Theoretical and Applied Mechanics Letters理论与应用力学快报
Theoretical and Applied Mechanics Letters(英文缩写 THEOR APPL MECH LETT),ISSN 2095-0349,eISSN 2589-0336,中文译名:理论与应用力学快报 是一本学术期刊。本页汇总该期刊的最新影响因子、分区信息以及最新收录于 PubMed 的文献,帮助您快速了解期刊全貌。
发文量统计区间：2025-10-01 至 2026-09-30，按本站收录文献的发表日期统计。
期刊介绍
历年影响因子趋势
| JCR 数据年份 | 影响因子 | JCR 分区 |
|---|---|---|
| 2021 | 未收录 | N/A |
| 2022 | 3.400 | N/A |
| 2023 | 3.200 | Q2 |
| 2024 | 3.300 | Q2 |
| 2025 | 3.000 | Q2 |
Theoretical and Applied Mechanics Letters 最新收录文献
-
1. Hybridndiff-UQ: Uncertainty quantification for hybrid neural differentiable modeling.
PMID:日期:2026-03-10The hybrid neural differentiable models mark a significant advancement in the field of scientific machine learning. These models, integrating numerical representations of known physics into deep neural networks, offer enhanced predictive capabilities and show great potential for data-driven modeling of complex physical systems. However, a critical and yet unaddressed challenge lies in the quantification of inherent uncertainties stemming from multiple sources. Addressing this gap, we introduce a novel method, uncertainty quantification for hybrid neural differentiable modeling, for effective and efficient uncertainty propagation and estimation in hybrid neural differentiable models, leveraging the strengths of deep ensemble Bayesian learning and nonlinear transformations. Specifically, our approach effectively discerns and quantifies both aleatoric uncertainties, arising from data noise, and epistemic uncertainties, resulting from model-form discrepancies and data sparsity. This is achieved within a Bayesian model averaging framework, where aleatoric uncertainties are modeled through hybrid neural models. The unscented transformation plays a pivotal role in enabling the flow of these uncertainties through the nonlinear functions within the hybrid model. In contrast, epistemic uncertainties are estimated using an ensemble of stochastic gradient descent trajectories. This approach offers a practical approximation to the posterior distribution of both the network parameters and the physical parameters. Notably, our framework is designed for simplicity in implementation and high scalability, making it suitable for parallel computing environments. The merits of the proposed method have been demonstrated through problems governed by both ordinary and partial differentiable equations.