iconLogo
Published:2025/8/22 17:22:24

TDDFT爆速化!新材料開発を加速🚀

超要約: 機械学習(FNO)でTDDFT(電子計算)を爆速化!新材料開発とか、色々捗るよ~!✨

ギャル的キラキラポイント✨ ● TDDFTを高速化して、計算時間大幅カット!時短最高~💖 ● レーザー照射とか、色んな条件を試せるように!実験みたいで楽しい♪ ● 新材料開発とか、デバイス設計がはかどる!IT業界もアゲ⤴︎︎︎

詳細解説 背景 TDDFT(時間依存密度汎関数理論)って、電子の動きを計算するスゴい方法😎✨でも計算が大変なのよね😢IT業界でも、新材料とか光の分野で使われてるんだけど、時間がネックだった!

方法 FNO(自己回帰型ニューラルオペレーター)っていう、機械学習の技術を使って、TDDFTの計算を爆速にしたの!🥳従来の計算方法より、精度も計算速度もUPを目指したよ!

続きは「らくらく論文」アプリで

Machine Learning Time Propagators for Time-Dependent Density Functional Theory Simulations

Karan Shah / Attila Cangi

Time-dependent density functional theory (TDDFT) is a widely used method to investigate electron dynamics under external time-dependent perturbations such as laser fields. In this work, we present a novel approach to accelerate electron dynamics simulations based on real time TDDFT using autoregressive neural operators as time-propagators for the electron density. By leveraging physics-informed constraints and featurization, and high-resolution training data, our model achieves superior accuracy and computational speed compared to traditional numerical solvers. We demonstrate the effectiveness of our model on a class of one-dimensional diatomic molecules under the influence of a range of laser parameters. This method has potential in enabling real-time, on-the-fly modeling of laser-irradiated molecules and materials with varying experimental parameters.

cs / cond-mat.mtrl-sci / cs.LG / physics.comp-ph