Cumulative temporal vegetation indices from unoccupied aerial systems allow maize (Zea mays L.) hybrid yield to be estimated across environments with fewer flights

Abstract

Unoccupied aerial systems (UAS) based high throughput phenotyping studies require further investigation to combine different environments and planting times into one model. Here 100 elite breeding hybrids of maize (Zea mays L.) were evaluated in two environment trials–one with optimal planting and irrigation (IHOT), and one dryland with delayed planting (DHOT). RGB (Red-Green-Blue) based canopy height measurement (CHM) and vegetation indices (VIs) were estimated from a UAS platform. Time series and cumulative VIs, by both summation (ΣVI-SUMs) and area under the curve (ΣVI-AUCs), were fit via machine learning regression modeling (random forest, linear, ridge, lasso, elastic net regressions) to estimate grain yield. VIs were more valuable predictors of yield to combine different environments than CHM. Time series VIs and CHM produced high accuracies (~68–72%), but inconsistent models. A little sacrifice in accuracy (~60–65%) produced consistent models using ΣVI-SUMs and CHM during pre-reproductive vegetative growth. Absence of VIs produced poorer accuracies (by about ~5–10%). Normalized difference type VIs produced maximum accuracies, and flowering times were the best times for UAS data acquisition. This study suggests that the best yielding varieties can be accurately predicted in new environments at or before flowering when combining multiple temporal flights and predictors.

Corn Grain Yield Prediction Using UAV-Based High Spatiotemporal Resolution Imagery, Machine Learning, and Spatial Cross-Validation

“…They found that the RF model performed the best for yield prediction, and that the ML models generally performed better than the stepwise regression model. Chatterjee et al [87] used temporally accumulated VIs as features fed into ML models and found that normalized difference type VIs produced the best model performance and that the flowering growth stage was the best time to acquire imagery. Some yield prediction works explored the prediction power of different types and combinations of features.…”

Deciphering temporal growth patterns in maize: integrative modeling of phenotype dynamics and underlying genomic variations

“…So far, several attempts have been successfully applied for using temporal phenotype (e.g. temporal plant height and NDVI) in maize (Han et al ., 2019; Wang et al ., 2019, 2021; Anderson et al ., 2020; Tirado et al ., 2020; Adak et al ., 2021b, 2023b; Oehme et al ., 2022; Rodene et al ., 2022; Chatterjee et al ., 2023), sorghum (Miao et al ., 2020), cotton (Pauli et al ., 2016), and rice (Sun et al ., 2022). However, several important limitations exist when examining temporal phenotypes and incorporating these into QTL or genomic association mapping.…”

Field-based high-throughput phenotyping enhances phenomic and genomic predictions for grain yield and plant height across years in maize

“…Other VIs like the normalized green red difference index have been associated with water use efficiency ( Yang et al . 2020 ) and also are recognized as an important predictor of GY in maize ( Chatterjee et al . 2023 ).…”