Solving higher-order Lane-Emden-Fowler type equations using physics-informed neural networks: benchmark tests comparing soft and hard constraints

TL;DR

This paper explores the use of physics-informed neural networks (PINNs) to solve higher-order singular differential equations, comparing soft and hard constraint methods through benchmark tests.

Contribution

It introduces and compares two PINNs variants for solving higher-order Lane-Emden-Fowler equations, highlighting their advantages and limitations.

Findings

PINNs effectively solve higher-order singular ODEs.

Hard constraints ensure boundary conditions exactly.

Soft constraints offer flexibility but may be less precise.

Abstract

In this paper, numerical methods using Physics-Informed Neural Networks (PINNs) are presented with the aim to solve higher-order ordinary differential equations (ODEs). Indeed, this deep-learning technique is successfully applied for solving different classes of singular ODEs, namely the well known second-order Lane-Emden equations, third order-order Emden-Fowler equations, and fourth-order Lane-Emden-Fowler equations. Two variants of PINNs technique are considered and compared. First, a minimization procedure is used to constrain the total loss function of the neural network, in which the equation residual is considered with some weight to form a physics-based loss and added to the training data loss that contains the initial/boundary conditions. Second, a specific choice of trial solutions ensuring these conditions as hard constraints is done in order to satisfy the differential equation, contrary to the first variant based on training data where the constraints appear as soft ones. Advantages and drawbacks of PINNs variants are highlighted.