Prediction of fatty acid composition in camellia oil by 1H NMR combined with PLS regression

A rapid method for the determination of fatty acid (FA) composition in camellia oils was developed based on the 1H NMR technique combined with partial least squares (PLS) method. Outliers detection, LVs optimization and data pre-processing selection were explored during the model building process. The results showed the optimal models for predicting the content of C18:1, C18:2, C18:3, saturated, unsaturated, monounsaturated and polyunsaturated FA were achieved by Pareto scaling (Par) pretreatment, with correlation coefficient (R2) above 0.99, the root mean square error of estimation and prediction (RMSEE, RMSEP) lower than 0.954 and 0.947, respectively. Mean-centering (Ctr) was more suitable for the model of C16:0 and C18:0 with the best performance indicators (R2 ≥ 0.945, RMSEE ≤ 0.377, RMSEP ≤ 0.212). This study indicated that 1H NMR has the potential to be applied as a rapid and routine method for the analysis of FA composition in camellia oils.