Scalable growth models for time‐series multispectral images

Abstract

Abstract Vegetation indices (VIs) are produced as a combination of different reflectance bands that are captured by multispectral images (MSIs). These indices, such as normalized difference vegetation index (NDVI), are reported to be proxy indicators of photosynthetic activity, plant canopy biomass, and leaf area index. To determine the utility of using VI derived from MSI to model plant growth, random regression (RR) models with linear splines and different orders of Legendre polynomials were applied to data collected (years 2019 and 2020) as part of the Genome‐to‐Fields initiative. Growth curves of maize (Zea mays L.) hybrids were modeled using both NDVI and cumulative NDVI (cNDVI) phenotypes. Due to the difference in MSI recording dates, and sparse overlap in hybrids between years, all the analyses were nested within a year. Results indicate that RR models using Legendre polynomials provide a robust and scalable method for modeling growth curves using phenotypes extracted from MSI; however, RR models using linear splines showed inconsistent convergence. Growth curves estimated using NDVI and cNDVI showed low‐to‐moderate heritability (0.11–0.44) and a range of genetic correlations (−0.15 to 0.97) with grain yield. This study demonstrates the utility of MSI for modeling genetic growth trends, with the best modeling results obtained when using Legendre polynomials and cNDVI.