KPPax: preprocess differentiable kinetic ODE for machine learning in atmospheric chemistry

Wenqing Peng, Michael Boy, Zhi-Song Liu|October 27, 2026arXiv

Key Takeaway

By making atmospheric chemistry models differentiable, KPPax enables automatic computation of parameter sensitivities and hybrid physics-ML models without hand-coded adjoints—reducing emission estimation errors by 2.4–5× in demonstrated applications.

Summary

KPPax converts atmospheric chemistry models from KPP format into differentiable JAX code, enabling automatic differentiation and machine learning integration.

training efficiency applications

Key Terms

differentiable fisher-information-matrix adjoint-method stiff-differential-equations hybrid-physics-machine-learning