Code for the paper Ji, Weiqi, and Sili Deng. "Autonomous Discovery of Unknown Reaction Pathways from Data by Chemical Reaction Neural Network." arXiv preprint arXiv:2002.09062 (2020). https://arxiv.org/abs/2002.09062
The repo corresponds to the initial version of the CRNN paper, in which we train CRNN by first approaximating dydt from concentration time-series data. In the later version, we have instead adopted neural-ordinary differential equations to train CRNN. For the latest version of CRNN code, please refer to https://github.com/DENG-MIT/CRNN