The Transferability of Spectral Grain Yield Prediction in Wheat Breeding across Years and Trial Locations.

Abstract

Grain yield (GY) prediction based on non-destructive UAV-based spectral sensing could make screening of large field trials more efficient and objective. However, the transfer of models remains challenging, and is affected by location, year-dependent weather conditions and measurement dates. Therefore, this study evaluates GY modelling across years and locations, considering the effect of measurement dates within years. Based on a previous study, we used a normalized difference red edge ( NDRE 1) index with PLS (partial least squares) regression, trained and tested with the data of individual dates and date combinations, respectively. While strong differences in model performance were observed between test datasets, i.e., different trials, as well as between measurement dates, the effect of the train datasets was comparably small. Generally, within-trials models achieved better predictions (max. R 2 = 0.27-0.81), but R 2 -values for the best across-trials models were lower only by 0.03-0.13. Within train and test datasets, measurement dates had a strong influence on model performance. While measurements during flowering and early milk ripeness were confirmed for within- and across-trials models, later dates were less useful for across-trials models. For most test sets, multi-date models revealed to improve predictions compared to individual-date models.

Plant phenotyping relevance

UAVスペクトルセンシングとPLS回帰による穀粒収量推定法の、年次・試験地間の転移性と性能を評価しており、表現型取得・推定手法の検証が中心である。

Code and data availability

The paper's UAV multispectral spectral data and grain yield phenotype measurements are not publicly deposited; the Data Availability Statement requires contacting the authors. The MDPI supplementary file contains only derived figures and descriptive tables (weather, scatterplots, model metrics, GY summary statistics),,

No evidence-backed public reproduction asset is currently recorded.