欢迎访问《草业学报》官方网站,今天是

草业学报 ›› 2025, Vol. 34 ›› Issue (12): 85-96.DOI: 10.11686/cyxb2025033

• 研究论文 • 上一篇    下一篇

光谱指数助力机器学习提高玉米叶片含水量估测精度

肖娅婷1,2(), 唐彧哲1,2, 王潞1,2, 白宇飞1,2, 杨海波1,2, 李斐1,2()   

  1. 1.内蒙古农业大学草原与资源环境学院,内蒙古自治区土壤质量与养分资源重点实验室,内蒙古 呼和浩特 010018
    2.农业生态安全与绿色发展自治区高等学校重点实验室,内蒙古 呼和浩特 010018
  • 收稿日期:2025-02-02 修回日期:2025-03-10 出版日期:2025-12-20 发布日期:2025-10-20
  • 通讯作者: 李斐
  • 作者简介:E-mail: Lifei@imau.edu.cn
    肖娅婷(1998-),女,内蒙古巴彦淖尔人,在读硕士。E-mail: XiaoYT@emails.imau.edu.cn
  • 基金资助:
    国家重点研发计划(2023YFD1900404-03);国家重点研发计划课题(2024YFD1700400)

Use of spectral index-assisted machine learning to improve the accuracy of maize leaf water content estimation

Ya-ting XIAO1,2(), Yu-zhe TANG1,2, Lu WANG1,2, Yu-fei BAI1,2, Hai-bo YANG1,2, Fei LI1,2()   

  1. 1.College of Grassland,Resources and Environment,Inner Mongolia Agricultural University,Inner Mongolia Key Laboratory of Soil Quality and Nutrient Resources,Hohhot 010018,China
    2.Key Laboratory of Agricultural Ecological Security and Green Development in Higher Education Institutions of Inner Mongolia Autonomous Region,Hohhot 010018,China
  • Received:2025-02-02 Revised:2025-03-10 Online:2025-12-20 Published:2025-10-20
  • Contact: Fei LI

摘要:

玉米水分状况的快速无损监测对于水分诊断和灌溉管理具有重要意义,而光谱指数是作物叶片含水量(LWC)无损实时估测的重要指标之一,然而传统的光谱指数在估测LWC时易受外界环境因素影响,导致估测精度较低。机器学习(ML)算法在预测作物水分状况方面有显著的优势,特别是针对精准农业和作物水分监测等应用。因此,本研究旨在将光谱指数与机器学习结合来进一步提高LWC的估测精度,实现玉米水分的高效利用。研究于2023-2024年在内蒙古玉米种植的典型区域进行不同水分梯度的田间试验,测定玉米叶片3个关键生育时期的高光谱反射率,分析13种水敏感的光谱指数与玉米LWC的相关关系后,利用ReliefF技术筛选主要光谱特征作为偏最小二乘(PLSR)、随机森林(RF)、高斯过程回归(GPR)3种机器学习算法的输入变量,构建玉米LWC的估测模型。结果表明,在13种水情指数中改良的DATT指数(MDATT)预测性能最佳(决定系数R2=0.52),但估测精度受生育时期和玉米叶片层位影响较大,不能有效监测玉米LWC。而将全波段光谱(350~2500 nm)和通过ReliefF技术筛选的主要光谱指数分别投入3种机器学习算法中,LWC的估测精度提升了7%~45%。其中以光谱指数作为输入特征的模型整体表现较好,RF和GPR模型在LWC估测中表现较为优越,可解释玉米LWC 88%~89%的变异。最后利用独立数据集对RF和GPR模型进行验证,RF和GPR模型决定系数R2分别为0.89和0.88,均方根误差(RMSE)为1.95%和2.04%。总体来看,光谱指数与RF和GPR算法耦合起到了级联效应,可以显著提高玉米LWC的估测精度,研究结果将为玉米LWC的估测提供可靠的方法,并为玉米水肥一体化管理提供科学有效的依据。

关键词: 玉米叶片, 含水量, 光谱指数, 机器学习

Abstract:

Rapid and non-destructive monitoring of the water status of maize (Zea mays) is important for water status diagnosis and irrigation management. Spectral indices serve as crucial tools for non-destructive real-time estimation of crop leaf water content (LWC). However, traditional spectral indices are sensitive to external environmental factors, resulting in reduced prediction accuracy when they are used to estimate LWC. Machine learning (ML) algorithms demonstrate distinct advantages in predicting crop water status, particularly when applied in precision agriculture and crop water status monitoring. Therefore the aims of this study were to enhance the accuracy of LWC estimation by integrating spectral indices with ML approaches, with an overall goal to facilitate efficient water resource utilization during maize cultivation. Field experiments with varying water gradients were conducted in typical maize cultivation regions of Inner Mongolia during 2023-2024. The hyperspectral reflectance of maize leaves were measured across three critical growth stages, and then correlation analyses were conducted between maize LWC and 13 water-sensitive spectral indices. To develop LWC estimation models, spectral features selected via the ReliefF technique were used as input variables for three ML algorithms-partial least squares regression (PLSR), random forest (RF), and Gaussian process regression (GPR). The results demonstrate that among the 13 hydrological indices, the modified DATT index exhibited optimal predictive performance (coefficient of determination R2=0.52). However, its accuracy was affected by the growth stage and leaf canopy position, limiting its effectiveness for LWC monitoring. Integrating full-spectrum data (350-2500 nm) with ReliefF-selected spectral indices into ML algorithms enhanced the accuracy of LWC estimates by 7%-45%. Models utilizing spectral indices as input features demonstrated superior overall performance, with the RF and GPR models explaining 88%-89% of LWC variability. Independent validations confirmed the robustness of the models, with coefficient of determination R2 values of 0.89 (RF) and 0.88 (GPR) and root mean square error values of 1.95% and 2.04%. Our results show that the synergistic combination of spectral indices with RF/GPR algorithms had cascading effects, significantly improving the accuracy of LWC estimation. This methodology provides a reliable approach for monitoring maize water status and establishes a scientific foundation for the development of precise integrated water-fertilizer management systems.

Key words: maize leaves, water content, spectral index, machine learning