Today, Earth Observation (EO) data are freely available in large quantities. However, the main obstacle to their use by the general public is that these data are sometimes hard to access, and a precise image can be hard to find from the large amount of data available. The data cannot always be exploited due to weather conditions, and its interpretation can be challenging (different bands, resolution and geometry, …). Another reason why these data are not widely used by the general public is that they are not currently highlighted by search engines (e.g. a query returns almost no results from EO).
The ambition of the SnapEarth project is to foster the Market growth of COPERNICUS by instigating the development of new EO applications and to develop general public awareness to EO data.
SnapEarth is to initiate the creation of a virtuous circle of innovation by providing to EO data users an innovative platform with leading edge EO segmented datasets, Neural Networks models and Cloud computing ecosystem. SnapEarth will thus be able to unlock new value, derive actionable and additional service ideas on top of EO big data collections, and anticipate future priorities by leveraging cutting-edge AI and Cloud technologies.
From a user perspective, SnapEarth will alleviate the burden of building and configuring an EO processing environment linked to a DIAS platform. Beyond the DIAS platforms, SnapEarth will have the capacity to be connected with any EO data or processing service providers.
SnapEarth aims to facilitate also access to EO data from the general public thanks to EO data labelling and indexation innovations and access from the Qwant search engine.
The result of the project will be a portal for natural language queries on images. The use of language processing as an interface between the user and the system for extracting information from images is one of the keys to the broad adoption of the system. This will allow users even without knowledge of EO to perform complex semantic searches.
The innovative services will be developed by project partners based on the needs expressed by their customers together with an innovative platform and leading sets of earth observation data.
The main building blocks for making SnapEarth platform and these services:
SafeScale - an open source (Apache License) Infrastructure and Platform as a Code tool. It offers an APIs and a CLI (Command Line Interface) tools to deploy versatile computing clusters that span multiple Clouds. SafeScale is the foundation of the SnapEarth platforms. The processing framework will be supplied by SafeScale and the computing infrastructure deployed on future Copernicus DIASs. SafeScale APIs will offer to user self-service web portal to manage their computing infrastructure. SafeScale ensures to EC both an incomparable power and a no vendor lock-in for access and processing of Earth Observation data, through the associated EarthSelf-Service (3).
Earth Signature - is based on artificial intelligence (deep learning models) designed to extract biophysical land cover semantic information from satellite imagery. It automatically and accurately maps the images provided by satellites for indexation. All data produced by EarthSignature dataset will be automatically indexed and accessible with the EarthSearch Portal (4).
To demonstrate how the platform can be used to reveal the tremendous potential of EO data to a very large audience, well beyond their usual perimeter, 2 services and 4 business pilot projects will be presented:
EarthSelf - technological component enables any business or user to take advantage of highly scalable cloud environments for analysis, visualization and production of Earth observation value-added services.
Earth Search - a portal for natural language queries on images. User will be able to express questions in natural language on images and get either a text response or an imagery response.
Earth Press - aims to deliver value-added products to editors and journalists allowing them to enrich the content of their publications and articles. Such contents tailored to specific user needs will be notably based on EO data (e.g., disaster extent maps, background imagery) and aggregated information from social media, websites, etc. on a given topic. It will provide added value data to the media industry allowing them to disseminate the success of Copernicus to the citizens;
Earth Climate - services to support climate monitoring activities: (1) air quality and carbon dioxide emissions monitoring and (2) urban heat islands monitoring. EarthClimate services will be combined with other Copernicus data and local data coming from sensors and monitoring programs;
Earth Food Security - service is built on top of in-situ information of crop conditions, and runs with Copernicus Climate Change Service projections of climate change;
Earth Agri - support agriculture monitoring activities. It will improve the performance and the accuracy of the Sen2-Agri processing chains.
Upon request, service provider users will be able to access to EarthSignature from their working environment to adapt AI processing/ NN models for their own applications. SnapEarth aims to facilitate also access to EO data from the general public thanks to EO data labelling and indexation innovations and access from Qwant search engine.