Soil moisture sensor for predicting seed planting depth

A near-infrared (NIR) sensor was built to predict corn seed planting depth based on moisture content and matric potential. The sensor uses three NIR wavelengths and a maximum likelihood classifier to predict a “plant deeper” or “plant at current depth” judgment. The sensor was trained on 29 different soils that varied in soil texture and organic matter content and was able to predict the –10, –30, –50 kPa potentials from the –100 and –1500 kPa potentials with 82% accuracy. The system was tested in the field on a silt loam soil and predicted a “plant at current depth” for moisture contents above 19.44% and a “plant deeper” for moisture contents below 19.44% with 82% accuracy. The moisture contents for the field test ranged from 7 to 32%.