Surfactants Critical Micelle Concentration Prediction with Uncertainty-Aware Graph Neural Network

The critical micelle concentration (CMC) is a fundamental physicochemical property of surfactants with significant implications across multiple industries. This paper presents uncertainty-aware graph neural network that integrates molecular structure and temperature to simultaneously predict CMC values and prediction uncertainties. Trained on a curated dataset of 1,829 surfactants with temperature annotations, our GNN achieves competitive performance (RMSE = 0.352, MAE = 0.244) on an external test set, outperforming previous models in RMSE. The model provides statistically sound, adequately calibrated uncertainty estimates that reliably quantify prediction confidence. This dual-output approach enables reliable CMC prediction with quantifiable confidence intervals, addressing a practical need for safety-critical applications where underestimation of uncertainty could have serious consequences.