Since the Noble prize winning invention of the scanning tunnelling microscope (STM) by Gerd Binnig and Heinrich Rohrer in 1981, it has been associated with some of the most inspirational and elegant experimental works in physics and chemistry. Arguably the instrument enables the ultimate imaging and control of matter on surfaces; by exploiting the rules of quantum mechanics one can image and even manipulate individual atoms, going far beyond traditional imaging techniques. It also, unfortunately, can be one of the most frustrating techniques used by the nanoscientist because the instruments operation is inherently reliant on the quality of a probe scanning (under feedback) just a few Angstroms (one ten millionth of a millimetre) above the surface of inquiry. Many difficult hours are spent manually altering the microscopes control parameters to coerce the arrangement of atoms, or atom, at the probes apex into a configuration that yields, retains, and accurately reproduces atomic resolution images.
In an effort to make scanning probe microscopy (SPM) a more effective and efficient technique, Dr. Richard Woolley and collaborators from the Nanoscience group, Computer Science (UoN) and the Beckman Institute (Illinois) developed a machine learning protocol that utilizes evolutionary optimization algorithms to automatically control and optimize SPM. The genetic algorithm allows both the probe, which is used to scan the surface of interest, and the associated control parameters to be tuned automatically to provide the best image possible.
The group’s work was recently honoured at the 2012 Human-Competitive awards or “Humies”, a contest hosted as part of the Genetic and Evolutionary Computation Conference (GECCO), with the silver award for human-competitive results in evolutionary and genetic programming.
Posted on Monday 22nd October 2012