Estimating Plant Traits of Grasslands from UAV-Acquired Hyperspectral Images: A Comparison of Statistical Approaches

Abstract

Grassland ecosystems cover around 40% of the entire Earth's surface. Therefore, it is necessary to guarantee good grassland management at field scale in order to improve its conservation and to achieve optimal growth. This study identified the most appropriate statistical strategy, between partial least squares regression (PLSR) and narrow vegetation indices, for estimating the structural and biochemical grassland traits from UAV-acquired hyperspectral images. Moreover, the influence of fertilizers on plant traits for grasslands was analyzed. Hyperspectral data were collected from an experimental field at the farm Haus Riswick, near Kleve in Germany, for two different flight campaigns in May and October. The collected image blocks were geometrically and radiometrically corrected for surface reflectance. Spectral signatures extracted for the plots were adopted to derive grassland traits by computing PLSR and the following narrow vegetation indices: the MERIS Terrestrial Chlorophyll Index (MTCI), the ratio of the Modified Chlorophyll Absorption in Reflectance and Optimized Soil-Adjusted Vegetation Index (MCARI/OSAVI) modified by Wu, the Rededge Chlorophyll Index (CIred-edge), and the Normalized Difference Red Edge (NDRE). PLSR showed promising results for estimating grassland structural traits and gave less satisfying outcomes for the selected chemical traits (crude ash, crude fiber, crude protein, Na, K, metabolic energy). Established relations are not influenced by the type and the amount of fertilization, while they are affected by the grassland health status. PLSR is found to be the best strategy, among the approaches analyzed in this paper, for exploring structural and biochemical features of grasslands. Using UAV-based hyperspectral sensing allows for the highly detailed assessment of grassland experimental plots.

Field Scanalyzer: An automated robotic field phenotyping platform for detailed crop monitoring

“…Statistical methods are most commonly used and are based on univariate and multivariate regression models (Capolupo et al 2015). Although both regression models aim to predict crop performance traits, the univariate approach only uses a limited set of SRI (Gonzalez-Dugo et al 2015), whereas the multivariate approach utilises the entire spectrum to model plant response (Kipp et al 2014).…”

Identifying Urine Patches on Intensively Managed Grassland Using Aerial Imagery Captured From Remotely Piloted Aircraft Systems

“…In agricultural studies, practices that make use of remote sensing technologies have been widely developed to map a variety of spatial factors such as crop production estimation (Jensen et al, 2007;Hunt et al, 2010), grass nutrient content (Capolupo et al, 2015;Pullanagari et al, 2016), weed distribution (Jensen et al, 2003), soil spatial variability mapping (Stoorvogel et al, 2015), and diseased or damaged crops (Mirik et al, 2006). Remotely Piloted Aircraft Systems (RPAS) can fly at low altitude allowing acquisition of high spatial resolution imagery to observe small individual objects, such as grass patches, and can be deployed even in cloudy conditions for which the acquisition of satellite imagery or helicopter videography become difficult.…”

“…The challenge of automating patch-detection presents complex difficulties, such as the light variability effect on similar reflectance properties, the requirement of a high-resolution image, the identification and removal of unwanted plants and object reflectance interfering with the detection. Recently, numerous approaches have been developed to perform feature or land-cover detection on images from satellite imagery (Sammouda et al, 2014), phenology cameras (Filippa et al, 2016), microscopic or X-ray imagery, and remote sensing imagery from RPAS (Hunt et al, 2010;Mulla, 2012;Capolupo et al, 2015). For high resolution remotely sensed imagery (where image pixels are much smaller than the objects to be identified), an object based image analysis (OBIA) technique is more appropriate to use compared to a pixel based approach (Blaschke, 2010).…”

Evaluation of Different Irrigation Methods for an Apple Orchard Using an Aerial Imaging System

“…Figure 3 shows the UAV with its components and Figure 4 shows the UAV over the experimental orchard. The system used in this study is similar to others that have conducted research using multi-rotor UAVs [10][11][12]. …”