Precise Nitrogen Management of Biomass Sorghum Using Vegetation Indices.

Biomass sorghum [Sorghum bicolor (L.) Moench] is a promising feedstock for producing ethanol in Virginia. A precise N management is required to ensure farm profitability and avoid N losses to the environment. Crop sensing has shown to be a viable option to predict yield and develop sensor-based N management algorithms. Our main objectives were to determine (i) which vegetative indices (ii) which growth stage (time of sensing) and (iii) which method of reporting sensor data predict biomass sorghum yield the best under various N rates. In 2017, two upfront N rate trials were established in Virginia. Nitrogen rates applied at planting ranged from 0 kg N ha^-1 to 280 kg N ha^-1. Sensor data obtained from RGB images were aerial intensity (AI), aerial hue (AH), aerial lightness (AL), aerial a*, aerial b*, aerial u*, aerial v*, aerial green area(AGA; % pixels with 60<hue<120), and aerial greener area (AGGA; % pixels with 80<hue<120),as well as aerial crop stress index (ACSI). Ground-based and aerial normalized difference vegetation index (NDVI) data were also collected. We reported NDVI data as in-season estimated yield (INSEY) shown as (i) INSEY_DAP [NDVI divided by days after planting (DAP)], and (ii) INSEY_GDD [NDVI divided by growing degree days (GDD)], and the inverse simple ratio (ISR; [1–NDVI]/[1+NDVI]) divided by DAP (INSEY_ISR) and compared them with NDVI data. Scanning started 9 DAP and continued until 33 DAP when plants reached at 79 cm. Plants were harvested 49 DAP when average plant height was 182 cm. The best time of scanning was 33 DAP in site 1 (R² = 0.56; V9) and 26 DAP in site 2 (R² = 0.61; V7) to predict sorghum biomass yield. Relationship between NDVI and yield was stronger (R²= 0.70) for both site 1 (at V9) and site 2 (at V6) when yield was expressed as yield per plant. Detailed preliminary results of this research will be presented.