Estimation of soybean phenotypic parameters across growth stages using UAV-based multi-source feature fusion and XGBoost

Abstract

While essential for precision agriculture, the accurate and dynamic monitoring of crop phenotypic parameters faces challenges, including the constraints of single-data sources and insufficient model generalization across growth stages. This research introduced an integrated framework that leverages multi-source data fusion and the XGBoost algorithm to estimate key soybean parameters, including Leaf Area Index (LAI) and Above-Ground Biomass (AGB). Field experiments incorporated different irrigation methods (drip/micro-sprinkler) and planting densities (210,000/270,000 plants ha −1 ), multispectral images and corresponding ground truth data were acquired across five critical growth stages.We extracted 11 vegetation indices (V) and 8 texture features (T) and constructed inversion models using Support Vector Regression (SVR), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost) based on single and multi-source (V+T) features. The results indicated that: the multi-source feature fusion model outperformed single-feature models. The XGBoost algorithm outperformed all other models, achieving average R 2 values of 0.673, and 0.671, and RMSE values of 0.117, and 79.751 kg ha −1 for LAI, and AGB inversion, respectively. The full pod stage (R4) was identified as the optimal remote sensing observation window, where the best models achieved R 2 values of 0.846 (LAI) and 0.731 (AGB), with RMSE values of 0.131 and 81.01 kg ha −1 , respectively. Drip irrigation combined with high planting density significantly ( P < 0.05) increased soybean LAI and AGB. This study provides a robust, high-throughput technical solution for dynamic crop phenotyping, it highlights the value of fusing multi-source UAV features with machine learning for advancing data-driven smart agriculture. • Achieved dynamic soybean phenotyping by fusing unmanned aerial vehicle (UAV) multi-source features with machine learning. • Multi-source feature fusion outperformed single-feature models in accuracy and robustness. • Full pod stage identified as the optimal UAV remote sensing observation window. • Drip irrigation with high planting density significantly enhanced soybean Leaf Area Index and Above-Ground Biomass.

Plant phenotyping relevance

UAVマルチソース画像と機械学習により、LAIおよび地上部バイオマスを推定する方法を開発・比較検証しており、植物表現型取得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.