Active matter spans a wide range of time and length scales, from groups of cells and synthetic self-propelled colloids to schools of fish and flocks of birds. The theoretical framework describing these systems has shown tremendous success in finding universal phenomenology.
However, further progress is often burdened by the difficulty of determining the forces controlling the dynamics of individual elements within each system. Accessing this local information is pivotal for the understanding of the physics governing an ensemble of active particles and for the creation of numerical models capable of explaining the observed collective phenomena.
For this purpose, we have proposed a machine-learning tool, ActiveNet, that uses the collective movement of particles to learn one and two body forces acting on each particle. ActiveNet has been tested on simulations of Active Brownian particles (either repulsive or attractive), Active particles undergoing underdamped Langevin dynamics, and chiral active Brownian particles. We have demonstrated that ActiveNet can equally learn conservative or non-conservative forces as well as torques. Finally, we have applied ActiveNet to experiments of electrophoretic Janus particles, extracting the active and two-body forces that control the colloids' dynamics.
We believe that ActiveNet might open a new avenue for the study and modeling of experimental suspensions of active particles.