Saved in:
Bibliographic Details
Main Authors: Babić, Miloš, Rohrhofer, Franz M., Posch, Stefan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.04708
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913094470467584
author Babić, Miloš
Rohrhofer, Franz M.
Posch, Stefan
author_facet Babić, Miloš
Rohrhofer, Franz M.
Posch, Stefan
contents From neural ODEs to continuous-time machine learning, differentiable solvers allow physics, optimization, and simulation to become trainable components within deep learning systems. This has opened the path to a new generation of deep learning frameworks for scientific computing, with many promising applications still emerging. In this paper, we integrate a differentiable chemistry solver into a modified physics-informed neural network to solve parameterized reaction systems that are inherently stiff. The proposed framework introduces several key components required to overcome limitations of standard physics-informed neural networks. These include a differentiable chemistry solver, a network architecture for parameterized solutions, and residual weighting tailored to stiff reactions. We evaluate the framework on a set of differential equations related to hydrogen combustion, which include initial/boundary value problems, inverse parameter identification, and a parameterized partial differential equation. Our results highlight the ability of the proposed approach to extend physics-informed neural networks to stiff chemical systems that were previously inaccessible.
format Preprint
id arxiv_https___arxiv_org_abs_2605_04708
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Differentiable Chemistry in PINNs for Solving Parameterized and Stiff Reaction Systems
Babić, Miloš
Rohrhofer, Franz M.
Posch, Stefan
Machine Learning
From neural ODEs to continuous-time machine learning, differentiable solvers allow physics, optimization, and simulation to become trainable components within deep learning systems. This has opened the path to a new generation of deep learning frameworks for scientific computing, with many promising applications still emerging. In this paper, we integrate a differentiable chemistry solver into a modified physics-informed neural network to solve parameterized reaction systems that are inherently stiff. The proposed framework introduces several key components required to overcome limitations of standard physics-informed neural networks. These include a differentiable chemistry solver, a network architecture for parameterized solutions, and residual weighting tailored to stiff reactions. We evaluate the framework on a set of differential equations related to hydrogen combustion, which include initial/boundary value problems, inverse parameter identification, and a parameterized partial differential equation. Our results highlight the ability of the proposed approach to extend physics-informed neural networks to stiff chemical systems that were previously inaccessible.
title Differentiable Chemistry in PINNs for Solving Parameterized and Stiff Reaction Systems
topic Machine Learning
url https://arxiv.org/abs/2605.04708