Biomass Compositional Analysis Using Sparse Partial Least Squares Regression and Near Infrared Spectrum Technique

Forest bio-fuel, a new type renewable energy, has attracted increasing attention as a promising alternative. In this study, a new method called Sparse Partial Least Squares Regression(SPLS) is used to construct the proximate analysis model to analyze the fuel characteristics of sawdust combining Near Infrared Spectrum Technique. Moisture, Ash, Volatile and Fixed Carbon percentage of 80 samples have been measured by traditional proximate analysis. Spectroscopic data were collected by Nicolet NIR spectrometer. After being filtered by wavelet transform, all of the samples are divided into training set and validation set according to sample category and producing area. SPLS, Principle Component Regression (PCR), Partial Least Squares Regression (PLS) and Least Absolute Shrinkage and Selection Operator (LASSO) are presented to construct prediction model. The result advocated that SPLS can select grouped wavelengths and improve the prediction performance. The absorption peaks of the Moisture is covered in the selected wavelengths, well other compositions have not been confirmed yet. In a word, SPLS can reduce the dimensionality of complex data sets' and interpret the relationship between spectroscopic data and composition concentration, which will play an increasingly important role in the field of NIR application.