Machine intelligence-accelerated discovery of all-natural plastic substitutes

Tianle Chen; Zhenqian Pang; Shuaiming He; Yang Li; Snehi Shrestha; Joshua M Little; Haochen Yang; Tsai-Chun Chung; Jiayue Sun; Hayden Christopher Whitley; I-Chi Lee; Taylor J Woehl; Teng Li; Liangbing Hu; Po-Yen Chen

doi:10.1038/s41565-024-01635-z

Machine intelligence-accelerated discovery of all-natural plastic substitutes

Nat Nanotechnol. 2024 Jun;19(6):782-791. doi: 10.1038/s41565-024-01635-z. Epub 2024 Mar 18.

Authors

Tianle Chen^#¹, Zhenqian Pang^#², Shuaiming He^#¹, Yang Li¹, Snehi Shrestha¹, Joshua M Little¹, Haochen Yang¹, Tsai-Chun Chung¹, Jiayue Sun³, Hayden Christopher Whitley¹, I-Chi Lee⁴, Taylor J Woehl^{1

3}, Teng Li⁵, Liangbing Hu⁶, Po-Yen Chen^{7

8}

Affiliations

¹ Department of Chemical and Biomolecular Engineering, University of Maryland, College Park, MD, USA.
² Department of Mechanical Engineering, University of Maryland, College Park, MD, USA.
³ Department of Chemistry and Biochemistry, University of Maryland, College Park, MD, USA.
⁴ Department of Biomedical Engineering and Environmental Sciences, National Tsing Hua University, Hsinchu, Taiwan.
⁵ Department of Mechanical Engineering, University of Maryland, College Park, MD, USA. [email protected].
⁶ Department of Materials Science and Engineering, University of Maryland, College Park, MD, USA. [email protected].
⁷ Department of Chemical and Biomolecular Engineering, University of Maryland, College Park, MD, USA. [email protected].
⁸ Maryland Robotics Center, College Park, MD, USA. [email protected].

^# Contributed equally.

Abstract

One possible solution against the accumulation of petrochemical plastics in natural environments is to develop biodegradable plastic substitutes using natural components. However, discovering all-natural alternatives that meet specific properties, such as optical transparency, fire retardancy and mechanical resilience, which have made petrochemical plastics successful, remains challenging. Current approaches still rely on iterative optimization experiments. Here we show an integrated workflow that combines robotics and machine learning to accelerate the discovery of all-natural plastic substitutes with programmable optical, thermal and mechanical properties. First, an automated pipetting robot is commanded to prepare 286 nanocomposite films with various properties to train a support-vector machine classifier. Next, through 14 active learning loops with data augmentation, 135 all-natural nanocomposites are fabricated stagewise, establishing an artificial neural network prediction model. We demonstrate that the prediction model can conduct a two-way design task: (1) predicting the physicochemical properties of an all-natural nanocomposite from its composition and (2) automating the inverse design of biodegradable plastic substitutes that fulfils various user-specific requirements. By harnessing the model's prediction capabilities, we prepare several all-natural substitutes, that could replace non-biodegradable counterparts as exhibiting analogous properties. Our methodology integrates robot-assisted experiments, machine intelligence and simulation tools to accelerate the discovery and design of eco-friendly plastic substitutes starting from building blocks taken from the generally-recognized-as-safe database.