Zhang Ao, Guan Haibin, Dong Zhiheng, Jia Xin, Xue Yan, Han Fengyu, Meng Lingjiang, Yu Xiuling, Wang Xiaoqin, Cao Yang
College of Pharmacy, Inner Mongolia Medical University, Hohhot, China.
Department of Pharmacy, Affiliated Hospital of Inner Mongolia Medical University, Hohhot, China.
Front Plant Sci. 2025 Aug 19;16:1612898. doi: 10.3389/fpls.2025.1612898. eCollection 2025.
Water and nitrogen are essential elements prone to deficiency during plant growth. Current water-fertilizer monitoring technologies are unable to meet the demands of large-scale cultivation. Near-ground remote sensing technology based on unmanned aerial vehicle (UAV) multispectral image is widely used for crop growth monitoring and agricultural management and has proven to be effective for assessing water and nitrogen status. However, integrated models tailored for medicinal plants remain underexplored.
This study collected UAV multispectral images of under various water and nitrogen treatments and extracted vegetation indices (VIs). Field phenotypic indicators (PIs), including plant height (PH), tiller number (TN), soil plant analysis development values (SPAD), and nitrogen content (NC), were synchronously measured. Models were constructed using backpropagation neural network (BP), support vector machine (SVM), and random forest (RF) to evaluate PIs to predict yield and monitor growth dynamics. Yield predictions based on PIs were further compared with validate model performance.
The results demonstrated that both the RF algorithm and excess green index (EXG) exhibited versatility in growth monitoring and yield prediction. PIs collectively achieved high-precision predictions (mean 0.42 ≤ ≤ 0.94), with the prediction of PH using green leaf index (GLI) in BP algorithm attaining peak accuracy ( = 0.94). VIs and PIs exhibited comparable predictive capacity for yield, with multi-indicators integrated modeling significantly enhancing performance: VIs achieved = 0.87 under RF algorithms, whereas PIs reached = 0.81 using BP algorithms. Further analysis revealed that PH served as the central predictor, achieving = 0.74 under standalone predictions of RF algorithm, whereas other parameters primarily enhanced model accuracy through complementarity effects, thereby providing supplementary diagnostic value.
This research established a high-precision, time-efficient, and practical UAV remote sensing-based method for growth monitoring and yield prediction in , offering a novel solution for standardized production of medicinal plant resources.
水和氮是植物生长过程中易缺乏的必需元素。当前的水肥监测技术无法满足大规模种植的需求。基于无人机（UAV）多光谱图像的近地遥感技术被广泛用于作物生长监测和农业管理，并且已被证明在评估水氮状况方面是有效的。然而，针对药用植物量身定制的综合模型仍未得到充分探索。
本研究收集了在不同水氮处理下的无人机多光谱图像，并提取了植被指数（VIs）。同步测量了包括株高（PH）、分蘖数（TN）、土壤植物分析发展值（SPAD）和氮含量（NC）在内的田间表型指标（PIs）。使用反向传播神经网络（BP）、支持向量机（SVM）和随机森林（RF）构建模型，以评估PIs来预测产量并监测生长动态。基于PIs的产量预测进一步与验证模型性能进行比较。
结果表明，随机森林（RF）算法和过量绿度指数（EXG）在生长监测和产量预测方面都具有通用性。PIs总体上实现了高精度预测（平均0.42≤≤0.94），BP算法中使用绿叶指数（GLI）预测PH达到了最高精度（=0.94）。VIs和PIs在产量预测方面表现出可比的预测能力，多指标综合建模显著提高了性能：在RF算法下VIs达到=0.87，而使用BP算法时PIs达到=0.81。进一步分析表明，PH作为核心预测指标，在RF算法单独预测下达到=0.74，而其他参数主要通过互补效应提高模型精度，从而提供补充诊断价值。
本研究建立了一种基于无人机遥感的高精度、高效且实用的方法，用于的生长监测和产量预测，为药用植物资源的标准化生产提供了一种新的解决方案。
