Systematic Identification of Atom-Centered Symmetry Functions for the Development of Neural Network Potentials

Mudassir, Mohammed Wasay; Srinivasan, Sriram Goverapet; Mynam, Mahesh; Rai, Beena

doi:10.1021/acs.jpca.2c04508

Cited by 2 publications

(1 citation statement)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Indeed, a plethora of ACSF flavors has emerged throughout the years to exploit their full potential, − which has crystallized in countless ML applications. − However, unlike end-to-end approaches such as SchNet, , hand-crafted descriptors require careful fine-tuning of their underlying hyperparameters. Although some attempts have been proposed to aid this feature selection procedure, , the work is still scarce and most of the approaches require a large evaluation of uniformly distributed symmetry functions. Besides requiring some prior knowledge of the system, which is not always obvious, the latter is a particularly tedious task that can hinder the development of ACSF-based models.…”

Section: Introductionmentioning

confidence: 99%

An Unsupervised Machine Learning Approach for the Automatic Construction of Local Chemical Descriptors

Gallegos,

Isamura,

Popelier

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Condensing the many physical variables defining a chemical system into a fixed-size array poses a significant challenge in the development of chemical Machine Learning (ML). Atom Centered Symmetry Functions (ACSFs) offer an intuitive featurization approach by means of a tedious and labor-intensive selection of tunable parameters. In this work, we implement an unsupervised ML strategy relying on a Gaussian Mixture Model (GMM) to automatically optimize the ACSF parameters. GMMs effortlessly decompose the vastness of the chemical and conformational spaces into well-defined radial and angular clusters, which are then used to build tailor-made ACSFs. The unsupervised exploration of the space has demonstrated general applicability across a diverse range of systems, spanning from various unimolecular landscapes to heterogeneous databases. The impact of the sampling technique and temperature on space exploration is also addressed, highlighting the particularly advantageous role of hightemperature Molecular Dynamics (MD) simulations. The reliability of the resulting features is assessed through the estimation of the atomic charges of a prototypical capped amino acid and a heterogeneous collection of CHON molecules. The automatically constructed ACSFs serve as high-quality descriptors, consistently yielding typical prediction errors below 0.010 electrons bound for the reported atomic charges. Altering the spatial distribution of the functions with respect to the cluster highlights the critical role of symmetry rupture in achieving significantly improved features. More specifically, using two separate functions to describe the lower and upper tails of the cluster results in the best performing models with errors as low as 0.006 electrons. Finally, the effectiveness of finely tuned features was checked across different architectures, unveiling the superior performance of Gaussian Process (GP) models over Feed Forward Neural Networks (FFNNs), particularly in low-data regimes, with nearly a 2-fold increase in prediction quality. Altogether, this approach paves the way toward an easier construction of local chemical descriptors, while providing valuable insights into how radial and angular spaces should be mapped. Finally, this work opens the possibility of encoding many-body information beyond angular terms into upcoming ML features.

show abstract

Section: Introductionmentioning

confidence: 99%

An Unsupervised Machine Learning Approach for the Automatic Construction of Local Chemical Descriptors

Gallegos,

Isamura,

Popelier

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

Automatic Feature Selection for Atom-Centered Neural Network Potentials Using a Gradient Boosting Decision Algorithm

Li,

Wang,

Singh

et al. 2024

J. Chem. Theory Comput.

View full text Add to dashboard Cite

Atom-centered neural network (ANN) potentials have shown high accuracy and computational efficiency in modeling atomic systems. A crucial step in developing reliable ANN potentials is the proper selection of atom-centered symmetry functions (ACSFs), also known as atomic features, to describe atomic environments. Inappropriate selection of ACSFs can lead to poor-quality ANN potentials. Here, we propose a gradient boosting decision tree (GBDT)-based framework for the automatic selection of optimal ACSFs. This framework takes uniformly distributed sets of ACSFs as input and evaluates their relative importance. The ACSFs with high average importance scores are selected and used to train an ANN potential. We applied this method to the Ge system, resulting in an ANN potential with root-mean-square errors (RMSE) of 10.2 meV/atom for energy and 84.8 meV/Å for force predictions, utilizing only 18 ACSFs to achieve a balance between accuracy and computational efficiency. The framework is validated using the grid searching method, demonstrating that ACSFs selected with our framework are in the optimal region. Furthermore, we also compared our method with commonly used feature selection algorithms. The results show that our algorithm outperforms the others in terms of effectiveness and accuracy. This study highlights the significance of the ACSF parameter effect on the ANN performance and presents a promising method for automatic ACSF selection, facilitating the development of machine learning potentials.

show abstract

Systematic Identification of Atom-Centered Symmetry Functions for the Development of Neural Network Potentials

Cited by 2 publications

References 48 publications

An Unsupervised Machine Learning Approach for the Automatic Construction of Local Chemical Descriptors

An Unsupervised Machine Learning Approach for the Automatic Construction of Local Chemical Descriptors

Automatic Feature Selection for Atom-Centered Neural Network Potentials Using a Gradient Boosting Decision Algorithm

Contact Info

Product

Resources

About