Reproductive stage superiority in irrigation scheduling: UAV spectral mechanisms validated by field canopy architecture for soybean yield prediction

Abstract

Improving crop yield prediction accuracy is crucial for precision agriculture, particularly for irrigation management. Unmanned aerial vehicle (UAV)-based multispectral imaging has become a key tool for crop phenotyping due to its high spatiotemporal resolution and cost-effectiveness. In this study, field experiments were conducted in northwestern China over two consecutive growing seasons (2021–2022), incorporating different mulching practices and supplemental irrigation treatments, to systematically analyze the sensitivity of soybean seed yield to various physiological and growth indices measured at different phenological stages. The results indicated that the full pod stage (R4) was the most sensitive window for yield prediction. At this stage, canopy cover (CC) and chlorophyll content reached their peak values. Most vegetation indices (VIs), texture features (TFs), and texture indices (TIs) extracted from the UAV imagery showed significant correlations (P < 0.05) with final seed yield. Among these, the ratio texture index (RTI, defined as DIS1/HOM3) exhibited the strongest correlation with yield (R = 0.69). A three-source data fusion framework combining VIs, TFs, and TIs was constructed, and an extreme gradient boosting (XGBoost) algorithm was applied to optimize feature weighting. This integrated model achieved optimal performance at the R4 stage, with coefficient of determination R² = 0.83 on the validation set, root mean square error (RMSE) = 280.80 kg ha⁻¹ , and mean relative error (MRE) = 6.32 %. Compared to a model based solely on spectral VIs (R² = 0.63), the multi-source XGBoost model improved R² by 31.7 % and reduced the error metrics (RMSE) by up to 17.5 %. These findings provides a theoretical basis for precise field management in arid areas and a technical framework for remote sensing monitoring of crop yield.

Plant phenotyping relevance

UAVマルチスペクトル画像からキャノピー形態・生理指標を抽出し、特徴量融合とXGBoostで大豆収量を推定する手法が中心であり、検証性能も報告している。

Code and data availability

公開状態または取得可能な本文経路を確認できませんでした。

No evidence-backed public reproduction asset is currently recorded.