Autonomous Discovery of Unknown Reaction Pathways from Data by Chemical Reaction Neural Network
- 20 January 2021
- journal article
- research article
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry A
- Vol. 125 (4) , 1082-1092
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 because of 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.Keywords
All Related Versions
Funding Information
- Karl Chang (1965) Innovation Fund, Massachusetts Institute of Technology
This publication has 27 references indexed in Scilit:
- Data-driven discovery of coordinates and governing equationsProceedings of the National Academy of Sciences, 2019
- A robotic platform for flow synthesis of organic compounds informed by AI planningScience, 2019
- An ANN based hybrid chemistry framework for complex fuelsFuel, 2019
- Reactive SINDy: Discovering governing reactions from concentration dataThe Journal of Chemical Physics, 2019
- A machine learning approach to predict metabolic pathway dynamics from time-series multiomics datanpj Systems Biology and Applications, 2018
- Data-driven discovery of partial differential equationsScience Advances, 2017
- Reaction Mechanism Generator: Automatic construction of chemical kinetic mechanismsComputer Physics Communications, 2016
- Inferring Biological Networks by Sparse Identification of Nonlinear DynamicsIEEE Transactions on Molecular, Biological, and Multi-Scale Communications, 2016
- Recent advances in laser absorption and shock tube methods for studies of combustion chemistryProgress in Energy and Combustion Science, 2014
- Distilling Free-Form Natural Laws from Experimental DataScience, 2009