Machine-Learning-Assisted Acceleration on High-Symmetry Materials Search: Space Group Predictions from Band Structures

Xi, Bin; Tse, Kin Fai; Kok, Tsz Fung; Chan, Ho Ming; Chan, Man Kit; Chan, Ho Yin; Wong, Kwan Yue Clinton; Yuen, Shing Hei Robin; Zhu, Junyi

doi:10.1021/acs.jpcc.2c03156

Cited by 3 publications

(2 citation statements)

References 100 publications

(109 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, genetic algorithms have been used in a variety of symmetry problems from the relevant literature [19][20][21]. Recently, Krippendorf and Syvaeri used artificial neural networks to detect symmetries in datasets [22], Qiao et al [23] used deep-learning techniques to predict the energy solutions of the Schrödinger equations using symmetryadapted atomic orbital features, Xi et al [24] used deep-learning methods on high-symmetry material space, Selvaratnam et al [25] used symmetry functions on large chemical spaces through convolutional neural networks, and Wang et al [26] used symmetry-adapted graph neural networks for constructing molecular dynamics force fields.…”

Section: Introductionmentioning

confidence: 99%

Prediction of COVID-19 Cases Using Constructed Features by Grammatical Evolution

Tsoulos

Tzallas²,

Tsalikakis³

2022

Symmetry

View full text Add to dashboard Cite

A widely used method that constructs features with the incorporation of so-called grammatical evolution is proposed here to predict the COVID-19 cases as well as the mortality rate. The method creates new artificial features from the original ones using a genetic algorithm and is guided by BNF grammar. After the artificial features are generated, the original data set is modified based on these features, an artificial neural network is applied to the modified data, and the results are reported. From the comparative experiments done, it is clear that feature construction has an advantage over other machine-learning methods for predicting pandemic elements.

show abstract

Section: Introductionmentioning

confidence: 99%

Prediction of COVID-19 Cases Using Constructed Features by Grammatical Evolution

Tsoulos

Tzallas²,

Tsalikakis³

2022

Symmetry

View full text Add to dashboard Cite

show abstract

“…Potential energy surface approaches based on empirical interatomic potentials − are fast, however, often inaccurate. Recently, machine learning (ML) techniques − with density functional theory (DFT) results as inputs yield fast simulations and accurate results. One popular choice is the descriptor-based neural network (NN) approaches ,,− , by regarding the energy as a function of bond lengths, bond angles, or related symmetry functions. ,− ,, However, there are three main issues: (1) large amount of symmetry functions, predetermined subjectively; (2) time-consuming and poor accuracy in force fitting, based on gradient of energy; (3) no objective distribution criteria in the training data generation.…”

mentioning

confidence: 99%

Parameter-Free and Electron Counting Satisfied Material Representation for Machine Learning Potential Energy and Force Fields

Xi,

Chan,

Bao

et al. 2024

J. Phys. Chem. Lett.

Self Cite

View full text Add to dashboard Cite

We proposed a parameter-free volume element representation that satisfies the electron counting model and obtains accurate machine learning potential energy and direct force fitting of randomly perturbed hexagonal BN. Our method preserves permutational, translational, and rotational invariance and can be extended to three-dimensional systems, verified by a system of bulk Si. As a result, we obtained 0.57 meV/atom potential energy root mean squared error (RMSE) and 59 meV/Å force RMSE for perturbed bulk BN systems and 0.43 meV/atom potential energy RMSE and 36 meV/Å force RMSE for perturbed Si systems. In addition, an unbiased perturbation-based data set construction scheme is introduced and a continuous population distribution is obtained with a training data set of 4500, which is about 1 order of magnitude smaller than standard methods based on first-principles molecular dynamics simulations and saves a large amount of computing resources. General validity of our model is verified by structure optimization, molecular dynamics simulations, and extrapolations.

show abstract

Application and Prospect of Machine Learning in Photoelectron Spectroscopy

Deng Xiang-Wen,

Wu Li-Yuan,

Zhao Rui

et al. 2024

Acta Phys. Sin.

View full text Add to dashboard Cite

Photoelectron spectroscopy serves as a prevalent characterization technique within the realm of material science. Specifically, angle-resolved photoelectron spectroscopy (ARPES) provides a direct method for determining the energy-momentum dispersion relationship and Fermi surface structure of electrons within a material system. This makes ARPES a potent tool for the investigation of many-body interactions and correlated quantum materials. The field of photoelectron spectroscopy has seen continuous advancements, with the emergence of technologies such as time-resolved ARPES and nano-ARPES. Concurrently, the evolution of synchrotron radiation devices has led to the generation of an increasing volume of high throughput and high dimension experimental data. This underscores the growing urgency for the development of more efficient and precise data processing methods, as well as the extraction of deeper physical information. In light of these developments, machine learning is poised to play an increasingly significant role across various fields, including but not limited to ARPES. This paper reviews the application of machine learning in photoelectron spectroscopy, which primarily encompasses three aspects:<br>1.Data Denoising: Machine learning can be utilized for denoising photoelectron spectroscopy data. The denoising process via machine learning algorithms can be bifurcated into two methods. Both of the two methods do not need for manual data annotation. The first approach involves the use of noise generation algorithms to simulate experimental noise, thereby obtaining effective low signal-to-noise ratio to high signal-to-noise ratio data pairs. Alternatively, the second approach can be employed to extract noise and clean spectral data, respectively.<br>2.Electronic Structure and Chemical Composition Analysis: Machine learning can be applied for the analysis of electronic structure and chemical composition. (Angle-resolved) photoelectron spectroscopy contains abundant information about material structure. Information such as energy band structure, self-energy, binding energy, and other condensed matter data can be rapidly acquired through machine learning schemes.<br>3.Prediction of Photoelectron Spectroscopy: the electronic structure information obtained by combining first-principles calculation can also predict the photoelectron spectroscopy. The rapid acquisition of photoelectron spectroscopy data through machine learning algorithms also holds significance for material design. Photoelectron spectroscopy holds significant importance in the study of condensed matter physics. In the context of synchrotron radiation development, the construction of an automated data acquisition and analysis system could play a pivotal role in condensed matter physics research. In addition, adding more physical constraints to the machine learning model will improve the interpretability and accuracy of the model. There exists a close relationship between photoelectron spectroscopy and first-principles calculations with respect to electronic structure properties. The integration of these two through machine learning is anticipated to significantly contribute to the study of electronic structure properties. Furthermore, as machine learning algorithms continue to evolve, the application of more advanced machine learning algorithms in photoelectron spectroscopy research is expected. By building automated data acquisition and analysis systems, designing comprehensive workflows based on machine learning and first-principles methods, and integrating new machine learning techniques, it will help accelerate the progress of photoelectron spectroscopy experiments and facilitate the analysis of electronic structure properties and microscopic physical mechanisms, which will advance the frontier research in quantum materials and condensed matter physics.

show abstract

Machine-Learning-Assisted Acceleration on High-Symmetry Materials Search: Space Group Predictions from Band Structures

Cited by 3 publications

References 100 publications

Prediction of COVID-19 Cases Using Constructed Features by Grammatical Evolution

Prediction of COVID-19 Cases Using Constructed Features by Grammatical Evolution

Parameter-Free and Electron Counting Satisfied Material Representation for Machine Learning Potential Energy and Force Fields

Application and Prospect of Machine Learning in Photoelectron Spectroscopy

Contact Info

Product

Resources

About