دورية أكاديمية

Interpretable delta-learning of GW quasiparticle energies from GGA-DFT

التفاصيل البيبلوغرافية
العنوان: Interpretable delta-learning of GW quasiparticle energies from GGA-DFT
المؤلفون: Artem Fediai, Patrick Reiser, Jorge Enrique Olivares Peña, Wolfgang Wenzel, Pascal Friederich
المصدر: Machine Learning: Science and Technology, Vol 4, Iss 3, p 035045 (2023)
بيانات النشر: IOP Publishing, 2023.
سنة النشر: 2023
المجموعة: LCC:Computer engineering. Computer hardware
LCC:Electronic computers. Computer science
مصطلحات موضوعية: delta learning, machine learning, GW, graph neural networks, GGA-DFT, Computer engineering. Computer hardware, TK7885-7895, Electronic computers. Computer science, QA75.5-76.95
الوصف: Accurate prediction of the ionization potential and electron affinity energies of small molecules are important for many applications. Density functional theory (DFT) is computationally inexpensive, but can be very inaccurate for frontier orbital energies or ionization energies. The GW method is sufficiently accurate for many relevant applications, but much more expensive than DFT. Here we study how we can learn to predict orbital energies with GW accuracy using machine learning (ML) on molecular graphs and fingerprints using an interpretable delta-learning approach. ML models presented here can be used to predict quasiparticle energies of small organic molecules even beyond the size of the molecules used for training. We furthermore analyze the learned DFT-to-GW corrections by mapping them to specific localized fragments of the molecules, in order to develop an intuitive interpretation of the learned corrections, and thus to better understand DFT errors.
نوع الوثيقة: article
وصف الملف: electronic resource
اللغة: English
تدمد: 2632-2153
Relation: https://doaj.org/toc/2632-2153
DOI: 10.1088/2632-2153/acf545
URL الوصول: https://doaj.org/article/49feba63772b4741ae246f56b447cc7a
رقم الأكسشن: edsdoj.49feba63772b4741ae246f56b447cc7a
قاعدة البيانات: Directory of Open Access Journals
الوصف
تدمد:26322153
DOI:10.1088/2632-2153/acf545