Relationships Between Oat Phenotypes and UAV Multispectral Imagery Under Different Water Deficit Conditions by Structural Equation Modelling

The prediction of soil moisture conditions using multispectral data from unmanned aerial vehicles (UAVs) has advantages over ground measurements in terms of costs and monitoring range. However, the prediction accuracy for moisture conditions using spectral data alone is low. In this study, relations...

Full description

Saved in:
Bibliographic Details
Main Authors: Yayang Feng, Guoshuai Wang, Jun Wang, Hexiang Zheng, Xiangyang Miao, Xiulu Sun, Peng Li, Yan Li, Yanhui Jia
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Agronomy
Subjects:
Online Access:https://www.mdpi.com/2073-4395/15/6/1389
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849423834823786496
author Yayang Feng
Guoshuai Wang
Jun Wang
Hexiang Zheng
Xiangyang Miao
Xiulu Sun
Peng Li
Yan Li
Yanhui Jia
author_facet Yayang Feng
Guoshuai Wang
Jun Wang
Hexiang Zheng
Xiangyang Miao
Xiulu Sun
Peng Li
Yan Li
Yanhui Jia
author_sort Yayang Feng
collection DOAJ
description The prediction of soil moisture conditions using multispectral data from unmanned aerial vehicles (UAVs) has advantages over ground measurements in terms of costs and monitoring range. However, the prediction accuracy for moisture conditions using spectral data alone is low. In this study, relationships between water deficits and phenotypic characteristics in oats were evaluated and used to develop a UAV multispectral-based water prediction model. The vegetation indices NDRE (Normalized Difference Red Edge), CIG (Chlorophyll Index), and MCARI (Modified Chlorophyll Absorption in Reflectance Index) were highly correlated with oat yield. Based on a multipath analysis in the structural equation modeling framework, irrigation (<i>p</i> < 0.01), leaf area index (LAI) (<i>p</i> < 0.001), and SPAD (<i>p</i> < 0.001) had direct positive effects on NDRE. Three distinct machine learning approaches—linear regression (LR), random forest (RF), and artificial neural network (ANN) were employed to establish predictive models between the Normalized Difference Red Edge Index (NDRE) and soil water content (SWC). The linear regression model showed moderate correlation (<i>R</i><sup>2</sup> = 0.533). Machine learning approaches demonstrated markedly superior performance (RF: <i>R</i><sup>2</sup> = 0.828; ANN: <i>R</i><sup>2</sup> = 0.810). Nonlinear machine learning algorithms (RF and ANN) significantly outperform conventional linear regression in estimating SWC from spectral vegetation indices.
format Article
id doaj-art-c0e9aca0abae4052aaf2930d6ff81c6f
institution Kabale University
issn 2073-4395
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Agronomy
spelling doaj-art-c0e9aca0abae4052aaf2930d6ff81c6f2025-08-20T03:30:25ZengMDPI AGAgronomy2073-43952025-06-01156138910.3390/agronomy15061389Relationships Between Oat Phenotypes and UAV Multispectral Imagery Under Different Water Deficit Conditions by Structural Equation ModellingYayang Feng0Guoshuai Wang1Jun Wang2Hexiang Zheng3Xiangyang Miao4Xiulu Sun5Peng Li6Yan Li7Yanhui Jia8Yinshanbeilu Grassland Eco-Hydrology National Observation and Research Station, China Institute of Water Resources and Hydropower Research, Beijing 100038, ChinaYinshanbeilu Grassland Eco-Hydrology National Observation and Research Station, China Institute of Water Resources and Hydropower Research, Beijing 100038, ChinaYinshanbeilu Grassland Eco-Hydrology National Observation and Research Station, China Institute of Water Resources and Hydropower Research, Beijing 100038, ChinaYinshanbeilu Grassland Eco-Hydrology National Observation and Research Station, China Institute of Water Resources and Hydropower Research, Beijing 100038, ChinaYinshanbeilu Grassland Eco-Hydrology National Observation and Research Station, China Institute of Water Resources and Hydropower Research, Beijing 100038, ChinaFarmland Irrigation Research Institute, Chinese Academy of Agricultural Sciences (CAAS), Xinxiang 453002, ChinaFarmland Irrigation Research Institute, Chinese Academy of Agricultural Sciences (CAAS), Xinxiang 453002, ChinaDancheng County Agricultural and Rural Bureau, Zhoukou 477150, ChinaShandong Facility Horticulture Bioengineering Research Center, Weifang University of Science and Technology, Weifang 262700, ChinaThe prediction of soil moisture conditions using multispectral data from unmanned aerial vehicles (UAVs) has advantages over ground measurements in terms of costs and monitoring range. However, the prediction accuracy for moisture conditions using spectral data alone is low. In this study, relationships between water deficits and phenotypic characteristics in oats were evaluated and used to develop a UAV multispectral-based water prediction model. The vegetation indices NDRE (Normalized Difference Red Edge), CIG (Chlorophyll Index), and MCARI (Modified Chlorophyll Absorption in Reflectance Index) were highly correlated with oat yield. Based on a multipath analysis in the structural equation modeling framework, irrigation (<i>p</i> < 0.01), leaf area index (LAI) (<i>p</i> < 0.001), and SPAD (<i>p</i> < 0.001) had direct positive effects on NDRE. Three distinct machine learning approaches—linear regression (LR), random forest (RF), and artificial neural network (ANN) were employed to establish predictive models between the Normalized Difference Red Edge Index (NDRE) and soil water content (SWC). The linear regression model showed moderate correlation (<i>R</i><sup>2</sup> = 0.533). Machine learning approaches demonstrated markedly superior performance (RF: <i>R</i><sup>2</sup> = 0.828; ANN: <i>R</i><sup>2</sup> = 0.810). Nonlinear machine learning algorithms (RF and ANN) significantly outperform conventional linear regression in estimating SWC from spectral vegetation indices.https://www.mdpi.com/2073-4395/15/6/1389oat phenotypewater deficitUAV multispectral imageryvegetation indexstructural equation model (SEM)
spellingShingle Yayang Feng
Guoshuai Wang
Jun Wang
Hexiang Zheng
Xiangyang Miao
Xiulu Sun
Peng Li
Yan Li
Yanhui Jia
Relationships Between Oat Phenotypes and UAV Multispectral Imagery Under Different Water Deficit Conditions by Structural Equation Modelling
Agronomy
oat phenotype
water deficit
UAV multispectral imagery
vegetation index
structural equation model (SEM)
title Relationships Between Oat Phenotypes and UAV Multispectral Imagery Under Different Water Deficit Conditions by Structural Equation Modelling
title_full Relationships Between Oat Phenotypes and UAV Multispectral Imagery Under Different Water Deficit Conditions by Structural Equation Modelling
title_fullStr Relationships Between Oat Phenotypes and UAV Multispectral Imagery Under Different Water Deficit Conditions by Structural Equation Modelling
title_full_unstemmed Relationships Between Oat Phenotypes and UAV Multispectral Imagery Under Different Water Deficit Conditions by Structural Equation Modelling
title_short Relationships Between Oat Phenotypes and UAV Multispectral Imagery Under Different Water Deficit Conditions by Structural Equation Modelling
title_sort relationships between oat phenotypes and uav multispectral imagery under different water deficit conditions by structural equation modelling
topic oat phenotype
water deficit
UAV multispectral imagery
vegetation index
structural equation model (SEM)
url https://www.mdpi.com/2073-4395/15/6/1389
work_keys_str_mv AT yayangfeng relationshipsbetweenoatphenotypesanduavmultispectralimageryunderdifferentwaterdeficitconditionsbystructuralequationmodelling
AT guoshuaiwang relationshipsbetweenoatphenotypesanduavmultispectralimageryunderdifferentwaterdeficitconditionsbystructuralequationmodelling
AT junwang relationshipsbetweenoatphenotypesanduavmultispectralimageryunderdifferentwaterdeficitconditionsbystructuralequationmodelling
AT hexiangzheng relationshipsbetweenoatphenotypesanduavmultispectralimageryunderdifferentwaterdeficitconditionsbystructuralequationmodelling
AT xiangyangmiao relationshipsbetweenoatphenotypesanduavmultispectralimageryunderdifferentwaterdeficitconditionsbystructuralequationmodelling
AT xiulusun relationshipsbetweenoatphenotypesanduavmultispectralimageryunderdifferentwaterdeficitconditionsbystructuralequationmodelling
AT pengli relationshipsbetweenoatphenotypesanduavmultispectralimageryunderdifferentwaterdeficitconditionsbystructuralequationmodelling
AT yanli relationshipsbetweenoatphenotypesanduavmultispectralimageryunderdifferentwaterdeficitconditionsbystructuralequationmodelling
AT yanhuijia relationshipsbetweenoatphenotypesanduavmultispectralimageryunderdifferentwaterdeficitconditionsbystructuralequationmodelling