Integration of UAV Remote Sensing and Machine Learning for Taro Blight Monitoring

Taro blight is a major disease affecting taro cultivation. Traditional methods for disease prevention rely on manual identification, which is limited by subjectivity and scope. An unmanned aerial vehicle (UAV) was utilized to capture spectral images of natural taro fields, facilitating the efficient...

Full description

Saved in:
Bibliographic Details
Main Authors: Yushuai Wang, Yuxin Chen, Zhou Shu, Shaolong Zhu, Weijun Zhang, Tao Liu, Chengming Sun
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Agronomy
Subjects:
Online Access:https://www.mdpi.com/2073-4395/15/5/1189
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849711270104662016
author Yushuai Wang
Yuxin Chen
Zhou Shu
Shaolong Zhu
Weijun Zhang
Tao Liu
Chengming Sun
author_facet Yushuai Wang
Yuxin Chen
Zhou Shu
Shaolong Zhu
Weijun Zhang
Tao Liu
Chengming Sun
author_sort Yushuai Wang
collection DOAJ
description Taro blight is a major disease affecting taro cultivation. Traditional methods for disease prevention rely on manual identification, which is limited by subjectivity and scope. An unmanned aerial vehicle (UAV) was utilized to capture spectral images of natural taro fields, facilitating the efficient monitoring of taro blight. Field survey data were integrated with these images to develop a model for monitoring taro blight severity. The back propagation neural network (BPNN) model showed optimal performance during the early and middle stages of taro formation when hyperspectral parameters were used as input variables. In the early stage, the BPNN model achieved a coefficient of determination (R<sup>2</sup>) of 0.92 and an RMSE of 0.054 on the training set, and it obtained an R<sup>2</sup> of 0.89 with a root mean square error (RMSE) of 0.074 on the validation set. The random forest regression (RFR) model performed best during the early stage of taro formation with multispectral vegetation indices as input variables. The models exhibited robust predictive capabilities across various stages, especially during the early stage of taro formation. The results demonstrate that UAV remote sensing, combined with characteristic parameters and disease indices, presents a precise taro blight monitoring method that can substantially improve disease management in taro cultivation.
format Article
id doaj-art-6a38834d096d41fea8a54792f4a68c18
institution DOAJ
issn 2073-4395
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Agronomy
spelling doaj-art-6a38834d096d41fea8a54792f4a68c182025-08-20T03:14:39ZengMDPI AGAgronomy2073-43952025-05-01155118910.3390/agronomy15051189Integration of UAV Remote Sensing and Machine Learning for Taro Blight MonitoringYushuai Wang0Yuxin Chen1Zhou Shu2Shaolong Zhu3Weijun Zhang4Tao Liu5Chengming Sun6Cultivation and Construction Site of National Key Laboratory for Crop Genetics and Physiology in Jiangsu Province, Yangzhou University, Yangzhou 225009, ChinaCultivation and Construction Site of National Key Laboratory for Crop Genetics and Physiology in Jiangsu Province, Yangzhou University, Yangzhou 225009, ChinaCultivation and Construction Site of National Key Laboratory for Crop Genetics and Physiology in Jiangsu Province, Yangzhou University, Yangzhou 225009, ChinaCultivation and Construction Site of National Key Laboratory for Crop Genetics and Physiology in Jiangsu Province, Yangzhou University, Yangzhou 225009, ChinaCultivation and Construction Site of National Key Laboratory for Crop Genetics and Physiology in Jiangsu Province, Yangzhou University, Yangzhou 225009, ChinaCultivation and Construction Site of National Key Laboratory for Crop Genetics and Physiology in Jiangsu Province, Yangzhou University, Yangzhou 225009, ChinaCultivation and Construction Site of National Key Laboratory for Crop Genetics and Physiology in Jiangsu Province, Yangzhou University, Yangzhou 225009, ChinaTaro blight is a major disease affecting taro cultivation. Traditional methods for disease prevention rely on manual identification, which is limited by subjectivity and scope. An unmanned aerial vehicle (UAV) was utilized to capture spectral images of natural taro fields, facilitating the efficient monitoring of taro blight. Field survey data were integrated with these images to develop a model for monitoring taro blight severity. The back propagation neural network (BPNN) model showed optimal performance during the early and middle stages of taro formation when hyperspectral parameters were used as input variables. In the early stage, the BPNN model achieved a coefficient of determination (R<sup>2</sup>) of 0.92 and an RMSE of 0.054 on the training set, and it obtained an R<sup>2</sup> of 0.89 with a root mean square error (RMSE) of 0.074 on the validation set. The random forest regression (RFR) model performed best during the early stage of taro formation with multispectral vegetation indices as input variables. The models exhibited robust predictive capabilities across various stages, especially during the early stage of taro formation. The results demonstrate that UAV remote sensing, combined with characteristic parameters and disease indices, presents a precise taro blight monitoring method that can substantially improve disease management in taro cultivation.https://www.mdpi.com/2073-4395/15/5/1189taro blightUAV remote sensingcharacteristic parametersvegetation indexdisease index
spellingShingle Yushuai Wang
Yuxin Chen
Zhou Shu
Shaolong Zhu
Weijun Zhang
Tao Liu
Chengming Sun
Integration of UAV Remote Sensing and Machine Learning for Taro Blight Monitoring
Agronomy
taro blight
UAV remote sensing
characteristic parameters
vegetation index
disease index
title Integration of UAV Remote Sensing and Machine Learning for Taro Blight Monitoring
title_full Integration of UAV Remote Sensing and Machine Learning for Taro Blight Monitoring
title_fullStr Integration of UAV Remote Sensing and Machine Learning for Taro Blight Monitoring
title_full_unstemmed Integration of UAV Remote Sensing and Machine Learning for Taro Blight Monitoring
title_short Integration of UAV Remote Sensing and Machine Learning for Taro Blight Monitoring
title_sort integration of uav remote sensing and machine learning for taro blight monitoring
topic taro blight
UAV remote sensing
characteristic parameters
vegetation index
disease index
url https://www.mdpi.com/2073-4395/15/5/1189
work_keys_str_mv AT yushuaiwang integrationofuavremotesensingandmachinelearningfortaroblightmonitoring
AT yuxinchen integrationofuavremotesensingandmachinelearningfortaroblightmonitoring
AT zhoushu integrationofuavremotesensingandmachinelearningfortaroblightmonitoring
AT shaolongzhu integrationofuavremotesensingandmachinelearningfortaroblightmonitoring
AT weijunzhang integrationofuavremotesensingandmachinelearningfortaroblightmonitoring
AT taoliu integrationofuavremotesensingandmachinelearningfortaroblightmonitoring
AT chengmingsun integrationofuavremotesensingandmachinelearningfortaroblightmonitoring