A Data-Driven Sparse-Learning Approach to Model Reduction in Chemical Reaction Networks

TL;DR

This paper introduces an optimization-based sparse learning method to identify key reactions in chemical networks, enabling the creation of simplified yet accurate reaction mechanisms with reduced computational effort.

Contribution

It presents a novel relaxation technique for mixed-integer quadratic programming to efficiently determine influential reactions in chemical networks.

Findings

The approach accurately captures network structural properties.

It reduces computational complexity compared to traditional methods.

Validated on chemical reaction networks with promising results.

Abstract

In this paper, we propose an optimization-based sparse learning approach to identify the set of most influential reactions in a chemical reaction network. This reduced set of reactions is then employed to construct a reduced chemical reaction mechanism, which is relevant to chemical interaction network modeling. The problem of identifying influential reactions is first formulated as a mixed-integer quadratic program, and then a relaxation method is leveraged to reduce the computational complexity of our approach. Qualitative and quantitative validation of the sparse encoding approach demonstrates that the model captures important network structural properties with moderate computational load.