Prediction of the self-accelerating decomposition temperature of organic peroxides using the quantitative structure–property relationship (QSPR) approach

• We developed QSPR model to predict SADT of organic peroxides for the first time.
• Our model is based only on simple descriptors calculated from molecular structures.
• Our model is validated to be reliable, interpretable, predictive and easy to apply.
• This study provided a new way for predicting thermal hazards of organic peroxides.
• This study provided insight into what structure features are most related to SADT.

The reactivity hazard of organic peroxides has been reported as one of the main causes for fire and explosion in process industries. The self-accelerating decomposition temperature (SADT) is one of the most important thermal hazard parameters for risk assessment and safe management of organic peroxides during storage and transportation. This study proposed a quantitative structure–property relationship (QSPR) model to predict the SADT of organic peroxides for the estimation of their thermal stability and reactivity hazards, from only the knowledge of their molecular structures. Various kinds of molecular descriptors were calculated to represent the molecular structures of organic peroxides. Genetic algorithm based multiple linear regression is employed to select optimal subset of descriptors that have significant contribution to the overall SADT property. The best resulted model is a six-variable multilinear model with the average absolute error for the external test set being 5.7 °C. Model validation was performed to check the stability and predictivity of this model. The results showed that the model is valid and predictive. The mean effect method was also performed to identify the relative significance of each descriptor contributing to the thermal hazards of organic peroxides. The proposed study can provide a new, quick and easy applicable way to predict the SADT of organic peroxides for identifying the reactivity hazards that may lead to safe practices in the process industries for engineering.