Accelerating colloidal quantum dot innovation with algorithms and automation

Abstract

This review discusses how high-throughput experimentation and data-driven strategies, such as the use of machine learning models, are being used to enable rapid advances in colloidal quantum dot technologies.

Expanding the Horizons of Machine Learning in Nanomaterials to Chiral Nanostructures

“…Furthermore, the occasional omission of errors and uncertainties from laboratory equipment and experimental setups, along with the constraints of finite data ranges, can limit the analysis and further implementation of derived dependencies. [4] Furthermore, in order to build a sufficiently complex model for an accurate description of synthesis-structure-property correlations, it is insufficient to obtain data from one set of experiments, and it is of the utmost importance to collect as much data as possible. Tremendous amounts of data are dispersed across many different sources, including in-depth discussion of results in the literature, which can be extracted by text mining methods.…”

“…Furthermore, the occasional omission of errors and uncertainties from laboratory equipment and experimental setups, along with the constraints of finite data ranges, can limit the analysis and further implementation of derived dependencies. [ 4 ]…”

“…An excellent review from Munyebvu et al focuses on the use of high‐throughput microfluidic synthesis in combination with ML to study the properties of colloidal quantum dots (QDs) and to facilitate the translation of QDs to production and applications. [ 4 ] These relatively low‐cost and simple systems can be designed to be extremely versatile and modular, can be easily customized from smaller components, and can be tailored to specific applications. Moreover, the data generated is standardized and already in a machine‐friendly format, and several parameters can be collected/monitored simultaneously and continuously in time allowing the design of a high‐quality data space efficiently.…”

“…Furthermore, interested readers may refer to several recent reviews on the application of ML in different research directions of materials science. [ 3–5 ] AI, and more specifically ML, are exciting prospects for improving the quality and speed of the development of materials science and, in particular, chiral nanomaterials (NMs). This is reflected in the sizeable number of recent reviews and perspectives which are devoted to the discovery of novel NMs, for example 2D materials, [ 6 ] plasmonic NMs, [ 7 ] carbon‐based NMs, [ 8 ] and beyond.…”

Optical Properties Prediction for Red and Near‐Infrared Emitting Carbon Dots Using Machine Learning

“…[8,9] The ML approaches can be used for i) data mining, including text recognition; ii) managing large datasets, including data curation and analysis; iii) analysis of materials synthesis-morphology-properties correlation; iv) prediction and optimization of novel materials with properties of interest and high performance. The interested reader is referred to several recent reviews [10][11][12][13] and research articles. [14][15][16] ML can also be used for the prediction and optimization of the desired properties of nanomaterials, including establishment of the influence of their synthetic parameters on optical properties of nanoparticles, based on datasets split into train and test and applied to regression modeling.…”