Advancing holocellulose content prediction in Chinese fir via transfer learning and Raman integration

Abstract

Holocellulose, a term encompassing both cellulose and hemicellulose, constitutes a crucial component of plant cell walls. Traditional wet chemistry methods (WCMs) for measuring holocellulose content have been criticized for their environmental unfriendliness and low efficiency. In the southern part of China, Chinese fir plantations play a significant role as a resource for wood, paper, and bioenergy. This study proposes the use of Raman signals, along with various algorithms, to predict the holocellulose content of Chinese fir as an alternative to traditional WCMs. The results indicate the successful development of a reliable predictive model by carefully selecting the most suitable internal standard peak and algorithm. Furthermore, transfer learning is demonstrated to enhance the accuracy and efficiency of the model. Consequently, the establishment of such predictive models is recommended for consideration in similar endeavors aiming to be a complementary method to WCMs.