English
Related papers

Related papers: B-PINNs: Bayesian Physics-Informed Neural Networks…

200 papers

The main contribution of this paper is to develop a hierarchical Bayesian formulation of PINNs for linear inverse problems, which is called BPINN-IP. The proposed methodology extends PINN to account for prior knowledge on the nature of the…

Machine Learning · Statistics 2026-02-05 Ali Mohammad-Djafari

Physics-informed neural networks (PINNs) have emerged as a powerful paradigm for solving partial differential equations (PDEs) by embedding physical laws directly into neural network training. However, solving high-fidelity PDEs remains…

Machine Learning · Computer Science 2026-02-03 Olaf Yunus Laitinen Imanov

The recent success of deep neural network models with physical constraints (so-called, Physics-Informed Neural Networks, PINNs) has led to renewed interest in the incorporation of mechanistic information in predictive models. Statisticians…

Methodology · Statistics 2025-11-20 Christopher K. Wikle , Joshua North , Giri Gopalan , Myungsoo Yoo

We develop a new Bayesian framework based on deep neural networks to be able to extrapolate in space-time using historical data and to quantify uncertainties arising from both noisy and gappy data in physical problems. Specifically, the…

Machine Learning · Computer Science 2022-03-14 Xuhui Meng , Liu Yang , Zhiping Mao , Jose del Aguila Ferrandis , George Em Karniadakis

In this paper, we present a novel methodology for automatic adaptive weighting of Bayesian Physics-Informed Neural Networks (BPINNs), and we demonstrate that this makes it possible to robustly address multi-objective and multi-scale…

Computational Physics · Physics 2023-08-09 Sarah Perez , Suryanarayana Maddu , Ivo F. Sbalzarini , Philippe Poncet

Physics-informed neural networks (PINNs) are effective in solving integer-order partial differential equations (PDEs) based on scattered and noisy data. PINNs employ standard feedforward neural networks (NNs) with the PDEs explicitly…

Computational Physics · Physics 2021-11-03 Guofei Pang , Lu Lu , George Em Karniadakis

We present a novel framework combining Deep Operator Networks (DeepONets) with Physics-Informed Neural Networks (PINNs) to solve partial differential equations (PDEs) and estimate their unknown parameters. By integrating data-driven…

Machine Learning · Computer Science 2025-08-05 Amogh Raj , Carol Eunice Gudumotou , Sakol Bun , Keerthana Srinivasa , Arash Sarshar

A significant advancement in Neural Network (NN) research is the integration of domain-specific knowledge through custom loss functions. This approach addresses a crucial challenge: how can models utilize physics or mathematical principles…

Machine Learning · Computer Science 2025-03-27 Seyedeh Azadeh Fallah Mortezanejad , Ruochen Wang , Ali Mohammad-Djafari

Although physics-informed neural networks(PINNs) have progressed a lot in many real applications recently, there remains problems to be further studied, such as achieving more accurate results, taking less training time, and quantifying the…

Machine Learning · Computer Science 2022-12-01 Bin Shan , Ye Li , Shengjun Huang

Scientific machine learning has been successfully applied to inverse problems and PDE discovery in computational physics. One caveat concerning current methods is the need for large amounts of ("clean") data, in order to characterize the…

Numerical Analysis · Mathematics 2021-11-30 Christophe Bonneville , Christopher J. Earls

Data-driven discovery of governing equations in computational science has emerged as a new paradigm for obtaining accurate physical models and as a possible alternative to theoretical derivations. The recently developed physics-informed…

Machine Learning · Computer Science 2023-10-18 Zongren Zou , Xuhui Meng , George Em Karniadakis

Physics-informed neural networks (PINNs) represent a significant advancement in scientific machine learning by integrating fundamental physical laws into their architecture through loss functions. PINNs have been successfully applied to…

Machine Learning · Computer Science 2024-07-16 Wei Zhou , Y. F. Xu

Solving differential equations from limited or noisy data remains a key challenge for physics-informed neural networks (PINNs), which are typically applied to already known and smooth solutions. In this work, we explore Bayesian PINNs and…

High Energy Physics - Theory · Physics 2025-09-30 Filip Landgren , Marika Taylor

Physics-informed neural networks (PINNs) provide a mesh-free framework for solving PDE-constrained inverse problems, but their extension to Bayesian inversion still faces a fundamental difficulty: prior distributions are typically defined…

Geophysics · Physics 2026-05-15 Ryoichiro Agata , Tomohisa Okazaki

Physics-informed neural networks (PINNs) have recently emerged as an alternative way of solving partial differential equations (PDEs) without the need of building elaborate grids, instead, using a straightforward implementation. In…

Analysis of PDEs · Mathematics 2019-09-04 Dongkun Zhang , Lu Lu , Ling Guo , George Em Karniadakis

Physics-Informed Neural Networks (PINNs) are gaining popularity as a method for solving differential equations. While being more feasible in some contexts than the classical numerical techniques, PINNs still lack credibility. A remedy for…

Machine Learning · Computer Science 2022-12-15 Olga Graf , Pablo Flores , Pavlos Protopapas , Karim Pichara

Physics-informed neural networks (PINNs) [31] use automatic differentiation to solve partial differential equations (PDEs) by penalizing the PDE in the loss function at a random set of points in the domain of interest. Here, we develop a…

Neural and Evolutionary Computing · Computer Science 2019-12-03 E. Kharazmi , Z. Zhang , G. E. Karniadakis

Physics-informed neural networks (PINNs) are an influential method of solving differential equations and estimating their parameters given data. However, since they make use of neural networks, they provide only a point estimate of…

Machine Learning · Computer Science 2024-05-15 Lena Podina , Mahdi Torabi Rad , Mohammad Kohandel

Training physics-informed neural networks (PINNs) for forward problems often suffers from severe convergence issues, hindering the propagation of information from regions where the desired solution is well-defined. Haitsiukevich and Ilin…

Machine Learning · Computer Science 2025-07-03 Kevin Innerebner , Franz M. Rohrhofer , Bernhard C. Geiger

We study the posterior contraction rate of Bayesian Physics-Informed Neural Networks (PINNs) for solving a general class of elliptic partial differential equations (PDEs). We focus on learning of the elliptic equation with a non-homogeneous…

Statistics Theory · Mathematics 2026-05-12 Yuxuan Zhao , Yulong Lu