Data and Modelling
We have access to an increasing amount of data – data both from the laboratory and data from computer simulations and calculations. As the quantity and quality of the data increases, we have a growing opportunity to leverage this data towards accelerated scientific discovery. This can have massive benefits in reducing wasted time and effort by fully exploiting what is already known. Data-driven approaches include the use of artificial intelligence, such as machine learning, as well as optimisation algorithms. The increasing availability of open-source data and algorithms will change the landscape of the molecular design and fabrications across molecular and materials discovery.
The aim of the Data and Modelling pillar is to advance the application of data-driven and modelling approaches across the area, promoting that data is findable, accessible, interoperable and reusable (FAIR) and the development of the skills needed to leverage this data for data-driven discovery through the development and application of algorithms. This will not only include analysis of generated data after experiments or simulations, but on-the-fly analysis for efficient optimisation and closed-loop approaches with automation.