Identification and Classification of Technical Lignins by means of Principle Component Analysis and k‐Nearest Neighbor Algorithm

The characterization of technical lignins is a key step for the efficient use and processing this material into valuable chemicals quality control. In study 31 lignin samples were prepared from different biomass sources (hardwood, softwood, straw, grass) pulping processes (sulfite, Kraft, organosolv). Each was analyzed by attenuated total reflectance Fourier transform infrared (ATR-FT-IR) spectroscopy. Statistical analysis ATR-FT-IR spectra means principal component (PCA) showed significant differences between lignins. Hence, can be separated PCA according to original biomass. observed in result primarily relative ratios p-hydroxyphenyl, guaiacyl syringyl units. Only limited influence process reflected spectral data. do not differ processed Kraft or organosolv processes. Lignosulfonates are clearly distinguishable other samples. For classification model created using k-nearest neighbor (k-NN) algorithm. Different data pretreatment steps compared k=1 … 20. validation purposes, 5-fold cross-validation chosen criteria Accuracy (Acc), Error Rate (Err), Sensitivity (TPR) specificity (TNR) introduced. optimized k=4 gives values Acc=98.9 %, Err=1.1 TPR=99.2 % TNR=99.6 %.