Estimating Maize Leaf Water Content Using Machine Learning with Diverse Multispectral Image Features

Leaf water content (LWC) is a key physiological parameter for assessing maize moisture status, with direct implications for crop growth and yield. Accurate LWC estimation is essential for water resource management and precision agriculture. This study introduces a high-precision method for estimatin...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuchen Wang, Jianliang Wang, Jiayue Li, Jiacheng Wang, Hanzeyu Xu, Tao Liu, Juan Wang
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Plants
Subjects:
Online Access:https://www.mdpi.com/2223-7747/14/6/973
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850091279746072576
author Yuchen Wang
Jianliang Wang
Jiayue Li
Jiacheng Wang
Hanzeyu Xu
Tao Liu
Juan Wang
author_facet Yuchen Wang
Jianliang Wang
Jiayue Li
Jiacheng Wang
Hanzeyu Xu
Tao Liu
Juan Wang
author_sort Yuchen Wang
collection DOAJ
description Leaf water content (LWC) is a key physiological parameter for assessing maize moisture status, with direct implications for crop growth and yield. Accurate LWC estimation is essential for water resource management and precision agriculture. This study introduces a high-precision method for estimating maize LWC utilizing UAV-based multispectral imagery combined with a Random Forest Regression (RFR) model. By extracting vegetation indices, image coverage, and texture features and integrating them with ground-truth data, the study examines the variation in LWC estimation accuracy across different growth stages. The results indicate that the RFR model performs optimally during the seedling stage, with a root relative mean square error (RRMSE) of 2.99%, whereas estimation errors are larger during the tasseling stage, with an RRMSE of 4.13%. Moreover, the RFR model consistently outperforms multiple linear regression (MLR) and ridge regression (RR) models throughout the growing season, demonstrating lower errors on both training and testing datasets. Notably, the RFR model exhibits significantly reduced errors in the training dataset compared to both MLR and RR models. Following particle swarm optimization (PSO), the prediction accuracy of the RFR model is notably enhanced, with the RRMSE on the training dataset decreasing from 1.46% to 1.19%. This study provides an effective approach for estimating maize LWC across different growth stages, supporting crop water management and precision agriculture, and offering valuable insights for the estimation of water content in other crops.
format Article
id doaj-art-43fd7593ec8d4af4bda9050a05abafb9
institution DOAJ
issn 2223-7747
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Plants
spelling doaj-art-43fd7593ec8d4af4bda9050a05abafb92025-08-20T02:42:25ZengMDPI AGPlants2223-77472025-03-0114697310.3390/plants14060973Estimating Maize Leaf Water Content Using Machine Learning with Diverse Multispectral Image FeaturesYuchen Wang0Jianliang Wang1Jiayue Li2Jiacheng Wang3Hanzeyu Xu4Tao Liu5Juan Wang6College of Hydraaulic Science and Engineering, Yangzhou University, Yangzhou 225009, ChinaJiangsu Key Laboratory of Crop Genetics and Physiology/Jiangsu Key Laboratory of Crop Cultivation and Physiology, Agricultural College of Yangzhou University, Yangzhou 225009, ChinaJiangsu Key Laboratory of Crop Genetics and Physiology/Jiangsu Key Laboratory of Crop Cultivation and Physiology, Agricultural College of Yangzhou University, Yangzhou 225009, ChinaJiangsu Key Laboratory of Crop Genetics and Physiology/Jiangsu Key Laboratory of Crop Cultivation and Physiology, Agricultural College of Yangzhou University, Yangzhou 225009, ChinaJiangsu Key Laboratory of Crop Genetics and Physiology/Jiangsu Key Laboratory of Crop Cultivation and Physiology, Agricultural College of Yangzhou University, Yangzhou 225009, ChinaJiangsu Key Laboratory of Crop Genetics and Physiology/Jiangsu Key Laboratory of Crop Cultivation and Physiology, Agricultural College of Yangzhou University, Yangzhou 225009, ChinaCollege of Hydraaulic Science and Engineering, Yangzhou University, Yangzhou 225009, ChinaLeaf water content (LWC) is a key physiological parameter for assessing maize moisture status, with direct implications for crop growth and yield. Accurate LWC estimation is essential for water resource management and precision agriculture. This study introduces a high-precision method for estimating maize LWC utilizing UAV-based multispectral imagery combined with a Random Forest Regression (RFR) model. By extracting vegetation indices, image coverage, and texture features and integrating them with ground-truth data, the study examines the variation in LWC estimation accuracy across different growth stages. The results indicate that the RFR model performs optimally during the seedling stage, with a root relative mean square error (RRMSE) of 2.99%, whereas estimation errors are larger during the tasseling stage, with an RRMSE of 4.13%. Moreover, the RFR model consistently outperforms multiple linear regression (MLR) and ridge regression (RR) models throughout the growing season, demonstrating lower errors on both training and testing datasets. Notably, the RFR model exhibits significantly reduced errors in the training dataset compared to both MLR and RR models. Following particle swarm optimization (PSO), the prediction accuracy of the RFR model is notably enhanced, with the RRMSE on the training dataset decreasing from 1.46% to 1.19%. This study provides an effective approach for estimating maize LWC across different growth stages, supporting crop water management and precision agriculture, and offering valuable insights for the estimation of water content in other crops.https://www.mdpi.com/2223-7747/14/6/973UAVmultispectral imagemachine learningwheatleaf water content
spellingShingle Yuchen Wang
Jianliang Wang
Jiayue Li
Jiacheng Wang
Hanzeyu Xu
Tao Liu
Juan Wang
Estimating Maize Leaf Water Content Using Machine Learning with Diverse Multispectral Image Features
Plants
UAV
multispectral image
machine learning
wheat
leaf water content
title Estimating Maize Leaf Water Content Using Machine Learning with Diverse Multispectral Image Features
title_full Estimating Maize Leaf Water Content Using Machine Learning with Diverse Multispectral Image Features
title_fullStr Estimating Maize Leaf Water Content Using Machine Learning with Diverse Multispectral Image Features
title_full_unstemmed Estimating Maize Leaf Water Content Using Machine Learning with Diverse Multispectral Image Features
title_short Estimating Maize Leaf Water Content Using Machine Learning with Diverse Multispectral Image Features
title_sort estimating maize leaf water content using machine learning with diverse multispectral image features
topic UAV
multispectral image
machine learning
wheat
leaf water content
url https://www.mdpi.com/2223-7747/14/6/973
work_keys_str_mv AT yuchenwang estimatingmaizeleafwatercontentusingmachinelearningwithdiversemultispectralimagefeatures
AT jianliangwang estimatingmaizeleafwatercontentusingmachinelearningwithdiversemultispectralimagefeatures
AT jiayueli estimatingmaizeleafwatercontentusingmachinelearningwithdiversemultispectralimagefeatures
AT jiachengwang estimatingmaizeleafwatercontentusingmachinelearningwithdiversemultispectralimagefeatures
AT hanzeyuxu estimatingmaizeleafwatercontentusingmachinelearningwithdiversemultispectralimagefeatures
AT taoliu estimatingmaizeleafwatercontentusingmachinelearningwithdiversemultispectralimagefeatures
AT juanwang estimatingmaizeleafwatercontentusingmachinelearningwithdiversemultispectralimagefeatures