Application of Machine Learning Techniques to the N-particle Expansion

by Tlektes Zhanabekova
Doctoral thesis
Date of Examination:2024-10-08
Date of issue:2025-10-08
Advisor:Prof. Dr. Ricardo A. Mata
Referee:Prof. Dr. Ricardo A. Mata
Referee:Prof. Dr. Martin A. Suhm
Persistent Address: http://dx.doi.org/10.53846/goediss-11539

 

 

Files in this item

Name:PhD_Thesis_TZ.pdf
Size:13.8Mb
Format:PDF

The following license files are associated with this item:

Abstract

English

This thesis explores the use of computational methods in quantum chemistry, focusing on the challenge of accurately computing full configuration interaction (FCI) energies. While FCI represents the exact solution to the electronic Schrödinger equation, its exponential scaling limits applications to small systems. To address this, machine learning–based correction methods are developed to improve the extrapolation of coupled cluster results toward the FCI limit. These approaches are benchmarked against standard extrapolation techniques and demonstrate superior accuracy and efficiency. The applicability of these methods is further examined through the study of ground-state dissociation energies of 1-naphthol complexes, in collaboration with experimental efforts. Together, these results highlight the potential of combining data-driven techniques with traditional quantum chemical methods to expand their reach toward larger and more realistic chemical systems.
Keywords: full configuration interaction; extrapolation techniques; machine learning; regression models; electronic structure theory; data-driven methods; coupled cluster methods
 
Statistik