Machine‐Learning‐Based Exploration of Bending Flexoelectricity in Novel 2D Van der Waals Bilayers

Accurate examination of electricity generation stemming from higher-order deformation (flexoelectricity) in 2D layered materials is a highly challenging task to be investigated with either conventional computational or experimental tools. To address this challenge herein an innovative and computationally efficient approach on the basis density functional theory (DFT) machine-learning interatomic potentials (MLIPs) incorporated long-range interactions accurately investigate flexoelectric energy conversion van der Waals (vdW) bilayers proposed. In approach, short-range are defined using moment tensor trained over inexpensive DFT-based datasets. The electrostatic (charge dipole) vdW interaction parameters calibrated DFT simulations. Elaborated comparison mechanical piezoelectric properties extracted proposed available data confirms accuracy devised strategy. It shown that bilayer transition metal dichalcogenides can show coefficient 2–7 times larger than their monolayer counterparts. Noticeably, enhancement reaches up 20 for Janus diamane fluorinated boron-nitrogen derivatives bilayers. presented results improve understanding effect heterostructures moreover MLIP-based methodology offers robust tool design novel harvesting devices.