Assessing maize foliar water stress levels under field conditions using in-situ spectroscopy

Abstract

Plant physiological processes required for crop productivity are dependent on the availability of water to crops. Water availability to crops therefore requires real time monitoring for timeous rescue or intervention measures. Such monitoring over vast areas is only possible through remotely sensed techniques such as spectroscopy with its numerous fine wavelengths and is non-destructive to the crops as opposed to other traditional ground-based methods. The management of spectral reflectance data to extract information of importance for plant water status has been motivated by knowledge of the availability of specific bands in the electromagnetic spectrum responsible for water absorption. The purpose of this study was to investigate the potential of using selected spectral bands to develop water indices that could monitor the water status at leaf level on maize (Zea mays) plants grown under field conditions. Leaf spectral reflectance of maize plants was collected under three different water conditions being healthy (H), intermediary water stressed (IWS) and water stressed (WS) using a leaf-clip of a handheld spectroradiometer. The spectral reflectance indicated an increased reflectance in portions of the visible,  near-infrared and short infrared regions of the electromagnetic spectrum for the water stressed maize plants. The random forest (RF) algorithm was utilised to  extract wavelengths of importance from which water indices were developed among which were the normalised difference water index (NDWI860-1240) and the water band index (WBI950-970). The indices were used in a combined algorithm of RF and partial least square (PLS) for its predictive ability to classify the maize leaf water  status into the three categories (H, IWS and WS). The results showed an overall accuracy of 70±1.2 %. Therefore, confirming the potential of assessing leaf water content using in-situ spectroscopy. The three most important indices were  NDWI_860-1240, NDWI_860-1240 and NDWI_860-1240. An in-depth study would be required to quantify and measure actual water content in maize leaves and possibly upscale to canopy level which would directly support irrigation management plans.

Keywords: in-situ spectroscopy, maize, partial least square, random forest, water spectral indices, water stress