A novel approach, namely MC-UVE-RF, to improve multi-class classification performance of tobacco leaf grades by NIR spectroscopy.

Purpose: The health of rhizosphere soil microorganisms is an important indicator to evaluate soil quality. Therefore, understanding the response of rhizosphere soil microorganisms to tobacco crop succession is crucial for promoting the sustainable development of agriculture. Methods: The microbial diversity and community structure of rhizosphere soil in continuous cropping and non-cropped tobacco for 7 years were analyzed by the Illumina platform. Result: (1) Continuous cropping tobacco cause rhizosphere soil acidification and reduction in alkaline nitrogen (AN) and soil organic matter (SOM). (2) Continuous cropping tobacco reduces the diversity of rhizosphere soil microbial communities, increasing harmful functional microorganisms and declining beneficial ones. (3) The abundance of bacteria that perform nitrification and saprophytic fungi in the rhizosphere soil of continuous cropping areas decreases, inhibiting carbon and nitrogen cycling processes. (4) The composition and diversity of the soil rhizosphere microbial community are affected by the imbalance in the physicochemical property of the rhizosphere. Conclusion: Continuous cropping tobacco cause rhizosphere soil acidification and nutrient imbalance, and the carbon and nitrogen cycles involved in microorganisms were damaged. Furthermore, the decreased diversity of rhizosphere soil microorganisms and the increased abundance of pathogenic fungi contribute to the continuous cropping obstacles of tobacco.

The maturity affects the yield, quality, and economic value of tobacco leaves. Leaf maturity level discrimination is an important step in manual harvesting. However, the maturity judgment of fresh tobacco leaves by grower visual evaluation is subjective, which may lead to quality loss and low prices. Therefore, an objective and reliable discriminant technique for tobacco leaf maturity level based on near-infrared (NIR) spectroscopy combined with a deep learning approach of convolutional neural networks (CNNs) is proposed in this study. To assess the performance of the proposed maturity discriminant model, four conventional multiclass classification approaches—K-nearest neighbor (KNN), backpropagation neural network (BPNN), support vector machine (SVM), and extreme learning machine (ELM)—were employed for a comparative analysis of three categories (upper, middle, and lower position) of tobacco leaves. Experimental results showed that the CNN discriminant models were able to precisely classify the maturity level of tobacco leaves for the above three data sets with accuracies of 96.18%, 95.2%, and 97.31%, respectively. Moreover, the CNN models with strong feature extraction and learning ability were superior to the KNN, BPNN, SVM, and ELM models. Thus, NIR spectroscopy combined with CNN is a promising alternative to overcome the limitations of sensory assessment for tobacco leaf maturity level recognition. The development of a maturity-distinguishing model can provide an accurate, reliable, and scientific auxiliary means for tobacco leaf harvesting.

A novel calibration transfer approach, WTCCA, combining the advantages of WT and CTCCA has been proposed for NIRS multivariate calibration.

Flavor is an important index to evaluate the sensory quality of tobacco. The process of fermentation is a key step in the production of aromatic substances in tobacco leaves and an important factor in improving their quality. Worldwide, reams of research show that chromatographic technology plays an irreplaceable role in the tobacco aromatic chemistry. Nevertheless, the degradation mechanism of latent aromatic compounds and the formation mechanism of characteristic aromatic substances have not been fully and systematically elucidated. In this study, the latest progress of basic methods, techniques, and research results of the separation, analysis, and identification of aromatic substances in fermented tobacco leaves were reviewed, and the next research and application directions were prospected. It is expected to provide theoretical reference for the study of molecular mechanism of tobacco flavor, reveal the degradation mechanism of potential aroma compounds, and help improve the quality of tobacco.