Dr. Michael Fernandez obtained his Dr. Eng. in Information Sciences from the Kyushu Institute of Technology, Japan in 2011. His is interested in data-driven solutions for the analysis and understanding of complex phenomena in chemical, biochemical and materials systems. In the last decade, his research carrier has been focused on machine leaning and evolutionary computing strategies to identify structural-property relationships patterns. As part of the Molecular and Materials Modelling Laboratory in Data61, CSIRO, he is developing a data-driven artificial intelligence framework for the accelerated discovery of high-performing nanomaterials, including nanoporous materials, carbon nanoparticles, metallic nanocrystals and functional coating additives.
YOW! Data 2016 Sydney
Data Analytics for Accelerated Materials Discovery
Data analytics and machine learning are at the centre of social, marketing, healthcare and manufacturing research. In material discovery, they play a fundamental role to successfully tackle the exponential increase in size and complexity of functional materials. This presentation will discuss how data analytics tools can drastically accelerate materials discovery and reveal intrinsic relationships between structural features and functional properties of novel materials. Multivariate statistics techniques and simple decision tree predictors can identify design principles from high throughput data on candidate materials. Meanwhile, more complex deep learning models are calibrated on the performance of small set of materials and later generalise to identify high-performing candidates across large virtual material libraries. It will be demonstrated that data-driven predictors can rapidly discriminate among potential candidate materials at a fraction of the traditional cost, whilst providing new opportunities to understand structure-performance paradigms for novel material applications.