The first activity involves strengthening of the human capacity in the scientific exploration of generic tools for data science technologies, and in the application of domain-specific tools in the context of agriculture research. We envision one PhD in software engineering tools for (big) data science and three MA’s. The second activity entails developing and making available a suite of tangible assets that are part of the generic body of knowledge on data science tools and techniques. The third activity involves developing and making available a suite of tangible assets that are part of the domain specific body of knowledge on how to apply state of the art technologies in data science. The fourth activity entails the assembly of a hardware and software infrastructure for (i) data management and (ii) data science research activities. The fifth activity involves setting up a dissemination platform for project results for Projects 1-3. The last activity entails improving the human capacity regarding proposal writing, scientific communication and the correct application of statistical methods in the execution of ongoing and the launching of future research projects.