Accelerating the Calculation of Koopmans Screening Parameters Using Machine Learning
Offered By: Materials Cloud via YouTube
Course Description
Overview
Explore an advanced Quantum ESPRESSO tutorial focusing on accelerating the calculation of Koopmans screening parameters using machine learning. Delve into the intricacies of Hubbard and Koopmans functionals from linear response, covering topics such as project overview, step-by-step processes, mapping orbital densities, local decomposition, invariance, power spectrum, and retrogression. Learn about the equipment workflow, model testing, and analysis of results, including mean model, training outcomes, baseline model comparisons, and test findings. Gain valuable insights into this cutting-edge approach for computational materials science and engage with the material through a comprehensive syllabus designed to enhance understanding of complex quantum mechanical calculations.
Syllabus
Intro
Project overview
Step by step
First step
Second step
Mapping orbital densities
Local decomposition
Invariance
Power spectrum
Retrogression
Equipments workflow
Testing the model
Results
Mean model
Training results
Baseline model
Test results
Conclusions
Questions
Taught by
Materials Cloud
Related Courses
Fractionalized Metallic Phases in the Single Band Hubbard Model - Quantum Phases of Matter XXIIInternational Centre for Theoretical Sciences via YouTube Twisted Transition Metal Dicalcogenides - Tests of Quantum Embedding and Theories
Institute for Pure & Applied Mathematics (IPAM) via YouTube Basics of Dynamical Mean Field Theory
International Centre for Theoretical Sciences via YouTube Supraconductivité à Haute Température Critique et Modèle de Hubbard
Institut Henri Poincaré via YouTube SCAN Functional and DFT Errors for Open-Shell d- and f-Electron Systems
MuST Program for Disordered Materials via YouTube