Using the world’s fourth most powerful supercomputer, Tianhe II (image), a team of China-based researchers mined a database of 11,000 marine fossil species in search of undetected extinct species. In their paper, they show how machine learning helped analyze the large marine Paleozoic dataset, creating a record with time intervals of only ∼26,000 years—a fine-scale resolution of the fossil record that is typically marred by large temporal jumps, millions of years wide.