Semi-Supervised Clustering and Radiative Transfer Modeling (Prospect) for Estimating Alterations of Primary Plant Traits in Broomrape-Infected Carrots

Abstract

In this study, we explore spectral heterogeneity within plant canopies, a characteristic often observed in stressed plants where certain leaves or intra-leaf regions exhibit stress symptoms while others remain unaffected. Such variability in spectral signatures holds promise for enhancing remote sensing methodologies aimed at plant stress detection. Typically, remote sensing techniques analyze the plant as a whole, potentially overlooking stress-related spectral signatures due to the inclusion of unaffected pixels. We devised a semi-supervised clustering-based technique to differentiate spectral patterns associated with and unique to pixels from broomrape-infected (Orobanche spp. and Phelipanche spp.) carrots from unrelated patterns. Ground-based hyperspectral (400 nm - 1000 nm) images of broomrape-infected and non-infected carrot canopies were used in an agglomerative clustering procedure followed by spectral angle mapper (SAM) analysis to identify a spectral endmember indicative of broomrape infection symptoms. Pixels from this cluster constituted an average of 8.5% and 11.5% of P. aegyptiaca and O. crenata infected plants, respectively. Subsequently, we: (a) examined the relationship between carrot leaf mineral content and the percentage of symptomatic pixels to explore stress-induced alterations creating the unique spectral signatures of infected plants; and (b) utilized the backward mode of PROSPECT, a radiative transfer model (RTM), to derive primary plant traits from the distinct spectral data of each cluster. We found that deficits in two macro elements, phosphorous and potassium, along with two pigments, chlorophyll and carotenoid, were correlated with the symptomatic cluster in infected plants. The methodology presented in this study paves the way for further research into broomrape detection in various crop species, as well as other plant stressors.

Keywords: Hyperspectral, semi-supervised clustering, radiative transfer modeling, broomrape, stress detection, site specific weed management