Learning to Use the Force: Fitting Repulsive Potentials in Density-Functional Tight-Binding with Gaussian Process Regression, Theoretical and Computational Chemistry, ChemRxiv
4.5 (473) In stock
The Density-Functional Tight Binding (DFTB) method is a popular semiempirical approximation to Density Functional Theory (DFT). In many cases, DFTB can provide comparable accuracy to DFT at a fraction of the cost, enabling simulations on length- and time-scales that are unfeasible with first principles DFT. At the same time (and in contrast to empirical interatomic potentials and force-fields), DFTB still offers direct access to electronic properties such as the band-structure. These advantages come at the cost of introducing empirical parameters to the method, leading to a reduced transferability compared to true first-principle approaches. Consequently, it would be very useful if the parameter-sets could be routinely adjusted for a given project. While fairly robust and transferable parameterization workflows exist for the electronic structure part of DFTB, the so-called repulsive potential Vrep poses a major challenge. In this paper we propose a machine-learning (ML) approach to fitting Vrep, using Gaussian Process Regression (GPR). The use of GPR circumvents the need for non-linear or global parameter optimization, while at the same time offering arbitrary flexibility in terms of the functional form. We also show that the proposed method can be applied to multiple elements at once, by fitting repulsive potentials for organic molecules containing carbon, hydrogen and oxygen. Overall, the new approach removes focus from the choice of functional form and parameterization procedure, in favour of a data-driven philosophy.
Neural network potentials for chemistry: concepts, applications
OpenKIM · SNAP ZuoChenLi 2019quadratic Li MO_041269750353_000
PDF) Semiempirical Hamiltonians learned from data can have
Quantum machine learning for chemistry and physics - Chemical Society Reviews (RSC Publishing) DOI:10.1039/D2CS00203E
Analysis of Density Functional Tight Binding with Natural Bonding
OpenKIM · SNAP ZuoChenLi 2019quadratic Mo MO_692442138123_000
PDF) Electrostatic Embedding of Machine Learning Potentials
Machine learning methods in photochemistry and photophysics - ScienceDirect
Machine learning methods in photochemistry and photophysics - ScienceDirect
Density-Functional Tight-Binding (DFTB) as fast approximate DFT
PDF) Electrostatic Embedding of Machine Learning Potentials
Density-Functional Tight-Binding (DFTB) as fast approximate DFT
Interfacing q-AQUA with a Polarizable Force Field: The Best of
Machine learning methods in photochemistry and photophysics - ScienceDirect
Hip Lifting Breathable Abdominal Tightening Waist Binding & Hip Suppor – 99store
Sn5636 Plastic Book Binding Clips Account Book Paper One Slotted
The TTABlog®: Double Meaning of CINCH for Snowboard Bindings
- KNETLI Lycra Saree Shapewear Petticoat for Women, Shapers for
- Cobbler's Choice Water and Stain Repellent Spray - Waterproofs & Protects Leather, Suede, and Fabric from the elements! : Clothing, Shoes & Jewelry
- Even&Odd LONG PUFF SLEEVES RUSHING BODYCON DRESS - Cocktail dress
- Anti-Peep Magnetic Case for iPhone 14/13/12,360 Degree
- Beyond Yoga, Pants & Jumpsuits, Beyond Yoga Spacedye Outlines High Waisted Midi Legging In Green Grass Heather
- Fall Travel Outfits for Plane Rides, Road Trips & Beyond - Mia Mia Mine