Data mining is often used by businesses such as retailers to find isolated trends buried into the mountains of data gathered at their cash registers. But this process cannot really be applied to science for discovering new materials even if you have huge databases describing all your previous experiments. This is why an interdisciplinary team of researchers and engineers at Purdue University is working on 'knowledge discovery', a new computer-aided product design method that uses supercomputing, AI and large 3D displays.

"Instead of mining for a nugget of gold, knowledge discovery is more like sifting through a warehouse filled with small gears, levers, etc., none of which is particularly valuable by itself. After appropriate assembly, however, a Rolex watch emerges from the disparate parts," said James Caruthers, a professor of chemical engineering.

The system allows researchers to interact with their data in their own languages and uses a 12x7 feet tiled wall to display the results. Read this summary for selected excerpts.