Changes in spatial and temporal variability in yield estimation are detectable through plant biophysical characteristics observed at different phenological development stages of corn. A multispectral red-edge sensor mounted on an Unmanned Aerial Systems (UAS) can provide spatial and temporal information with high resolution. Spectral analysis of UAS acquired spatiotemporal images can be used to develop a statistical model to predict yield based on different phenological stages. Identifying critical vegetation indices (VIs) and significant spectral information could lead to increased yield prediction accuracy. The objective of this study was to develop a yield prediction model at specific phenological stages using spectral data obtained from a corn field. The available spectral bands (red, blue, green, near infrared (NIR), and red-edge) were used to analyze 26 different VIs. The spectral information was collected from a cornfield at Mississippi State University using a MicaSense multispectral red-edge sensor, mounted on a UAS. In this research, a new empirical method used to reduce the effects of bare soil pixels in acquired images was introduced. The experimental design was a randomized complete block that consisted of 16 blocks with 12 rows of corn planted in each block. Four treatments of nitrogen (N) including 0, 90, 180, and 270 kg/ha were applied randomly. Random forest was utilized as a feature selection method to choose the best combination of variables for different stages. Multiple linear regression and gradient boosting decision trees were used to develop yield prediction models for each specific phenological stage by utilizing the most effective variables at each stage. At the V3 (3 leaves with visible leaf collar) and V4-5 (4-5 leaves with visible leaf collar) stages, the Optimized Soil Adjusted Vegetation Index (OSAVI) and Simplified Canopy Chlorophyll Content Index (SCCCI) were the single dominant variables in the yield predicting models, respectively. A combination of the Green Atmospherically Resistant Index (GARI), Normalized Difference Red-Edge (NDRE), and green Normalized Difference Vegetation Index (GNDVI) at V6-7, SCCCI, and Soil-Adjusted Vegetation Index (SAVI) at V10,11, and SCCCI, Green Leaf Index (GLI), and Visible Atmospherically Resistant Index (VARI_green) at tasseling stage (VT) were the best indices for predicting grain yield of corn. The prediction models at V10 and VT had the greatest accuracy with a coefficient of determination of 0.90 and 0.93, respectively. Moreover, the SCCCI as a combined index seemed to be the most proper index for predicting yield at most of the phenological stages. As corn development progressed, the models predicted final grain yield more accurately.

Applying the optimum rate of fertilizer nitrogen (N) is a critical factor for field management. Multispectral information collected by active canopy sensors can potentially indicate the leaf N status and aid in predicting grain yield. Crop Circle multispectral data were acquired with the purpose of measuring the reflectance data to calculate vegetation indices (VIs) at different growth stages. Applying the optimum rate of fertilizer N can have a considerable impact on grain yield and profitability. The objectives of this study were to evaluate the reliability of a handheld Crop Circle ACS-430, to estimate corn leaf N concentration and predict grain yield of corn using machine learning (ML) models. The analysis was conducted using four ML models to identify the best prediction model for measurements acquired with a Crop Circle ACS-430 field sensor at three growth stages. Four fertilizer N levels from deficient to excessive in 50/50 spilt were applied to corn at 1–2 leaves, with visible leaf collars (V1–V2 stage) and at the V6–V7 stage to establish widely varying N nutritional status. Crop Circle spectral observations were used to derive 25 VIs for different growth stages (V4, V6, and VT) of corn at the W. B. Andrews Agricultural Systems farm of Mississippi State University. Multispectral raw data, along with Vis, were used to quantify leaf N status and predict the yield of corn. In addition, the accuracy of wavelength-based and VI-based models were compared to examine the best model inputs. Due to limited observed data, the stratification approach was used to split data to train and test set to obtain balanced data for each stage. Repeated cross validation (RCV) was then used to train the models. Results showed that the Simplified Canopy Chlorophyll Content Index (SCCCI) and Red-edge ratio vegetation index (RERVI) were the most effective VIs for estimating leaf N% and that SCCCI, Red-edge chlorophyll index (CIRE), RERVI, Soil Adjusted Vegetation Index (SAVI), and Normalized Difference Vegetation Index (NDVI) were the most effective VIs for predicting corn grain yield. Additionally, among the four ML models utilized in this research, support vector regression (SVR) achieved the most accurate results for estimating leaf N concentration using either spectral bands or VIs as the model inputs.

The varying influence of the environment on N supply and demand dictates the need for annually updated fertilizer N recommendations. Currently, crop yield goal (CYG) methods are used by 34 land grant universities, including Mississippi State University, these do not consider environmental variations. This research tested the efficacy of CYG by determining the agronomic optimum N rate (AONR) and the economic optimum N rate for Mississippi corn (Zea mays L.) production. In total, 12 treatments in 2020 and 11 in 2021 were replicated four times over four locations in a randomized complete block design. The optimum N rates were calculated by fitting linear, quadratic, linear plateau, and quadratic plateau models by means of three different goodness of fit measures. Furthermore, differences between the CYG rate calculated from the Mississippi yield goal equation and AONR were compared at different management levels (14 comparisons) (all data combined, both years combined, sites combined by year, and individual sites). Overall, AONR varied from 134 to 301 kg N ha^–1 at different management levels_. When we compared the AONR to the CYG rate, the CYG rate over‐recommended N in 12 of the 14 possible comparisons, with differences ranging from 69 kg N ha^–1 less to 110 kg N ha^–1 greater than the AONR. These differences between AONR values highlight variability caused by factors such as the soil, environment, and their interaction with N supply and demand, which are unaccounted for by the CYG method.

Constant‐rate blanket applications of fertilizer N can result in both an over and under supply relative to crop utilization on a field‐by‐field basis. Variable‐rate (VR) applications tailored to better meet crop demand can improve N use efficiency on spatially variable soils. The objectives of this study were to compare the response in corn (Zea mays L.) canopy reflectance derived vegetation indices (VI) to varying fertilizer N rates and to determine relationships between resulting VIs acquired using two different sensing platforms. Four fertilizer N rates in 50/50 split at V1–2 and V6–7 leaf stages were applied, from deficient to excessive, to create varying corn nutritional N status. Sensing and biophysical sampling were performed throughout the season for analysis and comparison to calculated VIs. Grain yield plateaued around 135±10 kg N ha^–1 across the study. Furthermore, strong relationships between VIs and fertilizer N rates were found, with the strongest using combined indices that incorporate the red‐edge wavelength (720 nm). Relationships strengthened at later growth stages. The response models were found to be sensor specific, VI specific, and mostly non‐transferable between sensors. Results from this study demonstrate the utility of using remote sensing technologies to predict corn N status more accurately for eventual use in VR prescription development.

Associative nitrogen (N₂)‐fixation (ANF) by bacteria in the root‐zone of perennial bioenergy grasses has the potential to replace or supplement N fertilizer and support sustainable production of biomass, but its application in marginal ecosystems requires further evaluation. In this study, we first combined both greenhouse and field experiments, to explore the N₂ fixation effects of three temperate feedstocks Miscanthus × giganteus (giant miscanthus, Freedom), Panicum virgatum (switchgrass, Alamo), and Saccharum sp. (energycane, Ho 02‐147). In field studies across three growing seasons, plant and soil pools of candidate feedstocks were partially composed of N derived from the atmosphere (Ndfa). Energycane, giant miscanthus, and switchgrass were estimated to derive >30%, %Ndfa. Greenhouse studies were also performed to trace isotopically labeled ¹⁵N₂ into plant biomass and soil pools. Evidence for Ndfa was detected in all three feedstock grasses (using reference ¹⁵N of soil, chicory, and sorghum, δ¹⁵N~+7.0). Isotopically labeled ¹⁵N₂ was traced into biomass (during grass elongation stage) and soil pools. Extrapolation of rates during the 24 hr labeling period to 50 days estimated 30%–55% of plant Ndfa, with the greatest Ndfa for energycane. The findings of the field natural abundance and greenhouse ¹⁵N₂ feeding experiments provided complementary evidence that perennial bioenergy grasses have the potential to support relatively high rates of ANF, and accumulate diazotroph‐derived N into biomass when grown on non‐fertilized soil.