发表机构
The University of Manchester（曼彻斯特大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出积分化学反应神经网络（iCRNN），通过积分配点与数值求积替代ODE求解，实现更快、更稳定的训练，并在基准CRN上显著提速且保持同等精度。
AI 中文摘要
从时间序列浓度数据中发现化学反应网络（CRNs）的结构和动力学是化学动力学中的一个基本挑战，现有方法依赖于先验的机理假设，或遭受高计算成本和噪声敏感性的困扰。在本工作中，我们提出了积分化学反应神经网络（iCRNNs），该框架将化学反应神经网络（CRNNs）的可解释、物理约束架构与控制动力学的积分配点公式相结合。不同于在每个训练步骤中向前求解常微分方程（ODEs），我们直接使用数值求积来近似学习到的速率函数的积分。这产生了仅包含矩阵运算的完全代数前向传递，消除了标准CRNN中重复的自适应ODE求解，并产生更平滑、更可预测的训练过程。我们提供了恢复误差分析，刻画了限制网络可辨识性的病态条件的结构来源（守恒定律、反应可逆性和共享反应物集）。在两个基准CRN上，iCRNN在四物种机制上的训练墙钟时间约为基线CRNN方法的一半，在五物种机制上快三到四倍，同时可靠地完成每次训练运行并获得相当或更低的损失。
英文摘要
Discovering the structure and kinetics of chemical reaction networks (CRNs) from time-series concentration data is a fundamental challenge in chemical kinetics, with existing approaches relying on prior mechanistic assumptions or suffering from high computational cost and noise sensitivity. In this work, we present integral chemical reaction neural networks (iCRNNs), a framework that combines the interpretable, physics-constrained, architecture of chemical reaction neural networks (CRNNs) with an integral collocation formulation of the governing dynamics. Rather than solving ODEs forward in time at each training step, we approximate the integral of the learned rate functions directly using numerical quadrature. This yields an entirely algebraic forward pass consisting only of matrix operations, eliminating the repeated adaptive ODE solves of standard CRNN and producing smoother, more predictable training. We provide a recovery error analysis characterising the structural sources of ill-conditioning (conservation laws, reaction reversibility, and shared reactant sets) that limit network identifiability. On two benchmark CRNs, iCRNN trains in roughly half the wall-clock time of the baseline CRNN method on a four-species mechanism and between three and four times faster on a five-species mechanism, while completing every training run reliably and attaining comparable or lower loss.
Comments18 pages, 4 figures
