Big data meets materials science: Training the future generation
“Big data” is making big changes to all fields of science and engineering and revolutionizing the way researchers work and interact. The data revolution in materials and ceramics research has been driven principally by two major developments: multi-billion-dollar investments in scientific characterization instrumentation at federal laboratories1 and universities2 during the past two decades; and advances in high-throughput computational materials discovery.3,4 Further, real-time sensing coupled with robust data analytics has transformed product development and manufacturing. This area has become a target for investment by several large manufacturing companies5 and has since been referred to as the Industrial Internet of Things (IIOT).
Big data is characterized by the “three Vs”—volume, velocity, and variety—and materials research is seeing huge growth along each of these facets. As an example, the Advanced Photon Source at Argonne National Laboratory can generate more than one terabyte of data per day from some beamlines, which is expected to increase to hundreds of terabytes or even petabytes per day in 10 years.