Abstract
The thermal hazard, has become one of the basic characteristics of different Ionic Liquids (ILs). The thermal decomposition of ionic liquids (ILs) is also an important aspect to evaluate the thermal hazard of ILs. So, in the present manuscript, we have paid our attention to predict the thermal decomposition temperature (Td) of ionic liquids (ILs). To justify our goal, the quantitative structure–property relationship (QSPR) models via SMILES notation of molecular structures of ILs using the Monte Carlo algorithm of CORAL software is applied to calculate the Td of 263 imidazolium ionic liquids. Here, four QSPR models have been constructed using a hybrid optimal descriptor based on correlation weights derived from SMILES and molecular hydrogen-suppressed graphs (HSG) and validated using the criterion index of ideality correlation (IIC). The experimental dataset is indiscriminately split into training, invisible training, calibration, (approximately 74%) and validation (approximately 26%) sets. The range of the value of various statistical features of constructed models are: r2Training = 0.8798–0.8981, Q2Training = 0.8782–0.8994, Fischer F-ratio (F Training) = 625–767 and r2Validation = 0.8654–0.9004, Q2Validation = 0.8584–0.8995, Fischer F-ratio (F Validation) = 392–609. The structural attributes responsible for the increase and decrease of the Td are also extracted.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
