Quantum cascade lasers (QCLs) are semiconductor devices that emit light in the mid-infrared and terahertz regions of the electromagnetic spectrum. Population inversion is achieved between intersubband electronic transitions in the conduction band of a multi-quantum well heterostructure formed by alternating InGaAs (well) and AlInAs (barrier) layers. The figure of merit (FoM), a measure for laser performance, the gain coefficient, and emission wavelength can be tailored based on selecting the number of layers, layer thicknesses, and applied electric field in the design.
Here, a machine learning (ML) framework is developed to optimize the FoM for an initial QCL design, and find new QCL structures, based on the layer thicknesses and applied electric field. The entire layer thickness and applied electric field design space is canvassed by ML to reveal new structures with high FoM. This thesis research focuses on the techniques used to build QCL datasets suitable for ML, the neural network optimization process used to make a ML algorithm for QCL FoM prediction, as well as the results and limitations of the algorithm to optimize an initial QCL design and predict new ones.
The first section presents the development of a code to automatically identify the electronic state-pair transition in a QCL design that has a potential for population inversion, i.e., the laser transition. The code is used to build datasets consisting of the number of layers, layer thicknesses, and applied electric field of many QCL designs as inputs, and the energy difference, FoM, dipole matrix element, gain coefficient, and effective scattering time between the identified laser transition states as outputs. Techniques have been developed to generate QCL designs, lower the data collection time, and devise filter methods to identify possible laser transitions.
Second, a multi-layer perceptron neural network is used on the QCL datasets. The software MATLAB is used to optimize the number of hidden layers, neurons, solver, activation function, and number of epochs needed to obtain the lowest root-mean-square error on the predicted outputs. The limitations of the algorithm to predict QCL designs are discussed, as well as neural network parameter optimization based on computational resources and time to train.
Lastly, this framework is applied to optimize an initial 10-layer structure. Two datasets each with 1800 random structures from two random layer thickness tolerance ranges: [-2, +3] Å and [-5, +20] Å are generated with an electric field sweep of 10-150 kV/cm in 10 kV/cm increments, predicting 27000 designs in about 36 hours using a virtual machine. Two algorithms are trained and used to predict the FoM for ~ 109 designs in about 8 hours on a personal computer, a significant, many orders of magnitude, increase in prediction speed when compared to building our datasets. The algorithms show which QCL layers should be altered, and by how much, and at what electric field these structures are best operated, to maximize the FoM in this design space, with prediction errors around 16%. They also reveal ways in which the dataset and laser transition code can be improved to better predict and locate QCL designs.