Presentation by D. Bronte Ciriza at the 19th Electromagnetic and Light Scattering Conference

Comparison between the Geometrical Optics (GO) method and the Neural Network (NN) for the optical forces and torques calculation. The NN improvement in speed and accuracy could help to study the motion of active particles in optical landscapes. Image by D. Bronte Ciriza.
Machine learning to enhance the calculation of optical forces in the geometrical optics approximation
David Bronte Ciriza, Alessandro Magazzù, Agnese Callegari, Maria A. Iatì, Giovanni Volpe, Onofrio M. Maragò
Submitted to: ELS-XIX (2021)
Date: 14 July
Time: 12:50 CEST

Short Abstract:
We show how machine learning can improve the speed and accuracy of the optical force calculations in the geometrical optics approximation

Extended Abstract:
Since the pioneering work by Ashkin in the 1970’s, optical forces have played a fundamental role in fields like biology, nanotechnology, or atomic physics. In all these fields, numerical simulations are of great help for validating theories, for the planning of experiments, and in the interpretation of the results. However, the calculation of the forces is computationally expensive and prohibitively slow for numerical simulations when the forces need to be calculated many times in a sequential way.

Recently, machine learning has been demonstrated to be a promising approach to improve the speed of these calculations and therefore, to expand the applicability of numerical simulations for experimental design and analysis. In this work we show that machine learning can be used to improve not only the speed but also the accuracy of the force calculation in the geometrical optics regime, valid when the particles are significantly bigger than the wavelength of the incident light. This is first demonstrated for the case of a spherical particle with 3 degrees of freedom and later expanded to 9 degrees of freedom by including all the relevant parameters involved in the optical forces calculation. Machine learning is proved as a compact, accurate, and fast approach for optical forces calculation and presents a tool that can be used to study systems that, due to computation limitations, were out of the scope of the traditional ray optics approach.

Improving epidemic testing and containment strategies using machine learning on ArXiv

Comparison of different evolution regimes of disease spreading: free evolution (bottom left half) vs network strategy (top right half). Image by L. Natali.
Improving epidemic testing and containment strategies using machine learning
Laura Natali, Saga Helgadottir, Onofrio M. Maragò, Giovanni Volpe
arXiv: 2011.11717

Containment of epidemic outbreaks entails great societal and economic costs. Cost-effective containment strategies rely on efficiently identifying infected individuals, making the best possible use of the available testing resources. Therefore, quickly identifying the optimal testing strategy is of critical importance. Here, we demonstrate that machine learning can be used to identify which individuals are most beneficial to test, automatically and dynamically adapting the testing strategy to the characteristics of the disease outbreak. Specifically, we simulate an outbreak using the archetypal susceptible-infectious-recovered (SIR) model and we use data about the first confirmed cases to train a neural network that learns to make predictions about the rest of the population. Using these prediction, we manage to contain the outbreak more effectively and more quickly than with standard approaches. Furthermore, we demonstrate how this method can be used also when there is a possibility of reinfection (SIRS model) to efficiently eradicate an endemic disease.