Building a Smart EM Environment - AI-Enhanced Aperiodic Micro-Scale Design of Passive EM Skins

An innovative process for the design of static passive smart skins (SPSSs) is proposed to take into account, within synthesis, electromagnetic (EM) interactions due their finite (macro-level) size and aperiodic (micro-scale) layouts. Such an approach leverages on combination inverse source (IS) formulation, define SPSS surface currents, instance System-by-Design paradigm, synthesize unit cell (UC) descriptors suitable supporting these currents. As this latter step, enhanced Artificial Intelligence (IA)-based digital twin (DT) built efficiently reliably predict relationships among UCs non-uniform coupling effects arising when are irregularly assembled build corresponding SPSS. Towards end unlike state-of-the-art approaches, small-scale model derived generate training database DT implementation. A set representative numerical experiments, dealing with different radiation objectives skin apertures, reported assess reliability conceived illustrate features resulting layouts, validated accurate full-wave simulations, as well.