Predicting Nitrogen Flavanol Index (NFI) in <i>Mentha arvensis</i> Using UAV Imaging and Machine Learning Techniques for Sustainable Agriculture

Crop growth monitoring at various growth stages is essential for optimizing agricultural inputs and enhancing crop yield. Nitrogen plays a critical role in plant development; however, its improper application can reduce productivity and, in the long term, degrade soil health. The aim of this study w...

Full description

Saved in:
Bibliographic Details
Main Authors: Bhavneet Gulati, Zainab Zubair, Ankita Sinha, Nikita Sinha, Nupoor Prasad, Manoj Semwal
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Drones
Subjects:
Online Access:https://www.mdpi.com/2504-446X/9/7/483
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849246521047908352
author Bhavneet Gulati
Zainab Zubair
Ankita Sinha
Nikita Sinha
Nupoor Prasad
Manoj Semwal
author_facet Bhavneet Gulati
Zainab Zubair
Ankita Sinha
Nikita Sinha
Nupoor Prasad
Manoj Semwal
author_sort Bhavneet Gulati
collection DOAJ
description Crop growth monitoring at various growth stages is essential for optimizing agricultural inputs and enhancing crop yield. Nitrogen plays a critical role in plant development; however, its improper application can reduce productivity and, in the long term, degrade soil health. The aim of this study was to develop a non-invasive approach for nitrogen estimation through proxies (Nitrogen Flavanol Index) in <i>Mentha arvensis</i> using UAV-derived multispectral vegetation indices and machine learning models. Support Vector Regression, Random Forest, and Gradient Boosting were used to predict the Nitrogen Flavanol Index (NFI) across different growth stages. Among the tested models, Random Forest achieved the highest predictive accuracy (R<sup>2</sup> = 0.86, RMSE = 0.32) at 75 days after planting (DAP), followed by Gradient Boosting (R<sup>2</sup> = 0.75, RMSE = 0.43). Model performance was lowest during early growth stages (15–30 DAP) but improved markedly from mid to late growth stages (45–90 DAP). The findings highlight the significance of UAV-acquired data coupled with machine learning approaches for non-destructive nitrogen flavanol estimation, which can immensely contribute to improving real-time crop growth monitoring.
format Article
id doaj-art-e07353950ec54cb69dde8010047ea980
institution Kabale University
issn 2504-446X
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Drones
spelling doaj-art-e07353950ec54cb69dde8010047ea9802025-08-20T03:58:27ZengMDPI AGDrones2504-446X2025-07-019748310.3390/drones9070483Predicting Nitrogen Flavanol Index (NFI) in <i>Mentha arvensis</i> Using UAV Imaging and Machine Learning Techniques for Sustainable AgricultureBhavneet Gulati0Zainab Zubair1Ankita Sinha2Nikita Sinha3Nupoor Prasad4Manoj Semwal5Computational Biology Department, CSIR–Central Institute of Medicinal and Aromatic Plants, Lucknow 226015, IndiaComputational Biology Department, CSIR–Central Institute of Medicinal and Aromatic Plants, Lucknow 226015, IndiaDepartment of Electronics and Communication Engineering, Christ University, Bangalore 560074, IndiaDepartment of Electronics and Communication Engineering, Christ University, Bangalore 560074, IndiaPlant Protection and Production Division, CSIR-Central Institute of Medicinal and Aromatic Plants, Lucknow 226015, IndiaComputational Biology Department, CSIR–Central Institute of Medicinal and Aromatic Plants, Lucknow 226015, IndiaCrop growth monitoring at various growth stages is essential for optimizing agricultural inputs and enhancing crop yield. Nitrogen plays a critical role in plant development; however, its improper application can reduce productivity and, in the long term, degrade soil health. The aim of this study was to develop a non-invasive approach for nitrogen estimation through proxies (Nitrogen Flavanol Index) in <i>Mentha arvensis</i> using UAV-derived multispectral vegetation indices and machine learning models. Support Vector Regression, Random Forest, and Gradient Boosting were used to predict the Nitrogen Flavanol Index (NFI) across different growth stages. Among the tested models, Random Forest achieved the highest predictive accuracy (R<sup>2</sup> = 0.86, RMSE = 0.32) at 75 days after planting (DAP), followed by Gradient Boosting (R<sup>2</sup> = 0.75, RMSE = 0.43). Model performance was lowest during early growth stages (15–30 DAP) but improved markedly from mid to late growth stages (45–90 DAP). The findings highlight the significance of UAV-acquired data coupled with machine learning approaches for non-destructive nitrogen flavanol estimation, which can immensely contribute to improving real-time crop growth monitoring.https://www.mdpi.com/2504-446X/9/7/483UAVmultispectral remote sensingnitrogen<i>Mentha arvensis</i>machine learningprecision agriculture
spellingShingle Bhavneet Gulati
Zainab Zubair
Ankita Sinha
Nikita Sinha
Nupoor Prasad
Manoj Semwal
Predicting Nitrogen Flavanol Index (NFI) in <i>Mentha arvensis</i> Using UAV Imaging and Machine Learning Techniques for Sustainable Agriculture
Drones
UAV
multispectral remote sensing
nitrogen
<i>Mentha arvensis</i>
machine learning
precision agriculture
title Predicting Nitrogen Flavanol Index (NFI) in <i>Mentha arvensis</i> Using UAV Imaging and Machine Learning Techniques for Sustainable Agriculture
title_full Predicting Nitrogen Flavanol Index (NFI) in <i>Mentha arvensis</i> Using UAV Imaging and Machine Learning Techniques for Sustainable Agriculture
title_fullStr Predicting Nitrogen Flavanol Index (NFI) in <i>Mentha arvensis</i> Using UAV Imaging and Machine Learning Techniques for Sustainable Agriculture
title_full_unstemmed Predicting Nitrogen Flavanol Index (NFI) in <i>Mentha arvensis</i> Using UAV Imaging and Machine Learning Techniques for Sustainable Agriculture
title_short Predicting Nitrogen Flavanol Index (NFI) in <i>Mentha arvensis</i> Using UAV Imaging and Machine Learning Techniques for Sustainable Agriculture
title_sort predicting nitrogen flavanol index nfi in i mentha arvensis i using uav imaging and machine learning techniques for sustainable agriculture
topic UAV
multispectral remote sensing
nitrogen
<i>Mentha arvensis</i>
machine learning
precision agriculture
url https://www.mdpi.com/2504-446X/9/7/483
work_keys_str_mv AT bhavneetgulati predictingnitrogenflavanolindexnfiinimenthaarvensisiusinguavimagingandmachinelearningtechniquesforsustainableagriculture
AT zainabzubair predictingnitrogenflavanolindexnfiinimenthaarvensisiusinguavimagingandmachinelearningtechniquesforsustainableagriculture
AT ankitasinha predictingnitrogenflavanolindexnfiinimenthaarvensisiusinguavimagingandmachinelearningtechniquesforsustainableagriculture
AT nikitasinha predictingnitrogenflavanolindexnfiinimenthaarvensisiusinguavimagingandmachinelearningtechniquesforsustainableagriculture
AT nupoorprasad predictingnitrogenflavanolindexnfiinimenthaarvensisiusinguavimagingandmachinelearningtechniquesforsustainableagriculture
AT manojsemwal predictingnitrogenflavanolindexnfiinimenthaarvensisiusinguavimagingandmachinelearningtechniquesforsustainableagriculture