Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

A ground-based sensing system was developed for determination of nitrogen (N) status in cotton plants. The system consists of a multi-spectral optical sensor, an ultrasonic sensor, and a data-acquisition and processing unit. The optical sensor's light source provides modulated panchromatic illumination of a plant canopy with light-emitting diodes. The sensor measures plant reflectance at four spectral wavebands (400 to 500 nm, 520 to 570 nm, 610 to 710 nm, and 750 to 1100 nm). The ultrasonic sensor is used to determine plant height. The data-acquisition and processing unit is based on a single-board computer that collects data from the multi-spectral optical sensor and the ultrasonic sensor, and spatial information from a Global Positioning System receiver. Field tests of the system over two years involved measuring spectral reflectance and plant height simultaneously in real time in situ. An artificial neural network was developed to predict N status in cotton plants based on data from the sensing system. The network was trained with actual leaf N concentration data that corresponded to sensor spectral data and plant height. Results showed that the spectral information and plant height measured by the sensing system had significant correlation with leaf N concentration of the cotton plants. Trained neural networks were able to predict N status of the cotton plants at 90% accuracy when N status was divided into two categories: deficiency and non-deficiency.