Crystal Structure Prediction Using Neural Network Potential And Age Fitness Pareto Genetic Algorithm
Download Crystal Structure Prediction Using Neural Network Potential And Age Fitness Pareto Genetic Algorithm PDF/ePub or read online books in Mobi eBooks. Click Download or Read Online button to get Crystal Structure Prediction Using Neural Network Potential And Age Fitness Pareto Genetic Algorithm book now. This website allows unlimited access to, at the time of writing, more than 1.5 million titles, including hundreds of thousands of titles in various foreign languages.
Crystal structure prediction using neural network potential and age-fitness Pareto genetic algorithm
Author: Sadman Sadeed Omee
language: en
Publisher: OAE Publishing Inc.
Release Date: 2024-03-02
While crystal structure prediction (CSP) remains a longstanding challenge, we introduce ParetoCSP, a novel algorithm for CSP, which combines a multi-objective genetic algorithm (GA) with a neural network inter-atomic potential model to find energetically optimal crystal structures given chemical compositions. We enhance the updated multi-objective GA (NSGA-III) by incorporating the genotypic age as an independent optimization criterion and employ the M3GNet universal inter-atomic potential to guide the GA search. Compared to GN-OA, a state-of-the-art neural potential-based CSP algorithm, ParetoCSP demonstrated significantly better predictive capabilities, outperforming by a factor of 2.562 across 55 diverse benchmark structures, as evaluated by seven performance metrics. Trajectory analysis of the traversed structures of all algorithms shows that ParetoCSP generated more valid structures than other algorithms, which helped guide the GA to search more effectively for the optimal structures. Our implementation code is available at https://github.com/sadmanomee/ParetoCSP.
An Introduction to Genetic Algorithms for Scientists and Engineers
This invaluable book has been designed to be useful to most practising scientists and engineers, whatever their field and however rusty their mathematics and programming might be. The approach taken is largely practical, with algorithms being presented in full and working code (in BASIC, FORTRAN, PASCAL AND C) included on a floppy disk to help the reader get up and running as quickly as possible. The text could also be used as part of an undergraduate course on search and optimisation. Student exercises are included at the end of several of the chapters, many of which are computer-based and designed to encourage exploration of the method.
Introduction to Genetic Algorithms
Author: S.N. Sivanandam
language: en
Publisher: Springer Science & Business Media
Release Date: 2007-10-24
Theoriginofevolutionaryalgorithmswasanattempttomimicsomeoftheprocesses taking place in natural evolution. Although the details of biological evolution are not completely understood (even nowadays), there exist some points supported by strong experimental evidence: • Evolution is a process operating over chromosomes rather than over organisms. The former are organic tools encoding the structure of a living being, i.e., a cr- ture is “built” decoding a set of chromosomes. • Natural selection is the mechanism that relates chromosomes with the ef ciency of the entity they represent, thus allowing that ef cient organism which is we- adapted to the environment to reproduce more often than those which are not. • The evolutionary process takes place during the reproduction stage. There exists a large number of reproductive mechanisms in Nature. Most common ones are mutation (that causes the chromosomes of offspring to be different to those of the parents) and recombination (that combines the chromosomes of the parents to produce the offspring). Based upon the features above, the three mentioned models of evolutionary c- puting were independently (and almost simultaneously) developed.