Machine learning guided full-color V4C3 MXene quantum dots for building WLEDs. Issue 38 (12th September 2022)

• Record Type: Journal Article
• Authors: Li, Shouzhen; Zheng, Huayu; Ding, Lan; Xiao, Xie; Niu, Yingchun; Tang, Yaoyao; Liu, Zeyang; Zhang, Weiye; Zhou, Yang; Xu, Quan
• Is Part Of: Journal of materials chemistry. Volume 10:Issue 38(2022)
• Page Start: 14282
• Page End: 14287
• Publication Date: 2022-09-12
• Subjects: Materials -- Periodicals; Chemistry, Analytic -- Periodicals; Optical materials -- Research -- Periodicals; Electronics -- Materials -- Research -- Periodicals; 543.0284
• DOI: 10.1039/d2tc02969c
• Languages: English
• ISSNs: 2050-7526

Abstract

Abstract : In this paper, we report for the first time the preparation of full-color MXene quantum dots (MQDs) using V4 C3 . Importantly, the ML-driven XGB model guided our success in obtaining the optimal WLED with CIE color coordinates of (0.333, 0.397). Abstract : Recently, machine learning (ML) in advanced materials has demonstrated outstanding potential for avoiding lengthy construction and testing cycles. The reasonable application of the data-driven ML algorithm to establish models to predict new materials and applications shows great potential. Here, we report for the first time the preparation of full-color MXene quantum dots (MQDs) using V4 C3 and using the ML method to drive the construction of white light emitting diodes (WLEDs) successfully. The experimental results show that the B/Y/R-MQDs all exhibit excellent blue (428 nm), yellow (524 nm) and red (618 nm) fluorescence. White light emission with tunable color coordinates is achieved, by using XGBoost (XGB) of the ML model to combine B/Y/R-MQDs. Importantly, the ML-driven XGB model guided our success in obtaining the optimal WLED with CIE color coordinates of (0.333, 0.397), which has important significance for guiding the synthesis of WLEDs and accelerating the development of materials science.