The successful prediction of minimum ignition energies (MIEs) for 55 flammable organic molecules has been accomplished through group contribution and machine learning methods. The applied techniques include least squares regression, Huber regression, and kernel ridge regression, with the Marrero/Gani method applied to determine structurally dependent descriptors to uniquely characterize each molecule. These descriptors were used as predictors for the aforementioned regressions techniques to develop four predictive models. The rudimentary least squares regression resulted in a modest R of 0.939 on the at-large data set, but overpredicted the MIEs of several compounds. An improved least squares regression featured a lower R of 0.840, but with virtually no overprediction. Outlier analysis was conducted with the Huber and kernel ridge techniques, and these models exhibited reduced outlier influence and considered the non-linear relationship between predictors and MIEs. These improved algorithms also used L regularization to reduce sensitivity of MIE predictions on statistically insignificant descriptors. Resulting R values for models developed using the Huber and kernel ridge techniques came out to be 0.878 and 0.991, respectively, when applied to the at-large data set, and featured little overprediction. Thus, it is concluded that simple group contribution methods, optimized by Huber and kernel ridge techniques, are potential modeling alternatives for simple and accurate prediction of organic molecule MIEs.

中文翻译：

---

用于 MIE 预测的官能团分析和机器学习技术

通过团队贡献和机器学习方法，成功预测了 55 种易燃有机分子的最小点火能 (MIE)。所应用的技术包括最小二乘回归、Huber 回归和核岭回归，并应用 Marrero/Gani 方法来确定结构相关描述符以唯一地表征每个分子。这些描述符被用作上述回归技术的预测因子，以开发四种预测模型。基本最小二乘回归在大数据集上得出的 R 值适中，为 0.939，但高估了几种化合物的 MIE。改进的最小二乘回归的 R 值较低为 0.840，但几乎没有过度预测。使用 Huber 和核岭技术进行离群值分析，这些模型表现出减少的离群值影响，并考虑了预测变量和 MIE 之间的非线性关系。这些改进的算法还使用 L 正则化来降低 MIE 预测对统计上不显着的描述符的敏感性。当应用于大数据集时，使用 Huber 和核岭技术开发的模型的最终 R 值分别为 0.878 和 0.991，并且几乎没有过度预测。因此，得出的结论是，通过 Huber 和核岭技术优化的简单基团贡献方法是简单而准确地预测有机分子 MIE 的潜在建模替代方案。