Canopy-Level Rice Yield and Yield Component Estimation Using NIR-Based Vegetation Indices

Accurately predicting rice yield and its components is crucial for optimizing agricultural practices and ensuring food security. Traditional methods of assessing crop status wwcan be time-consuming and labor-intensive. This study investigated the use of drone-based multispectral imagery and machine...

Full description

Saved in:
Bibliographic Details
Main Authors: Hyeok-Jin Bak, Eun-Ji Kim, Ji-Hyeon Lee, Sungyul Chang, Dongwon Kwon, Woo-Jin Im, Do-Hyun Kim, In-Ha Lee, Min-Ji Lee, Woon-Ha Hwang, Nam-Jin Chung, Wan-Gyu Sang
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Agriculture
Subjects:
Online Access:https://www.mdpi.com/2077-0472/15/6/594
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849392769602158592
author Hyeok-Jin Bak
Eun-Ji Kim
Ji-Hyeon Lee
Sungyul Chang
Dongwon Kwon
Woo-Jin Im
Do-Hyun Kim
In-Ha Lee
Min-Ji Lee
Woon-Ha Hwang
Nam-Jin Chung
Wan-Gyu Sang
author_facet Hyeok-Jin Bak
Eun-Ji Kim
Ji-Hyeon Lee
Sungyul Chang
Dongwon Kwon
Woo-Jin Im
Do-Hyun Kim
In-Ha Lee
Min-Ji Lee
Woon-Ha Hwang
Nam-Jin Chung
Wan-Gyu Sang
author_sort Hyeok-Jin Bak
collection DOAJ
description Accurately predicting rice yield and its components is crucial for optimizing agricultural practices and ensuring food security. Traditional methods of assessing crop status wwcan be time-consuming and labor-intensive. This study investigated the use of drone-based multispectral imagery and machine learning to improve the prediction of rice yield and yield components. Time-series VIs were collected from 152 rice samples across various nitrogen treatments, transplanting times, and rice varieties in 2023 and 2024, using an UAV at approximately 3-day intervals. A four-parameter log-normal model was applied to analyze the VI curves, effectively quantifying the maximum value, spread, and baseline of each index, revealing the dynamic influence of nitrogen and transplanting timing on crop growth. Machine learning regression models were then used to predict yield and yield components using the log-normal parameters and individual VIs as input. Results showed that the maximum (<i data-eusoft-scrollable-element="1">a</i>) and variance (<i data-eusoft-scrollable-element="1">c</i>) parameters of the log-normal model, derived from the VI curves, were strongly correlated with yield, grain number, and panicle number, emphasizing the importance of mid-to-late growth stages. Among the tested VIs, NDRE, LCI, and NDVI demonstrated the highest accuracy in predicting yield and key yield components. This study demonstrates that integrating log-normal modeling of time-series multispectral data with machine learning provides a powerful and efficient approach for precision agriculture, enabling more accurate and timely assessments of rice yield and its contributing factors.
format Article
id doaj-art-6403647bc93c4fd7b4613ffeefc0b024
institution Kabale University
issn 2077-0472
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Agriculture
spelling doaj-art-6403647bc93c4fd7b4613ffeefc0b0242025-08-20T03:40:42ZengMDPI AGAgriculture2077-04722025-03-0115659410.3390/agriculture15060594Canopy-Level Rice Yield and Yield Component Estimation Using NIR-Based Vegetation IndicesHyeok-Jin Bak0Eun-Ji Kim1Ji-Hyeon Lee2Sungyul Chang3Dongwon Kwon4Woo-Jin Im5Do-Hyun Kim6In-Ha Lee7Min-Ji Lee8Woon-Ha Hwang9Nam-Jin Chung10Wan-Gyu Sang11National Institute of Crop Science, Rural Development Administration, Jeonju 55365, Republic of KoreaNational Institute of Crop Science, Rural Development Administration, Jeonju 55365, Republic of KoreaNational Institute of Crop Science, Rural Development Administration, Jeonju 55365, Republic of KoreaNational Institute of Crop Science, Rural Development Administration, Jeonju 55365, Republic of KoreaNational Institute of Crop Science, Rural Development Administration, Jeonju 55365, Republic of KoreaNational Institute of Crop Science, Rural Development Administration, Jeonju 55365, Republic of KoreaNational Institute of Crop Science, Rural Development Administration, Jeonju 55365, Republic of KoreaNational Institute of Crop Science, Rural Development Administration, Jeonju 55365, Republic of KoreaNational Institute of Crop Science, Rural Development Administration, Jeonju 55365, Republic of KoreaNational Institute of Crop Science, Rural Development Administration, Jeonju 55365, Republic of KoreaDepartment of Agronomy, Jeonbuk National University, Jeonju 54896, Republic of KoreaNational Institute of Crop Science, Rural Development Administration, Jeonju 55365, Republic of KoreaAccurately predicting rice yield and its components is crucial for optimizing agricultural practices and ensuring food security. Traditional methods of assessing crop status wwcan be time-consuming and labor-intensive. This study investigated the use of drone-based multispectral imagery and machine learning to improve the prediction of rice yield and yield components. Time-series VIs were collected from 152 rice samples across various nitrogen treatments, transplanting times, and rice varieties in 2023 and 2024, using an UAV at approximately 3-day intervals. A four-parameter log-normal model was applied to analyze the VI curves, effectively quantifying the maximum value, spread, and baseline of each index, revealing the dynamic influence of nitrogen and transplanting timing on crop growth. Machine learning regression models were then used to predict yield and yield components using the log-normal parameters and individual VIs as input. Results showed that the maximum (<i data-eusoft-scrollable-element="1">a</i>) and variance (<i data-eusoft-scrollable-element="1">c</i>) parameters of the log-normal model, derived from the VI curves, were strongly correlated with yield, grain number, and panicle number, emphasizing the importance of mid-to-late growth stages. Among the tested VIs, NDRE, LCI, and NDVI demonstrated the highest accuracy in predicting yield and key yield components. This study demonstrates that integrating log-normal modeling of time-series multispectral data with machine learning provides a powerful and efficient approach for precision agriculture, enabling more accurate and timely assessments of rice yield and its contributing factors.https://www.mdpi.com/2077-0472/15/6/594UAVvegetation indicescrop monitoringriceremote sensingyield estimation
spellingShingle Hyeok-Jin Bak
Eun-Ji Kim
Ji-Hyeon Lee
Sungyul Chang
Dongwon Kwon
Woo-Jin Im
Do-Hyun Kim
In-Ha Lee
Min-Ji Lee
Woon-Ha Hwang
Nam-Jin Chung
Wan-Gyu Sang
Canopy-Level Rice Yield and Yield Component Estimation Using NIR-Based Vegetation Indices
Agriculture
UAV
vegetation indices
crop monitoring
rice
remote sensing
yield estimation
title Canopy-Level Rice Yield and Yield Component Estimation Using NIR-Based Vegetation Indices
title_full Canopy-Level Rice Yield and Yield Component Estimation Using NIR-Based Vegetation Indices
title_fullStr Canopy-Level Rice Yield and Yield Component Estimation Using NIR-Based Vegetation Indices
title_full_unstemmed Canopy-Level Rice Yield and Yield Component Estimation Using NIR-Based Vegetation Indices
title_short Canopy-Level Rice Yield and Yield Component Estimation Using NIR-Based Vegetation Indices
title_sort canopy level rice yield and yield component estimation using nir based vegetation indices
topic UAV
vegetation indices
crop monitoring
rice
remote sensing
yield estimation
url https://www.mdpi.com/2077-0472/15/6/594
work_keys_str_mv AT hyeokjinbak canopylevelriceyieldandyieldcomponentestimationusingnirbasedvegetationindices
AT eunjikim canopylevelriceyieldandyieldcomponentestimationusingnirbasedvegetationindices
AT jihyeonlee canopylevelriceyieldandyieldcomponentestimationusingnirbasedvegetationindices
AT sungyulchang canopylevelriceyieldandyieldcomponentestimationusingnirbasedvegetationindices
AT dongwonkwon canopylevelriceyieldandyieldcomponentestimationusingnirbasedvegetationindices
AT woojinim canopylevelriceyieldandyieldcomponentestimationusingnirbasedvegetationindices
AT dohyunkim canopylevelriceyieldandyieldcomponentestimationusingnirbasedvegetationindices
AT inhalee canopylevelriceyieldandyieldcomponentestimationusingnirbasedvegetationindices
AT minjilee canopylevelriceyieldandyieldcomponentestimationusingnirbasedvegetationindices
AT woonhahwang canopylevelriceyieldandyieldcomponentestimationusingnirbasedvegetationindices
AT namjinchung canopylevelriceyieldandyieldcomponentestimationusingnirbasedvegetationindices
AT wangyusang canopylevelriceyieldandyieldcomponentestimationusingnirbasedvegetationindices