Enhancing Pigment Phenotyping and Classification in Lettuce through the Integration of Reflectance Spectroscopy and AI Algorithms

Abstract

In this study, we investigated the use of artificial intelligence algorithms (AIAs) in combination with VIS-NIR-SWIR hyperspectroscopy for the classification of eleven lettuce plant varieties. For this purpose, a spectroradiometer was utilized to collect hyperspectral data in the VIS-NIR-SWIR range, and 17 AIAs were applied to classify lettuce plants. The results showed that the highest accuracy and precision were achieved using the full hyperspectral curves or the specific spectral ranges of 400–700 nm, 700–1300 nm, and 1300–2400 nm. Four models, AdB, CN2, G-Boo, and NN, demonstrated exceptional R2 and ROC values, exceeding 0.99, when compared between all models and confirming the hypothesis and highlighting the potential of AIAs and hyperspectral fingerprints for efficient, precise classification and pigment phenotyping in agriculture. The findings of this study have important implications for the development of efficient methods for phenotyping and classification in agriculture and the potential of AIAs in combination with hyperspectral technology. To advance our understanding of the capabilities of hyperspectroscopy and AIs in precision agriculture and contribute to the development of more effective and sustainable agriculture practices, further research is needed to explore the full potential of these technologies in different crop species and environments.

Reflectance Spectroscopy for the Classification and Prediction of Pigments in Agronomic Crops

“…The absorbance curve of pigments in vitro was analyzed between 350 and 1100 nm using a Shimadzu UV–3600 Plus UV–VIS–NIR spectrophotometer (Shimadzu Inc., Tokyo, Japan). The quantification of pigment profiles was performed and expressed in terms of area and mass, as detailed in [ 14 , 26 ].…”

“…This technology leverages the unique spectral “fingerprints” of different plant species and conditions, thereby facilitating applications such as plant classification, growth assessments, and the monitoring of plant health and leaf structure–water characteristics. Such techniques have proven their efficacy in classifying diverse plant varieties, a factor that contributes significantly to improved horticulture crop yields [ 13 , 14 ]. With the ability to accurately identify and monitor specific plant varieties through their unique spectral signatures, farmers can implement more efficient practices, taking corrective action when spectral data suggest impending issues.…”

“…The application of remote sensing 5.0 techniques has seen an increase in efforts to estimate the use of machine learning, data mining, and deep learning to classify crops such as corn and soybean [ 23 ], wheat [ 6 ], coffee [ 24 ], and lettuce [ 14 ]. The use of UV–VIS–NIR–SWIR hyperspectral imaging is expected to be highly valuable [ 8 , 25 ].…”

Prediction of leaf nitrogen in sugarcane (Saccharum spp.) by Vis-NIR-SWIR spectroradiometry

“…This happened because the pigments present in the chloroplasts absorb the greatest part of light in the range of green, especially in the wavelengths above 530 nm [ 48 ]. Chlorophyll, in this case, participates in the interaction between the electromagnetic radiation and the internal components of the leaf, mainly influencing radiation absorption [ 48 , 49 ]. Therefore, leaves with high N content present a higher absorbance level.…”

Real-Time AI-Assisted Push-Broom Hyperspectral System for Precision Agriculture

“…This characteristic allows for a more comprehensive analysis of the optical reflectance spectrum, enabling the precise identification and characterization of various materials, including plants and their health indicators [ 4 , 5 , 6 ]. This innovative approach to remote sensing, when coupled with the power of artificial intelligence (AI), holds great promise for enhancing our ability to monitor and manage crops with unprecedented detail and accuracy [ 7 , 8 , 9 , 10 , 11 ].…”