VIS-NIR-SWIR Hyperspectroscopy Combined with Data Mining and Machine Learning for Classification of Predicted Chemometrics of Green Lettuce

VIS-NIR-SWIR hyperspectroscopy is a significant technique used in remote sensing for classification of prediction-based chemometrics and machine learning. Chemometrics, together with biophysical biochemical parameters, laborious technique; however, researchers are very interested this field because the benefits terms optimizing crop yields. In study, we investigated hypothesis that could be efficiently applied prediction leaf thickness pigment profiling green lettuce reflectance, transmittance, absorbance data according to variety. For purpose, spectroradiometer visible, near-infrared, shortwave ranges (VIS-NIR-SWIR). The results showed many chemometric parameters fingerprints 400–2500 nm spectral curve range. Therefore, technique, combined rapid mining, learning algorithms, other multivariate statistical analyses such as PCA, MCR, LDA, SVM, KNN, PLSR, can tool classify plants highest accuracy precision. hyperspectral indicated presence functional groups associated components lettuce, allowing correctly classified higher (99 100%). Biophysical predicted using PLSR models, which R2P RMSEP values greater than >0.991 6.21, respectively, relationship between reflectance or transmittance spectroscopy curves. Thus, report methodology confirm ability simultaneously predict high precision, at low cost acquisition, based on tool, enable successful management crops precision agriculture systems.