Autonomous Discovery of Unknown Reaction Pathways from Data by Chemical Reaction Neural Network

Abstract

Chemical reactions occur in energy, environmental, biological, and many other natural systems, and the inference of the reaction networks is essential to understand and design the chemical processes in engineering and life sciences. Yet, revealing the reaction pathways for complex systems and processes is still challenging due to the lack of knowledge of the involved species and reactions. Here, we present a neural network approach that autonomously discovers reaction pathways from the time-resolved species concentration data. The proposed Chemical Reaction Neural Network (CRNN), by design, satisfies the fundamental physics laws, including the Law of Mass Action and the Arrhenius Law. Consequently, the CRNN is physically interpretable such that the reaction pathways can be interpreted, and the kinetic parameters can be quantified simultaneously from the weights of the neural network. The inference of the chemical pathways is accomplished by training the CRNN with species concentration data via stochastic gradient descent. We demonstrate the successful implementations and the robustness of the approach in elucidating the chemical reaction pathways of several chemical engineering and biochemical systems. The autonomous inference by the CRNN approach precludes the need for expert knowledge in proposing candidate networks and addresses the curse of dimensionality in complex systems. The physical interpretability also makes the CRNN capable of not only fitting the data for a given system but also developing knowledge of unknown pathways that could be generalized to similar chemical systems.

References in corpus (7)

• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• DeepXDE: A deep learning library for solving differential equations
• Data-driven discovery of coordinates and governing equations
• Simulation-based optimal Bayesian experimental design for nonlinear systems
• PDE-Net: Learning PDEs from Data
• Understanding and mitigating gradient pathologies in physics-informed neural networks
• Reverse Engineering Chemical Reaction Networks from Time Series Data

Cited by in corpus (19)

• Stiff-PINN: Physics-Informed Neural Network for Stiff Chemical Kinetics
• Improving aircraft performance using machine learning: a review
• Stiff Neural Ordinary Differential Equations
• KAN-ODEs: Kolmogorov-Arnold Network Ordinary Differential Equations for Learning Dynamical Systems and Hidden Physics
• Machine Learning Approaches to Learn HyChem Models
• Model selection of chaotic systems from data with hidden variables using sparse data assimilation
• Data-driven discovery of multiscale chemical reactions governed by the law of mass action
• Chemical Reaction Neural Networks for Fitting Accelerating Rate Calorimetry Data
• Structural Inference of Networked Dynamical Systems with Universal Differential Equations
• ChemKANs for Combustion Chemistry Modeling and Acceleration
• Using (Not-so) Large Language Models to Generate Simulation Models in a Formal DSL: A Study on Reaction Networks
• Arrhenius.jl: A Differentiable Combustion SimulationPackage
• ChemNODE: A Neural Ordinary Differential Equations Approach for Chemical Kinetics Solvers
• Learning surrogate equations for the analysis of an agent-based cancer model
• Autonomous Kinetic Modeling of Biomass Pyrolysis using Chemical Reaction Neural Networks
• A Layered Swarm Optimization Method for Fitting Battery Thermal Runaway Models to Accelerating Rate Calorimetry Data
• Atoms to Processes: The Role of Artificial Intelligence and Machine Learning in Chemical Engineering
• Learning continuous state of charge dependent thermal decomposition kinetics for Li-ion cathodes using Kolmogorov-Arnold Chemical Reaction Neural Networks (KA-CRNNs)
• Neural Differential Equations for Inverse Modeling in Model Combustors