the Company will be able to execute on its growth initiatives; whether the Company will be able to successfully close the agreement to acquire the business of Holding Sinergise d.o.o. in a timely manner, or at all; the successful integration of and ability to achieve potential benefits from strategic acquisitions; how the Company will execute on its partnerships and contracts and how the Company’s partners and customers will utilize the Company’s data and technology; and the Company’s financial outlook. Words such as “expect,” “estimate,” “project,” “budget,” “forecast,” “anticipate,” “intend,” “plan,” “seek,” “may,” “will,” “could,” “can,” “should,” “would,” “believes,” “predicts,” “potential,” “strategy,” “opportunity,” “aim,” “continue” and similar expressions or the negative thereof, or discussions of strategy, plans, objectives, intentions, estimates, forecasts, outlook, assumptions, or goals, are intended to identify such forward-looking statements. Forward-looking statements are based on the Company’s management’s beliefs, as well as assumptions made by, and information currently available to them. Because such statements are based on expectations as to future financial and operating results and are not statements of fact, actual results may differ materially from those projected. Factors which may cause actual results to differ materially from current expectations include, but are not limited to: whether the market for the Company’s products and services that is built upon its data set, which has not existed before, will grow as expected; the Company’s ability to manage its growth effectively; whether current customers or prospective customers adopt the Company’s platform; the Company’s international operations creating business and economic risks that could impact its operations and financial results; downturns or volatility in general economic conditions; and the other factors described under the heading “Risk Factors” in the Annual Report on Form 10-K filed by the Company with the Securities and Exchange Commission (SEC) and any subsequent filings with the SEC the Company may make. Copies of each filing may be obtained from the Company or the SEC. All forward-looking statements reflect the Company’s beliefs and assumptions only as of the date of this press release. The Company undertakes no obligation to update forward-looking statements to reflect future events or circumstances.

Developing Next Generation EO Applications

The Company

RSS-Hydro is a Luxembourg-based company developing innovative water and climate risk solutions to help public sector and industry clients achieve impact in the SDGs for a better and safer future. We are regularly carrying out a number of research projects with national and international partners to develop science-based commercial solutions using the newest advances in Earth Observation (EO) and space technologies and combine this with numerical modeling and novel computing architecture. This allows us to push current state-of-the-art capabilities to the next level, so we can build next generation products  and offer them today.

One of our flagship EO products that has now entered its commercialization phase, is FloodSENS, an AI-based algorithm that creates valuable flood impact maps even from clouded satellite images to support the financial risk industry as well as the international disaster response community.

Motivation for FloodSENS

The value of satellite sensors  for mapping and monitoring floods has long been established and oftentimes during flood disasters satellites represent the only means of obtaining actionable information. Over just the last couple of years, under a strong climate risk signal and economic insecurities, we have witnessed disastrous flood events, spanning across unprecedented spatial and temporal scales. These disasters trigger humanitarian crises, massive asset damage and very often result in large displacements of people that cause security and conflict concerns. During such large events that are unmeasurable and cannot be monitored with traditional field equipment, satellites are one of the only means to gather crucial information for mitigation, response and recovery. Although SAR (Synthetic Aperture Radar) may be the obvious choice for detecting flooding during adverse weather conditions, the present archive of available SAR images is still rather small to infer trends about flood risk and climatology of floods whereas optical satellite sensors of various resolutions have been around for more than 50 years now, albeit hampered by cloud cover during floods. Nonetheless, there are many examples of flood disasters where optical satellite sensors have been providing cloud-free or partially clouded imagery.  

The FloodSENS Algorithm

It is clear that overcoming the cloud cover issue in optical flood images would certainly be beneficial since it would allow a higher number of impacted areas to be mapped and it would also greatly extend the archive of flood maps from satellites, thereby providing better information to both the flood response sectors, including defense intelligence, as well as the financial risk industry, particularly the insurance and reinsurance sectors. To this end, RSS-Hydro has gathered needs and requirements from both the humanitarian and reinsurance sectors, and together with the UN WFP and Willis Towers Watson (WTW) as stakeholders, has joined ESA’s InCubed program to  develop a Machine Learning (ML) application, called FloodSENS, to extract flooded area in optical flood images, whether cloud-free or partially clouded.

Example tiles of FloodSENS from different regions in the world.

The ML model is based on the well-known U-Net architecture and uses Sentinel-2 (S-2) flood images and derivative layers from digital elevation models relating to topography and waterflow to map flooding even below partial cloud cover. The algorithm further employs a squeeze and excitation network to extract information about the importance of the different input layers. During the project, FloodSENS was trained on a large number of expertly labelled S-2 flood images across different biomes, events and locations to ensure acceptable transferability, which is to become an important part of RSS-Hydro’s IPR of FloodSENS. Internal application testing and validation shows, unexpectedly, varying degrees of performance and accuracy. Overall, on average, FloodSENS performs at least as well as any robust and calibrated traditional band ratio index (>90% correct prediction), and in some cases outperforms such, and even maps below low cloud cover and correctly includes flood impact areas from dried out areas by following debris lines.

Moving to the Next Level of Implementation

Many exciting developments are happening in the new space sector, from smallsat SAR or thermal sensor constellations and satellite video to in space data relay systems  and even in-orbit computing platforms. 

Our growing international partner network, in which EARSC plays an important role, allows us to play a major part in these exciting developments with our EO applications that we thrive to improve with potential stakeholders in an agile development process.

One of our latest exciting developments includes the partnership we have with NVIDIA. We use various geospatial datasets with NVIDIA’s scene-generation platform Omniverse to build realistic 3D animations of disaster impact that help increase resilience of vulnerable communities.

A snapshot scene from our own 3D animation creation using the Omniverse platform of the flooding in the coastal areas of Mozambique caused by the massive tropical cyclone Idai in March 2019, mapped with FloodSENS 

From these partnerships and collaboration we, at RSS-Hydro, ensure that our products can seamlessly grow in value-add and market share potential. 

“Together, let’s shape the future of the global EO market”

Contact

Visit our website: https://rss-hydro.lu/ 

Follow us on social networks: LinkedIn Twitter

Email us at: info@rss-hydro.lu 

Paris, France – April 20, 2022

CGG, a global technology and HPC leader, and Paragon Geophysical Services, Inc., a leading seismic acquisition company based in Wichita, Kansas and offering subsurface mapping services across the United States, have signed a Memorandum of Understanding (MoU) to combine their respective capabilities in support of energy transition customers and, more specifically, add value to the development, operation, and monitoring of carbon sequestration sites in North America. 

CGG can draw on its subsurface imaging leadership, proven geoscience expertise, high-tech Sercel solutions for acquiring subsurface information, and more than 15 years of experience supporting high-profile carbon sequestration projects globally in areas such as storage site characterization, selection of optimal geophysical technologies for monitoring, and operational monitoring best practices, to optimize the design, development and operation of carbon sequestration sites. 

Paragon has thirty years of experience in geophysical data acquisition and project execution for oil & gas and carbon capture storage applications, including, more recently, participation in the world’s largest carbon capture and storage project under development in the Midwestern United States. Its crews are equipped with the very latest Sercel technology to deliver the highest-resolution, most accurate geophysical data available in the industry.

Together, the two companies will support key forward-thinking energy transition customers in North America to explore, develop and execute technically demanding carbon sequestration projects in order to efficiently and effectively operate storage sites and optimize operational monitoring of the CO2 in the subsurface. 

Peter Whiting, EVP, Geoscience, CGG, said: “Our collaboration with Paragon, to support the development of subsurface carbon sequestration assets in North America with our innovative technologies, reflects CGG’s ongoing commitment to provide essential services for the energy transition. With our combined strengths in this key area for achieving net-zero targets, we will provide clients with critical insight, enabling them to optimize their storage and monitoring plans, reduce costs and have greater confidence in site conformance for improved operations and public acceptance.”

Aaron Bateman, President of Operations, Paragon, said: “We are delighted to combine our capabilities with CGG, with whom we share the same spirit of technological innovation and dedication to customer service, to address this growing market and societal demand for energy transition solutions. We see significant opportunity to add substantial value to our customers through enhanced integration of data acquisition and subsurface imaging to facilitate cost-effective carbon sequestration project development and operational monitoring.”

CGG provides leading geological carbon storage and monitoring expertise to support safe, long-term carbon storage from point source capture and direct air capture (DAC) facilities (image courtesy of CGG).

CGG provides leading geological carbon storage and monitoring expertise to support safe, long-term carbon storage from point source capture and direct air capture (DAC) facilities (image courtesy of CGG).

About CGG

CGG (www.cgg.com) is a global technology and HPC leader that provides data, products, services and solutions in Earth science, data science, sensing and monitoring. Our unique portfolio supports our clients in efficiently and responsibly solving complex digital, energy transition, natural resource, environmental, and infrastructure challenges for a more sustainable future. CGG employs around 3,400 people worldwide.

Contacts

Carbon StorageKyle ManleyTel: + 1 314 757 9513E-Mail: kyle.manley@cgg.com




Media RelationsSara Pink-ZerlingTel: +33 1 64 47 38 83E-mail: media.relations@cgg.com

Yield prediction for arable crops in Germany based on Sentinel-1 SAR data 

For a farm in Thuringia/Germany, we have developed a model based on historical yield data and  ESVI (enhanced SAR Vegetation Index) that enables the yield to be reliably estimated.  Sentinel-1 satellites deliver data regularly every 12 days worldwide with a resolution of 20x20 m.  The ESVI is based on this data and can be seen as a proxy for fresh biomass.  SAR data are independent of daylight and atmospheric disturbances and are therefore ideal for time series analysis. In this evaluation, we used yield and satellite data from all years 2018 - 2022.  

Data: Zonal statistics were created for all individual plots, all years, and for each acquisition date,  which resulted in the mean value, the maximum, and the minimum being extracted from the respective ESVI data sets.  

This data was then compiled in data tables and compared with the yield data for the respective years. Yield data results from weighing logs captured after harvest.  

Method: For the modeling of the yield values, 5 consecutive ESVI datasets were used. The same formula was used for all cultures and all years.  

The formula depends on a weighting table for each crop-type, which is valid for all years.  Depending on the weather conditions, the start of the season may be delayed by a few days.  The model allows a corresponding adjustment if it becomes apparent that the growth phase in the current year will start much earlier or later than in ‘normal’ years.  

The evaluation in the graphic below, for one plot and one year, shows a slightly thicker green line. It represents the mean value of the individual plot. The line is flanked by 3 other lines showing the mean value over all plots of the same crop-type and the same year. In addition, you see the simple standard deviation around the mean as a confidence interval. The two gray bars indicate the period for which the yield modeling was calculated in this example (early March – mid-April). 

On the right-hand side you can see the modeled yield values for the individual plot (minimum, mean  and maximum) in the bar chart and below that the harvest date, the measured yield and the moisture content in the grains. 

Results: The tables for every single year can be seen in Annexes 2-6. In the header of each table you can see the acquisition dates on which the last of the 5 succeeding ESVI datasets were used for yield modelling. The table shows the deviation of the modeled yield/ha from the measured yield/ha.  A value of 104 in this table means, that the model overestimated the yield by 4 %.  

In the first line of each table you see the deviation of the modeled yield from the mean ESVI value over all plots of the same crop-type and the same year. 

Plots with relatively low yield values but high ESVI values were massively overestimated. However, it  is also possible that the assignment of yield per plot data, in the logistic chain or the weighing log  was not always without errors. On average over the entire farm, the results are surprisingly good.  

In the following table you see an aggregation over all five years. The result from all years, all plots  and all varieties show a result close to 100% compared to the measured yield. Yield prediction can be done from early April and with high reliability from early May to mid of June. 

Overall, it can be said that the model seems to be stable over the years. Even if individual plots stand  out as outliers, the average over all plots of one crop type is close to the measured yield.  

The standard deviation indicates, that yield prediction between early and mid May, for each single  crop and over all crop-types deviates from the real yield in 2 from 3 years by less than 10 %.  Only in 1 from 20 years it can be expected, that the predicted yield deviates by more than 20%.  

Based on this data, a farmer can plan at an early stage how much storage capacity is needed or how  much of his predicted yield he can sell in advance into the market.  

Various applications based on yield estimation can be seen in crop insurance and agricultural  trading.  

Considering the current situation in Ukraine, a reliable and early yield forecast would be important  for the entire logistics chain right down to the end consumers. 

Implementation: The software enterprise ESRI built an application where the algorithm for the yield  prediction is already onboarded. The tool allows the farmer to select single plots or all plots of one  crop-type to calculate the yield prediction for the actual year, based on the map product ESVI.  Customers who register for that service have as well access to other map products from the same  sensor like SWI (SAR Water Index), which is useful to monitor drought condition in cropland.  Within ArcGIS online they can easily apply seasonal and annual change detection on-the-fly. 

The data will be actualized according to the acquisition schedule of Sentinel-1 with a delay of less  than 48 hours and is later available in the online platform ArcGIS Imagery

iMap| software that moves us 2/2

Download the PDF version: