#	Pagina
attuale pagina	/open-h2020/projects/214372/results.html

Report

Teaser, summary, work performed and final results

Periodic Reporting for period 1 - CANDELA (Copernicus Access Platform Intermediate Layers Small Scale Demonstrator)

Teaser

Summary

CANDELA is a 30-month research and innovation action financed by the European Commission under the H2020 Research and Innovation Programme in the topic of European Earth Observation. The project aims at building a platform who delivers building blocks and services which enable users to quickly use, manipulate, explore and process Copernicus data.
CANDELA project main objective is to allow the creation of value from Copernicus data through the provisioning of modelling and analytics tools given that the tasks of data collection, processing, storage and access will be provided by the Copernicus Data and Information Access Service (DIAS).
More concrete objectives of the CANDELA tools are the following:
- Generic Big data analytics building block allowing the analysis of large volume of Earth Observation Data.
- Tools for fusion of various multi-sensor Earth Observation (Copernicus optical and radar data, contributing missions) with Copernicus in-situ data and additional information from the web such as social networks or Open Data in order to create new applications and services.
- Compatibility of the analytics building blocks with any cloud computing back office layers (PaaS/IaaS) in order to run on a distributed architecture with a complete scalability and elasticity and eventually be deployed on top the DIAS.
- Guarantee easy compatibility between CANDELA and existing European assets and namely future DIAS.
- Capacity of these tools to generate economic and social value assessment in two use cases fulfilling the needs of public authorities and private end-users and mostly based on Copernicus and contributing missions open data.
- Develop realistic reference scenarios that demonstrate the platform capabilities and showcases its functionalities to external new users.

Work performed

The overall project approach and objectives have been fully confirmed in the first months of project operations and brought into implementation, in line with the Description of the Action (DoA).
At month 18 (October 2019) a total of 30 Deliverables have been submitted. All Deliverables produced in the project except the ones related to Management and Exploitation are Public, and already published in the project website at http://www.candela-h2020.eu/deliverables, together with other interesting dissemination material, e.g. three 6-monthly-newsletters.
Four main blocks of tools are being developed in CANDELA:
- Earth Observation data mining for classification and change detection, allowing users to refine their query by iteratively specifying a set of relevant and non-relevant images.
- Deep Learning for Change Detection on time series for optical and radar Earth observation data. For optical data, it provides generic change detection maps for every couple of images and transform these maps in a temporal curve of more interpretable change indicator. In the case of radar data, it provides a classification of each image and a change detection map for each couple of images.
- Semantic search and indexation on the output of the Earth observation library and non-image data, to allow users to make requests using multi-criteria classification.
- Data fusion techniques to merge pre-processed data that came from various sources, enabling to combine multiple image sources for classification.
A first version of the platform is running and continuously updated since December 2018. The platform is built on the cloud infrastructure provided by CloudFerro, same as for CreoDIAS, the CloudFerro instance of DIAS (Data and Information Access Service, ESA program to ease the access to Copernicus data). On top of this infrastructure, a PaaS layer (Kubernetes) and service management tools have been set up to integrate data analytics workflows provided by partners in charge of developing the analytic tools coming from WP2. A frontend layer has also been installed (Jupyter notebook environment) to interact with the workflow execution engine.
Docker is used as the basis containerization technology, and Kubernetes as the PaaS technology to setup the cluster and ensure the container management.
The need in terms of computation resources is very variable depending on the algorithms executed on the platform by the users. To adapt to this variable consumption, an elastic provisioning of the cloud computation resources has to be implemented.

Final results

CANDELA will design, implement and validate algorithms related to crop health and yield assessment at national level, and urban development at regional level. The project will also probe the value of remote sensing data collection for the monitoring of forest health conditions. More details about the project use cases and their expected impact are provided below.
Urban Expansion and Agriculture. Land cover and land use changes driven by climate changes and population growth are crucial factors that affect economy, agriculture and decision-making strategies among others. This sub-use case aims at closely studying urban expansion and the resulting agricultural surfaces shrinking. To achieve the latter objective, robust and generic data analytics tools and various remote sensing data sources are used to detect changes of interest.
Change Detection in Vineyards. Wine-making is one of the largest agricultural industries in many countries over the world including France. However, natural hazards such as frost and hail cause large damages in vineyards resulting in enormous financial loss. This sub-use case aims at using data analytics tools with remote sensing data in order to quantify the damages caused by natural hazards, which is of great interest for winemaking syndicates, farmers and insurance companies.
The abrupt natural disasters use case. This use case was expressed by State Forests in Poland after windfall that happened in August 2017. The disaster was a result of a bow echo weather phenomenon that brought winds blowing at 100-150 km/h and sweeping off forest stands on its path ranging from the Baltic Sea coast to the region of Lower Silesia. It is estimated that windfall covered almost 10 mln cubic meters of trees fallen on the area of almost 1,000 square kilometres. The disaster affected whole ecosystems and forest stands (rather than individual types and/or species and/or habitats of trees), including 22 natural reserves, 134 â€œNature 2000â€ areas, 15 protected bird habitats and breeding areas covering, inter alia, the areas protected under the Bird and Habitat Directive. In the CANDELA project satellite images will be used to train algorithms that will quickly identify areas affected by damage. This will allow foresters to efficiently manage tree cut and restoration of forest.
Forest health monitoring. This use case was expressed by people related to forest management and nature protection. Knowledge of the condition of forests and its monitoring is important for many reasons. Forests are one of the most relevant renewable resources, both economically and socially. They help to maintain the balance in the natural environment, while preserving biodiversity. Do not overlook the impact that forests have on limiting air pollution. Therefore information about the state of health of the forest and its ongoing monitoring is so important. Knowledge about the location of tree stands weakened or attacked by diseases and insects, allows for the application of appropriate preventive measures.