AI, Machine Learning Accelerate Materials Research, Compress R&D TimelinesAI, Machine Learning Accelerate Materials Research, Compress R&D Timelines

Two recent developments in artificial intelligence (AI) and machine learning have the potential to accelerate product development by streamlining materials research. Israel-based MaterialsZone, a cloud-based materials discovery platform, has introduced what it calls AI-Guided Product Development, which provides real-time experiment recommendations to guide researchers through iterative improvements in product design. Meanwhile, researchers in Japan have harnessed machine learning to optimize polymer production.

Aligning experimentation with R&D timelines

MaterialsZone leverages expertise in material science, data science, and software development to better help researchers align experimentation with R&D timelines, said the company, which was founded in 2018. The new AI-driven feedback loop reportedly transforms trial-and-error-based experimentation by building on successful use cases to gradually narrow parameters for a given application. It accelerates product development goals while considering critical material and process constraints, including cost optimization and carbon footprint reduction, according to MaterialsZone.

As each suggested experiment is completed and documented within the MaterialsZone platform, the AI model is used to refine recommendations according to the latest data, enhancing precision and efficiency. Available to researchers and technicians, this seamless cycle integrates data enrichment, machine learning, experiment synthesis, and feedback, optimizing development and reducing experimental cycles — all within a no-code framework.

Related:AI Powers Next-Gen Plastic-Film Recycling

Machine learning models polymerization process

The use of machine learning to reduce the need for time-consuming and expensive experimentation related to polymer production is at the heart of research conducted at Japan’s Nara Institute of Science and Technology. Researchers led by Professor Mikiya Fujii have used machine learning to mathematically model the polymerization process and more rapidly identify ideal manufacturing conditions.

Machine-learning algorithms need data, notes a release published in Asia Research News, so the researchers designed a polymerization process that would quickly and efficiently generate experimental data to feed into the mathematical model. The target molecule was a styrene-methyl methacrylate co-polymer, which was made by mixing styrene and methyl methacrylate monomers, both already dissolved in a solvent with an added initiator substance, then heating them in a water bath.

The two monomer solutions were mixed and heated in a constant flow — a process called flow synthesis — to allow for better mixing, more efficient heating, and more precise control of heating time and flow rate.

The flow synthesis reactor with two bottles containing a monomer, initiator, and solvent mixed using a micro-mixer. The synthesis is controlled with AI-based design of experimental conditions such as temperature and flow rate. Image courtesy of Asia Research News.

The modeling evaluated the effect of five key variables in the polymerization process:

The goal was to have an end product with as close to 50% styrene as possible.

Five calculation cycles achieve successful outcome

The machine learning process took only five calculation cycles to reach the ideal proportion of styrene to methyl methacrylate. Key to this outcome was a lower temperature and longer time in the water bath, as well as lower relative concentration of the monomer in the solvent. The researchers said they were surprised to discover that the solvent concentration was just as important as the proportion of monomers going into the mix, notes the news release.

“Our results demonstrate that machine learning not only can explicitly reveal what humans may have implicitly taken for granted but can also provide new insights that weren’t recognized before,” said Fujii. “The use of machine learning in chemistry could open the door for smarter, greener manufacturing processes with reduced waste and energy consumption.”

The research is published in the peer-reviewed journal, Science and Technology of Advanced Materials: Methods.