Skip to content
DraconiticResearch
Search Sources API
186,631 studies31 sourcesUpdated 15 min ago
Peer-reviewedCC BYPLOS One

Monitoring seasonal and long-term forest canopy dynamics using Sentinel-2 imagery and Random Forest on the Google Earth Engine platform

  • Pavan Kumar1
  • Rahul Kumar2
  • Soumyajeet Sahu2
  • Manmohan Dobriyal3
  • Pankaj Lavania1
  • Manish Srivastav4
  • Prem Chandra Pandey5
  • Benson Turyasingura6
6 affiliations
  1. 1Department of Forest Resource Management, College of Horticulture and Forestry, Rani Lakshmi Bai Central Agricultural University, Jhansi, India.
  2. 2Centre of Geospatial Science and Technology, College of Horticulture and Forestry, Rani Lakshmi Bai Central Agricultural University, Jhansi, India.
  3. 3Department of Silviculture and Agroforestry, College of Horticulture and Forestry, Rani Lakshmi Bai Central Agricultural University, Jhansi, India.
  4. 4College of Horticulture and Forestry, Rani Lakshmi Bai Central Agricultural University, Jhansi, India.
  5. 5Department of Life Sciences, School of Natural Sciences (SoNS), Shiv Nadar Institution of Eminence (Deemed to be University), Greater Noida, India.
  6. 6Faculty of Agriculture and Environmental Sciences, Department of Environment and Natural Resources, Kabale University, Kabale, Kampala, Uganda.
Read full textPDFDOICite

Abstract

Understanding forest canopy dynamics is critical for assessing the condition, resilience, and conservation priorities of protected landscapes. This study evaluated the spatiotemporal and seasonal variation in mapped forest canopy density within the Orchha Wildlife Sanctuary, Madhya Pradesh, India, using multi-seasonal Sentinel-2 imagery and a Google Earth Engine (GEE)-based Random Forest (RF) classification framework. Sentinel-2 data for pre-monsoon (March–May) and post-monsoon (October–December) periods in 2016 and 2024 were analyzed independently. Canopy-density information was derived from NDVI, NDMI, elevation, slope, and GLCM texture features and classified into four classes: non-forest, open, moderate, and dense canopy. The same RF procedure was applied to all four season-year datasets using NDVI-informed canopy-density strata and balanced reference sampling. Overall accuracy ranged from 97.80% to 98.95%, with Kappa coefficients of 0.970–0.986. The results indicated clear seasonal and interannual redistribution of mapped canopy-density classes. During the pre-monsoon period, non-forest and open classes decreased by 39.62% and 7.15%, respectively, while moderate and dense classes increased by 231.64% and 240.43%. During the post-monsoon period, moderate canopy increased by 26.01%, whereas dense canopy decreased by 9.46%. Within the common comparison area of 4,533.54 ha, transition analysis revealed substantial class persistence and redistribution, particularly among adjacent canopy-density classes such as open-to-moderate and dense-to-moderate transitions. Spatial changes were distributed across riparian, interior, and peripheral zones. Because 2016 used Level-1C top-of-atmosphere data and 2024 used Level-2A surface-reflectance products, interannual differences should be interpreted as changes in mapped canopy-density classes rather than precise biophysical changes in canopy structure. The framework provides a replicable approach for seasonal forest monitoring and spatially targeted conservation planning.

Related

  1. Seasonal Dynamics, Host Network Structure, and Environmental Drivers of Gamasid Mite Communities on Small Mammals in a Dry-Hot Valley: A Year-Round Monitoring Study.
    Peng-Wu Yin, Yan Lv, Wen-Yu Song +6
    Animals : an open access journal from MDPIPeer-reviewedCC BYFull textEcologyEurope PMC
  2. Monitoring the seasonal functioning of tropical ecosystems with phenocams
    Adeline Fayolle, Léna Royen, Emma R. Bush +7
    African Journal of EcologyPeer-reviewedLicence not statedFull text1 citedEcologyHAL
  3. Winter wheat yield prediction using temporal fusion of multispectral imagery and LiDAR point clouds acquired from a ground-based phenotyping platform
    Haodong Li, Yeping Zhu, Shengping Liu +7
    Frontiers in Plant SciencePeer-reviewedCC BY 4.0Full textEcologyCrossrefEurope PMCPMC
  4. The capability of very high-resolution satellite imagery for plot-level early wheat stem rust disease detection, monitoring, and phenotyping in Ethiopia
    Gerald Blasch, Ashenafi Gemechu, Gizachew Hirpa Regasa +5
    Scientific ReportsPeer-reviewedCC BY 4.0EcologyCrossref
  5. Seasonal wetting and drying dynamics drive greenhouse gas emissions across Australia’s river network
    Adam T. Rexroade, Marcus B. Wallin, Dylan J. Irvine +5
    Communications Earth & EnvironmentPeer-reviewedCC BY-NC-ND 4.0Full textEcologyCrossref

Cite

BibTeXRIS
BibTeX
@article{kumar2026monitoring,
  title = {{Monitoring seasonal and long-term forest canopy dynamics using Sentinel-2 imagery and Random Forest on the Google Earth Engine platform}},
  author = {Pavan Kumar and Rahul Kumar and Soumyajeet Sahu and Manmohan Dobriyal and Pankaj Lavania and Manish Srivastav and Prem Chandra Pandey and Benson Turyasingura},
  journal = {PLOS One},
  year = {2026},
  month = oct,
  doi = {10.1371/journal.pone.0361024},
  url = {https://doi.org/10.1371/journal.pone.0361024},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - Monitoring seasonal and long-term forest canopy dynamics using Sentinel-2 imagery and Random Forest on the Google Earth Engine platform
AU  - Pavan Kumar
AU  - Rahul Kumar
AU  - Soumyajeet Sahu
AU  - Manmohan Dobriyal
AU  - Pankaj Lavania
AU  - Manish Srivastav
AU  - Prem Chandra Pandey
AU  - Benson Turyasingura
PY  - 2026
DA  - 2026/10/21
JO  - PLOS One
DO  - 10.1371/journal.pone.0361024
UR  - https://doi.org/10.1371/journal.pone.0361024
AB  - Understanding forest canopy dynamics is critical for assessing the condition, resilience, and conservation priorities of protected landscapes. This study evaluated the spatiotemporal and seasonal variation in mapped forest canopy density within the Orchha Wildlife Sanctuary, Madhya Pradesh, India, using multi-seasonal Sentinel-2 imagery and a Google Earth Engine (GEE)-based Random Forest (RF) classification framework. Sentinel-2 data for pre-monsoon (March–May) and post-monsoon (October–December) periods in 2016 and 2024 were analyzed independently. Canopy-density information was derived from NDVI, NDMI, elevation, slope, and GLCM texture features and classified into four classes: non-forest, open, moderate, and dense canopy. The same RF procedure was applied to all four season-year datasets using NDVI-informed canopy-density strata and balanced reference sampling. Overall accuracy ranged from 97.80% to 98.95%, with Kappa coefficients of 0.970–0.986. The results indicated clear seasonal and interannual redistribution of mapped canopy-density classes. During the pre-monsoon period, non-forest and open classes decreased by 39.62% and 7.15%, respectively, while moderate and dense classes increased by 231.64% and 240.43%. During the post-monsoon period, moderate canopy increased by 26.01%, whereas dense canopy decreased by 9.46%. Within the common comparison area of 4,533.54 ha, transition analysis revealed substantial class persistence and redistribution, particularly among adjacent canopy-density classes such as open-to-moderate and dense-to-moderate transitions. Spatial changes were distributed across riparian, interior, and peripheral zones. Because 2016 used Level-1C top-of-atmosphere data and 2024 used Level-2A surface-reflectance products, interannual differences should be interpreted as changes in mapped canopy-density classes rather than precise biophysical changes in canopy structure. The framework provides a replicable approach for seasonal forest monitoring and spatially targeted conservation planning.
SN  - 1932-6203
ER  -