Skip to content
Open access

Scientific machine learning meets semi-analytical computation: a hybrid NIM-PINN approach for nonlinear PDEs

Sep 2026 · Scientific Reports · Vol 16 · 0 citations · 51 references

Abstract

In this paper, a hybrid semi-analytical–deep learning framework for the solution of nonlinear partial differential equations (PDEs) is proposed that integrates the New Iterative Method (NIM) with Physics-Informed Neural Networks (PINNs). Low–order NIM expansion provides an analytic baseline that meets the required initial and boundary conditions; a neural network is trained to learn only the residual correction between the analytic baseline and the exact solution. The framework is evaluated on three problems: a linear diffusion equation, the nonlinear reaction–diffusion Newell–Whitehead–Segel (NWS) equation with a sharp transition front, and the nonlinear convective Burgers equation with a sigmoidal travelling front. All three problems are explicitly solved with Dirichlet boundary conditions, and for the baseline-corrected hybrid model, a single network architecture (three inputs, four hidden layers consisting of eighty tanh units, one output) is used in the same way as in a pure PINN control, so that all reported comparisons are architecture-matched. For all of the test examples, the mean absolute error and the relative \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$L^2$$\end{document} error of the raw NIM baseline are lowered by one to two orders of magnitude. The controlled ablation over the baseline truncation order \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$m_0=1,2,3$$\end{document} demonstrates the baseline error decays geometrically due to the NIM initialization error, confirming the separation of the NIM initialization error from the neural correction error. All the numerical statements in the text can be verified directly against a single source, as the single unified results table reports the mean absolute error, root-mean-square error, relative \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$L^2$$\end{document} error, maximum error, PDE residual norm, and boundary residual norm for each method–problem pair. The results demonstrate that the hybrid approach is a stable and effective method to reduce the overall function space that the correction network needs to learn, but it is problem-dependent and this is explicitly discussed.

Read PDF

Similar papers

Open access 2026

A Physics-Informed Neural Network Approach for Solving the Monge-Ampère Partial Differential Equation

This paper presents a comparative study of classical numerical and machine learning techniques for solving the nonlinear Monge–Ampère Equation (MAE). A finite difference method (FDM) implemented in MATLAB is first validated using a quadratic exact solution on a square domain. Two neural network approaches are then inve...

C. Ogbonna, Maliki Olaniyi S, Nkem Ogbonna · 0 citations
Open access Sep 2026

A novel new iterative method–physics-informed neural networks approach for accurate and efficient solutions of nonlinear damped Burgers’ equations

In this work, a hybrid semi-analytical and deep learning framework is proposed for solving nonlinear damped Burgers equations by combining the New Iterative Method (NIM) with Physics-Informed Neural Networks (PINNs). The developed methodology consists of the use of NIM to build an analytical baseline approximation, and...

A. Alshehry, Saima Noor, Humaira Yasmin et al. · 0 citations
#machine learning Preprint Sep 2026

Linearized PINN with pretrained nonlinear layers

Compared with vanilla PINNs, lPINN achieves lower solution and parameter errors while reducing online inference times by approximately one to more than three orders of magnitude, with the largest gains generally observed for limited residual or measurement data.

Wen-Hao Chen, Alexandre M. Tartakovsky · 0 citations
Oct 2026

An efficient custom neural network framework for solving second order partial differential equations

This paper aims to develop an efficient neural network-based method for solving two-dimensional partial differential equations (PDEs) with prescribed initial and boundary conditions. The goal is to overcome the persistent challenge of balancing computational accuracy and efficiency faced by many existing neural net...

Shang-Jie Li, Hui-Zhen Liu, Shu-Ning Zhang et al. · 0 citations
Open access 2026

Adaptive Weighting Strategies and Loss Balancing For Physics Informed Neural Network Solution of the Monge Ampere Partial Differential Equation

In this research we present a comprehensive computational framework for solving the nonlinear Monge-Ampère equation using an adaptive Physics-Informed Neural Network (PINN) approach. The Monge-Ampère equation is a fully nonlinear second-order partial differential equation which plays a fundamental role in optimal trans...

C. Ogbonna, Maliki Olaniyi S, Nkem Ogbonna · 0 citations
Open access 2026

Soliton solutions to KdV and KP equations using physics-informed neural networks

This work systematically investigates the ability of PINNs to capture the nonlinear dynamics of the Korteweg–de Vries (KdV) equation and its two-dimensional generalization, the Kadomtsev–Petviashvili (KP) equation, and compares network architectures, activation functions and optimization strategies while benchmarking P...

Karnav Raval, Nadia Aiaseh, Nima Hosseini Dashtbayaz et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.