Genetic Algorithm Procreation Operators for Alloy Nanoparticle Catalysts

Active-learning for global optimization of Ni-Ceria nanoparticles: The case of Ce4-xNixO8- x (x = 1, 2, 3)

Ni-CeO2 nanoparticles (NPs) are promising nanocatalysts for water splitting and water gas shift reactions due to the ability of ceria to temporarily donate oxygen to the catalytic reaction and accept oxygen after the reaction is completed. Therefore, elucidating how different properties of the Ni-Ceria NPs relate to the activity and selectivity of the catalytic reaction, is of crucial importance for the development of novel catalysts. In this work the active learning (AL) method based on machine learning regression and its uncertainty is used for the global optimization of Ce(4-x)NixO(8-x) (x = 1, 2, 3) nanoparticles, employing density functional theory calculations. Additionally, further investigation of the NPs by mass-scaled parallel-tempering Born-Oppenheimer molecular dynamics resulted in the same putative global minimum structures found by AL, demonstrating the robustness of our AL search to learn from small datasets and assist in the global optimization of complex electronic structure systems.

Graph Neural Network-Accelerated Multitasking Genetic Algorithm for Optimizing PdxTi1-xHy Surfaces under Various CO2 Reduction Reaction Conditions

Palladium (Pd) hydride-based catalysts have been reported to have excellent performance in the CO2 reduction reaction (CO2RR) and hydrogen evolution reaction (HER). Our previous work on doped PdH and Pd alloy hydrides showed that Ti-doped and Ti-alloyed Pd hydrides could improve the performance of the CO2 reduction reaction compared with pure Pd hydride. Compositions and chemical orderings of the surfaces with only one adsorbate under certain reaction conditions are linked to their stability, activity, and selectivity toward the CO2RR and HER, as shown in our previous work. In fact, various coverages, types, and mixtures of the adsorbates, as well as state variables such as temperature, pressure, applied potential, and chemical potential, could impact their stability, activity, and selectivity. However, these factors are usually fixed at common values to reduce the complexity of the structures and the complexity of the reaction conditions in most theoretical work. To address the complexities above and the huge search space, we apply a deep learning-assisted multitasking genetic algorithm to screen for PdxTi1-xHy surfaces containing multiple adsorbates for CO2RR under different reaction conditions. The ensemble deep learning model can greatly speed up the structure relaxations and retain a high accuracy and low uncertainty of the energy and forces. The multitasking genetic algorithm simultaneously finds globally stable surface structures under each reaction condition. Finally, 23 stable structures are screened out under different reaction conditions. Among these, Pd0.56Ti0.44H1.06 + 25%CO, Pd0.31Ti0.69H1.25 + 50%CO, Pd0.31Ti0.69H1.25 + 25%CO, and Pd0.88Ti0.12H1.06 + 25%CO are found to be very active for CO2RR and suitable to generate syngas consisting of CO and H2.

GAMaterial-A genetic-algorithm software for material design and discovery

Genetic algorithms (GAs) are stochastic global search methods inspired by biological evolution. They have been used extensively in chemistry and materials science coupled with theoretical methods, ranging from force-fields to high-throughput first-principles methods. The methodology allows an accurate and automated structural determination for molecules, atomic clusters, nanoparticles, and solid surfaces, fundamental to understanding chemical processes in catalysis and environmental sciences, for instance. In this work, we propose a new genetic algorithm software, GAMaterial, implemented in Python3.x, that performs global searches to elucidate the structures of atomic clusters, doped clusters or materials and atomic clusters on surfaces. For all these applications, it is possible to accelerate the GA search by using machine learning (ML), the ML@GA method, to build subsequent populations. Results for ML@GA applied for the dopant distributions in atomic clusters are presented. The GAMaterial software was applied for the automatic structural search for the Ti₆ O₁₂ cluster, doping Al in Si₁₁ (4Al@Si₁₁ ) and Na₁₀ supported on graphene (Na₁₀ @graphene), where DFTB calculations were used to sample the complex search surfaces with reasonably low computational cost. Finally, the global search by GA of the Mo₈ C₄ cluster was considered, where DFT calculations were made with the deMon2k code, which is interfaced with GAMaterial.

Fast atomic structure optimization with on-the-fly sparse Gaussian process potentials. JOURNAL OF PHYSICS. CONDENSED MATTER : AN INSTITUTE OF PHYSICS JOURNAL 2022;34:344007. [PMID: 35675808 DOI: 10.1088/1361-648x/ac76ff]

We apply on-the-fly machine learning potentials (MLPs) using the sparse Gaussian process regression (SGPR) algorithm for fast optimization of atomic structures. Great acceleration is achieved even in the context of a single local optimization. Although for finding the exact local minimum, due to limited accuracy of MLPs, switching to another algorithm may be needed. For random gold clusters, the forces are reduced to ∼0.1 eV Å^-1within less than ten first-principles (FP) calculations. Because of highly transferable MLPs, this algorithm is specially suitable for global optimization methods such as random or evolutionary structure searching or basin hopping. This is demonstrated by sequential optimization of random gold clusters for which, after only a few optimizations, FP calculations were rarely needed.

Automatic structural elucidation of vacancies in materials by active learning

The artificial intelligence method based on active learning for the automatic structural elucidation of vacancies in materials. This is implemented in the quantum machine learning software/agent for material design and discovery (QMLMaterial).

Argyrodite configuration determination for DFT and AIMD calculations using an integrated optimization strategy

When constructing a partially occupied model structure for use in density functional theory (DFT) and ab initio molecular dynamics (AIMD) calculations, the selection of appropriate configurations has been a vexing issue. Random sampling and the ensuing low-Coulomb-energy entry selection have been routine. Here, we report a more efficient way of selecting low-Coulomb-energy configurations for a representative solid electrolyte, Li₆PS₅Cl. Metaheuristics (genetic algorithm, particle swarm optimization, cuckoo search, and harmony search), Bayesian optimization, and modified deep Q-learning are utilized to search the large configurational space. Ten configuration candidates that exhibit relatively low Coulomb energy values and thereby lead to more convincing DFT and AIMD calculation results are pinpointed along with computational cost savings by the assistance of the above-described optimization algorithms, which constitute an integrated optimization strategy. Consequently, the integrated optimization strategy outperforms the conventional random sampling-based selection strategy.

When constructing a partially occupied model structure for use in density functional theory (DFT) and ab initio molecular dynamics (AIMD) calculations, the selection of appropriate configurations has been a vexing issue. We suggest a reasonable strategy to sort out this issue.

Atomic Structure Optimization with Machine-Learning Enabled Interpolation between Chemical Elements

We introduce a computational method for global optimization of structure and ordering in atomic systems. The method relies on interpolation between chemical elements, which is incorporated in a machine-learning structural fingerprint. The method is based on Bayesian optimization with Gaussian processes and is applied to the global optimization of Au-Cu bulk systems, Cu-Ni surfaces with CO adsorption, and Cu-Ni clusters. The method consistently identifies low-energy structures, which are likely to be the global minima of the energy. For the investigated systems with 23-66 atoms, the number of required energy and force calculations is in the range 3-75.

Physically Compatible Machine Learning Study on the Pt-Ni Nanoclusters

Pt-Ni alloy nanoclusters are essential for high-performance catalysis, and the full description for the finite temperature properties is highly desired. Here we developed an efficient machine learning method to evaluate the accurate structure-stability correspondence in a Pt_(85-x)-Ni_x nanocluster over the structural space with a dimension of 3.84 × 10²⁵. On the basis of the physical model and big-data analysis, for the first time, we demonstrated that the segregation-extent bond order parameter (BOP) and the shell-resolved undercoordination ratio play the key roles in the structural stability. This a priori knowledge extremely reduced the computational costs and enhanced the accuracies. With the 500-sample train data set generated by density functional theory (DFT)-level geometry optimizations, we fit the machine-learning excess energy potential and verified the mean-square-error is <0.13. Our physically niche genetic-machine learning program (PNG-ML) searched 2.5 × 10⁵ structures and predicted precisely the most stable Pt₄₃-Ni₄₂ (x = 42). The structural space dimension was reduced by 10²⁰ fold using our PNG-ML method. The Pt/Ni ratio of the most stable nanocluster is 1.02, which is highly consistent with the experimental observation of 1.0. The above results provide reliable theoretical references for the realistic applications of Pt-Ni nanoclusters and suggest feature engineering for future studies on binary alloys nanostructures.

The atomic simulation environment-a Python library for working with atoms

The atomic simulation environment (ASE) is a software package written in the Python programming language with the aim of setting up, steering, and analyzing atomistic simulations. In ASE, tasks are fully scripted in Python. The powerful syntax of Python combined with the NumPy array library make it possible to perform very complex simulation tasks. For example, a sequence of calculations may be performed with the use of a simple 'for-loop' construction. Calculations of energy, forces, stresses and other quantities are performed through interfaces to many external electronic structure codes or force fields using a uniform interface. On top of this calculator interface, ASE provides modules for performing many standard simulation tasks such as structure optimization, molecular dynamics, handling of constraints and performing nudged elastic band calculations.

Decoupling strain and ligand effects in ternary nanoparticles for improved ORR electrocatalysis

Ternary Pt–Au–M (M = 3d transition metal) nanoparticles show reduced OH adsorption energies and improved activity for the oxygen reduction reaction (ORR) compared to pure Pt nanoparticles, as obtained by density functional theory.

A DFT-based genetic algorithm search for AuCu nanoalloy electrocatalysts for CO₂ reduction

Using a DFT-based genetic algorithm (GA) approach, we have determined the most stable structure and stoichiometry of a 309-atom icosahedral AuCu nanoalloy, for potential use as an electrocatalyst for CO2 reduction. The identified core-shell nano-particle consists of a copper core interspersed with gold atoms having only copper neighbors and a gold surface with a few copper atoms in the terraces. We also present an adsorbate-dependent correction scheme, which enables an accurate determination of adsorption energies using a computationally fast, localized LCAO-basis set. These show that it is possible to use the LCAO mode to obtain a realistic estimate of the molecular chemisorption energy for systems where the computation in normal grid mode is not computationally feasible. These corrections are employed when calculating adsorption energies on the Cu, Au and most stable mixed particles. This shows that the mixed Cu135@Au174 core-shell nanoalloy has a similar adsorption energy, for the most favorable site, as a pure gold nano-particle. Cu, however, has the effect of stabilizing the icosahedral structure because Au particles are easily distorted when adding adsorbates.

Designing mixed metal halide ammines for ammonia storage using density functional theory and genetic algorithms

New superior ammonia storage materials are suggested from computational screening. Global optimum of 27 000 mixtures identified testing only ∼1.5% of the candidates, proving the success of the genetic algorithm.