Artificial neural networks-driven modeling of semiconductor optical amplifiers

This paper presents the development of several multilayer feed-forward artificial neural network (ANN) models aimed at the simulation and parametrization of semiconductor optical amplifiers (SOAs). In the <i>direct</i> approach, it is assumed that the SOA physical parameters are known, and the ANNs can reproduce the results of detailed SOA models up to 20 times faster. In the <i>inverse</i> approach, it is assumed that the SOA is a grey-box with a known model but unknown parameters, and the ANNs infer the SOA model parameters from the input-output data. These results provide efficient surrogate models to represent SOAs in future digital twins for on-line optimization of ultra-wide band transmission systems that employ the SOA as the repeater element.