Advanced Design of a III-Nitride Light-Emitting Diode via Machine Learning

Gallium nitride (GaN)-based light-emitting diodes (LEDs) have obtained great market success in the past 20 years. However, the traditional research paradigm, i.e., experimental trial-and-error method, no longer adapts to the industry development. In this work, an efficient approach is demonstrated to design and optimize GaN-based LED structures via machine learning (ML). By using the dataset of GaN-based LED structures over the past decade to train four typical ML models, it is found that the convolutional neural network (CNN) provides the most accurate prediction, with a root mean square error (RMSE) of 1.03% for internal quantum efficiency (IQE) and 11.98 W cm-2 for light output power density (LOPD). Based on the CNN model, 1) the feature importance analysis is adopted to reveal the critical features for LED performance; 2) the predicted trends of IQE and LOPD match well with the physical mechanism, being consistent with the experimental and simulation results; and 3) a high-throughput screening is demonstrated to predict the properties of over 20 000 structures within seconds to obtain high efficiency LED structures. This ML-based LED design method enables direct guiding of the LED structure optimization in terms of key parameter selection during manufacturing and greatly accelerates the development cycle of GaN-based LEDs. An efficient approach to design and optimize gallium nitride (GaN)-based light-emitting diode (LED) structures via machine learning (ML) is established. With the best-performed convolutional neural network model, the internal quantum efficiencies (IQEs) and light output power densities (LOPDs) of different LED structures can be predicted with high accuracy. This method enables direct guiding and acceleration of the development cycle of GaN-based LEDs.image

Automated summary

An efficient approach to design and optimize GaN-based LED structures using machine learning is demonstrated. The convolutional neural network model provides accurate predictions of internal quantum efficiency and light output power density for different LED structures. This method enables direct guiding and accelerates the development cycle of GaN-based LEDs.