Fujitsu Combines Quantum, AI, Supercomputer for Chemical Simulation

Fujitsu has combined quantum chemical simulation technology and artificial intelligence running on a classical supercomputer to develop a catalyst that produces ammonia more sustainably.

Working with Icelandic startup Atmonia, Fujitsu used the quantum technology with its specialized scientific discovery AI. They halved the search time for a catalyst material that efficiently synthesizes ammonia from water, air and electricity at ambient temperatures and pressures.

The companies carried out quantum chemical calculations on a Fujitsu supercomputer using Atmonia’s ammonia synthesis simulation data. They then used the output data to train an AI simulation model to quickly identify candidate catalysts.

This produced more than 10,000 candidate catalyst molecules. To further narrow which of these candidates would produce the best results, the company fed further data into the AI engine about what makes a catalyst effective, such as the type and position of the atoms that make it up.

By inputting this structural data as AI training data, the companies could predict new catalyst material candidates 100 times faster than conventional quantum chemical calculations alone.

The companies plan to use this technology to select some of these candidate catalysts and verify their effectiveness at producing sustainable ammonia.

By combining the generation of simulation data to speed quantum chemical calculations with high-performance computing and train AI simulation models to predict unknown data, the two companies have developed technology that can significantly increase the efficiency of catalyst search.