AI-driven research labs are taking off

Science Daily reports that an artificial intelligence-driven materials science lab can do research and plan new experiments about 10-fold faster than humans. This is a big deal.

By switching from slow, traditional methods to real-time, dynamic chemical experiments, researchers have created a self-driving lab that collects 10 times more data, drastically accelerating progress. This new system not only saves time and resources but also paves the way for faster breakthroughs in clean energy, electronics, and sustainability—bringing us closer to a future where lab discoveries happen in days, not years.

Self-driving laboratories are robotic platforms that combine machine learning and automation with chemical and materials sciences to discover materials more quickly. The automated process allows machine-learning algorithms to make use of data from each experiment when predicting which experiment to conduct next to achieve whatever goal was programmed into the system. 

"We've now created a self-driving lab that makes use of dynamic flow experiments, where chemical mixtures are continuously varied through the system and are monitored in real time," Abolhasani says. "In other words, rather than running separate samples through the system and testing them one at a time after reaching steady-state, we've created a system that essentially never stops running. The sample is moving continuously through the system and, because the system never stops characterizing the sample, we can capture data on what is taking place in the sample every half second.  

"The most important part of any self-driving lab is the machine-learning algorithm the system uses to predict which experiment it should conduct next," Abolhasani says. "This streaming-data approach allows the self-driving lab's machine-learning brain to make smarter, faster decisions, honing in on optimal materials and processes in a fraction of the time. That's because the more high-quality experimental data the algorithm receives, the more accurate its predictions become, and the faster it can solve a problem. This has the added benefit of reducing the amount of chemicals needed to arrive at a solution."

Summary of how it works: A robotic machine feeds very precise amounts of chemical solutions (colored bottles) into tiny channels etched in glass or plastic. An arrays of instruments positioned near the channels detect and measure changes in the chemicals and reaction conditions as they react in real time (squiggly arrows on the right). Data the instruments collect (image at bottom) is then fed to AI for analysis (image on left) and the analysis is output for reading by humans top image). AI and/or humans analyze the data and then prepare the machine to plan follow-on experiments to test hypotheses that pop out of the data from the 1st experiment. The chemical reactions are conducted in volumes of less than 1 fluid oz, maybe ~1/500th oz volume (~1 drop from an eyedropper).  

Improvements in AI-driven lab research will come fairly soon. This idea has already been applied in other areas of research including life sciences and biomedical research. This amounts to a fundamental shift in how research in areas amenable to fluid chemical and physiological reactions can be researched.

This really is a big deal, here and now.

By Germaine: Getting more efficient all the time. Or not.