Classification of rhizosphere components using visible–near infrared spectral images

Abstract

To establish new techniques for automatic classification of rhizosphere components, we investigated the utility of visible (VIS) and near-infrared (NIR) spectral images of the rhizosphere under two soil moisture conditions (mean volumetric water content: 0.39 and 0.16 cm 3 cm −3 ). Spectral reflectance images of the belowground parts of hybrid poplar cuttings (Populus deltoides × P. euramericana, I45/ 51) grown in a rhizobox were recorded at 120 spectral bands ranging from 480 to 972 nm. We examined which wavelengths were suitable and the number of spectral bands needed to accurately classify live roots of four age classes, dead roots, leaf mold, and soil. VIS reflectance (<700 nm) of live roots first increased and then decreased with age, whereas NIR reflectance (≥700 nm) was stable in mature roots. The reflectance of dead roots was lower than that of mature roots in both the VIS and NIR spectral regions. VIS reflectance did not differ among dead roots, leaf mold, and soil, but the NIR reflectance was clearly lower in soil than in the other materials. The reflectance of leaf mold and soil increased mainly in the NIR spectral region with reducing soil moisture, but this increase did not affect the order of reflectance intensity among the rhizosphere components in general. Although the most suitable spectral bands statistically selected for classifying rhizosphere components differed somewhat between moist and dry conditions, the spectral bands 580-679 nm (VIS) and 848-894 nm (NIR) provided high reliability under both conditions. Classification accuracy was higher when using two to five VIS-NIR images (overall accuracy ≥87.8%) than three VIS images (red, green, and blue; accuracy <67.1%). The high accuracy with VIS-NIR was mainly due to successful separation of leaf mold and soil. Irrespective of soil moisture condition, the overall accuracy tended to be stable at 92-94% with use of four VIS-NIR images. The spectral bands effective in wet soil conditions could also be used for classification in dry conditions, with overall accuracies >86.9%. These results suggest that automatic image analysis using VIS-NIR images at four spectral bands, including red and NIR, allows for accurate classification of the growth stage or live/dead status of roots and distinguishes between leaf mold and soil.

Use of near-infrared reflectance spectroscopy to predict the percentage of dead versus living grass roots

“…This shows that the NIRS method can detect changes of soluble or structural compounds (e.g., carbohydrates, amino acids) of recently dead roots, as recently shown by Nakaji et al (2008). According to these authors, higher absorbance of dead roots could be ascribed by (1) changes in pigmentation in the Vis region and (2) infiltration of water into the decomposing tissue leading to greater air-space in addition to changes in chemical composition, in the Nir region.…”

“…This can be explained by between-species differences in root pigmentation; Fr having darker roots than other species, and confirms that the dark root colouring increases absorbance in the Vis region (Nakaji et al 2008). This reinforces the fact that roots of contrasting grasses exhibit different NIRS 'signatures' as stated by Roumet et al (2006), due to differential root colouration and/or chemical composition.…”

Minirhizotrons in Modern Root Studies

“…The equipment size used by Nakaji et al (2010) is not compatible with standard minirhizotron tubes, and the large hyperspectral digital camera is positioned outside a clear glass pot. In hybrid poplar cuttings, VIS-NIR (356-976 nm) spectral images allow accurate root classification (number of roots), as reflectance decreases with root ageing, regardless of soil moisture conditions.…”

Neutron radiography as a tool for revealing root development in soil: capabilities and limitations

“…It is difficult to observe tightly enmeshed roots in an opaque soil matrix without disturbance. Better understanding of root behaviour in heterogeneous soil, requires efficient non-invasive techniques to analyze root and soil structure in situ (Fitz et al 2005;Pierret et al 2005;Nakaji et al 2008;Pierret 2008).…”