Random Forest and K-Nearest Neighbors Prediction of the Optical Properties of 2D Ultra-thin Quantum Dots under Hydrostatic Pressure

Optical absorption spectra from the $GW$-Bethe-Salpeter framework for thousands of atoms

The frequency-dependent absorption and emission of light determine the colors of matter and underpin today's technologies, from solar cells to light-emitting diodes. Predicting optical properties from first principles remains a computational challenge, especially for large and disordered systems. The $GW$ plus Bethe-Sa...

Machine learning enhanced prediction of optical properties via reverse Monte Carlo method.

This approach enables the direct prediction of the ELF and optical constants from measured REELS spectra with reduced computational cost as compared to the previous RMC method, and the predicted ELFs from ML exhibit high accuracy as verified by sum rules.

High-speed prediction of slow light behavior of ring-hole photonic crystal waveguides using artificial neural networks

AI-Driven Surrogate Modeling and Inverse Design of Type-II Superlattice Infrared Detectors

The conventional design of Type-II superlattice (T2SL) infrared detectors relies on iterative physics-based simulations, which can make broad exploration computationally costly. Here, we develop an AI-driven surrogate workflow for InAs/GaSb T2SL detectors. Two separately trained Transformer regressors with the same lay...

Fast prediction of photonic crystal microcavity frequency based on multilayer feedforward neural network

Photonic crystal microcavities play an important role in modern integrated optical devices. However, traditional electromagnetic simulations based on the Plane Wave Expansion (PWE) method or Finite-Difference Time-Domain (FDTD) method consume significant computational resources and time, which severely restricts the ef...

Machine learning prediction of frontier orbital energies in graphene and silicon carbide quantum dots

This work addresses a critical gap in data-driven modeling of low-dimensional quantum materials by curating a dataset of 254 functionalized and doped graphene and silicon carbide quantum dots with DFT-computed HOMO and LUMO energies, establishing a foundation for high-throughput screening and inverse design of quantum...