Construction and application of a drought classification model for tea plantations based on multi-source remote sensing

In the backdrop of global climate change, drought is identified as a major natural hazard, posing a severe threat to tea production. Traditional methods for assessing drought stress in tea plants rely on manual investigation. However, this approach is time-consuming and labor-intensive. While unmann...

Full description

Saved in:
Bibliographic Details
Main Authors: Yang Xu, Yilin Mao, He Li, Xiaojiang Li, Litao Sun, Kai Fan, Zhipeng Li, Shuting Gong, Zhaotang Ding, Yu Wang
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:Smart Agricultural Technology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772375525003648
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849417490135777280
author Yang Xu
Yilin Mao
He Li
Xiaojiang Li
Litao Sun
Kai Fan
Zhipeng Li
Shuting Gong
Zhaotang Ding
Yu Wang
author_facet Yang Xu
Yilin Mao
He Li
Xiaojiang Li
Litao Sun
Kai Fan
Zhipeng Li
Shuting Gong
Zhaotang Ding
Yu Wang
author_sort Yang Xu
collection DOAJ
description In the backdrop of global climate change, drought is identified as a major natural hazard, posing a severe threat to tea production. Traditional methods for assessing drought stress in tea plants rely on manual investigation. However, this approach is time-consuming and labor-intensive. While unmanned aerial vehicle (UAV) remote sensing offers efficient alternatives, existing studies predominantly rely on single-sensor data (e.g., multispectral (MS) or thermal infrared (TIR)), overlooking the potential of multi-source fusion—especially for tea plantations. To address this gap, we propose RSDCM (Remote Sensing-based Drought Classification Model), an improved Genetic Algorithm-Backpropagation (GA-BP) combined with MS + TIR framework that optimizes initial weights and thresholds via GA's global search (hidden layer=1, neurons in the hidden layers=5, 50 generations, population size=5, NonUnifMutation operators) to escape local minima and accelerate convergence. A UAV platform equipped with MS, RGB, and TIR sensors collected multi-source data from drought-stressed tea plantations in Eastern China. The RSDCM model was benchmarked against single BP and three classical machine learning models (SVM, RF, ELM).The study found that: (1) Multi-source data fusion outperformed single-source data, with MS + TIR achieving optimal performance (Accuracy: 0.983, Precision: 0.967-1.000, Recall: 0.967-1.000, F1-score: 0.967-1.000)—surpassing MS (Accuracy: 0.950, Precision: 0.894-1.000, Recall: 0.917-0.983, F1-score: 0.924-0.983), TIR (Accuracy: 0.925, Precision: 0.862-0.982, Recall: 0.867-0.983, F1-score: 0.889-0.967), and RGB (Accuracy: 0.904, Precision: 0.824-0.950, Recall: 0.783-0.950, F1-score: 0.847-0.950) alone. (2) The RSDCM model (accuracy: 0.983) performed better than the other four models, with high generalizability across all drought levels (F1-scores: 0.967–1.000 for severe/moderate/light/normal classes). (3) The RSDCM model could accurately classify drought stress levels in tea plantations.Thus, RSDCM provides a novel, robust solution for UAV-based drought assessment in tea plantations, combining multi-sensor fusion and deep learning.
format Article
id doaj-art-e8a065e2ffea483c97b641a0c3e9ead1
institution Kabale University
issn 2772-3755
language English
publishDate 2025-12-01
publisher Elsevier
record_format Article
series Smart Agricultural Technology
spelling doaj-art-e8a065e2ffea483c97b641a0c3e9ead12025-08-20T03:32:49ZengElsevierSmart Agricultural Technology2772-37552025-12-011210113210.1016/j.atech.2025.101132Construction and application of a drought classification model for tea plantations based on multi-source remote sensingYang Xu0Yilin Mao1He Li2Xiaojiang Li3Litao Sun4Kai Fan5Zhipeng Li6Shuting Gong7Zhaotang Ding8Yu Wang9College of Horticulture, Qingdao Agricultural University, Qingdao 266109, PR ChinaCollege of Horticulture, Qingdao Agricultural University, Qingdao 266109, PR ChinaCollege of Horticulture, Qingdao Agricultural University, Qingdao 266109, PR ChinaTea Research Institute, Shandong Academy of Agricultural Sciences, Jinan 250100, PR ChinaTea Research Institute, Shandong Academy of Agricultural Sciences, Jinan 250100, PR ChinaCollege of Horticulture, Qingdao Agricultural University, Qingdao 266109, PR ChinaCollege of Horticulture, Qingdao Agricultural University, Qingdao 266109, PR ChinaCollege of Horticulture, Qingdao Agricultural University, Qingdao 266109, PR ChinaCollege of Horticulture, Qingdao Agricultural University, Qingdao 266109, PR China; Tea Research Institute, Shandong Academy of Agricultural Sciences, Jinan 250100, PR China; Corresponding authors.College of Horticulture, Qingdao Agricultural University, Qingdao 266109, PR China; Corresponding authors.In the backdrop of global climate change, drought is identified as a major natural hazard, posing a severe threat to tea production. Traditional methods for assessing drought stress in tea plants rely on manual investigation. However, this approach is time-consuming and labor-intensive. While unmanned aerial vehicle (UAV) remote sensing offers efficient alternatives, existing studies predominantly rely on single-sensor data (e.g., multispectral (MS) or thermal infrared (TIR)), overlooking the potential of multi-source fusion—especially for tea plantations. To address this gap, we propose RSDCM (Remote Sensing-based Drought Classification Model), an improved Genetic Algorithm-Backpropagation (GA-BP) combined with MS + TIR framework that optimizes initial weights and thresholds via GA's global search (hidden layer=1, neurons in the hidden layers=5, 50 generations, population size=5, NonUnifMutation operators) to escape local minima and accelerate convergence. A UAV platform equipped with MS, RGB, and TIR sensors collected multi-source data from drought-stressed tea plantations in Eastern China. The RSDCM model was benchmarked against single BP and three classical machine learning models (SVM, RF, ELM).The study found that: (1) Multi-source data fusion outperformed single-source data, with MS + TIR achieving optimal performance (Accuracy: 0.983, Precision: 0.967-1.000, Recall: 0.967-1.000, F1-score: 0.967-1.000)—surpassing MS (Accuracy: 0.950, Precision: 0.894-1.000, Recall: 0.917-0.983, F1-score: 0.924-0.983), TIR (Accuracy: 0.925, Precision: 0.862-0.982, Recall: 0.867-0.983, F1-score: 0.889-0.967), and RGB (Accuracy: 0.904, Precision: 0.824-0.950, Recall: 0.783-0.950, F1-score: 0.847-0.950) alone. (2) The RSDCM model (accuracy: 0.983) performed better than the other four models, with high generalizability across all drought levels (F1-scores: 0.967–1.000 for severe/moderate/light/normal classes). (3) The RSDCM model could accurately classify drought stress levels in tea plantations.Thus, RSDCM provides a novel, robust solution for UAV-based drought assessment in tea plantations, combining multi-sensor fusion and deep learning.http://www.sciencedirect.com/science/article/pii/S2772375525003648Tea plantDrought stressUAVMulti-source remote sensingData fusionDeep learning
spellingShingle Yang Xu
Yilin Mao
He Li
Xiaojiang Li
Litao Sun
Kai Fan
Zhipeng Li
Shuting Gong
Zhaotang Ding
Yu Wang
Construction and application of a drought classification model for tea plantations based on multi-source remote sensing
Smart Agricultural Technology
Tea plant
Drought stress
UAV
Multi-source remote sensing
Data fusion
Deep learning
title Construction and application of a drought classification model for tea plantations based on multi-source remote sensing
title_full Construction and application of a drought classification model for tea plantations based on multi-source remote sensing
title_fullStr Construction and application of a drought classification model for tea plantations based on multi-source remote sensing
title_full_unstemmed Construction and application of a drought classification model for tea plantations based on multi-source remote sensing
title_short Construction and application of a drought classification model for tea plantations based on multi-source remote sensing
title_sort construction and application of a drought classification model for tea plantations based on multi source remote sensing
topic Tea plant
Drought stress
UAV
Multi-source remote sensing
Data fusion
Deep learning
url http://www.sciencedirect.com/science/article/pii/S2772375525003648
work_keys_str_mv AT yangxu constructionandapplicationofadroughtclassificationmodelforteaplantationsbasedonmultisourceremotesensing
AT yilinmao constructionandapplicationofadroughtclassificationmodelforteaplantationsbasedonmultisourceremotesensing
AT heli constructionandapplicationofadroughtclassificationmodelforteaplantationsbasedonmultisourceremotesensing
AT xiaojiangli constructionandapplicationofadroughtclassificationmodelforteaplantationsbasedonmultisourceremotesensing
AT litaosun constructionandapplicationofadroughtclassificationmodelforteaplantationsbasedonmultisourceremotesensing
AT kaifan constructionandapplicationofadroughtclassificationmodelforteaplantationsbasedonmultisourceremotesensing
AT zhipengli constructionandapplicationofadroughtclassificationmodelforteaplantationsbasedonmultisourceremotesensing
AT shutinggong constructionandapplicationofadroughtclassificationmodelforteaplantationsbasedonmultisourceremotesensing
AT zhaotangding constructionandapplicationofadroughtclassificationmodelforteaplantationsbasedonmultisourceremotesensing
AT yuwang constructionandapplicationofadroughtclassificationmodelforteaplantationsbasedonmultisourceremotesensing