To accelerate development of useful new materials, researchers at Berkeley Lab have automated the novel-materials testing process by incorporating AI-guided robots that can work around the clock. In doing so, they have been able to test 50 to 100 times as many samples each day compared to a human researcher.
Nanomaterials, which have dimensions of 1–100 nanometers, are a major focus of novel materials research because they have unique properties that can be exploited in a wide range of applications. (Northwestern University)
Biomimicry, which uses nature as a model to create new materials, is an important approach in novel materials research. (Nature Journal)
3D printing is revolutionizing novel materials research by allowing researchers to create complex structures with precise control over their properties. (Science Direct)
Similar to how scientists knew there were undiscovered elements that would eventually fill the gaps in the periodic table, scientists have computationally predicted hundreds of thousands of novel materials that could be promising for new technologies—but testing to see whether any of those materials can be made in reality is a slow process. Scientific testing is pretty much the same today as it was in the mid 1900s. A sample material is created, it’s tested, results are recorded by hand, results are analyzed by a scientist, the researcher determines what needs tweaking, a new formula is created, it's tested, and the process repeats itself in incrementally slow and tedious steps until a new material is created or a dead-end is reached.
Enter A-Lab, the automated lab at the Department of Energy’s Lawrence Berkeley National Laboratory (Berkeley Lab), where robots assisted by AI can process 50 to 100 times as many samples as a human every day. A-Lab uses AI to speed up the cycle by having machines that quickly analyze readings, correct themselves, and pursue promising finds while rejecting poor ones as they move toward discovering the materials of the future.
The robots can mix a sample, test it, analyze the data, and then, using AI, decide what to do next to get closer to the goal. The system is composed of three robotic arms, operates all day / every day, and routinely tests 100 to 200 samples per day. It’s similar to a manufacturing environment, where robotics and automation has been used for a long time.
The system at A-Lab is designed as a “closed-loop,” where decision making is handled without human interference. The setup is adaptive, so the AI can handle the changing research environment as it occurs rather than always doing the same thing, even if it is no longer appropriate. In addition, the robots operate around the clock, freeing researchers to spend more time designing experiments.
As the automated system creates and analyzes samples, the data flows back to A-Lab researchers, as well as data repositories, such as the Materials Project. Scientists are also building out integrations with other projects, such as MaterialSynthesis.org, and leveraging x-rays from Berkeley Lab’s powerful synchrotron, the Advanced Light Source.
“You can imagine the power of a lab that autonomously starts with predictions, requests data and computations to get the information it needs, and then proceeds,” notes Yan Zeng, head of the lab. “As A-Lab tests materials, we’re going to learn the gap between our computations and reality. That will not only give us a handful of useful new materials, but also train our models to make better predictions that can guide future science.”
At the moment, A-Lab researchers are focusing on finding new materials for batteries and energy storage, which addresses a critical need for an affordable, equitable and sustainable energy supply. However, they believe that the A-Lab process can be adapted to help identify and fast-track materials for several research areas, including solar cells, fuel cells, thermoelectrics (materials that generate energy from temperature differences) and other clean energy technologies.
A-Lab began operating in February and has already synthesized several novel materials in collaboration with the Materials Project. Researchers are currently fine-tuning the system while continuing to add features. These include robots that can restock supplies and change precursors, synthesis instruments that let them mix and heat liquids, and additional equipment to analyze newly created materials.