Browsing by Author "Garge Sandhya Kiran"

Now showing 1 - 3 of 3

Harnessing Spectral Libraries From AVIRIS-NG Data for Precise PFT Classification: A Deep Learning Approach
(John Wiley and Sons Inc, 2025) Agradeep Mohanta; Garge Sandhya Kiran; Ramandeep Kaur M. Malhi; Pankajkumar C. Prajapati; Kavi K. Oza; Shrishti Rajput; Sanjay S. Shitole; Prashant Kumar Srivastava
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. © 2025 John Wiley & Sons Ltd.
Satellites for forest monitoring and mapping
(Elsevier, 2025) Ramandeep Kaur M. Malhi; Agradeep Mohanta; Pankajkumar C. Prajapati; Prem C. Pandey; Shrishti Rajput; Prashant Kumar Srivastava; Garge Sandhya Kiran
The crucial role of forest monitoring in maintaining global ecological balance, with a particular focus on remote sensing technologies, is explored in this chapter. Forests, essential for biodiversity conservation, climate change mitigation, and supporting livelihoods, are increasingly threatened by human activities such as deforestation and habitat destruction. Given the vast and often remote nature of forests, traditional monitoring approaches are becoming insufficient, making the use of advanced remote sensing technologies—spanning satellites, aircraft, drones, and ground-based sensors—essential. These technologies provide invaluable data on forest parameters, including canopy cover, biomass, forest health, and species diversity, all critical for informed forest management and conservation efforts. Remote sensing offers unparalleled advantages, including large-scale coverage, temporal consistency, and detailed data that are essential for tracking forest changes over time. The chapter delves into the electromagnetic spectrum’s role in forest monitoring, particularly focusing on visible, near-infrared, and microwave wavelengths. It further explores the various satellite platforms—optical, radar, hyperspectral, and LiDAR—each contributing unique strengths and facing specific limitations. By combining data from multiple sensor types, a more comprehensive understanding of forest dynamics is achieved, aiding in the detection of forest degradation and biodiversity loss. Moreover, the chapter highlights the importance of remote sensing in enhancing conservation strategies, reducing disturbance impacts such as wildfires, and supporting sustainable forest management decisions. It concludes by reflecting on the global shift towards remote sensing-driven forest monitoring and its transformative potential for guiding policies aimed at protecting forest ecosystems and promoting the sustainable use of forest resources for the benefit of both the environment and human societies. © 2026 Elsevier Inc. All rights reserved..
Traditional ground-based and geospatial approaches for aboveground biomass estimation of forest trees
(Elsevier, 2025) Ramandeep Kaur M. Malhi; Garge Sandhya Kiran; Prashant Kumar Srivastava
Forests are essential for regulating global carbon balance, controlling the rise of greenhouse gas concentrations in the atmosphere, protecting biodiversity, and ensuring a stable global climate. Quantification of forest biomass is imperative to comprehend forest carbon cycling, resource development, and carbon storage estimates. The measurement, monitoring, and evaluation of forest aboveground biomass (AGB) have now become a growing area of interest for researchers worldwide. Moreover, it is critical to employ a proper and rigorous method to accurately assess forest biomass. The methodologies for AGB estimations of forest trees are covered in this chapter. Traditional ground-based techniques are described, including a destructive approach that necessitates tree felling and a nondestructive approach for AGB calculations. Although the conventional traditional destructive approach is seen to be the most precise and dependable approach, it is also the most time- and money-consuming, difficult, and cannot be used to cover vast regions. Nondestructive traditional techniques also take up a lot of time and resources. Allometric equations-based indirect methods of AGB estimations are established by relating AGB to various forest characteristics, including diameter at breast height and height of forest tree and are less time- and money-consuming. Geospatial approaches are also extensively used by researchers for estimating AGB of forest trees. This technique allows accurate spatiotemporal quantification of AGB and is both cost- and time-effective. It can be used to estimate AGB for sizable forest areas. For AGB estimations, a variety of geospatial data, including optical, microwave, combined optical and microwave, hyperspectral, light detection and ranging, drones, and unmanned aerial vehicles, are extensively investigated. © 2026 Elsevier Inc. All rights reserved..