Machine intelligence accelerated design of conductive MXene aerogels with programmable properties

Designing ultralight conductive aerogels with tailored electrical and mechanical properties is critical for various applications. This research develops an integrated workflow combining collaborative robotics with machine learning to accelerate the design of conductive aerogels with programmable properties. An automated robot prepares mixtures of MXene, cellulose, gelatin, and glutaraldehyde. A support vector machine classifier trains on the resulting aerogels' structural integrity. Active learning cycles with data augmentation lead to an artificial neural network prediction model. This model predicts aerogel properties from fabrication parameters and inversely designs aerogels for specific property requirements. Model interpretation and finite element simulations validate correlations between density and strength. The model suggests high-conductivity, customized strength, and pressure-insensitive aerogels for compression-stable Joule heating in wearable thermal management.

Snehi Shrestha, Kieran James Barvenik, Tianle Chen, Haochen Yang, Yang Li, Meera Muthachi Kesavan, Joshua M. Little, Hayden C. Whitley, Zi Teng, Yaguang Luo, Eleonora Tubaldi, Po-Yen Chen