Proximal Sensing to Estimate Yield of Brown Midrib Forage Sorghum

Abstract

Forage sorghum has potential as alternative to corn silage in rotation with winter cereals. Crop sensing is a promising approach for predicting end‐of‐season yields. Yield prediction is the first step in development of algorithms for sensor‐based N management. To develop reliable algorithms for fertility management of forage sorghum in double crop rotations that account for timing, height of scanning and sensor orientation. To evaluate which method of reporting of sensor measurements (NDVI, INSEYGDD, or INSEYDAP) gives the better prediction of yield. Increasing home‐grown forage production is important for the dairy industry. Double cropping of forage crops like corn (Zea mays L.) silage with cereal rye (Secale cereale L.) or triticale (× Triticosecale spp.) can increase full‐season yield but could impact the length of the growing season for corn silage. Brown midrib (BMR) brachytic dwarf forage sorghum (Sorghum bicolor L.) has great potential as an alternative to corn silage in double crop rotations. Both winter cereals and forage sorghum require N management. Crop sensing is a promising approach for predicting end‐of‐season yields, the first step in development of algorithms for sensor‐based N management. Here we evaluated the impact of timing, sensor orientation and height of scanning, and the use of normalized difference vegetation index (NDVI) data vs. in‐season estimated yield (INSEY) on the ability of sensor data to predict yield of forage sorghum. Four trials with N rates ranging from 0 to 224 or 280 kg of N ha−1 at planting (site‐specific) were implemented in four replications in 2014–2015. Scanning took place from 19 to 69 d after planting (DAP). Yield was measured at soft dough (111–124 DAP). Sensor height and orientation impacted the NDVI prior to 45 DAP but not once the canopy was fully developed. Most accurate yield predictions were obtained 49 DAP when the sorghum was 0.76 m tall. The INSEY expressed as plant growth per day (INSEYDAP) best correlated with yield. We conclude that crop sensors can be used to accurately predict forage sorghum yields.