Early Detection of Fusarium oxysporum Infection in Processing Tomatoes (Solanum lycopersicum) and Pathogen–Soil Interactions Using a Low-Cost Portable Electronic Nose and Machine Learning Modeling

Abstract

The early detection of pathogen infections in plants has become an important aspect of integrated disease management. Although previous research demonstrated the idea of applying digital technologies to monitor and predict plant health status, there is no effective system for detecting pathogen infection before symptomatology appears. This paper presents the use of a low-cost and portable electronic nose coupled with machine learning (ML) models for early disease detection. Several artificial neural network models were developed to predict plant physiological data and classify processing tomato plants and soil samples according to different levels of pathogen inoculum by using e-nose outputs as inputs, plant physiological data, and the level of infection as targets. Results showed that the pattern recognition models based on different infection levels had an overall accuracy of 94.4–96.8% for tomato plants and between 94.81% and 96.22% for soil samples. For the prediction of plant physiological parameters (photosynthesis, stomatal conductance, and transpiration) using regression models or tomato plants, the overall correlation coefficient was 0.97–0.99, with very significant slope values in the range 0.97–1. The performance of all models shows no signs of under or overfitting. It is hence proven accurate and valid to use the electronic nose coupled with ML modeling for effective early disease detection of processing tomatoes and could also be further implemented to monitor other abiotic and biotic stressors.

Analysis of Wheat Grain Infection by Fusarium Mycotoxin-Producing Fungi Using an Electronic Nose, GC-MS, and qPCR

“…Feng et al [ 65 ] reported early detection of Fusarium oxysporum infection in tomato processing using a low-cost portable electronic nose with a classification accuracy in the range of 84–95%.…”

Whole-Plant Physiological Identification and Quantification of Disease Progression

“…Notably, in the case of Fol, this indication came up to 49 days before the manifestation of visual symptoms (Table 1, Row 7) and an average of 35.2 days before any morphological symptoms were observable. Other studies have reported a decline in vascular flow or water loss slightly before the appearance of wilt symptoms in infected plants (Feng et al, 2022;Street & Cooper, 1984;Wang et al, 2012). To document this, Wang et al (2012) and Feng et al (2022) used a Li-6400 gas exchange system (Li-Cor Inc.); whereas Street and Cooper (1984) used a Scholander pressure bomb.…”

“…Other studies have reported a decline in vascular flow or water loss slightly before the appearance of wilt symptoms in infected plants (Feng et al, 2022;Street & Cooper, 1984;Wang et al, 2012). To document this, Wang et al (2012) and Feng et al (2022) used a Li-6400 gas exchange system (Li-Cor Inc.); whereas Street and Cooper (1984) used a Scholander pressure bomb. In contrast to the simple assessment using the PlantArray system, the aforementioned methods are time-consuming and laborious.…”

Integrated Management of Pathogens and Microbes in Cannabis sativa L. (Cannabis) under Greenhouse Conditions

“…The Bloodhound ® ST214′s efficacy in detecting disease presence by analyzing VOCs emitted by tomato plants infected with powdery mildew ( Oidium neolycopersici ) in greenhouse settings compared to healthy controls was demonstrated [ 137 ]. Similarly, a low-cost, portable e-nose combined with machine learning algorithms was used to accurately detect Fusarium oxysporum in tomato plants and soil samples [ 138 ], while Sun et al [ 139 ] were successful in detecting B. cinerea infection in tomatoes. A PEN 3, Win Muster Air-sense Analytics E-nose was used to identify infections caused by three fungi— Botrytis spp., Penicillium spp., and Rhizopus spp.—in strawberries [ 140 ].…”