Physics-Informed Neural Networks and Beyond: Enforcing Physical Constraints in Quantum Dissipative Dynamics

2024/04/22 by Arif Ullah, Yu Huang, Ullah, Arif +5 · 1 citation
Computer Science · Physics and Astronomy · #Advanced Thermodynamics and Statistical Mechanics #Chemical Physics (physics.chem-ph) #FOS: Physical sciences #Neural Networks and Applications #Neural Networks and Reservoir Computing

paper · pdf · doi:10.48550/arxiv.2404.14021

openalex publication_date 2024/04/22 · openalex created_date 2024/04/24 · openalex updated_date 2026/07/28

Abstract

Neural networks (NNs) accelerate simulations of quantum dissipative dynamics. Ensuring that these simulations adhere to fundamental physical laws is crucial, but has been largely ignored in the state-of-the-art NN approaches. We show that this may lead to implausible results measured by violation of the trace conservation. To recover the correct physical behavior, we develop physics-informed NNs (PINNs) that mitigate the violations to a good extend. Beyond that, we propose a novel uncertainty-aware approach that enforces perfect trace conservation by design, surpassing PINNs.

Cited by

• Chemistry-Enhanced Diffusion-Based Framework for Small-to-Large Molecular Conformation Generation

Related

• Machine learning meets \mathfraksu(n) Lie algebra: Enhancing quantum dynamics learning with exact trace conservation
• Physics-informed neural networks for quantum propagators in Wavepacket dynamics
• Quantum Port-Hamiltonian Neural Networks: Learning Conservative and Dissipative Dynamics via Measurement-Induced Nonlinearity
• Inverse Physics-informed neural networks procedure for detecting noise in open quantum systems
• Simulating Non-Markovian Open Quantum Dynamics with Neural Quantum States