Early Detection of Aphid Infestation and Insect-Plant Interaction Assessment in Wheat Using a Low-Cost Electronic Nose (E-Nose), Near-Infrared Spectroscopy and Machine Learning Modeling

Abstract

Advances in early insect detection have been reported using digital technologies through camera systems, sensor networks, and remote sensing coupled with machine learning (ML) modeling. However, up to date, there is no cost-effective system to monitor insect presence accurately and insect-plant interactions. This paper presents results on the implementation of near-infrared spectroscopy (NIR) and a low-cost electronic nose (e-nose) coupled with machine learning. Several artificial neural network (ANN) models were developed based on classification to detect the level of infestation and regression to predict insect numbers for both e-nose and NIR inputs, and plant physiological response based on e-nose to predict photosynthesis rate (A), transpiration (E) and stomatal conductance (gs). Results showed high accuracy for classification models ranging within 96.5–99.3% for NIR and between 94.2–99.2% using e-nose data as inputs. For regression models, high correlation coefficients were obtained for physiological parameters (gs, E and A) using e-nose data from all samples as inputs (R = 0.86) and R = 0.94 considering only control plants (no insect presence). Finally, R = 0.97 for NIR and R = 0.99 for e-nose data as inputs were obtained to predict number of insects. Performances for all models developed showed no signs of overfitting. In this paper, a field-based system using unmanned aerial vehicles with the e-nose as payload was proposed and described for deployment of ML models to aid growers in pest management practices.

Current State of Hyperspectral Remote Sensing for Early Plant Disease Detection: A Review

“…As an example of such works, one can cite the articles by Gold et al, where the mechanisms of physiological changes in potato plants were considered when inoculated by Alternaria solani and Phytophthora infestans pathogens in the analytical example of the contents of foliar nitrogen, total phenolics, sugar and starch [112,113]. Fuentes et al monitored the chemical fingerprints of different leaf samples and studied the correlation of aphid numbers in wheat plants with the presence and quantity alcohol, methane, hydrogen peroxide, aromatic compounds and amide functional groups compounds [228]. The paper [228] presented results on the implementation of SWIR HRS (1596-2396 nm) and a low-cost electronic nose (e-nose) coupled with machine learning.…”

“…Fuentes et al monitored the chemical fingerprints of different leaf samples and studied the correlation of aphid numbers in wheat plants with the presence and quantity alcohol, methane, hydrogen peroxide, aromatic compounds and amide functional groups compounds [228]. The paper [228] presented results on the implementation of SWIR HRS (1596-2396 nm) and a low-cost electronic nose (e-nose) coupled with machine learning. The authors believe that such study of plant physiology models open their use to assessing models of other biotic and abiotic stress effects on plants.…”

Computer Vision and Machine Learning Analysis of Commercial Rice Grains: A Potential Digital Approach for Consumer Perception Studies

“…The artificial neural networks (ANNs) for supervised ML are well-known for solving multiclass classifications due to their ability to deal with non-linear data for pattern recognition to obtain high accuracy. For example, the ANN models were used in previous studies to classify mulberry fruit according to the ripeness levels [27], detect beer faults using the electronic nose [35], and classify aphid infestation levels using the electronic nose and near-infrared spectroscopy [36].…”

Editorial: Special Issue “Implementation of Sensors and Artificial Intelligence for Environmental Hazards Assessment in Urban, Agriculture and Forestry Systems”

“…This special issue focused on the applications of AI to environmental systems related to hazard assessment in Urban, Agriculture and Forestry. A total of ten papers were published in this special issue, with topics ranging from reviewing the current climate-smart agriculture approaches for smart village development [ 1 ] to the integration of visible and infrared thermal cameras for automated urban green infrastructure monitoring on top of moving vehicles [ 2 ]; the implementation of machine learning to classify contaminant sources for urban water networks [ 3 ]; water network contamination assessment using machine learning in the UK [ 4 ]; future landscape changes, seismic and hazard assessment tested in Tabriz, Iran assessed using satellite remote sensing [ 5 ]; AI applied to a robotic dairy farm to assess milk productivity and quality traits using meteorological and cow data [ 6 ]; AI and computer vision from visible and infrared thermal images to obtain non-invasive biometrics from sheep to assess welfare [ 7 ]; the assessment of smoke contamination and smoke taint in wines due to bushfires using a low-cost electronic nose and AI [ 8 ]; the classification of smoke contaminated grapevine berries and leaves using chemical fingerprinting and machine learning [ 9 ]; and the detection of aphid infestation in wheat plants and insect-plant physiological interactions using low-cost electronic noses, chemical fingerprinting and machine learing [ 10 ].…”

“…Finally, low-cost electronic noses and near-infrared spectroscopy were also implemented to assess the infestation of insects in plants and the insect-plant interaction [ 10 ]. This study presented a novel way to sniff aphid infestation in wheat plants and estimate plant physiological parameters using machine learning modeling.…”