Application of Machine Learning to Quantum Cascade Laser Design

We propose to develop fully automated quantum cascade laser (QCL) design tools based on neural network machine learning (ML) codes. The current QCL design process requires human intervention at multiple points in the process. The primary goal of the Phase-II STTR program is to eliminate the need for human intervention, which will greatly accelerate the design process (>100x). In addition, we will utilize these codes to demonstrate high-performance QCL designs and implement these designs in a prototype device.ĀThe technical objectives of this proposal are: 1)ĀDevelop fully automatic QCL design tools based on machine learning;Ā(2)ĀImplement this design process to realize aĀprototype demonstration of a QCL meeting the target specifications:Ā> 15 W continuous wave output power at room temperature; M2Āno more than 1.5 in both the fast and slow axes; laser emission in the spectral range between 4.6 to 5.0 micrometers; and no unexpected and undesirable beam steering effect as the QCL drive current is increased.