Discrimination of tomato plants infected by fungal pathogens at different disease severity using E-nose and GC-MS

Abstract

Abstract Disease is a serious problem in tomato plant, causing huge economic loss. Disease detection is the premise of protection. This paper employed Electronic nose (E-nose) and Gas Chromatography-Mass Spectrometer (GC-MS), as an auxiliary technique, to identify disease type and its severity in the tomato plant. A total of twenty-five volatile constituents were identified using GC-MS, their concentrations were calculated and showed the difference in different groups. Furthermore, the results of E-nose and GC-MS were compared and showed a good correlation. Moreover, the possibility of E-nose in discriminating tomato plants infected with different types and severities of disease either respectively or together was proved based on both Principal Component Analysis (PCA) and Discriminant Functions Analysis (DFA). Then, Back-propagation neural network (BPNN) was introduced and showed that the correct classification rates were 98.3% for training set and 97.5% for testing set for predicting disease type and severity. This study demonstrates the feasibility of E-nose in detecting tomato plants with different disease types and severities. E-nose is an excellent technique for disease identification, which is very meaningful for prevention of disease spread and meets actual application needs.