TY  - JOUR
T1  - Prediction of Dehydrogenation Enthalpy Using Graph Isomorphism Network
AU  - Choi, Kun Young 
AU  - Yuk, Woo Hyun 
AU  - Han, Jeong Woo 
AU  - Hong, Cham Kill 
JO  - Journal of KIISE, JOK
PY  - 2024
DA  - 2024/1/14
DO  - 10.5626/JOK.2024.51.5.406
KW  - dehydrogenation enthalpy
KW  - graph isomorphism network
KW  - molecular embedding
AB  - This paper conducts dehydrogenation enthalpy prediction that could play an important role in selecting optimal liquid organic hydrogen carriers. We employed graph convolutional networks, which produced molecular embeddings for the prediction. Specifically, we adopted Graph Isomorphism Network (GIN) known to be the most expressive graph-based representation learning model. Our proposed approach could build molecular embeddings. Our proposed approach outperformed conventional machine learning solutions and traditional representations based on chemical physics algorithms. In addition, the performance of the proposed model could be improved with small batch sizes and deeper GCN layers using skip connections.