Searcharxiv⌕ Search

arXiv subjects

Shaodong Zhou

Publications and source records attributed to Shaodong Zhou.

7 recordsLinked to original sources
arXiv2026

DeepHartree: A Poisson-Coupled Neural Field for One-Shot Density Functional Theory

Linear-combination-of-atomic-orbital (LCAO) density functional theory (DFT) incurs steep costs when it constructs Coulomb terms and iterates the self-consistent field (SCF) equations. Matrix-learning approaches can bypass parts of this workflow, but their outputs inherit the dimensions and conventions of a fixed orbital basis. We introduce DeepHartree, a Poisson-coupled neural field that connects continuous real-space prediction to LCAO electronic structure. An E(3)-equivariant network predicts the Hartree potential, and the Poisson equation converts this potential into electron density. Atom-centred Gaussian fields resolve the near-nuclear region, while a molecule-level correction enforces the electron count. Numerical quadrature assembles the Kohn--Sham matrix. One diagonalization recovers energy components, frontier levels, and occupied subspaces and produces the density matrix used for SCF initialization. The molecular mean weighted normalized mean absolute error (wNMAE) is 0.361% on QM9 and 1.397% on the chemically broader VQM24 dataset. Our Hybrid7 scheme uses a seven-point finite difference to obtain the learned local density and first-order automatic differentiation to obtain its gradient. It avoids higher-order differentiation graphs, runs 1.33--1.37 times faster than full automatic differentiation, and remains stable for systems approaching 1,000 atoms. Without fine-tuning, the QM9 model attains a total-energy MAE of 15.601~meV atom$^{-1}$ on 1,000 larger OE62 molecules. DeepHartree initial guesses reduce SCF iterations for 88.62% of QM9 test molecules, with a 14.5% mean reduction. These results establish continuous electrostatic fields as an accurate and scalable interface between machine learning and LCAO DFT.

physics.chem-ph↗
arXiv2026

ChemFlow:A Hierarchical Neural Network for Multiscale Representation Learning in Chemical Mixtures

Accurate prediction of the physicochemical properties of molecular mixtures using graph neural networks remains a significant challenge, as it requires simultaneous embedding of intramolecular interactions while accounting for mixture composition (i.e., concentrations and ratios). Existing approaches are ill-equipped to emulate realistic mixture environments, where densely coupled interactions propagate across hierarchical levels - from atoms and functional groups to entire molecules - and where cross-level information exchange is continuously modulated by composition. To bridge the gap between isolated molecules and realistic chemical environments, we present ChemFlow, a novel hierarchical framework that integrates atomic, functional group, and molecular-level features, facilitating information flow across these levels to predict the behavior of complex chemical mixtures. ChemFlow employs an atomic-level feature fusion module, Chem-embed, to generate context-aware atomic representations influenced by the mixture state and atomic characteristics. Next, bidirectional group-to-molecule and molecule-to-group attention mechanisms enable ChemFlow to capture functional group interactions both within and across molecules in the mixture. By dynamically adjusting representations based on concentration and composition, ChemFlow excels at predicting concentration-dependent properties and significantly outperforms state-of-the-art models in both concentration-sensitive and concentration-independent systems. Extensive experiments demonstrate ChemFlow's superior accuracy and efficiency in modeling complex chemical mixtures.

physics.chem-ph↗
arXiv2025

MesoNet: A Fundamental Principle for Multi-Representation Learning in Complex Chemical Systems

Accurate prediction of molecular properties in complex chemical systems is crucial for accelerating material discovery and chemical innovation. However, current computational methods often struggle to capture the intricate compositional interplay across complex chemical systems, from intramolecular bonds to intermolecular forces. In this work, we introduce MesoNet, a novel framework founded on the principle of multi-representation learning and specifically designed for multi-molecule modeling. The core innovation of MesoNet lies in the construction of context-aware representation-dynamically enriched atomic descriptors generated via Neural Circuit Policies. These parameters efficiently capture both intrinsic atomic properties and their dynamic compositional context through a cross-attention mechanism spanning both intramolecular and intermolecular message passing. Driven by this mechanism, the influence of the mixed system is progressively applied to each molecule and atom, making message passing both efficient and meaningful. Comprehensive evaluations across diverse public datasets, spanning both pure components and mixtures, demonstrate that MesoNet achieves superior accuracy and enhanced chemical interpretability for molecular properties. This work establishes a powerful, interpretable approach for modeling compositional complexity, aiming to advance chemical simulation and design.

physics.chem-ph↗
arXiv2023

Neural Network Driven, Interactive Design for Nonlinear Optical Molecules Based on Group Contribution Method

A Lewis-mode group contribution method (LGC) -- multi-stage Bayesian neural network (msBNN) -- evolutionary algorithm (EA) framework is reported for rational design of D-Pi-A type organic small-molecule nonlinear optical materials is presented. Upon combination of msBNN and corrected Lewis-mode group contribution method (cLGC), different optical properties of molecules are afforded accurately and efficiently - by using only a small data set for training. Moreover, by employing the EA model designed specifically for LGC, structural search is well achievable. The logical origins of the well performance of the framework are discussed in detail. Considering that such a theory guided, machine learning framework combines chemical principles and data-driven tools, most likely, it will be proven efficient to solve molecular design related problems in wider fields.

stat.ML↗
arXiv2022

Nonparaxiality-triggered Landau-Zener transition in topological photonic waveguides

Photonic lattices have been widely used for simulating quantum physics, owing to the similar evolutions of paraxial waves and quantum particles. However, nonparaxial wave propagations in photonic lattices break the paradigm of the quantum-optical analogy. Here, we reveal that nonparaxiality exerts stretched and compressed forces on the energy spectrum in the celebrated Aubry-Andre-Harper model. By exploring the mini-gaps induced by the finite size of the different effects of nonparaxiality, we experimentally present that the expansion of one band gap supports the adiabatic transfer of boundary states while Landau-Zener transition occurs at the narrowing of the other gap, whereas identical transport behaviors are expected for the two gaps under paraxial approximation. Our results not only serve as a foundation of future studies of dynamic state transfer but also inspire applications leveraging nonparaxial transitions as a new degree of freedom.

cond-mat.mes-hall↗
arXiv2021

Optical vortex coronagraph imaging of a laser-induced plasma filament

A high contrast imaging technique based on an optical vortex coronagraph (OVC) is used to measure the spatial phase profile induced by an air plasma generated by a femtosecond laser pulse. The sensitivity of the OVC method significantly surpassed both in-line holographic and direct imaging methods based on air plasma fluorescence. The estimated phase sensitivity of 0.046 waves provides opportunities for OVC applications in areas such as bioimaging, material characterization, as well as plasma diagnostics.

physics.optics↗