Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userPhysically-motivated Recursively Embedded Atom Neural Networks: Incorporating Local Completeness and Nonlocality
105
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
Recent advances in machine-learned interatomic potentials largely benefit from the atomistic representation and locally invariant many-body descriptors. It was however recently argued that including three- (or even four-) body features is incomplete to distinguish specific local structures. Utilizing an embedded density descriptor made by linear combinations of neighboring atomic orbitals and realizing that each orbital coefficient physically depends on its own local environment, we propose a recursively embedded atom neural network model. We formally prove that this model can efficiently incorporate complete many-body correlations without explicitly computing high-order terms. This model not only successfully addresses challenges regarding local completeness and nonlocality in representative systems, but also provides an easy and general way to update local many-body descriptors to have a message-passing form without changing their basic structures.
rate research
Read More
We propose a simple, but efficient and accurate machine learning (ML) model for developing high-dimensional potential energy surface. This so-called embedded atom neural network (EANN) approach is inspired by the well-known empirical embedded atom method (EAM) model used in condensed phase. It simply replaces the scalar embedded atom density in EAM with a Gaussian-type orbital based density vector, and represents the complex relationship between the embedded density vector and atomic energy by neural networks. We demonstrate that the EANN approach is equally accurate as several established ML models in representing both big molecular and extended periodic systems, yet with much fewer parameters and configurations. It is highly efficient as it implicitly contains the three-body information without an explicit sum of the conventional costly angular descriptors. With high accuracy and efficiency, EANN potentials can vastly accelerate molecular dynamics and spectroscopic simulations in complex systems at ab initio level.
We present a novel halo painting network that learns to map approximate 3D dark matter fields to realistic halo distributions. This map is provided via a physically motivated network with which we can learn the non-trivial local relation between dark matter density field and halo distributions without relying on a physical model. Unlike other generative or regressive models, a well motivated prior and simple physical principles allow us to train the mapping network quickly and with relatively little data. In learning to paint halo distributions from computationally cheap, analytical and non-linear density fields, we bypass the need for full particle mesh simulations and halo finding algorithms. Furthermore, by design, our halo painting network needs only local patches of dark matter density to predict the halos, and as such, it can predict the 3D halo distribution for any arbitrary simulation box size. Our neural network can be trained using small simulations and used to predict large halo distributions, as long as the resolutions are equivalent. We evaluate our models ability to generate 3D halo count distributions which reproduce, to a high degree, summary statistics such as the power spectrum and bispectrum, of the input or reference realizations.
We apply the atom-atom potentials to molecular crystals of iron (II) complexes with bulky organic ligands. The crystals under study are formed by low-spin or high-spin molecules of Fe(phen)$_{2}$(NCS)$_{2}$ (phen = 1,10-phenanthroline), Fe(btz)$_{2}$(NCS)$_{2}$ (btz = 5,5$^{prime }$,6,6$^{prime}$-tetrahydro-4textit{H},4$^{prime}$textit{H}-2,2$^{prime }$-bi-1,3-thiazine), and Fe(bpz)$_{2}$(bipy) (bpz = dihydrobis(1-pyrazolil)borate, and bipy = 2,2$^{prime}$-bipyridine). All molecular geometries are taken from the X-ray experimental data and assumed to be frozen. The unit cell dimensions and angles, positions of the centers of masses of molecules, and the orientations of molecules corresponding to the minimum energy at 1 atm and 1 GPa are calculated. The optimized crystal structures are in a good agreement with the experimental data. Sources of the residual discrepancies between the calculated and experimental structures are discussed. The intermolecular contributions to the enthalpy of the spin transitions are found to be comparable with its total experimental values. It demonstrates that the method of atom-atom potentials is very useful for modeling organometalic crystals undergoing the spin transitions.
The nuclear obscurer of Active Galactic Nuclei (AGN) is poorly understood in terms of its origin, geometry and dynamics. We investigate whether physically motivated geometries emerging from hydro-radiative simulations can be differentiated with X-ray reflection spectroscopy. For two new geometries, the radiative fountain model of Wada (2012) and a warped disk, we release spectral models produced with the ray tracing code XARS. We contrast these models with spectra of three nearby AGN taken by NuSTAR and Swift/BAT. Along heavily obscured sight-lines, the models present different 4-20keV continuum spectra. These can be differentiated by current observations. Spectral fits of the Circinus Galaxy favor the warped disk model over the radiative fountain, and clumpy or smooth torus models. The necessary reflector (NH>10^25/cm^2) suggests a hidden population of heavily Compton-thick AGN amongst local galaxies. X-ray reflection spectroscopy is a promising pathway to understand the nuclear obscurer in AGN.
The applications of machine learning techniques to chemistry and materials science become more numerous by the day. The main challenge is to devise representations of atomic systems that are at the same time complete and concise, so as to reduce the number of reference calculations that are needed to predict the properties of different types of materials reliably. This has led to a proliferation of alternative ways to convert an atomic structure into an input for a machine-learning model. We introduce an abstract definition of chemical environments that is based on a smoothed atomic density, using a bra-ket notation to emphasize basis set independence and to highlight the connections with some popular choices of representations for describing atomic systems. The correlations between the spatial distribution of atoms and their chemical identities are computed as inner products between these feature kets, which can be given an explicit representation in terms of the expansion of the atom density on orthogonal basis functions, that is equivalent to the smooth overlap of atomic positions (SOAP) power spectrum, but also in real space, corresponding to $n$-body correlations of the atom density. This formalism lays the foundations for a more systematic tuning of the behavior of the representations, by introducing operators that represent the correlations between structure, composition, and the target properties. It provides a unifying picture of recent developments in the field and indicates a way forward towards more effective and computationally affordable machine-learning schemes for molecules and materials.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
