Globally, the common dry bean varieties (Phaseolus vulgaris L.) are regarded as valuable food crops. Due to diversion-farm and postharvest management requirements, quick, reliable, and cost-effective varietal discrimination is critical for optimal management during growth and after harvesting. The large number of valuable wavelengths that characterize hyperspectral remotely sensed datasets in concert with emerging robust discriminant analysis techniques offers great potential for on-farm dry bean varietal discrimination. In this study, an integrated approach of partial least-squares discriminant analysis (PLS-DA) on hyperspectral data was used to determine the bean’s optimal timing for on-farm varietal discrimination. Based on experimental plots underirrigated and rain-fed watering regimes, hyperspectral data were collected at three major phenological stages. Data at each stage were first used to generate PLS-DA models to determine variable (wavebands) importance in the projection (VIP) and the VIP bands used to generate VIP conditioned PLS-DA models. The study identified 6 weeks (branching and rapid vegetative growth) and 10 weeks (flowering and pod development) after seed sowing as optimal stages for varietal discrimination. The study offers insight into the optimal period to discriminate dry bean varieties using spectroscopy, valuable for on-farm and after-farm management and crop monitoring sensor development.
Imaging spectroscopy can provide real-time high throughput information on growing crops. The spectroscopic data can
be obtained from space-borne, air-borne and handheld sensors. Such data have been used for assessing the nutritional
status of some field crops (maize, rice, barely, potato etc.). In this study a handheld FieldSpec 3 spectroradiometer in
the 350 - 2500 nm range of the electromagnetic spectrum was evaluated for its use to estimate sugarcane leaf nitrogen
concentrations. Sugarcane leaf samples from one variety viz., N19 of two age groups (4-5 and 6-7 months) were
subjected to spectral and chemical measurements. Leaf reflectance data were collected under controlled conditions and
leaf nitrogen concentration was obtained using an automated combustion technique (Leco TruSpec N). The potential
of spectroscopic data for estimating sugarcane leaf nitrogen status was evaluated using univariate correlation and
regression analyses methods with the first-order reflectance across the spectral range from 400 to 2500 nm. The variables
that presented high correlation with nitrogen concentration were used to develop simple indices combining reflectances
of 2-wavelengths. Simple linear regression was then used to select a model that yielded the highest <i>R</i><sup>2</sup>. These were the
R<sub>744</sub> / R<sub>2142</sub> index for the 4-5 months old cane crop and the (R<sub>2200</sub> - R<sub>2025</sub>) / (R<sub>2200</sub> + R<sub>2025</sub>) index for the 6-7 months old
cane crop, with <i>R</i><sup>2</sup> of 0.74 and 0.87, respectively.