arXiv subjects

Shahzad Akram

Publications and source records attributed to Shahzad Akram.

3 recordsLinked to original sources

arXiv2026

OrbGNN: A Wave function-based Machine Learning Interelectronic Representation

Machine learning interatomic potentials (MLIPs) have become emerging tools in molecular modeling and computational chemistry. By learning high-dimensional potential energy surfaces from quantum chemical data, MLIPs enable accurate and efficient predictions of structural, thermodynamic, and dynamical properties. However, such models have limitations in predictions of electronic properties and the effects of static electron correlation due to their lack of electronic structure information. This work presents OrbGNN, an electronic structure graph architecture analogous to molecular graph and MLIP frameworks, where pair-orbital interactions constitute the graph representation, while orbital entanglement encodes the connectivity between them. By embedding information derived from orbital correlation metrics directly into the graph topology, OrbGNN provides a compact representation of a molecule s orbital landscape and electron correlation patterns. Analysis of the behavior of the feature space in an orbital graph are shown to demonstrate model robustness. The model is evaluated for the dissociation of nitrogen and for a larger dataset of diatomic molecules. Finally, the OrbGNN model is applied to a set of octahedral iron(II) complexes to predict spin-state energy gaps.

physics.chem-ph↗

arXiv2026

Non-covalent Interactions at cm$^{-1}$ Accuracy: Data Efficient Physics-Informed Distillation for Machine Learning Interatomic Potentials

Foundation models in atomistic machine learning encode interaction physics across diverse atomic environments, but whether that structure can be transferred when building specialist potentials at quantum-chemical accuracy remains open. Here we show that knowledge distillation from a pretrained universal machine-learning interatomic potential (MLIP), followed by coupled-cluster fine-tuning with single and double excitations and perturbative triples [CCSD(T)], transfers not only low-cost labels but a physically meaningful prior on interaction length scales, anisotropy, and the repulsive-dispersive balance, which CCSD(T) data then sharpens to quantum-chemical accuracy. For He--benzene, fine-tuning with 30% of the CCSD(T) data outperforms direct training using the full 80%; a 60% reduction in the high-fidelity compute budget. A symmetry-adapted perturbation theory (SAPT)-informed adaptive short-range/long-range architecture further lowers the validation MAE from 0.75 1/cm to 0.49 1/cm. Across a circumarene series of polycyclic aromatic hydrocarbons (PAHs), swapping the MLIP teacher under an otherwise identical pipeline changes the coronene error by an order of magnitude while leaving the larger PAHs stable, direct evidence that distillation transfers physical structure, not labels alone. Together, these results identify the choice of pretrained teacher as a primary design axis for data-efficient quantum-chemical-accuracy potentials, alongside architecture and training protocol.

physics.chem-ph↗

arXiv2026

Accurate Helium-Benzene Potential: from CCSD(T) to Gaussian Process Regression

The accurate modeling of non-covalent interactions between helium and graphitic materials is important for understanding quantum phenomena in reduced dimensions, with the helium-benzene complex serving as the fundamental prototype. However, creating a quantitatively reliable potential energy surface (PES) for this weakly bound system remains a significant computational challenge. In this work, we present a comprehensive, multi-level investigation of the He-Bz interaction, establishing benchmark energies using high-level coupled-cluster singles-and-doubles with perturbative triples (CCSD(T)) methods extrapolated to the complete basis set limit and assessing higher-order (CCSDT(Q)) contributions. We use symmetry-adapted perturbation theory (SAPT) to benchmark it against CCSD(T) and to decompose the interaction into its physical components-confirming it is dominated by a balance between dispersion and exchange-repulsion. A continuous, three-dimensional PES is constructed from discrete ab initio points using multifidelity Gaussian process regression that combines density functional theory results with sparse coupled-cluster energies. The result is a highly accurate PES with sub-cm-1 accuracy that obeys physical laws. This new PES is applied to path integral Monte Carlo (PIMC) simulations to study the solvation of 4He atoms on benzene at low temperatures. Our PIMC results reveal qualitatively different solvation behavior, particularly in the filling of adsorption layers, when compared to simulations using commonly employed empirical Lennard-Jones potentials. This work provides a benchmark PES essential for accurate many-body simulations of helium on larger polycyclic aromatic hydrocarbons towards graphene.

physics.chem-ph↗