1st round of Open Calls: Meet the Winners!
Meet the winners of the 1st Open Call for Use-cases in 4 Industrial Domains: Energy, Security, Health, Agriculture, with beneficiaries consortia of high-tech & at least 1 low-tech SME and a total funding up to €900.000 (up to €150.000 / 3-partner consortia, up to € 120.000 / 2-partner consortia).
SR4C3 – Super Resolution for Climate Crisis Context
Companies: SISTEMA GmbH / cmc-consulting (Conflict Management Consulting – CMC)
Countries: Austria / Belgium
Abstract: The “Super Resolution for Climate Crisis Context – SR4C3” proposed action is coordinated by SISTEMA GmbH and aims at bringing innovation to the climate crisis sector by enhancing the remote sensing based technological tools through the application of Artificial Intelligence (AI) algorithms on security domain challenges, with the support of the Conflict Management Consulting – CMC company. The integration of Earth Observation (EO) satellite data in the usage of new Super Resolution (SR) AI-based applications is particularly crucial for better information gathering and assessments in conflict or crisis affected areas otherwise largely inaccessible, to effectively contribute to global stability and peace. In particular, the combination of AI-based SR tool with Copernicus satellite data can support crisis response to flash flood disaster and conflict monitoring in the West Darfur (Sudan), a fragile geographic area in terms of many security. Starting from the available AI/SR prototype developed by SISTEMA, the SR4C3 methodology is planned to be launched as innovative and scalable service with an expected relevant business impact, in creating value propositions and awareness, by allowing an automatic increase of the EO data resolution and improving the potential geospatial intelligence output. The AI technology transfer to the security application domain, is guaranteed by high-tech application components docker-based cloud services as infrastructure and AI4EU, CREODIAS at data access level.
SCAVIHO – Scalable Vegetation Index and Harvesting Forecaster
Companies: ENCORE LAB / MAETIERRA IAE
Normalised Difference Vegetation Index (NDVI) is widely used in precision agriculture due to versatility and reliability in reporting general crop’s canopy status and is used during all the season. NDVI values range from 0 to 1, and although extreme values are well interpreted by farmers as a sign of problems in the crop (lack or excess of water or nutrients), intermediate values during the growing stage are not used due to its difficulty of interpretation although they can disclose important information about growing evolution of the crop. The main objective of the project is to broaden the intermediate values of NDVI corresponding to the growing stage of a crop and to provide a scale according to the phenological status of the crop with the aim of help farmers to assess the growth evolution, to advance hidden problems and to forecast harvesting dates based on historical NVDI Sentinel-2 data.
SLIDE – Satellite Images Prediction with Deep Learning
Companies: Solaïs / Transvalor
Abstract: The two project partners, Solaïs and Transvalor, will develop satellite images forecasting techniques using advanced Deep Learning (DL). The goal is to improve short term solar irradiation forecasts in the 15 minutes to 6 hours range, which is critical for off grid sites or isolated power grids. Innovative Deep Learning methods will be tested and validated against standard (persistence) and Machine Learning methods on past data. A special care will be taken to represent rapid solar irradiation changes called ramps. Criterion for images forecast evaluation will be studied to validate the forecast service over a large area. The result will be downstream services accessible through the AI4EU marketplace and running on a DIAS. Users will be able to provide geographical coordinates for which they need a forecast, and the request will be executed on DIAS hardware then output to the user.
VALENS – AI4 Copernicus Blue
Companies: Lelieur BV / VAKE AS / NSAS BVBA (North Sea Aviation Services)
Countries: Belgium / Norway
Abstract: The main ambition of the project is to create a platform for deep maritime insight, producing live alerts of high-risk vessels, and historical analysis to provide the past location and activity of vessels for potential proof for prosecution. Satellite imagery and satellite Radio Frequency (RF) surveillance is used for detections of hotspots and guidance on where this activity is happening by Vake and Lelieur. Whereas the inspection, reconnaissance and in-situ video collection are a part of the operational services being delivered by North Sea Aviation Services (NSAS, low tech SME). The VALENS consortium aims to showcase the power of data fusion, combining earth observation data from Sentinel-1, Sentinel-2, SAT-AIS, and satellite geo-location of Radio Frequency (RF) transmissions for improved intelligence and guidance of airplanes and drone patrols. The tools supplying alerts and locations of marine assets will be provided in containerised APIs which virtual drone/plane control towers can ingest. It will provide oversight, tracking, alerts, and guidance of marine operations in a GIS interface (e.g. patrols, drone deliveries, wind turbine or submarine cable inspections), essentially creating a novel virtual marine & airspace control tower.
Sen4Weeds – Automatic detection and mapping of in-field weeds
Companies: DigiFarm AS / ALTYN Sarl / Farmen Gard
Countries: Norway / Switzerland
Abstract: Sen4Weeds will develop a solution for automated large-scale detection and mapping of weeds in agricultural fields. The proposed technology leverages the latest advances in Remote Sensing and Artificial Intelligence and will utilise multiple AI models including super-resolved Sentinel-2 imagery developed by ALTYN and automated field delineation developed by DigiFarm, as well as AI-based spectral unmixing of Sentinel-2 multi-spectral imagery.
Companies: Pixstart / Keyaid Consulting
Abstract: Through this project, a remote sensing company already involved in several projects of land monitoring in sub-saharan Africa (Pixstart), is partnering with KeyAid consulting, specialised in NGO support, in order to address NGO needs for knowledge of actual geophysical states surrounding villages caught by crisis (available water, refugees camps size, agriculture status and capacity, …). As NGOs need fresh data, this project is using Sentinel 1 and 2 images, combined with contextual geographical, social network and topical data, in order to edit near-real time situation reports through a SaaS application. This project will combine two types of IA, for Sentinels data will be first processed by artificial neural networks, and then combined with contextual data by expert systems. Contextual geographical data will be for example Land Cover as provided by Copernicus services, while topical and social networks data will be gathered by KeyAid intelligence consultant. This project integrates a specific effort on the data visualisation to facilitate the user adoption of the application. This latter will be challenged by one of its future customers: Solidarités International, which participates in the project as a contributor.