Li Fengxiu, Zhao Chongqi, Ma Yingjie, Lv Ning, Guo Yanzhao
College of Hydraulic and Civil Engineering, Xinjiang Agricultural University, Urumqi, China.
Xinjiang Key Laboratory of Hydraulic Engineering Safety and Water Disaster Prevention, Urumqi, China.
Front Plant Sci. 2025 Aug 12;16:1639101. doi: 10.3389/fpls.2025.1639101. eCollection 2025.
Nitrogen plays a pivotal role in determining cotton yield and fiber quality. Nevertheless, because high-dimensional remote-sensing data are inherently complex and redundant, accurately estimating cotton plant nitrogen concentration (PNC) from unmanned aerial vehicle (UAV) imagery remains problematic, which in turn constrains both model precision and transferability.
Accordingly, this study introduces a hierarchical feature-selection scheme combining Elastic Net and Boruta-SHAP to eliminate redundant remote-sensing variables and evaluates six machine-learning algorithms to pinpoint the optimal method for estimating cotton nitrogen status.
Our findings reveal that five critical features (Mean_B, Mean_R, NDRE_GOSAVI, NDVI, GRVI) markedly enhanced model performance. Among the tested algorithms, random forest achieved superior performance (R² = 0.97-0.98; RMSE = 0.05-0.08), exceeding all alternatives. Both in-field observations and model outputs demonstrate that cotton PNC consistently decreases throughout development, but optimal conditions of 450 mm irrigation and 300 kg N ha⁻¹ sustain relatively elevated nitrogen levels.
Collectively, the study provides robust guidance for precision nitrogen management in cotton production within arid regions.
氮在决定棉花产量和纤维品质方面起着关键作用。然而，由于高维遥感数据本身复杂且冗余，从无人机图像中准确估算棉花植株氮浓度（PNC）仍然存在问题，这反过来又限制了模型的精度和可转移性。
因此，本研究引入了一种结合弹性网络和Boruta-SHAP的分层特征选择方案，以消除冗余遥感变量，并评估六种机器学习算法，以确定估算棉花氮素状况的最佳方法。
我们的研究结果表明，五个关键特征（Mean_B、Mean_R、NDRE_GOSAVI、NDVI、GRVI）显著提高了模型性能。在测试的算法中，随机森林表现出卓越的性能（R² = 0.97 - 0.98；RMSE = 0.05 - 0.08），超过了所有其他算法。田间观测和模型输出均表明，棉花PNC在整个生育期持续下降，但450毫米灌溉量和300千克氮公顷⁻¹的最佳条件能维持相对较高的氮水平。
总体而言，该研究为干旱地区棉花生产中的精准氮肥管理提供了有力指导。
