English
Related papers

Related papers: Applying physics-based loss functions to neural ne…

200 papers

We propose a self-supervised physics-informed neural network (PINN) framework that adaptively balances physics-based and data-driven supervision for scientific machine learning under data scarcity. Unlike prior PINNs that rely on fixed or…

Machine Learning · Computer Science 2026-05-08 Reza Pirayeshshirazinezhad

Physics-Informed Neural Networks (PINNs) have recently emerged as a novel approach to simulate complex physical systems on the basis of both data observations and physical models. In this work, we investigate the use of PINNs for various…

Analysis of PDEs · Mathematics 2024-03-27 Guillaume Coulaud , Maxime Le , Régis Duvigneau

Weather forecasting is essential but remains computationally intensive and physically incomplete in traditional numerical weather prediction (NWP) methods. Deep learning (DL) models offer efficiency and accuracy but often ignore physical…

Machine Learning · Computer Science 2025-05-26 Yingtao Luo , Shikai Fang , Binqing Wu , Qingsong Wen , Liang Sun

Recent applications of machine learning, in particular deep learning, motivate the need to address the generalizability of the statistical inference approaches in physical sciences. In this letter, we introduce a modular physics guided…

Machine Learning · Computer Science 2021-02-03 Suraj Pawar , Omer San , Burak Aksoylu , Adil Rasheed , Trond Kvamsdal

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

Physics-informed neural network (PINN) is a data-driven solver for partial and ordinary differential equations(ODEs/PDEs). It provides a unified framework to address both forward and inverse problems. However, the complexity of the…

Machine Learning · Computer Science 2024-01-17 Abdul Hannan Mustajab , Hao Lyu , Zarghaam Rizvi , Frank Wuttke

The application of deep learning methods to speed up the resolution of challenging power flow problems has recently shown very encouraging results. However, power system dynamics are not snap-shot, steady-state operations. These dynamics…

Machine Learning · Computer Science 2022-06-22 Mostafa Mohammadian , Kyri Baker , Ferdinando Fioretto

There is a growing consensus that solutions to complex science and engineering problems require novel methodologies that are able to integrate traditional physics-based modeling approaches with state-of-the-art machine learning (ML)…

Computational Physics · Physics 2022-03-15 Jared Willard , Xiaowei Jia , Shaoming Xu , Michael Steinbach , Vipin Kumar

Machine learning encompasses a broad range of algorithms and modeling tools used for a vast array of data processing tasks, which has entered most scientific disciplines in recent years. We review in a selective way the recent research on…

In recent years, the gap between Deep Learning (DL) methods and analytical or numerical approaches in scientific computing is tried to be filled by the evolution of Physics-Informed Neural Networks (PINNs). However, still, there are many…

Machine Learning · Computer Science 2024-08-16 Jassem Abbasi , Pål Østebø Andersen

Physics-Informed Neural Networks have become a powerful mesh-free method for solving partial differential equations, but their performance is often limited by spectral bias. Specifically, in standard MLPs used in PINNs, the global parameter…

Machine Learning · Computer Science 2026-05-04 Jianfeng Li , Feng Wang , Ke Tang

While there is currently a lot of enthusiasm about "big data", useful data is usually "small" and expensive to acquire. In this paper, we present a new paradigm of learning partial differential equations from {\em small} data. In…

Artificial Intelligence · Computer Science 2018-01-17 Maziar Raissi , George Em Karniadakis

The paper presents an efficient and robust data-driven deep learning (DL) computational framework developed for linear continuum elasticity problems. The methodology is based on the fundamentals of the Physics Informed Neural Networks…

Machine Learning · Computer Science 2023-02-21 Arunabha M. Roy , Rikhi Bose

Physics Informed Neural Networks is a numerical method which uses neural networks to approximate solutions of partial differential equations. It has received a lot of attention and is currently used in numerous physical and engineering…

Numerical Analysis · Mathematics 2025-07-10 Dimitrios Gazoulis , Ioannis Gkanis , Charalambos G. Makridakis

In a landscape where scientific discovery is increasingly driven by data, the integration of machine learning (ML) with traditional scientific methodologies has emerged as a transformative approach. This paper introduces a novel,…

Machine Learning · Computer Science 2024-06-26 Yunjin Tong

The integration of deep learning techniques and physics-driven designs is reforming the way we address inverse problems, in which accurate physical properties are extracted from complex data sets. This is particularly relevant for quantum…

High Energy Physics - Lattice · Physics 2025-01-13 Gert Aarts , Kenji Fukushima , Tetsuo Hatsuda , Andreas Ipp , Shuzhe Shi , Lingxiao Wang , Kai Zhou

This study investigates the potential accuracy boundaries of physics-informed neural networks, contrasting their approach with previous similar works and traditional numerical methods. We find that selecting improved optimization algorithms…

Computational Physics · Physics 2024-12-16 Jorge F. Urbán , Petros Stefanou , José A. Pons

As the key component that facilitates long-haul transmission in optical fiber communications by increasing capacity and reducing costs, accurate characterization and gain settings of erbium-doped fiber amplifiers (EDFAs) are essential for…

Optics · Physics 2025-02-24 Xiaotian Jiang , Jiawei Dong , Yuchen Song , Jin Li , Min Zhang , Danshi Wang

This work proposes a solution for the problem of training physics-informed networks under partial integro-differential equations. These equations require an infinite or a large number of neural evaluations to construct a single residual for…

Machine Learning · Computer Science 2024-06-12 Ehsan Saleh , Saba Ghaffari , Timothy Bretl , Luke Olson , Matthew West

Physics-informed Neural Networks (PINNs) have been shown to be effective in solving partial differential equations by capturing the physics induced constraints as a part of the training loss function. This paper shows that a PINN can be…

Machine Learning · Computer Science 2023-05-08 Chandrajit Bajaj , Luke McLennan , Timothy Andeen , Avik Roy