Investigation of Random Laser in the Machine Learning Approach

Machine learning and deep learning are computational tools that fall within the domain of artificial intelligence. In recent years, numerous research works have advanced the application of machine and deep learning in various fields, including optics and photonics. In this article, we employ machine learning algorithms to investigate the feasibility of predicting a stochastic phenomenon: random laser emissions. This is possible because machine learning adapts to patterns and variations, optimizing for uncertainties in stochastic processes. Our results indicate that machine and deep learning have the capacity to accurately reproduce fluctuations characteristic of random lasers and distinguish the below and above threshold regions. Essentially, the algorithm described in this article is trained with one part of the spectrum to predict another part (random laser). By employing simple supervised learning algorithms, we demonstrate that the random laser intensity fluctuations can be predicted using spontaneous emission and pump intensity as input parameters in the models. Applications based on the demonstrated results are discussed.