UAV-based aerial phenotyping to assess key morphophysiological traits and yield in soybean

Abstract

• A UAV-based novel phenotyping pipeline using multispectral imaging and LASSO regression accurately predicts soybean traits and yield across growth stages by selecting key vegetation indices. • Red-edge and NIR indices best predict plant height, stomatal conductance, and yield. • Chlorophyll-related indices were effective for estimating LAI and leaf chlorophyll. • Best aerial phenotyping time is between pod development and the full seed stage. Morphophysiological parameters, such as plant height, leaf chlorophyll content, stomatal conductance, and leaf area index, are key indicators of soybean ( Glycine max (L.) Merril) yield potential. Traditional in situ methods for assessing these traits, while accurate in small areas, are slow, labor-intensive, and impractical for large-scale monitoring. Similarly, extrapolating yield from manual counts of plant stands, pods, and seeds per pod may provide unreliable results. Therefore, high throughput sensor-based approaches are becoming increasingly popular to efficiently quantify these traits and predict yield. Among various remote sensing sensors, multispectral provides information in the red, green, red-edge, and near-infrared bands, which are critical for studying plant growth and vegetation health by combining multiple spectral bands. While many studies have used vegetation indices (VIs) to estimate individual traits, fewer have predicted multiple traits and yield at the same time using multispectral data. Thus, a study was conducted to identify the most effective VIs and determine the optimal timing for aerial phenotyping using multispectral sensors and LASSO regression. The study suggested Red-edge and NIR-based indices were best for predicting plant height, stomatal conductance, and yield, while chlorophyll-related indices were more effective for LAI and chlorophyll content. The pod development to full seed stages was the best time for aerial phenotyping. Overall, UAV-derived MS images combined with LASSO regression proved to be a practical and efficient approach for large-scale soybean phenotyping and yield monitoring. This study supports precision agriculture by providing a remote sensing-based, rapid, and non-destructive method for assessing crop status.

Plant phenotyping relevance

UAVマルチスペクトル画像とLASSO回帰による複数の植物形質・収量の推定手法を開発・評価しており、フェノタイピング手法が研究の中心である。

Code and data availability

公開論文であることは確認できましたが、現在の公式API・許可済み取得経路では本文を自動取得できませんでした。

No evidence-backed public reproduction asset is currently recorded.