Estimating Tea Plant Physiological Parameters Using Unmanned Aerial Vehicle Imagery and Machine Learning Algorithms

Tea (<i>Camellia sinensis</i> L.) holds agricultural economic value and forestry carbon sequestration potential, with Taiwan’s annual tea production exceeding TWD 7 billion. However, climate change-induced stressors threaten tea plant growth, photosynthesis, yield, and quality, necessita...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhong-Han Zhuang, Hui-Ping Tsai, Chung-I Chen
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/7/1966
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849769621872181248
author Zhong-Han Zhuang
Hui-Ping Tsai
Chung-I Chen
author_facet Zhong-Han Zhuang
Hui-Ping Tsai
Chung-I Chen
author_sort Zhong-Han Zhuang
collection DOAJ
description Tea (<i>Camellia sinensis</i> L.) holds agricultural economic value and forestry carbon sequestration potential, with Taiwan’s annual tea production exceeding TWD 7 billion. However, climate change-induced stressors threaten tea plant growth, photosynthesis, yield, and quality, necessitating an accurate real-time monitoring system to enhance plantation management and production stability. This study surveys tea plantations at low, mid-, and high elevations in Nantou County, central Taiwan, collecting data from 21 fields using conventional farming methods (CFMs), which emphasize intensive management, and agroecological farming methods (AFMs), which prioritize environmental sustainability. This study integrates leaf area index (LAI), photochemical reflectance index (PRI), and quantum yield of photosystem II (ΦPSII) data with unmanned aerial vehicles (UAV)-derived visible-light and multispectral imagery to compute color indices (CIs) and multispectral indices (MIs). Using feature ranking methods, an optimized dataset was developed, and the predictive performance of eight regression algorithms was assessed for estimating tea plant physiological parameters. The results indicate that LAI was generally lower in AFMs, suggesting reduced leaf growth density and potential yield differences. However, PRI and ΦPSII values revealed greater environmental adaptability and potential long-term ecological benefits in AFMs compared to CFMs. Among regression models, MIs provided greater stability for tea plant physiological parameters, whereas feature ranking methods had minimal impact on accuracy. XGBoost outperformed all models in predicting parameters, achieving optimal results for (1) LAI: R<sup>2</sup> = 0.716, RMSE = 1.01, MAE = 0.683, (2) PRI: R<sup>2</sup> = 0.643, RMSE = 0.013, MAE = 0.009, and (3) ΦPSII: R<sup>2</sup> = 0.920, RMSE = 0.048, MAE = 0.013. Overall, we highlight the effectiveness of integrating gradient boosting models with multispectral data to capture tea plant physiological characteristics. This study develops generalizable predictive models for tea plant physiological parameter estimation and advances non-contact crop physiological monitoring for tea plantation management, providing a scientific foundation for precision agriculture applications.
format Article
id doaj-art-00865464fffb48cbbeb916bf9b2495cb
institution DOAJ
issn 1424-8220
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-00865464fffb48cbbeb916bf9b2495cb2025-08-20T03:03:21ZengMDPI AGSensors1424-82202025-03-01257196610.3390/s25071966Estimating Tea Plant Physiological Parameters Using Unmanned Aerial Vehicle Imagery and Machine Learning AlgorithmsZhong-Han Zhuang0Hui-Ping Tsai1Chung-I Chen2Department of Civil Engineering, National Chung Hsing University, Taichung 402, TaiwanDepartment of Civil Engineering, National Chung Hsing University, Taichung 402, TaiwanDepartment of Forestry, National Pingtung University of Science and Technology, Pingtung 912, TaiwanTea (<i>Camellia sinensis</i> L.) holds agricultural economic value and forestry carbon sequestration potential, with Taiwan’s annual tea production exceeding TWD 7 billion. However, climate change-induced stressors threaten tea plant growth, photosynthesis, yield, and quality, necessitating an accurate real-time monitoring system to enhance plantation management and production stability. This study surveys tea plantations at low, mid-, and high elevations in Nantou County, central Taiwan, collecting data from 21 fields using conventional farming methods (CFMs), which emphasize intensive management, and agroecological farming methods (AFMs), which prioritize environmental sustainability. This study integrates leaf area index (LAI), photochemical reflectance index (PRI), and quantum yield of photosystem II (ΦPSII) data with unmanned aerial vehicles (UAV)-derived visible-light and multispectral imagery to compute color indices (CIs) and multispectral indices (MIs). Using feature ranking methods, an optimized dataset was developed, and the predictive performance of eight regression algorithms was assessed for estimating tea plant physiological parameters. The results indicate that LAI was generally lower in AFMs, suggesting reduced leaf growth density and potential yield differences. However, PRI and ΦPSII values revealed greater environmental adaptability and potential long-term ecological benefits in AFMs compared to CFMs. Among regression models, MIs provided greater stability for tea plant physiological parameters, whereas feature ranking methods had minimal impact on accuracy. XGBoost outperformed all models in predicting parameters, achieving optimal results for (1) LAI: R<sup>2</sup> = 0.716, RMSE = 1.01, MAE = 0.683, (2) PRI: R<sup>2</sup> = 0.643, RMSE = 0.013, MAE = 0.009, and (3) ΦPSII: R<sup>2</sup> = 0.920, RMSE = 0.048, MAE = 0.013. Overall, we highlight the effectiveness of integrating gradient boosting models with multispectral data to capture tea plant physiological characteristics. This study develops generalizable predictive models for tea plant physiological parameter estimation and advances non-contact crop physiological monitoring for tea plantation management, providing a scientific foundation for precision agriculture applications.https://www.mdpi.com/1424-8220/25/7/1966unmanned aerial vehiclestea plantsmachine learningleaf area indexphotochemical reflectance indexquantum yield of photosystem II
spellingShingle Zhong-Han Zhuang
Hui-Ping Tsai
Chung-I Chen
Estimating Tea Plant Physiological Parameters Using Unmanned Aerial Vehicle Imagery and Machine Learning Algorithms
Sensors
unmanned aerial vehicles
tea plants
machine learning
leaf area index
photochemical reflectance index
quantum yield of photosystem II
title Estimating Tea Plant Physiological Parameters Using Unmanned Aerial Vehicle Imagery and Machine Learning Algorithms
title_full Estimating Tea Plant Physiological Parameters Using Unmanned Aerial Vehicle Imagery and Machine Learning Algorithms
title_fullStr Estimating Tea Plant Physiological Parameters Using Unmanned Aerial Vehicle Imagery and Machine Learning Algorithms
title_full_unstemmed Estimating Tea Plant Physiological Parameters Using Unmanned Aerial Vehicle Imagery and Machine Learning Algorithms
title_short Estimating Tea Plant Physiological Parameters Using Unmanned Aerial Vehicle Imagery and Machine Learning Algorithms
title_sort estimating tea plant physiological parameters using unmanned aerial vehicle imagery and machine learning algorithms
topic unmanned aerial vehicles
tea plants
machine learning
leaf area index
photochemical reflectance index
quantum yield of photosystem II
url https://www.mdpi.com/1424-8220/25/7/1966
work_keys_str_mv AT zhonghanzhuang estimatingteaplantphysiologicalparametersusingunmannedaerialvehicleimageryandmachinelearningalgorithms
AT huipingtsai estimatingteaplantphysiologicalparametersusingunmannedaerialvehicleimageryandmachinelearningalgorithms
AT chungichen estimatingteaplantphysiologicalparametersusingunmannedaerialvehicleimageryandmachinelearningalgorithms