ATR4PAZ

Objectives of the Product

Extracting intelligence from Synthetic Aperture Radar (SAR) imagery is challenging and time-consuming. ATR4PAZ is an AI-driven toolbox designed for PAZ SAR satellite imagery, overcoming these hurdles. This toolbox swiftly analyses high-resolution SAR imagery, providing valuable information about objects of interest within minutes. Rigorous testing, involving real and simulated SAR imagery, ensures the accuracy and viability of this novel approach, combining cutting-edge AI models with SAR data.

ATR4PAZ addresses the limitations of traditional interpretation processes, enabling SAR-based Intelligence, Surveillance, and Reconnaissance (IMINT) to reach optical imagery standards. The successful implementation of ATR4PAZ not only meets current challenges but also opens avenues for scalable product development. This approach can evolve to detect and classify new types of objects of interest, marking a significant advancement in SAR-based IMINT capabilities. ATR4PAZ represents an efficient solution for rapid and accurate intelligence extraction from satellite imagery, with potential for broader applications in the future.

Customers and their Needs

In general, the ATR4PAZ product targets governmental customers working in intelligence and security that employ satellite imagery such as MoDs, intelligence agencies, police, customs, etc.

The main identified needs they have in relation to the use of SAR satellite imagery are:

Automation of EO information extraction process in order to support rapid decision-making and mapping.
A tool that can be adapted for automatic detection and classification of different objects of interest found in SAR imagery.
The tool can also to be extended to include new types of objects.
The tool must be accurate and can be improved with the assistance of photointerpreters.

Currently, the spanish MoD follows this activity in order to first hand know the accuracy of the results.

Analytics companies (EO downstream) who generate IMINT for Security and Intelligence users (as contractors). They have similar needs to the governmental customers.

Targeted customer/users countries

MoD/SATCEN, Spain
NGA, USA
Value-adder and analytics, USA
NATO countries
EU countries

Product description

The main goal of the application is the sucessful detection and classification of objects that can be of interest to govermental customers in the framework of intelligence and Security. The picture below describes the overall ATR4PAZ tool that can be directly operated by a customer or used in the provision of a service where the customer receives only IMINT reports, avoiding the need of dealing with complex SAR imagery.

The tool automatically proccess SAR PAZ imagery, generating reports with the results, which can be supervised by the operator. This supervision of results is key for retraining AI models.

Supported by a SAR simulator for training AI models, new objects of interest can be added in different scenarios, making ATR4PAZ expandable to cater for new IMINT customers.

Added Value

The proposed de-risk activity aims to develop an operational tool for Automatic Target Recognition (ATR) using AI algorithms and PAZ satellite Synthetic Aperture Radar (SAR) images. Currently, AI techniques in ATR are limited due to the scarcity of large image datasets. The innovation lies in adapting a SAR simulator to generate realistic synthetic images from 3D object models, addressing the shortage of real satellite imagery. This approach offers significant advantages, including cost and time savings in acquiring training data.

Notably, there is a lack of successful and generalised ATR with SAR images in existing Earth Observation commercial software. While literature explores ATR with real images of specific objects, the proposed activity takes a pioneering step by combining synthetic and real SAR images to train AI algorithms. If successful, this approach would mark a significant milestone in SAR application development, demonstrating the feasibility of using simulated data in conjunction with real imagery for ATR training—an unprecedented achievement in the field.

Current Status

The project is ready for final review. To summarise, the main points are:

PAZ SAR Image object labelling and AI model training. Different trade-off performances were carried out in order to find the best suitable mode for automatic detection/classification of objects. Results have exceeded the set detection/classification goals of the project, confirming that PAZ real data can suffice to train ATR software.
SAR simulation/preprocessing. Simulation tools have been upgraded to improve the degree of realism of the SAR simulated imagery. ATR4PAZ has added the following new features:
- New SAR processor that enables the processing of long aperture SAR acquisitions.
- Object mask generation.
- Radiometric calibration, so simulations are compatible with PAZ SAR imagery.
Comparison of SAR simulations with real PAZ imagery has revealed high degrees of similarity, although some additional improvements in the simulation tool are needed to make the simulation solution fully operational.

agriKOPA

Objectives of the Product

Currently, many farmers are unable to access credits to buy inputs such as seed and fertilisers. Women and young people are particularly disadvantaged. With the agriKOPA service, agriBORA creates a credit score which provides more objective access to loans.

Working together with our agriHUBs, agriBORA already provides farmers with inputs, as well as linkage to the markets through contracts with agri-processors. We provide farmers with advice throughout the season, based largely on satellite EO data. But access to credit is generally acknowledged to be a major problem for farmers, negatively affecting their ability to make a living.

Since agriBORA’s major revenue stream comes from commission charged on transactions which take place over our platform, farmers’ lack of access to credit is also a problem for agriBORA.

The agriKOPA product produces a credit-score which enables Financial Service Providers (FSPs) to lend with confidence. In addition, during the growing season, EO-based yield forecasts help the lenders to constantly monitor their risk.

Customers and their Needs

We have three main customer groups for our product: smallholder farmers, agriHUBs and FSPs.

Smallholder farmers often lack money for high-quality seeds and fertilizers and also for services like ploughing and soil-testing. With our concept of earmarked loans, we provide farmers with financial resources exactly when they need it.

For agriHUBs and their managers, enabling loans means that the farmers have more money to spend on the products and services provided by the hubs. The agriKOPA service helps the agriHUBs retain their customers and build sustainable businesses.

FSPs see the smallholder farmer sector as risky and inefficient to service. Obtaining the basic data before even considering a loan is difficult and costly. Estimating the creditworthiness is a problem, with women particularly disadvantaged. FSPs also need information on the development of the harvests in regions where they have granted loans, in order to monitor their risks.

The picture below shows an agriBORA “agriHUB”, being visited in connection with the requirements definition phase of the project.

Targeted customer/users’ countries

The agriKOPA product will be first introduced in several of counties in Western Kenya. Thereafter, the product will be made available throughout Kenya, with expansion into other African countries also in the planning.

Product description

The agriKOPA product is innovative in many aspects. The application of EO data and the compilation of immutable transaction histories using information stored in the agriLEDGER is ground-breaking in the agricultural sector in Kenya. With EO data, agriKOPA monitors crop development and can give timely insights to banks and farmers regarding problems arising. The farmer interacts with this software-as-a-service platform through a phone, via a USSD-code menu, removing the need for a smartphone.

With banks, the interaction will be through an API interface, connecting agriKOPA’s software to the software of the bank. The diagram below shows the service to allow FSPs to monitor their risks.

Added Value

AgriKOPA’s main competitors provide farming inputs and services at different types of farmer service centres. They provide credit, often linked to insurance policies. Credits are financed directly by the company, or in cooperation with banks.

We bring added value through our innovative credit scoring algorithm and field monitoring which is enabled by Earth observation, machine learning and artificial intelligence.

AgriBORA is the only company which provides a true end-to-end service, ensuring that contracts are in place with agri-processors, thereby providing a guaranteed access to market. This in turn greatly reduces the risk of bad debts for FSPs.

Current Status

The final presentation took place online in October 2024 and was attended by over 30 people from a variety of different organisations interested in the project results. The final validation of the agriKOPA processes and the systems that support them revealed, in general, a high level of satisfaction among the different stakeholders (farmers, agriHUBs and the bank).

AgriBORA learned a number of vital lessons during pilot operations and validation, which we would not have learned without the agriKOPA project. This has led to some changes to the processes surrounding both lending and repayment.

As a next step, agriBORA plans to run agriKOPA during the long rain season in Kenya, starting in March 2025, involving substantially more farmers and agriHUBs, the first step in a planned rapid upscaling.

The most important lesson learned from agriKOPA was that many farmers are reluctant to sell directly after harvesting, since prices are generally lower. Instead, they store the product on their own premises, which usually leads to considerable loss. Harvest loss is a recognised problem in Kenya and the government has introduced a Warehouse Receipt System as a countermeasure. AgriBORA is now planning to open the first private sector-run warehouse in the country, in the Uasin Gishu County (December 2024), with support from the International Finance Corporation of the World Bank, the Agricultural Finance Corporation of the Kenya Government and the Warehouse Receipt System Council.

I*STAR

Objectives of the Product

The overarching objective of I*STAR is to minimize latency time between an event occurrence and the submission of a feasibility request. Leveraging advanced artificial intelligence techniques, I*STAR demonstrates the ability to:

Build User Profiles: Aggregating user preferences on data and acquisitions, I*STAR creates comprehensive user profiles to understand better individual needs.

Automatic Monitoring of Near-Real Time Events: Using artificial intelligence algorithms, I*STAR autonomously monitors near-real-time events, ensuring timely responsiveness.

Data Discovery: Identifying data of potential interest for users, I*STAR enhances the availability of pertinent information.

Automatic Gap Filling: Employing automation in the ground segment, I*STAR seamlessly fills programming gaps with new acquisitions tailored to user interests.

Cost Minimization: I*STAR minimizes operational costs in the ground segment, introducing efficiency and reducing manual intervention.

By applying artificial intelligence algorithms, I*STAR models user preferences, encompassing satellite platforms, themes, areas of interest, types of acquisitions, and suggested events. This enables to offer tailored recommendations, aligning precisely with users’ business needs. The specific outputs include suggestions for suitable catalogue products for download and intelligent mission programming.

The intelligent tasking capabilities not only optimize missions by utilizing orbit gaps left unused in standard programming but also significantly reduce operational costs through fully automated order scheduling, maximizing satellite capacity utilization. This adaptable solution can be delivered either as a full platform or as a service, offering flexibility to cater to diverse user requirements.

Customers and their Needs

Targeting EO constellation operators, I*STAR aims to streamline user interaction with the mission ground segment, optimize on-board resource utilization, reduce mission planning times, and enhance automation. With a focus on providing data and value-added services, I*STAR seeks to maximize data sales volumes for its customers. The primary challenges faced by I*STAR include unsaturated constellation capacity and missed opportunities for tasking. I*STAR proposes revenue growth by offering users tailored data through its monitoring services, tightly integrated with intelligent feasibility, thereby unlocking higher commercial opportunities for mission providers.

Targeted customer/users countries

Target customers are EO constellation operators who:

lack mission planning skills.
Need mission planning time optimization.

Product description

I*STAR is presented as an as-a-service application, aiming to enhance the capabilities of end-user platforms such as ground segments or any service platforms acting on behalf of users. The primary objectives include elevating user experience by suggesting relevant archived products and potential new acquisitions, automating end-user platform operations to reduce operational costs, improving mission efficiency by recommending new acquisitions to fill gaps in the planning process, and leveraging information from social and institutional portals to address acquisition needs based on events like floods or earthquakes.

To meet these objectives, I*STAR focuses on several key capabilities:

Collecting user and mission operator preferences to build personalized user profiles.
Gathering relevant events from social networks and institutional services within the earth observation domain.
Discovering archived data of potential interest for users.
Automatically filling programming gaps with new acquisitions tailored to user interests.

The as-a-service configuration of I*STAR provides access to functionalities and integrates with external entities, such as the Control Ground Segment, through APIs. It is designed for instantiation in a multi-tenant environment, allowing each Ground Segment to have a dedicated instance of I*STAR. Each instance is multi-mission, meaning that if a Ground Segment hosts multiple missions, all satellite platforms will be managed by the same I*STAR tenant in a multi-mission operating mode.

Added Value

To the best of our knowledge, there is currently no comparable solution on the market. Presently, each mission relies on a dedicated solution for satellite tasking, lacking a comprehensive view of satellite acquisition to effectively meet customer needs. I*STAR addresses this gap by introducing a unique data access pattern in Earth Observation, a novel approach not previously deployed for satellite data acquisitions. By guaranteeing a unified data access pattern to mission providers and usersh, I*STAR ensures the delivery of products and acquisitions tailored to user profiles, highly reducing the need for specific expertise on individual missions. This streamlines activities and delivers significant value to both service providers and end-users.

Notably, our solution is inherently mission and sensor agnostic, allowing easy configuration to support various missions and data sources. The adaptability of our AI algorithms ensures they automatically adjust to diverse needs, avoiding the need for specific development for a particular class of products or acquisitions. I*STAR adopts a micro-services architecture, packaged as Docker Containers, and is designed to run on Kubernetes or equivalent platforms. This “as-a-Service” infrastructure can be seamlessly instantiated and operated on any cloud provider or platform, providing flexibility and scalability for users.

Current Status

The project has reached a successful conclusion and is now accessible both as a standalone service and integrated within EASE-ground, a digital ground segment product within the Telespazio digital portfolio. This milestone marks the availability of the project to users in various deployment options, providing flexibility in choosing the most suitable approach based on their specific needs and preferences. Whether accessed independently as a service or seamlessly integrated into the comprehensive EASE-ground platform, the project aims to cater to a diverse range of users within the emerging New Space Economy.

SKAISEN

Objectives of the Product

Earth Observation missions generate a vast amount of data. Particularly, missions with hyper/multispectral cameras commonly collect hundreds of gigabytes per day. Up to 70% of this data consists of cloudy pixels lacking any added value and thus cannot be further utilized by the end users. SKAISEN addresses this challenge by helping Mission Owners, System Integrators, Payload Developers and Mission Operators mitigate these financial losses by identifying cloudy pixels directly onboard the satellites before the downlink costs occur. By leveraging the AI-driven SKAISEN solution, customers can significantly reduce their costs associated with the ground segment infrastructure while maximizing the valuable data downlink. SKAISEN is designed to be highly reusable and independent of the sensor and processing unit selected for the mission. This ensures its availability for any Earth Observation mission and its highly competitive price.

Customers and their Needs

The key customer segments targeted by SKAISEN are Mission Owners, System Integrators, Payload Developers and Mission Operators.

The main pains of these customers in data access are:

Data downlink is wasted with unusable data instead of actionable information
Wasted downlink resources increase latency and delay the access time to valuable data for end-users
Undesired high costs for ground segment infrastructure caused by unusable data transfer
Lower profit for data providers caused by downloading noisy data, which cannot be sold and has no added value
Long lead times and high prices for custom onboard data processing solutions, since there is a low number of COTS options
Time and cost-consuming data analysis by a mission operator

SKAISEN aims to bring a customer-friendly solution for acquiring valuable data only, reduce mission costs and increase mission profits.

Targeted customer/users countries

Mission Owners, System Integrators, Payload Developers and Mission Operators all over the world, focusing on Earth Observation missions.

Product description

The product SKAISEN is an onboard software solution designed to estimate cloud coverage on EO imagery. The key components of the product are:

Dataset – composed of open and commercial data as well as data from the target mission (if available)
Cloud screening model(s) – to predict cloud pollution
On-board software – software or hardware implementation of the cloud screening model optimised for the specific embedded processor or FPGA target

The role of SKAISEN in the context of the overall satellite system is a pluggable onboard software integrated into the data pipeline of the satellite, with the aim to provide additional information to the platform and mission operator. The product has no impact in terms of data modification or deletion. This decision remains with the mission operator or other responsible person.

Added Value

The principle of how SKAISEN works is described in the picture below. After collecting imagery by the satellite, SKAISEN processes the data and extracts valuable data only, which is then transported to Earth. This approach optimizes downlink by minimizing unnecessary data transmission.

There are several views on how to optimize data transfer to Earth. The most common approach is processing data before transportation. There are already available onboard data processing products in the market. The difference between them and SKAISEN lies in their reusability.

SENSOR INDEPENDENCE: While the existing products are operable, e.g., in the visible spectrum, SKAISEN is sensor independent, regardless of whether the optical sensor operates as monochromatic, RGB, multispectral or hyperspectral. The flexibility in choosing the right camera for the mission remains for the customer.

DPU INDEPENDENCE: Whether a single software solution or the entire payload is needed, SKAISEN offers both. SKAISEN is available in three different configurations, and there is no limitation in choosing the hardware part.HERITAGE: Operating in the space segment means understanding the emphasis placed on flight heritage. SKAISEN demonstrated its first capabilities during the VZLUSAT-2 mission in the summer of 2022. Additionally, three confirmed missions for SKAISEN are scheduled for 2024

Current Status

The activity kicked off in November 2023.

Tri-Band Monopulse Antenna

Objectives of the Product

EO and RS applications for collecting an ever-increasing volume of data from images and sensors, or in the event of natural hazards and disasters, have become extremely important for emergencies caused by global warming, pollution, continuous erosion, and destruction of the natural environment.

To monitor real weather or land surface conditions in near real time, national emergency services, private utility companies, governments need high resolution visual imagery.

This results in a huge volume of data requiring broadband for transmission to the receiving earth station gateways.

These wide bandwidths can no longer be provided by traditional X-band even when both polarizations are exploited, and the remedy for this limited bandwidth is to exploit K- or Ka-band.

Most antennas on the market operate in one or two frequency bands at a time, and even Dual-Band antennas that typically operate in the X and S bands have bandwidth and data rate limitations for new services, which can be managed by Banda Ka. The ITZ-TBMA-1.0 represents the development of one of the most advanced products in terms of flexibility of satellite bands on a single antenna (S – X – Ka), data reception capacity and bandwidth for EO – RS – IoT and compactness.

Customers and their Needs

The target customer who is also a strategic partner for this project is Telespazio. It has shown interest in the product (as have other users) as it is interested in the expected performance of the antenna system with reference to ground stations and more specifically in the expected capacity to fully satisfy the demand for an ever-increasing need for data reception volumes for EO-RS-IoT from satellites. Telespazio was involved in the project by assigning fundamental tasks such as the validation of specifications in accordance with market needs as well as the final verification of the product.

Targeted customer/users countries

Italy, Finland, and Germany.

Product description

The project represents the development of a Tri-Band (S-X-Ka) antenna with S-band that supports Rx/Tx mode for TT&C and X and Ka bands in receive mode. The design includes Monopulse tracking techniques for unprecedented precision, which is critical for receiving high-bandwidth data across all frequencies. The Telespazio customer has the task of validating the technical specifications of the product in accordance with market needs and verifying the final product.

Added Value

The proposed solution brings numerous and substantial advantages as it allows first of all to reduce the number of antennas by concentrating multiple bands in the same antenna, to offer new service scenarios as well as accuracy in satellite tracking and pointing thanks to the use of multiband monopulse satellite tracking and guarantees optimized management of latest generation compact multiband antennas and systems.

Compared to the identified competitors, the proposed solution is more advantageous because it offers a tri-band for antennas up to 13 m (7m, 9m, 11m, 13m). Thanks to the experience gained over the years, we can offer a wide range of equipment such as antennas, feeds, tracking receivers, antenna control units and therefore we are able to offer modular solutions up to a complete solution.

Furthermore, we can adapt our solutions to existing antennas. Unlike large companies that offer standard products, we tailor to customer needs and provide a customized solution

Current Status

During the first months of activity, thanks to a market analysis, consultation with stakeholders as well as the collaboration with the partner (and first customer) Telespazio, the product requirements were identified and subsequently translated into technical specifications. Based on the specifications, the preliminary design of the RF and the mechanical parts is starting.

Illegal construction detector

Objectives of the Product

Countries where high real-estate taxes exist also have issues with illegal constructions, because some people try to avoid paying the respective tax. The solution helps municipalities find owners who are not properly paying real-estate taxes by detecting buildings from satellite images.

Based on satellite data, the solution identifies new construction activities in an area. It filters out unlawful activities based on building registry data, enabling the automatic filtering of illegal activities from all detected construction activities. The web application not only detects constructions not paying the (proper) real-estate tax but also helps municipalities to contact the real-estate owners so they can start paying the tax properly.

We provide this solution by recognising buildings from high-resolution satellite images. To do so, we utilise machine learning algorithms on satellite data, to recognise construction activities and combine this data with building register data for our target use case.

Customers and their needs

Municipalities face substantial issues with undeclared constructions, resulting in lost tax revenue. The main issues include unpermitted swimming pools and extensions in private properties. Apart from the financial issue, illegal constructions also create a security problem, especially with pools that can be very dangerous when built on higher floors. In this case, they could potentially damage the structure of the building. Such cases are also more difficult to discover through manual inspection because officials have limited access to buildings.

Current methods, such as relying on citizen complaints and manual inspections, are inefficient and labor-intensive. Municipalities recognise the income loss from manual systems and are seeking more efficient methods.

Target customers/ users’ countries

Target customer: local municipalities
Primary focus: Spain

Product Description

The core of the product is the capability to detect objects of interest (buildings and pools) from 30 cm-resolution satellite data with sufficient precision and recall to support our business logic. Detections are compared with information on registered buildings to identify unregistered and misregistered buildings.

From the customer’s perspective, detections will be served to the client via a web application that has supporting features for follow-up actions regarding misregistered buildings (such as sending notices).

Added Value

Several companies in the market offer solutions for infrastructure monitoring based on data from satellites. One aspect, that sets our offering apart from the companies already operating in the market, is that our solution foresees integration with building registers, which enables automatic filtering of illegal actives from all detected construction activities.

Current Status

The following tasks were covered in the de-risking activity:

1) validation and improvement of the requirements specification.

2a) utilisation of machine learning algorithms on satellite data, with sufficient precision and suitable to offer construction surveillance services in Spain.

2b) combination of satellite data with building register data for our target use case.

The Product Development phase will most likely continue, where the web application of the product will be developed.

Satelligence Biomass

Objectives of the Product

Satelligence Biomass is a report- and platform-based solution that helps companies understand their Scope 3 emissions and where the biggest issues occur in their supply chain.

The service shows changes in aboveground biomass for different supply chain levels (from farm to aggregators like mills and suppliers) to be able to make more targeted sourcing decisions. Satelligence Biomass is a new module/feature on our existing solution platform. The information can be used as part of the Science-Based Targets Initiative (SBTI) reporting or internally to make sourcing/investment decisions.

For SBTI reporting, additional information on Scope 1, 2 and other Scope 3 data needs to be integrated through partners or our clients, hence dissemination should be also flexible (API, exporting capabilities etc.). Before the project started, we already developed our carbon (aboveground biomass) algorithms for a number of regions and landscapes in pilot projects, with corporates like Mondelez International, Cargill and Rabobank, but more work was required to make this a scalable off-the-shelf solution.

With Satelligence Biomass we now service all multinationals that have net-zero commitments with reliable, science-based results.

Customers and their Needs

The key customers segments targeted by our service are fast-moving consumer goods companies and large-sized traders active in soft commodity supply chains (e.g. palm oil, cocoa, soy).

Satelligence Biomass offers companies active in soft commodity supply chains a better understanding of their Scope 3 emissions due to land use change and agricultural expansion. This allows our customers to make better sourcing decisions and report progress towards compliance and reporting frameworks.

We have identified the following key pains:

Not being able to account for and report on Scope 3 emissions towards stakeholders.
Being at risk of unexpected carbon emissions due to forest loss in the supply chain.
Being at risk of unexpected exceedance of emission rights.
Having to compensate for unexpected carbon emissions in the supply chain.
Not being able to account for Scope 3 on emission-related statements and metrics (third party verification).

And the following key gains:

Access to carbon risk and storage potential data of the supply chain.
Being able to prioritise resources for net-zero commitments based on all scopes.
Insight in the spatial distribution of the risk of emissions over the sourcing landscapes.

Targeted customer/users countries

Our target customers and users operate globally. Monitoring mainly happens in the (sub)tropics because of our commodity focus.

Product description

The functional blocks of the Carbon estimation model that need to be developed are:

1.1 Satellite data processing: Landsat & Sentinel-1 and 2 (already developed).
1.2 Satellite data processing: GEDI data processing and filtering.
1.3 Satellite data processing: ICESAT data processing and filtering.

2. Allometry selection and application module.
3. Auxiliary data processing and look up module.
4. Analysis Ready data module.
5. AI carbon estimation training, tuning and prediction module.
6. User interface module.
7. Scaling: carbon estimation at global scale.

The model builds on results of the already operational satellite image distributed processing framework (DPROF).

The main (functional) modules are described in the table below. The modules can be separated into three main categories:

Extension of existing (data) models, storage and interfaces.
Development of new modules that will compose the Carbon estimation pipeline.
Designing and building end-user products.

Innovation versus the market:

Available solutions to measure net-zero commitments are models of consultancies.
Available solutions to measure carbon by satellites often focus on the offsetting market (carbon credits) due to supply chain complexities.
Many companies providing carbon services don’t have market access with corporates like Satelligence has.

We can bring together those elements and have a first-of-its-kind solution on the market.

Added Value

Access to carbon risk and storage potential data of the supply chain.
Being able to prioritise resources for net-zero commitments based on all scopes
Insight in the spatial distribution of the risk of emissions over the sourcing landscapes

Current Status

Satelligence Biomass had its kick-off on 6 July 2023.

The Satelligence team had several meetings with demonstration partners. Next, Satelligence also had a full day session with a consultancy to discuss a potential partnership.

We also started setting up an approach to sell Satelligence Biomass, including pricing options. These were tested throughout the project phase. The Final Review took place on 18 October 2024. By the project’s end, four customers signed up to the Satelligence Biomass service, totaling over € 250.000 in annual revenue.

The service is now ready to be commercialised at scale and we have a significant pipeline for the short- and mid-term periods.

Saturnalia

Objectives of the Product

Key Features:

Daily monitoring: receive daily updates on crop conditions, with high-resolution images and data.
Health analysis: utilise NDVI (Normalized Difference Vegetation Index) and other spectral indices to assess plant health and detect stress early. It includes a proprietary algorithm to compare different crop vintages.
Growth tracking: monitor growth stages based on continuous data collection and analysis.
Weather impact assessment: understand the impact of weather events on crops with historical and real-time weather data integration.
Damage assessment: provide accurate and timely damage assessments to support insurance claims, using satellite imagery and advanced analytics to quantify the extent of crop damage.
Enhanced risk knowledge: historical satellite time-series to assess risk level associated to every single crops.
Customised reporting: get tailored reports that meet the specific needs of growers and insurance companies, with actionable insights and recommendations.

Customers and their Needs

As the agriculture industry shifts towards precision farming, the demand for accurate and timely data is increasing. In addition, governments are pushing towards precision farming techniques by providing funds to invest in new technologies.

Crop insurance companies are looking for innovative solutions to enhance their services and reduce risks, making Saturnalia a perfect fit.

Saturnalia serves two core markets: agricultural producers and agricultural insurance companies. Producers use our service to optimise daily operations such as irrigation, fertilisation, and crop health monitoring. Insurance companies benefit from our technology to better estimate risks, manage claims, reduce fraud, and assess damages from natural disasters. The potential for transformation in these traditionally conservative industries is immense.

Target customers/users’ countries

Farmers targeted so far are located all around the world. To this day, more than 140 pilot cases have been completed across Italy, France, Austria, Germany, Portugal, Australia, US, South Africa and Argentina. The market for crop insurance companies is again global, with main contacts in Italy and Germany.

Product description

Saturnalia aims to enhance agricultural productivity and resilience, thereby improving lives through better resource management and crop protection.

A various set of heterogeneous data sources is organised and harmonised to offer easy access. Daily images and weather data are automatically ingested and processed every day.

Growers can benefit from all these datasets by using a web platform, available for all devices. Insurance companies may leverage results via API or via a web platform.

Added value

Saturnalia’s daily satellite crop monitoring service addresses critical needs in the agriculture and insurance sectors, offering a sophisticated, reliable, and user-friendly solution. By providing near real-time data and actionable insights, we empower growers to optimise their operations and insurers to manage risks effectively, driving overall productivity and sustainability in agriculture. Many competitors in this space often rely on lower resolution data and do not prioritise the interaction with the final users. On the other hand, for insurance companies specific damage models will allow them to save time of loss adjusters operations in the field.

Current Status

This activity is completed. The current service automatically ingests daily satellite data and distributes them via a simple web interface. A mobile app is also available on App Store and Play Store. It allows to run comparisons on the different datasets, to compare with what users might see with their own eyes and also to collect geolocated reports in the field to keep track of what is happening.

Insurance companies can benefit of our monitoring services as well as models to detect anomalies. More than 140 case studies have been completed across Italy, France, Austria, Germany, Portugal, Australia, US, South Africa and Argentina. Several crops have been tested, such as grapes, tomatoes, rice, corn, artichokes, apples, etc.

SIAMaas

Objectives of the Product

The Copernicus Programme and its Sentinel satellites generate more open and freely available satellite data than any other space programme ever before, but the key challenges are the same: converting big Earth observation data into information using transferable and automated methods that can also be used by non EO-experts. The Satellite Image Automatic Mapper (SIAM) software is an existing expert system that performs fully automatic, near real-time, preliminary classification. It categorises multispectral EO images using a physical model and produces semi-concepts (i.e. preclasses) at several levels of detail. SIAM has linear algorithmic complexity and is scalable to allow for processing big data volumes. Unlike unsupervised clustering routines or machine learning/deep learning approaches, the service produces stable, comparable, application-independent spectral categories with known semantic associations using a physical-model from EO imagery without the need for any sample data. We bring SIAMas- a-Service (SIAMaaS) into a scalable container-based infrastructure in the cloud where the data are located (e.g. DIAS), therefore making it accessible for everyone, not just EO experts. Users select images on an area-of-interest and timeframe, and SIAMaaS converts the data into information. Our approach takes care of the entire processing chain, i.e. data preparation, analysis and access to results. It will flexibly enable further online processing of results, thus establishing SIAMaaS as an anchor point for big EO data analysis, enhancing user’s workflows.

Customers and their Needs

The key customers segments targeted by our service are: (1) Public entities/authorities; (2) Scientists/research organisations in general, especially non-EO experts; and (3), Support/improve existing and future (Copernicus-related) services in a b2b business model to support geospatial services of private companies (incl. Copernicus service providers) and midstream providers, like ARD providers. User’s needs:

Big Earth observation (EO) (time series) data themselves do not have value if they are not transferred into information; however, may state-of-the art methods require training samples or application-specific design/algorithms and can be difficult to operate.
Updates and new versions of services are only available at some (longer) intervals (e.g., several years). Speed-ups of workflows using automatically obtained intermediate products are required: Repeatable, standardized analysis of Sentinel-2 data as an initial pre-processing step for automated EO based services. Stratify services (e.g. atmospheric correction) on reliable preprocessing, create fully automated change detection including alarms for suddenly changing environments on reliable pre-processing, increase the convergence of evidence and improve accuracies of existing services (e.g. LULC) based on reliable pre-processing.
Integrating EO data in analysis workflows requires skills and time (to learn), due to: Required knowledge of EO (physics, …), Sensor architecture (bands, …), Data formats. This is a hurdle to use EO data as non-EO experts.

Target customers/users countries

Worldwide, but initially identified users are located in Europe.

Product description

The Satellite Image Automatic Mapper (SIAM) software is an existing expert system (prior-knowledge-based decision tree) that performs fully automatic, near real-time, preliminary classification. The software produces semantic enrichment that contains different granularities (i.e. different number of spectral categories), as well as additional data-derived information layers (e.g., multi-spectral greenness index, brightness).

Innovation: We developed SIAM-as-a-Service (SIAMaaS) into a scalable containerbased infrastructure in the cloud (e.g. DIAS) making it accessible for everyone, not just EO experts. Users select single or multiple images based on an area-of-interest and timeframe, and SIAMaaS converts the data into information. Our approach takes care of the entire processing chain, i.e. data preparation, analysis and access to results. Itwill flexibly enable further online processing of results, thus establishing SIAMaaS asan anchor point for big EO data analysis, enhancing user’s workflows.

User interaction: Easy to use online web-interface and a CLI for batch processing. The web-interface is accessible under https://app.color33.io . While SIAMaaS has been developed for Sentinel-2, the 33 colors stand for the 33 spectral categories which can beautomatically derived for every calibrated multispectral-sensor allowing cross-sensor analysis beyond spectral reflectance values and number of bands. “color33” will be the name of the service when exposed to the users.

Added value

No existing service automatically classifies any user-selected Sentinel-2 data on-demand with similar depth in near real-time without user interaction, nor has a similarly proven application record. Machine-learning-based services exist, but require sample collection,
user interaction, and have not proven transferability to other geographic areas globally or to other sensors. Similar approaches are not ready for big data volumes, with respect to computation time, transferability, analyst subjectivity (e.g. samples, parametrisation) etc.
Paired with a broad / global application range these are USPs of SIAMaaS. Products built on top of SIAM are additional business opportunities and a factor for competitive sustainability. Ongoing R&D allow us to react to upcoming competitors. The original idea won the Copernicus Masters Prize Austria 2020.

Current Status

The activity is closed with November 2023 and is now continuing as an operational service and expanding into the market for creating added value services on top of it and participating in relevant public tenders.

AgriTrack Full DSS Stack

Objectives of the Product

The Full DSS is an innovative tool providing highly valuable insights obtained from the correlation of several data sources to support AI processes that can provide suggestions and better communication for the farmers inside the value chain.

As a matter of fact, the product is an advanced Decision Support System (DSS) able to combine modelling and remote sensing historical information to diagnose hot spots of vegetative stress, highlighted by remote sensing, pests and disease detection models.

The ambition is to overcome the two main problems of agricultural DSS:

Information overload.
Lack of spatial information and practical prescription.

In fact, satellite data collected and elaborated by AgriTech platforms are usually able to identify general issues (such as areas with reduced vigor within each field) but cannot provide precise diagnosis of the seriousness of the vegetation vigor issues and information on its possible causes. On the other hand, traditional DSS can provide specific information on single issues, such as field water or nutrients needs, pest risks etc., which usually refers to the whole field, without differentiating between areas of the field. With the Full DSS, all information can be integrated, providing tempestive feedback on what is happening in the field, where it is happening and why, giving some agronomic advice.

Customers and their Needs

AgriTrack Full DSS Stack can directly support a wide range of stakeholders with direct and indirect benefits. The targeted customers are:

Farmers, which could improve farm profitability through optimised use of inputs and reduce environmental impact.

Farmers’ associations, which could collect useful data and information to provide agronomic support to their consociates.

Cooperatives, which could monitor multiple fields and timely identify hot spots. Consortia, which could obtain an easy-to-use tool for providing agronomic support to numerous farms.

Agronomists, either independent professionals or within the above-mentioned organisations, can benefit from an effective tool for field monitoring, immediate intervention and communication with clients.

Facing an ever-evolving environmental and economic landscape, farmers, consultants, and other actors in the agronomic sector increasingly require identifying critical areas within the field and plan new and immediate intervention action remotely and timely.

On this regard, the AgriTrack Full DSS stack can respond to their needs to take agronomic decision-making based on reliable and spatialised information, improve the monitoring and data collection from several fields and farms, and be able to obtain tangible and reported results on farm’s agronomical performance. This is completed by the possibility provided to users to have spatial and detailed alert information and its causes.

Lastly, from the interviews carried out with target users, the urgence to be trained and supported in the use of innovative and technological tools strongly emerged. Therefore, the commercial offer will include a module of one-to-one training on the use of the tool, while videos and tips have been included within the platform.

Target customers/users countries

Italy and Spain.

Product description

The Full DSS is a functionality to be added to an existing cloud based FMIS. It will use all existing and new model outputs and sensed data (e.g., satellite, in-situ sensors) to obtain a probabilistic diagnosis of the abiotic agronomic issues affecting specific areas within the identified critical field. This information will be further enriched with alerts on pests and disease risk level.

This will be achieved by testing different Machine Learning and data-fusion approaches adopted as predictive tools within the large dataset that has been created by Agricolus in several years of smart farming experience. The AgriTrack Full DSS Stack consists of two modules. The first is a web application called Visualization Module, that displays sets of geospatial information and alerts, being the main interface and interaction point with the user. The second is the Computational Module, which produces such information and alerts combining different data sources into specific algorithms.

Added value

AgriTrack Full DSS is a new solution which brings four core innovations:

critical area diagnosis from interpretation of satellite images: the Full DSS is the only solution able to automatically detect real vigour issues within the field, inform the users and provide information about its causes.
Spatial model outputs on specific issues at sub-field level: the Full DSS is able to provide information about field’s criticalities, such as nutrient and water needs, pest risks, thermal stress, waterlogging and heat waves. Moreover, information is elaborated differentiating between field specific areas, allowing precise management of the issues.
Integration of several data sources into a single information: the Full DSS models will integrate information from a range of different sources (satellite, sensors, user data etc.) to provide the simplest and most useful information to the user, which will no longer have to retrieve data from different sources.
Sharing and aggregation of information at different levels: the Full DSS allows data exchange between hundreds of farms, fostering insights and communication at a large scale. Full DSS makes possible real-time and forecast data-based reporting among connected farms and other stakeholders, and agronomic management of the entire ecosystem with activity and support in optimising agronomic practices.

Current Status

The project activities are successfully concluded. The product reached TRL 9 and it is ready for commercialisation.

All WPs have been successfully concluded, and the product performances reached the identified KPI to fulfill the Service Requirements identified during WP2000. The validation activities with users have been successful, confirming the novelty and market adequacy of the product.