New paper is out in Optics Letters!

We demonstrate how artificial intelligence can be used for replacing time-consuming numerical simulations of ultrashort pulse propagation in optical fibres. We train a feed-forward neural network to learn differential propagation dynamics, allowing emulation of direct numerical integration of fiber propagation, and particularly the highly complex case of supercontinuum generation. The results open up a route for real-time optimization and control of nonlinear dynamics.

Check out our paper in Optics Letters.