Work

CodeJeNN: A simple C++ neural network generator for physics applications

Year: 2026

Type: software-paper

Abstract: Machine learning has shown promise in physics applications, but integrating Python-based libraries into high-performance C ++ solvers can create performance bottlenecks. We present CodeJeNN , which addresses this gap by auto-generating self-contained C ++ code from trained Keras models for inference. This eliminates external dependencies through inlined functions, allowing seamless integration into existing frameworks. We describe the Keras-to-C ++ workflow, supported architectures, and limitations. CodeJeNN is demonstrated through inference benchmarks against Keras (eager and optimized) and a computational fluid dynamics (CFD) simulation of a hydrogen-air mixing layer in which viscosity is modeled using a neural network, showing that the generated models integrate directly into a solver while remaining efficient and accurate.

Source: SoftwareX

DOI: 10.1016/j.softx.2026.103203

Authors: Jay Arcities, Pavel P. Popov, Eric J. Ching, Kamal Viswanath, Ryan F. Johnson

Institutions: San Diego State University, United States Naval Research Laboratory, Naval Research Laboratory Laboratories for Computational Physics & Fluid Dynamics

Language: English

Topic: Model Reduction and Neural Networks

Subfield: Statistical and Nonlinear Physics

Field: Physics and Astronomy

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $1,200

Funder: Office of Naval Research