Skip to main content

Data-Driven Bioeconomy

Periodic Reporting for period 1 - DataBio (Data-Driven Bioeconomy)

Reporting period: 2017-01-01 to 2018-06-30

DataBio (Data-driven Bioeconomy) is a H2020 Lighthouse project focusing on utilizing Big Data technologies (software components and datasets) to improve the productivity in bioeconomy in a sustainable way. It deploys over 90 state-of-the-art Big Data, Earth Observation and ICT technologies as well aspartners’ existing infrastructure and solutions, linked together through the DataBio Platform. It is driven by the development, use and evaluation of 26 pilots covering agriculture (13), forestry (7) and fishery (6). The pilots demonstrate how Big Dataincreases the efficiency of the production of raw materials from the 3 sectors, which in its turn grows the output of food, energy and biomaterials, responsibly and sustainably. DataBio organizes a series of trainings and hackathons to support the take-up of its results and to enable developers outside the consortium to create new components and services based on and for the DataBio Platform.

DataBio aims to show the benefits of Big Data technologies in bioeconomy, through continuous cooperation between experts from end user and technology provider companies, from bioeconomy and ICT-technology research institutes, and and stakeholders from the Big Data Value PPP programme.from other partners.

The DataBio pipelines of technology components aggregate data sets and data streams from sources within three identified sectors (agriculture, forestry and fishery). Further, the pipelines process and analyse the data and allow the three sectors to selectively utilize numerous platform components, according to their requirements.

In the pilots also associated partners and other external stakeholders are actively involved. The selected pilots and concepts will be transformed into pilot implementations using co-innovative approaches and tools. Iterative trial phases will provide feedback to the ICT/ Big Data and Earth Observation technology experts, allowing them to improve their solutions.

Based on the pilot results and the DataBio platform, new solutions and new business opportunities are expected to emerge.

The DataBio objectives include:
* Build a versatile DataBio platform suitable for different industries and user profiles
* Ensure effective utilization of existing data sets
* Ensure a wide-spread use of the DataBio platform technologies in the agriculture, forestry and fishery sectors
* Opening the possibilities for European ICT industry including SMEs to participate actively on European and WorldWide Bioeconomy Big Data market
* Opening the possibilities for European Earth Observation industry including SMEs offering their new Bioeconomy related services in Europe and World Wide
* Ensure interoperability and easy setup of new multivendor applications utilizing Big DataBio platform
In its first half DataBio has set up the pillars for the demonstrations, improvements and result take up to be done in its second half.

The DataBio pilots have been fully defined: 13 in agriculture, 7 in forestry and 6 in fishery. Both pilots and the technology solutions provided by the DataBio partners were modelled using ArchiMate formalism to enable proper linking of modules within pipelines and future meta-analysis.

The technology needs of the pilots were collected and matched with the technology solutions provided by the DataBio partners through an iterative process. Preliminary experiments around datasets were carried through.

The first version of the DataBio platform was developed. This included over 90 technology components and formed 13 major pipelines of components.

This allowed the final preparations for the execution of the first pilot trials. These trials should be concluded by October 2018.

In parallel, first versions of the DataBio business plan and the partners’ exploitation plans (individual and joint) were prepared. These were complemented by PESTLE, SOTA and stakeholder analyses , supporting the take-up of the project results.

The results so far are documented in the 14 public deliverables ( In addition, several internal deliverables have been produces. In addition, are the dscritions of the datasets, components, pipelines and pilots available from the searchable DataBioHub portal (
DataBio’s expected achievements include:
* Demonstrate increase of productivity in bioeconomy
* Increase of market share of Big Data technology providers in the bioeconomy sector
* More than double the use of Big Data technology in bioeconomy
* Leveraging additional target sector investments by a factor of >5
* Engage more than 100 organizations in demonstrations
* Liaison with other Big Data actions
* Closely working with the BDVA community

The first round of pilot trials, that will end in October 2018, will give concrete results and show to which extent the expected Big Data benefits listed above are achieved. Already now it can be seen that substantial progress towards these goals have been made. The software pipelines, based on partner´s components and datasets, have enabled the successful execution of a significantly bigger number of pilot trials than foreseen in the original plan. This is because similar technology solutions have been applied in multiple pilots saving a substantial amount of development effort. In the second phase of the project will the pipelines be made even more general enhancing the deployment of the solutions to the needs in farming forestry and fishery.

DataBio has actively taken part in BDVA activities, like having presentations and stands at summits and meetup events with the other Big Data projects.
DataBio logo
DataBio value creation