Machine Learning Models for Predicting Key Performance Characteristics of High-Temperature THz Quantum Cascade Lasers
Authors:
- Mihailo StojkovićMSMihailo Stojković
- Novak StanojevićNSNovak Stanojević
- Aleksandar MilićevićAMAleksandar Milićević
- Nikola VukovićNVNikola Vuković
- Dušan TopalovićDTDušan Topalović
- Milan IgnjatovićMIMilan Ignjatović
- Aleksandar DemićADAleksandar Demić
- Dragan IndjinDragan Indjin
- Jelena RadovanovićJRJelena Radovanović
Open Access
- 22 May 2026
- journal article
- research article
- Published by MDPI AG in Nanomaterials
- Vol. 16 (11) , 651
Abstract
In this work, we applied Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Artificial Neural Networks (ANN) to predict key performance characteristics of quantum cascade lasers (QCLs), including material gain, current density, and emission frequency. By developing a machine learning-based surrogate modeling framework that replaces computationally expensive simulations of QCLs, we enable orders-of-magnitude-faster evaluation and optimization of a high-dimensional configuration space. The training dataset was generated using a numerical simulator based on the density-matrix transport model. By combining physics simulations with machine learning, we achieved reliable predictions of device characteristics, with standardized RMSE values ranging from 0.21 to 0.55 for RF, 0.16 to 0.51 for XGBoost, and 0.04 to 0.22 for the ANN model, demonstrating the superior predictive performance of the ANN across all investigated performance characteristics. The ANN was subsequently used to analyze the full configuration space defined by possible layer thicknesses and electric fields. Approximately 44 million configurations were evaluated in about five minutes, achieving a speedup of approximately 90,000 times over the numerical simulator for a single configuration. This approach allowed the identification of designs with improved material gain and facilitated the efficient optimization of key parameters while maintaining high prediction reliability.Keywords
Funding Information
- Science Fund of the Republic of Serbia (10504)
- Ministarstvo Prosvete, Nauke i Tehnološkog Razvoja (451-03-34/2026-03/200103)
- Ministarstvo Prosvete, Nauke i Tehnološkog Razvoja (451-03-33/2026-03/200017)
This publication has 66 references indexed in Scilit:
- Numerical simulation-driven machine learning and particle swarm optimization of burner fuel distribution for cleaner combustion in a thermal power plantEngineering Applications of Artificial Intelligence, 2026
- Terahertz Quantum Cascade Lasers as Enabling Quantum TechnologyAdvanced Quantum Technologies, 2021
- Tackling Photonic Inverse Design with Machine LearningAdvanced Science, 2021
- Numerically efficient density-matrix technique for modeling electronic transport in mid-infrared quantum cascade lasersJournal of Computational Electronics, 2021
- In search of an optimal in-field calibration method of low-cost gas sensors for ambient air pollutants: Comparison of linear, multilinear and artificial neural network approachesAtmospheric Environment, 2019
- Performance optimization for terahertz quantum cascade laser at higher temperature using genetic algorithmOptical and Quantum Electronics, 2012
- Design optimization of quantum cascade laser structures at λ ∼ 11–12 µmPhysica Status Solidi (a), 2010
- THz and sub‐THz quantum cascade lasersLaser & Photonics Reviews, 2009
- Pulsed quantum cascade laser instrument with compact design for rapid, high sensitivity measurements of trace gases in airApplied Physics B, 2008
- Widely tunable mode-hop free external cavity quantum cascade lasers for high resolution spectroscopy and chemical sensingApplied Physics B, 2008