Uncertainty estimation in deep learning‐based property models: Graph neural networks applied to the critical properties

Deep learning and graph-based models have gained popularity in various life science applications such as property modeling, achieving state-of-the-art performance. However, the quantification of prediction uncertainty these is less studied not applied low dataset size regime, which characterizes many chemical engineering-related molecular properties. In this work, we apply two to model critical- temperature, pressure, volume three techniques (the bootstrap, ensemble, dropout) quantify uncertainty. The overall confidence evaluated using coverage. results suggest that perform better compared with current group-contribution-based modeling while eliminating tedious task developing descriptors.