Deep learning

Nanomaterials

Nanotechnology

Biological system

Wireless

Microfluidics

Biology

Absorbance

Operating system

Machine learning

Gaussian

Computational chemistry

Artificial intelligence

Nanoparticle

Throughput

Chemistry

Materials science

Bayesian optimization

Computer science

Gaussian process

Kriging

Process (computing)

Chromatography

Artificial neural network

Telecommunications

npj Computational Materials

In materials science, the discovery of recipes that yield nanomaterials with defined optical properties is costly and time-consuming. In this study, we present a two-step framework for a machine learning-driven high-throughput microfluidic platform to rapidly produce silver nanoparticles with the desired absorbance spectrum. Combining a Gaussian process-based Bayesian optimization (BO) with a deep neural network (DNN), the algorithmic framework is able to converge towards the target spectrum after sampling 120 conditions. Once the dataset is large enough to train the DNN with sufficient accuracy in the region of the target spectrum, the DNN is used to predict the colour palette accessible with the reaction synthesis. While remaining interpretable by humans, the proposed framework efficiently optimizes the nanomaterial synthesis and can extract fundamental knowledge of the relationship between chemical composition and optical properties, such as the role of each reactant on the shape and amplitude of the absorbance spectrum.

Two-step machine learning enables optimized nanoparticle synthesis