Optical Properties Prediction for Red and Near-Infrared Emitting Carbon Dots Using Machine Learning
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
Original language | English |
---|---|
Article number | 2310402 |
Journal / Publication | Small |
Volume | 20 |
Issue number | 29 |
Online published | 11 Feb 2024 |
Publication status | Published - 18 Jul 2024 |
Link(s)
Abstract
Functional nanostructures build up a basis for the future materials and devices, providing a wide variety of functionalities, a possibility of designing bio-compatible nanoprobes, etc. However, development of new nanostructured materials via trial-and-error approach is obviously limited by laborious efforts on their syntheses, and the cost of materials and manpower. This is one of the reasons for an increasing interest in design and development of novel materials with required properties assisted by machine learning approaches. Here, the dataset on synthetic parameters and optical properties of one important class of light-emitting nanomaterials – carbon dots are collected, processed, and analyzed with optical transitions in the red and near-infrared spectral ranges. A model for prediction of spectral characteristics of these carbon dots based on multiple linear regression is established and verified by comparison of the predicted and experimentally observed optical properties of carbon dots synthesized in three different laboratories. Based on the analysis, the open-source code is provided to be used by researchers for the prediction of optical properties of carbon dots and their synthetic procedures. © 2024 Wiley-VCH GmbH.
Research Area(s)
- carbon dots, luminescence, machine learning, multiple linear regression model, quantum yield
Citation Format(s)
Optical Properties Prediction for Red and Near-Infrared Emitting Carbon Dots Using Machine Learning. / Tuchin, Vladislav S.; Stepanidenko, Evgeniia A.; Vedernikova, Anna A. et al.
In: Small, Vol. 20, No. 29, 2310402, 18.07.2024.
In: Small, Vol. 20, No. 29, 2310402, 18.07.2024.
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review