A quantitative structure-property relationship study is performed to develop mathematical models for predicting the flammability characteristics of pure hydrocarbons. The molecular structures of the compounds are numerically represented by various kinds of molecular descriptors. Genetic algorithm based multiple linear regression is used to select most statistically effective descriptors on the flash point, the autoignition temperature, and the lower and upper flammability limits of hydrocarbons, respectively. The resulted models are four multilinear equations. These models are very simple and can predict the flash point, the autoignition temperature, and the lower and upper flammability limits for the test set with average absolute errors of 5.41 K, 28.00 K, 0.044 vol %, and 0.503 vol %, respectively. The models are further compared with other published method and are shown to be more superior. The proposed method can be used to predict the flammability characteristics of hydrocarbons from the knowledge of only the molecular structures. V
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.