BigDataGrapes aims to support all European companies active in two key industries powered by grapevines: the wine industry and the natural cosmetics one. It will help them respond to the significant opportunity that big data is creating in their relevant markets, by pursuing...
BigDataGrapes aims to support all European companies active in two key industries powered by grapevines: the wine industry and the natural cosmetics one. It will help them respond to the significant opportunity that big data is creating in their relevant markets, by pursuing two ambitious goals:
â— To develop powerful data processing technologies that will increase the efficiency of companies that need to take important business decisions dependent on access to vast and complex amounts of data
â— To catalyse the creation of a data ecosystem and economy that will increase the competitive advantage of companies that serve with IT solutions to these sectors
Grapes are one of the world’s largest fruit crops, with approximately 75 million tons produced each year. For this reason, it is the fruit crop with the highest total value of production in the world, representing almost 70 billion of US dollars. BigDataGrapes is directly aiming to support EU companies that are operating in two industries of extreme significance and potential for growth and innovation.
The wine industry is a booming one: there are more than one million wine makers in the world, producing around 2.8bn cases of wine each year. Global demand has hit nearly 3bn and is rising. But the global wine industry is changing shape, with the old world gradually losing its crown as the world\'s vineyard. European vineyards and wine producers need to remain at the bleeding edge of innovation in order to maintain their market positions with high quality products.
The cosmetic industry is also one of the largest ones internationally, with a market volume in the US, Europe, and Japan alone being about EUR €70bn per year and an estimated annual turnover of US$170 billion. Within this industry, the natural and organic market segment is constantly growing - expected to reach USD 25.11 billion by 2025 with approximate growth of 8-10% per year.
Work outcome: A set of detailed use case specifications highlighting the data challenges that decision makers face in important situations. A set of resulting research items on novel data processing components.
Related progress in the Reporting Period:
â— The first iteration of use case development gave emphasis to a selection of critical decisions of a vineyard owner that we can support. We have developed a number of detailed use cases associated with these decisions.
â— The second iteration focused on use cases associated to critical decisions that the quality assurance manager and procurement manager of a buyer takes. We have developed use cases related to these decisions.
â— The above have given a basis upon which the initial research experimentation of the project took place.
Work outcome: A big data software stack comprising the components that implement the novel methodologies for each technical challenge.
Related progress in the Reporting Period:
â— The initial deployment of a data platform MVP in one of the agricultural case studies of this CSA as well as the big data software stack that it has provided served as the starting point for selecting, assessing and incorporating components for our project.
â— We have worked on the definition and design of the architecture of a new data platform architecture that will include state-of-art components.
â— Candidate technologies for a number of select components have been developed and tested.
â— A micro-services architecture has been chosen, consuming data through a dedicated Data Ingestion Layer and offering both processed data and component execution through APIs.
Work outcome: Novel big data visualization components that effectively handle complex representations.
Related progress in the Reporting Period:
â— The project has focused on exploring different visualisation methods to provide decision support in cases when uncertainty is high.
Work outcome: A testing methodology that covers all aspects of components performance, efficiency, resource usage, along with the progressive results of the BigDataGrapes software assets under the testing methodology and their positioning with respect to the state-of-the-art.
Related progress in the Reporting Period:
â— The project has developed a testing methodology that will be used to perform rigorous and automated testing of the candidate components for our big data platform.
â— Initial experimentation and testing over data sets initially provided from use case partners took place.
Work outcome: A detailed evaluation and piloting for the BigDataGrapes technical outcomes under the specified use cases, providing the pilot workflow and the evaluation criteria.
Related progress in the Reporting Period:
â— The project has developed a detailed plan for a number of pilots that it will run with representatives of real industry stakeholders from its network.
â— A revised list of industry representatives to be involved in each pilot has been created, involving some leading companies in the grapevine-powered market segments that the project addresses.
Work outcome: A data marketplace proof-of-concept where grapevine-powered data assets will be shared and exchanged in interoperable formats and versions, by companies and organisations responsible for them.
Related progress in the Reporting Period:
â— The project has started to design the way that a data marketplace will be implemented, on top of the operational version of the big data platform.
BigDataGrapes is targeting technology challenges of the grapevine-powered data economy as its business problems and decisions requires processing, analysis and visualisation of data with rapidly increasing volume, velocity and variety.
In order to realize its vision, BigDataGrapes will achieve the following objectives:
1. Document how grapevine-powered business problems correspond to (big) data challenges: to start from the problems that companies in these industries face when taking business-critical decisions; and translate them into cross-sector data challenges that current technologies cannot efficiently handle.
2. Develop methods and tools that go beyond the state-of-the-art in Big Data management and processing: BigDataGrapes aspires to advance the Big Data technical landscape by defining novel methods for distributed indexing, processing and inference.
3. Leverage data value via insights and actionable recommendations: BigDataGrapes will incorporate techniques for the analysis and semantic enrichment of the examined datasets.
4. Rigorously assess the improvements on performance and resource usage: In order to accurately determine the technical advancements achieved, BigDataGrapes will define and apply a rigorous experimental testing methodology for all its produced technical assets.
5. Evaluate the proposed technical solution within real-world settings and against realistic requirements: The development of fully defined demonstrators for each of the grapevine-powered industry use cases will allow to showcase and evaluate the BigDataGrapes platform and components in the context of specific end-user requirements from the different areas.
6. Explore representative data flows within the covered industrial value chains in order to define and update appropriate data standards: The creation of an environment in which BigDataGrapes partners and other collaborating groups (such as from relevant big data projects) can discover, access and freely experiment with the data assets.
More info: http://www.bigdatagrapes.eu/.