Machine Learning Streamlines Carbon Dot Fabrication

In a recent study published in the journal Chemistry of Materials, a group of researchers has reported an intense gradient boosting (XGBoost) framework for directing the manufacturing of carbon dots with high photon emission intensity and controllable emission from p-benzoquinone (PBQ) and ethylenediamine (EDA) in various solvent systems at ambient temperature.

Machine Learning Streamlines Carbon Dot Fabrication

Study: Customized Carbon Dots with Predictable Optical Properties Synthesized at Room Temperature Guided by Machine Learning. Image Credit: archy13/Shutterstock.com

Because of its adjustable fluorescence and photo corrosion resilience, luminous carbon dots (CDs) are becoming more and more popular in the sensing and imaging industries.

However, multiple parameters, such as initial concentration, response time, and solvents play a role in the consistent and efficient fabrication of luminous CDs with precise optical characteristics. As a result, designing CDs with good optical characteristics is typically considered challenging.

What are Carbon Dots?

Carbon-based nanoparticles, particularly carbon dots (CDs), have gotten a lot of interest in recent years because of their distinctive attributes, such as easy synthesis, strong dissolution rate, excellent color distortion tolerance, low cytotoxicity, cheap cost, adjustable luminosity, and chemical stability.

CDs have been widely employed in biological imaging and biosensing because of their distinct benefits. Significant work has gone into developing different synthesis processes to generate high luminescent CDs.

Synthesis Methods of Carbon Dots

Since the identification of luminous CDs made from single-walled nanoparticles in 2004, two primary kinds of CD synthetic methods have been established: top-down and bottom-up approaches.

Large carbon compounds are broken down into little composites with diameters smaller than 10 nm using a top-down technique. The bottom-up technique, on the other hand, employs tiny carbon molecules as substrates to generate bigger carbon frameworks.

The room temperature approach is particularly advantageous among the bottom-up techniques since it does not need harsh synthesis conditions or complicated apparatus, and it is both sustainable and economical.

Nonetheless, obtaining CDs suited for bioimaging with the necessary features, such as a certain wavelength range, without completing a large-scale production and testing remains a challenge for scientists.

To prevent tedious repeated labor, a simple and highly dependable technique for obtaining CDs with desirable optical qualities must be developed.

Limitations of ML Applications for Fabrication of CDs

Machine learning (ML) has advanced fast in recent years as information and processing capacity have increased dramatically. Machine learning algorithms can develop a model based on sample data that can make accurate predictions or judgments even without fully comprehending the "black box”.

Because of these qualities, machine learning can be effectively employed in life sciences, such as spectrum forecasting, cancer biomarker identification, biosensor development, and green synthesis.

Despite this improvement, machine learning methods for CD fabrication are still in their infancy. This is because extracting adequate characteristics for the antecedents and explaining the hidden link between reactants and products is difficult for these ML models.

A Novel Machine Learning Model for CDs Production

To address the problem, the researchers looked at a variety of machine learning models for predicting the photocatalytic activity of CDs in various solvents. Using the most evaluated extreme gradient boosting (XGBoost) approach with a regression coefficient (R2) better than 0.96, more detailed research was undertaken and intricate changes were made compared to the prior DCNN version. 

In this study, the XGBoost model was used to estimate the highest fluorescence (FL) strength and emission sites of CDs produced at ambient temperature using p-benzoquinone (PBQ) and ethylenediamine (EDA) as precursor materials.

Research Conclusions and Prospects

In conclusion, under the supervision of machine learning techniques, experimental measurements gathered from 400 distinct CDs manufactured in the lab, this study enabled the accurately predicted production of CDs with controllable emission levels.

These CDs were tailored with desirable optical properties that could be used in a variety of situations, such as Fe3+ identification, extended-release of CDs stored in MSNs, whole-cell scanning, and the creation of PVA films.

This research shows that the XGBoost method, a machine learning technique, can monitor the crucial elements in CD fabrication and provide scientists with consistent and efficient availability to optimum process variables for the production of intended CDs, saving time and money when compared to conventional fabrication routes.

The XGBoost approach is also predicted to perform well in other fields of materials science.

Continue reading: Customized Carbon Dots with Predictable Optical Properties Synthesized at Room Temperature Guided by Machine Learning

Reference

Hong, Q. et al. (2022). Customized Carbon Dots with Predictable Optical Properties Synthesized at Room Temperature Guided by Machine Learning. Chemistry of Materials. Available at: https://pubs.acs.org/doi/10.1021/acs.chemmater.1c03220

Disclaimer: The views expressed here are those of the author expressed in their private capacity and do not necessarily represent the views of AZoM.com Limited T/A AZoNetwork the owner and operator of this website. This disclaimer forms part of the Terms and conditions of use of this website.

Hussain Ahmed

Written by

Hussain Ahmed

Hussain graduated from Institute of Space Technology, Islamabad with Bachelors in Aerospace Engineering. During his studies, he worked on several research projects related to Aerospace Materials & Structures, Computational Fluid Dynamics, Nano-technology & Robotics. After graduating, he has been working as a freelance Aerospace Engineering consultant. He developed an interest in technical writing during sophomore year of his B.S degree and has wrote several research articles in different publications. During his free time, he enjoys writing poetry, watching movies and playing Football.

Citations

Please use one of the following formats to cite this article in your essay, paper or report:

  • APA

    Ahmed, Hussain. (2022, January 19). Machine Learning Streamlines Carbon Dot Fabrication. AZoNano. Retrieved on November 21, 2024 from https://www.azonano.com/news.aspx?newsID=38538.

  • MLA

    Ahmed, Hussain. "Machine Learning Streamlines Carbon Dot Fabrication". AZoNano. 21 November 2024. <https://www.azonano.com/news.aspx?newsID=38538>.

  • Chicago

    Ahmed, Hussain. "Machine Learning Streamlines Carbon Dot Fabrication". AZoNano. https://www.azonano.com/news.aspx?newsID=38538. (accessed November 21, 2024).

  • Harvard

    Ahmed, Hussain. 2022. Machine Learning Streamlines Carbon Dot Fabrication. AZoNano, viewed 21 November 2024, https://www.azonano.com/news.aspx?newsID=38538.

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type
Submit

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.