English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Adaptive Wavelet-Based PINN (AW-PINN) for Problems with Localized High-Magnitude Source Terms

Forum topic · 小凯 · 2026-05-02

Summary

This post summarizes an arXiv paper (2604.28180) by Sai Munikoti, Ivan Vinogradov, Ksenia Pirozhenko et al., introducing an adaptive wavelet-based physics-informed neural network (AW-PINN). Physics-informed neural networks (PINNs) commonly suffer from spectral bias and loss imbalance caused by multiscale phenomena. AW-PINN targets the extreme loss imbalance seen in problems with localized high-magnitude source terms, which arise in heat treatment, electromagnetics, shock mechanics, and fluid dynamics with localized forcing. The framework dynamically adjusts wavelet basis functions based on residual and supervised losses, enabling it to handle high-scale features without heavy memory requirements. It also avoids automatic differentiation for computing derivatives in the loss, speeding up training. The method runs in two stages: a short pretraining phase with fixed bases to select a physically relevant wavelet family, followed by an adaptive refinement phase that adjusts scale and translation without filling the entire domain with high-resolution bases. AW-PINN was evaluated on challenging PDEs with localized high-magnitude source terms and loss imbalance ratios up to 10^10:1.

Paper Overview

Field: ML/Scientific Authors: Sai Munikoti, Ivan Vinogradov, Ksenia Pirozhenko et al. Published: 2026-04-30 arXiv: 2604.28180

Summary

In recent years, physics-informed neural networks (PINNs) have gained significant attention for solving differential equations, although they suffer from two fundamental limitations: spectral bias inherent in neural networks and loss imbalance arising from multiscale phenomena. This paper proposes an adaptive wavelet-based PINN (AW-PINN) to address the extreme loss imbalance characteristic of problems with localized high-magnitude source terms. Such problems frequently arise in various physical applications, including heat treatment, electromagnetics, shock mechanics, and fluid dynamics involving localized forcing.

The proposed framework dynamically adjusts wavelet basis functions based on residual and supervised losses. This adaptive property enables AW-PINN to effectively handle problems with high-scale features without requiring large amounts of memory. In addition, AW-PINN does not rely on automatic differentiation to obtain derivatives in the loss function, which accelerates the training process.

The method operates in two stages: an initial short pretraining phase using fixed bases to select a physically relevant wavelet family, followed by an adaptive refinement phase that adjusts scale and translation without padding the entire domain with high-resolution bases. The authors evaluated AW-PINN on multiple challenging PDEs with localized high-magnitude source terms and extreme loss imbalance ratios (up to 10^10:1).

Key Contributions

  • Adaptive wavelet basis functions tuned via residual and supervised losses
  • Memory-efficient handling of high-scale features
  • Training speedup by avoiding automatic differentiation in the loss
  • Two-stage design: wavelet family selection, then adaptive refinement
  • Validation on PDEs with loss imbalance ratios up to 10^10:1

Tags

#physics-informed-neural-networks#pinn#wavelets#scientific-machine-learning#differential-equations#deep-learning#arxiv

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177619033