Detecting biophysical characteristics and nitrogen status of finger millet at hyperspectral and multispectral resolutions

Authors: BAATH, GURJINDER - Oklahoma State University; Flynn, Kyle; Gowda, Prasanna; KAKANI, VIJAYA - Oklahoma State University; Northup, Brian

Submitted to: Frontiers in Agronomy
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 12/22/2020
Publication Date: 1/20/2021
Citation: Baath, G.S., Flynn, K.C., Gowda, P.H., Kakani, V.G., Northup, B.K. 2021. Detecting biophysical characteristics and nitrogen status of finger millet at hyperspectral and multispectral resolutions. Frontiers in Agronomy. 2. Article 604598. https://doi.org/10.3389/fagro.2020.604598.
DOI: https://doi.org/10.3389/fagro.2020.604598

Interpretive Summary: Finger millet (Eluesine coracana Gaertn L.) is an important grain crop for small farmers in many countries. Reliable estimates of crop parameters through remote sensing techniques can improve in-season management of finger millet. This study investigated the relationships of reflectance values of finger millet to various physical characteristics of finger millet using a relatively new partial least square regression (PLSR) method. Moreover, 13 vegetation indices (VIs) computed from the reflectance data as well as synthesized satellite data were evaluated and compared for estimating various physical characteristics with simple linear regression (SLR) and multilinear regression (MLR) models. VIs computed from synthesized satellite data resulted in similar or greater prediction accuracy than reflectance data alone with the new PLSR for various physical characteristics of finger millet, indicating publicly accessible satellite data could serve as a crop management decision tool for finger millet production.

Technical Abstract: Finger millet (Eluesine coracana Gaertn L.) is an important grain crop for small farmers in many countries. Reliable estimates of crop parameters through remote sensing techniques can improve in-season management of finger millet. This study investigated the relationships of hyperspectral reflectance with canopy height, green canopy cover, leaf area index (LAI), and nitrogen (N) concentrations of finger millet using an optimal waveband selection procedure in partial least square regression (PLSR). Predictive performance of 13 vegetation indices (VIs) computed from the original hyperspectral data as well as synthesized Landsat-8 and Sentinel-2 data were evaluated and compared for estimating various crop parameters with simple linear regression (SLR) and multilinear regression (MLR) models. The optimal wavebands determined by PLSR were mostly concentrated within 1000-1100 nm for both LAI and dry biomass, but were scattered for other canopy parameters. The SLR statistics showed the simple ratio pigment index (SRPI) and red/green index (RGI) performed best at predicting LAI and canopy cover. The blue/green index (BGI1) was strongly related to canopy height, dry biomass, and N concentration of finger millet, regardless of spectral resolutions. The MLR approach, using four maximum VIs as input variables, improved the prediction accuracy of canopy height and N concentration compared to SLR and waveband selection methods. VIs computed from synthesized Landsat-8 and Sentinel-2 satellite data resulted in similar or greater prediction accuracy than hyperspectral data for various canopy parameters of finger millet, indicating publicly accessible multispectral data could serve as alternative to hyperspectral data for improved crop management decisions via precision agriculture.