LANL: New Software Could Help Transform The Budding Bioplastics Industry

From left, Ghanshyam Pilania, Carl Iverson, Babetta Marone and Joseph Dumont of theLos Alamos National Laboratory BioManIAC project. Photo Courtesy LANL


Single-use plastics, such as water bottles, grocery bags, food packaging and the like make up around 50% of the world’s estimated 380 million tons of global plastic waste each year. While manufacturers are working to improve offerings in bioplastics, we are still decades away from truly competitive biodegradable solutions. High costs and time-consuming traditional research and development are required for new plastics.

But a new tool from Los Alamos National Laboratory, called BioManIAC (Bioplastics Manufacturing with Intelligent Adaptive Control), integrates machine-learning and big-data approaches to assist plastic producers in transitioning from petroleum-based polymers. Using new biopolymers instead, they can begin to meet government mandates and environmental stewardship needs.

“As a society, we generate a staggering amount of plastic waste, with severe consequences on the environment and human health,” said BioManIAC engineer Joseph Dumont. “We could mitigate the overwhelming problem of petroleum-derived plastic pollution with the development of bioplastics that safely, completely biodegrade. However, we are still decades away from developing large-scale, competitive bioplastic options. BioManIAC accelerates the development of new bioplastics, using a machine learning-based approach to predict biopolymer structures with the desired features necessary to replace conventional plastics. These new bioplastics will help us reduce our impact on the environment now and for generations to come.”

Filling data gaps without testing

The key to the BioManIAC software platform is that it fills the gaps in data to gain insight into new potential polymer properties without actually making and physically testing them. Polymer engineers can use BioManIAC software to extrapolate and tune new biopolymer properties to create small “smart libraries,” rather than going through large-scale trial and error testing.

This targeted design is expected to improve both time-to-market and R&D expenditure, as well as the resulting mechanical properties of biopolymers, enabling for more direct competition with traditional petroleum-based polymers. Making the development of biopolymers more accessible is a dramatic step forward for reducing the Earth’s plastic burden