Efficient Numerical Wave Propagation Enhanced By An End-to-End Deep Learning Model
In a variety of scientific and engineering domains, the need for high-fidelity and efficient solutions for high-frequency wave propagation holds great significance. Recent advances in wave modeling use sufficiently accurate fine solver outputs to train a neural network that enhances the accuracy of a fast but inaccurate coarse solver. In this paper we build upon the work of Nguyen and Tsai (2023) and present a novel unified system that integrates a numerical solver with a deep learning component into an end-to-end framework. In the proposed setting, we investigate refinements to the network architecture and data generation algorithm. A stable and fast solver further allows the use of Parareal, a parallel-in-time algorithm to correct high-frequency wave components. Our results show that the cohesive structure improves performance without sacrificing speed, and demonstrate the importance of temporal dynamics, as well as Parareal, for accurate wave propagation.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Diffusion prior as a direct regularization term for FWI
Diffusion models have recently shown promise as powerful generative priors for inverse problems. However, conventional applications require solving the full reverse diffusion process and operating on noisy intermediate s…
DenoisingSeismic ImagingPlasma Brain Dynamics (PBD): A Mechanism for EEG Waves Under Human Consciousness
EEG signals are records of nonlinear solitary waves in human brains. The waves have several types (e.g., a, b, g, q, d) in response to different levels of consciousness. They are classified into two groups: Group-1 consi…
EEGElectroencephalogram (EEG)Harnessing Loss Decomposition for Long-Horizon Wave Predictions via Deep Neural Networks
Accurate prediction over long time horizons is crucial for modeling complex physical processes such as wave propagation. Although deep neural networks show promise for real-time forecasting, they often struggle with accu…
PredictionTraffic Wave Properties for Automated Vehicles During Traffic Oscillations via Analytical Approximations
This paper presents an analytical approximation framework to understand the dynamics of traffic wave propagation for Automated Vehicles (AVs) during traffic oscillations. The framework systematically unravels the intrica…
Hybrid pulse propagation model and quasi-phase-matched four-wave mixing in multipass cells
We describe a nonlinear propagation model based on a generalized Schrödinger equation in the time domain coupled to Gaussian beam evolution through ABCD matrices that account for Kerr lensing in the spatial domain. This…