Autonomous Discovery of Advanced Materials

ongoing

Materials impact most aspects of our lives, including healthcare, energy production, data storage and pollution control. However, the design of functional materials cannot be approached with the certainty and the engineering rules that would be used in planning and constructing a macroscopic object, such as a car or bridge. This is because of the limited scope for design that exists at the atomic scale: experimentally realizable materials must correspond to local minima on a complex, multidimensional energy surface, whose positions and depths are difficult to predict. This project will change the way that we discover new molecular materials by revolutionizing the exploration process, rather than focussing on rules for intuitive design. This will be achieved through a unique synergistic partnership between three principal investigators, bringing together an international leader in crystal structure modelling and prediction methods, an experimental chemist with a track record for inventing new classes of functional materials, and a pioneer in robotics for laboratory and process automation. The programme integrates state-of-the-art computation, experiment and robotics, building on joint breakthroughs from our team (Nature, 2011; Nature, 2017) that lay the groundwork for a transformation in our materials discovery capabilities. We will build a Computational Engine for evolutionary exploration of chemical space using crystal structure prediction and machine learning of structure-property relationships for the assessment of molecules. In parallel, we will develop an Experimental Engine for autonomous synthesis and properties testing using newly-developed, artificially-intelligent, mobile ‘robot chemists’. The vision of ADAM is to couple these two engines together, creating an autonomous discovery platform that amplifies human creativity by searching the vast, unexplored chemical space for new materials with step change properties.