Association of Agrometeorologists

Determination of nitrogen and water stress with hyper spectral reflectance on maize using classification tree (CT) analysis

K. RAMACHANDIRAN and S. PAZHANIVELAN

Field experiments were conducted at the Tamil Nadu Agricultural University, Coimbatore, Tamilnadu, India during rabi (winter) season of 2013-14 with maize crop (TNAU maize hybrid Co 6). To ensure the stressed environment, the crop was subjected to two irrigation levels (IW/CPE: 0.80 and 0.50) and five staggered nitrogen levels (0, 50, 75, 100 and 125 % of recommended dose of nitrogen (RDN). The experiment was laid out in factorial randomized blocks design RBD (Factorial) with three replications. Hyper spectral observations were made with spectroradiometer GER 1500 at 60 and 90 days after sowing (DAS). Measured spectral reflectance curve of maize exhibited a broad low intensity peak centered in the green region at 550 nm and a sharp rise starting at about 675 nm to a plateau in the vicinity of 762 nm under unstressed environment created with irrigation at 0.80 IW/CPE ratio and fertilizer application at 100 % RDN. Significant differences in reflectance were established for nitrogen and water stress at green and NIR region. The results of Classification tree analysis revealed that nitrogen and water stress can be assessed and differentiated using reflectance data when transformed into spectral vegetation indices viz., NDVI, GNDVI, RVI, LCI, IR-RED and SR. Further the Classification tree algorithm could determine that NDVI was the most effective index to assess the combined effect of nitrogen and water stress in maize crop.

Classification tree, spectral vegetation indices, nitrogen and water stress, maize