Harnessing Spectral Libraries From AVIRIS‐NG Data for Precise PFT Classification: A Deep Learning Approach
Plant, Cell & Environment · 2026-10 · 49 (10) · 7315-7337
DOI: 10.1111/pce.15393 ↗At a glance
Journal article in Plant, Cell & Environment, published online on 2025-01-27. Written by Agradeep Mohanta and 7 co-authors. Institution: Ecophysiology and RS-GIS Laboratory, Department of Botany, Faculty of Science, The Maharaja Sayajirao University of Baroda, Vadodara, India. Major MEDLINE topics: Deep Learning, Hyperspectral Imaging, Plants. Cited 3 times so far (Crossref); 125 references. The full text is freely available in PubMed Central. Funded by: The authors received no specific funding for this work..
Abstract (original language)
The generation of spectral libraries using hyperspectral data allows for the capture of detailed spectral signatures, uncovering subtle variations in plant physiology, biochemistry, and growth stages, marking a significant advancement over traditional land cover classification methods. These spectral libraries enable improved forest classification accuracy and more precise differentiation of plant species and plant functional types (PFTs), thereby establishing hyperspectral sensing as a critical tool for PFT classification. This study aims to advance the classification and monitoring of PFTs in Shoolpaneshwar wildlife sanctuary, Gujarat, India using Airborne Visible/Infrared Imaging Spectrometer‐Next Generation (AVIRIS‐NG) and machine learning techniques. A comprehensive spectral library was developed, encompassing data from 130 plant species, with a focus on their spectral features to support precise PFT classification. The spectral data were collected using AVIRIS‐NG hyperspectral imaging and ASD Handheld Spectroradiometer, capturing a wide range of wavelengths (400–1600 nm) to encompass the key physiological and biochemical traits of the plants. Plant species were grouped into five distinct PFTs using Fuzzy C‐means clustering. Key spectral features, including band reflectance, vegetation indices, and derivative/continuum properties, were identified through a combination of ISODATA clustering and Jeffries‐Matusita (JM) distance analysis, enabling effective feature selection for classification. To assess the utility of the spectral library, three advanced machine learning classifiers—Parzen Window (PW), Gradient Boosted Machine (GBM), and Stochastic Gradient Descent (SGD)—were rigorously evaluated. The GBM classifier achieved the highest accuracy, with an overall accuracy (OAA) of 0.94 and a Kappa coefficient of 0.93 across five PFTs.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Ecophysiology and RS-GIS Laboratory, Department of Botany, Faculty of Science, The Maharaja Sayajirao University of Baroda, Vadodara, India.
- Department of Information Technology, Usha Mittal Institute of Technology, SNDT Women's University, Mumbai, India.
- Remote Sensing Laboratory, Institute of Environment and Sustainable Development, Banaras Hindu University, Varanasi, India.
Funding
- The authors received no specific funding for this work.
Cite
APA
Mohanta, A., Sandhya Kiran, G., Malhi, R. K. M., Prajapati, P. C., Oza, K. K., Rajput, S., Shitole, S., & Srivastava, P. K. (2026). Harnessing Spectral Libraries From AVIRIS‐NG Data for Precise PFT Classification: A Deep Learning Approach. Plant, Cell & Environment, 49(10), 7315-7337. https://doi.org/10.1111/pce.15393
Vancouver
Mohanta A, Sandhya Kiran G, Malhi RKM, Prajapati PC, Oza KK, Rajput S, et al. Harnessing Spectral Libraries From AVIRIS‐NG Data for Precise PFT Classification: A Deep Learning Approach. Plant, Cell & Environment. 2026;49(10):7315-7337. doi:10.1111/pce.15393
BibTeX
@article{Mohanta2026,
author = {Mohanta, Agradeep and Sandhya Kiran, Garge and Malhi, Ramandeep Kaur M and Prajapati, Pankajkumar C and Oza, Kavi K and Rajput, Shrishti and Shitole, Sanjay and Srivastava, Prashant Kumar},
title = {Harnessing Spectral Libraries From AVIRIS‐NG Data for Precise PFT Classification: A Deep Learning Approach},
journal = {Plant, Cell & Environment},
year = {2026},
volume = {49},
number = {10},
pages = {7315--7337},
doi = {10.1111/pce.15393}
}
EUVIMED