Detecting the attack of the fall armyworm (Spodoptera frugiperda) in cotton plants with machine learning and spectral measurements

• Published in: Precision agriculture 2022-04, Vol.23 (2), p.470-491
• Main Authors: Ramos, Ana Paula Marques, Gomes, Felipe David Georges, Pinheiro, Mayara Maezano Faita, Furuya, Danielle Elis Garcia, Gonçalvez, Wesley Nunes, Junior, José Marcato, Michereff, Mirian Fernandes Furtado, Blassioli-Moraes, Maria Carolina, Borges, Miguel, Alaumann, Raúl Alberto, Liesenberg, Veraldo, de Castro Jorge, Lúcio André, Osco, Lucas Prado
• Format: Article
• Language: English
• Subjects: Agriculture; Algorithms; Atmospheric Sciences; Biomedical and Life Sciences; Chemistry and Earth Sciences; Computer Science; Cotton; Cultivars; Damage detection; Inspection; Landsat; Learning algorithms; Life Sciences; Machine learning; Physics; Remote sensing; Remote Sensing/Photogrammetry; Self organizing maps; Sensors; Short wave radiation; Soil Science & Conservation; Spectra; Spectral sensitivity; Spectroradiometers; Spodoptera frugiperda; Statistics for Engineering; Wavelengths
• ISSN: 1385-2256; 1573-1618
• DOI: 10.1007/s11119-021-09845-4

The Spodoptera frugiperda (i.e., fall armyworm) causes irreversible damage in cotton cultivars, and its visual inspection on plants is a burdensome task for humans. A recent strategy to automatically do similar tasks is processing hyperspectral reflectance measurements with machine learning algorithms. Herein, its proposed a framework for modeling the spectral response of cotton plants under the fall armyworm attacks using machine learning algorithms, culminating in a theoretical model creation based on the band simulation process. A controlled experiment was conducted to collect hyperspectral radiance measurements from health and damage cotton plants over eight days. A hand-held spectroradiometer operating from 350 to 2500 nm was used. Several algorithms were evaluated, and a ranking approach was adopted to identify the most contributive wavelengths for detecting the damage. The Self-Organizing Map method was applied to organize the spectral wavelengths into groups, favoring the theoretical model creation for two sensors: OLI (Landsat-8) and MSI (Sentinel-2). It was found that the Random Forest algorithm produced the most suitable model, and the last day of analysis was better to separate healthy and damaged plants (F-measure: 0.912). The best spectral regions range from the red to near-infrared (650 to 1350 nm) and the shortwave infrared (1570 to 1640 nm). The theoretical model returned accurate results using both sensors (OLI, F-Measure = 0.865, and MSI, F-Measure = 0.886). In conclusion, the proposed framework contributes to accurately identifying cotton plants under the Spodoptera frugiperda attack for both hyperspectral and multispectral scales.