Predicting forest above-ground biomass using SAR imagery and GEDI data through machine learning in GEE cloud

The estimation of Forest above-ground biomass (AGB) is critical for comprehending forest ecosystems and promoting biodiversity restoration. The study was conducted to develop an effective approach to predict Forest Above-Ground Biomass (AGB) using Machine Learning, Image Classification, and GEE open...

Full description

Saved in:
Bibliographic Details
Main Authors: Chiranjit Singha, Kishore Chandra Swain, Satiprasad Sahoo, Ayad M. Fadhil Al-Quraishi, Joseph Omeiza Alao, Hussein Almohamad, Mohamed Fatahalla Mohamed Ahmed, Hazem Ghassan Abdo
Format: Article
Language:English
Published: Taylor & Francis Group 2025-04-01
Series:Forest Science and Technology
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/21580103.2025.2481122
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849335484188196864
author Chiranjit Singha
Kishore Chandra Swain
Satiprasad Sahoo
Ayad M. Fadhil Al-Quraishi
Joseph Omeiza Alao
Hussein Almohamad
Mohamed Fatahalla Mohamed Ahmed
Hazem Ghassan Abdo
author_facet Chiranjit Singha
Kishore Chandra Swain
Satiprasad Sahoo
Ayad M. Fadhil Al-Quraishi
Joseph Omeiza Alao
Hussein Almohamad
Mohamed Fatahalla Mohamed Ahmed
Hazem Ghassan Abdo
author_sort Chiranjit Singha
collection DOAJ
description The estimation of Forest above-ground biomass (AGB) is critical for comprehending forest ecosystems and promoting biodiversity restoration. The study was conducted to develop an effective approach to predict Forest Above-Ground Biomass (AGB) using Machine Learning, Image Classification, and GEE open-source fast processing system in the Similipal Tiger Reserve (STR), India. The study utilized six machine learning models and integrated various data sources, including Sentinel-1 and Sentinel-2 imagery, forest canopy height data from NASA’s GEDI Global Ecosystems Dynamics Investigation-LiDAR, geo-environmental Shuttle Radar Topography Mission (SRTM) data, and Climate Hazards Group Infrared precipitation with Station (CHIRPS) data. Sentinel-based optical and Synthetic Aperture Radar (SAR) signatures were also extracted before and after the monsoon season to evaluate AGB in a subtropical region. The Random forest-based Boruta method was used to examine the importance of multiple factors contributing to the prediction’s accuracy. In addition, the assessment of multicollinearity, which is accomplished by measuring the variance inflation factor (VIF), was carried out to address the issue of interrelatedness among variables that could affect the accuracy of the AGB mapping. The Random Forest model exhibited superior accuracy compared to other models, achieving an R2 of 0.71, MAE of 16.12Mg/ha, RMSD of 22.27Mg/ha, NRMSD of 0.212, and AUROC of 75%. The scatterplot analysis revealed a positive correlation between forest biomass and factors, such as forest canopy height, elevation, normalized differential vegetation index, normalized differential moisture index, and the ratio of VV/VH after the monsoon season. The VIF values ranged between 1.12 and 8.73, with VH_Jan_Mar having the maximum VIF and forest canopy height having the minimum VIF. As per the Boruta algorithm, 16 attributes were deemed important, while 14 attributes had less influence on AGB. The study presented a novel approach for estimating biomass in subtropical regions using remote sensing data set and machine learning models in Google platform. These results can be successfully used by the planners of STR for monitoring variation in AGB ensuring better habitat for wild animals.
format Article
id doaj-art-51ee3db6409141d5bfa363659e7b74f4
institution Kabale University
issn 2158-0103
2158-0715
language English
publishDate 2025-04-01
publisher Taylor & Francis Group
record_format Article
series Forest Science and Technology
spelling doaj-art-51ee3db6409141d5bfa363659e7b74f42025-08-20T03:45:15ZengTaylor & Francis GroupForest Science and Technology2158-01032158-07152025-04-0121218720610.1080/21580103.2025.2481122Predicting forest above-ground biomass using SAR imagery and GEDI data through machine learning in GEE cloudChiranjit Singha0Kishore Chandra Swain1Satiprasad Sahoo2Ayad M. Fadhil Al-Quraishi3Joseph Omeiza Alao4Hussein Almohamad5Mohamed Fatahalla Mohamed Ahmed6Hazem Ghassan Abdo7Department of Agricultural Engineering, Institute of Agriculture, Visva-Bharati (A Central University), Sriniketan, Birbhum, West Bengal, IndiaDepartment of Agricultural Engineering, Institute of Agriculture, Visva-Bharati (A Central University), Sriniketan, Birbhum, West Bengal, IndiaInternational Center for Agricultural Research in the Dry Areas (ICARDA), Maadi, Cairo, EgyptPetroleum and Mining Engineering Department, Faculty of Engineering, Tishk International University, Erbil, Kurdistan Region, IRAQDepartment of Physics, Air Force Institute of Technology, Kaduna, NigeriaDepartment of Geography, College of Languages and Human Sciences, Qassim University, Buraydah, Saudi ArabiaDepartment of Social Sciences, Faculty of Arts, University of Hail, Hail, Saudi ArabiaGeography Department, Faculty of Arts and Humanities, Tartous University, Tartous, Syria.The estimation of Forest above-ground biomass (AGB) is critical for comprehending forest ecosystems and promoting biodiversity restoration. The study was conducted to develop an effective approach to predict Forest Above-Ground Biomass (AGB) using Machine Learning, Image Classification, and GEE open-source fast processing system in the Similipal Tiger Reserve (STR), India. The study utilized six machine learning models and integrated various data sources, including Sentinel-1 and Sentinel-2 imagery, forest canopy height data from NASA’s GEDI Global Ecosystems Dynamics Investigation-LiDAR, geo-environmental Shuttle Radar Topography Mission (SRTM) data, and Climate Hazards Group Infrared precipitation with Station (CHIRPS) data. Sentinel-based optical and Synthetic Aperture Radar (SAR) signatures were also extracted before and after the monsoon season to evaluate AGB in a subtropical region. The Random forest-based Boruta method was used to examine the importance of multiple factors contributing to the prediction’s accuracy. In addition, the assessment of multicollinearity, which is accomplished by measuring the variance inflation factor (VIF), was carried out to address the issue of interrelatedness among variables that could affect the accuracy of the AGB mapping. The Random Forest model exhibited superior accuracy compared to other models, achieving an R2 of 0.71, MAE of 16.12Mg/ha, RMSD of 22.27Mg/ha, NRMSD of 0.212, and AUROC of 75%. The scatterplot analysis revealed a positive correlation between forest biomass and factors, such as forest canopy height, elevation, normalized differential vegetation index, normalized differential moisture index, and the ratio of VV/VH after the monsoon season. The VIF values ranged between 1.12 and 8.73, with VH_Jan_Mar having the maximum VIF and forest canopy height having the minimum VIF. As per the Boruta algorithm, 16 attributes were deemed important, while 14 attributes had less influence on AGB. The study presented a novel approach for estimating biomass in subtropical regions using remote sensing data set and machine learning models in Google platform. These results can be successfully used by the planners of STR for monitoring variation in AGB ensuring better habitat for wild animals.https://www.tandfonline.com/doi/10.1080/21580103.2025.2481122Forest above-ground biomassbiospheremachine learningsentinel imageryenvironment
spellingShingle Chiranjit Singha
Kishore Chandra Swain
Satiprasad Sahoo
Ayad M. Fadhil Al-Quraishi
Joseph Omeiza Alao
Hussein Almohamad
Mohamed Fatahalla Mohamed Ahmed
Hazem Ghassan Abdo
Predicting forest above-ground biomass using SAR imagery and GEDI data through machine learning in GEE cloud
Forest Science and Technology
Forest above-ground biomass
biosphere
machine learning
sentinel imagery
environment
title Predicting forest above-ground biomass using SAR imagery and GEDI data through machine learning in GEE cloud
title_full Predicting forest above-ground biomass using SAR imagery and GEDI data through machine learning in GEE cloud
title_fullStr Predicting forest above-ground biomass using SAR imagery and GEDI data through machine learning in GEE cloud
title_full_unstemmed Predicting forest above-ground biomass using SAR imagery and GEDI data through machine learning in GEE cloud
title_short Predicting forest above-ground biomass using SAR imagery and GEDI data through machine learning in GEE cloud
title_sort predicting forest above ground biomass using sar imagery and gedi data through machine learning in gee cloud
topic Forest above-ground biomass
biosphere
machine learning
sentinel imagery
environment
url https://www.tandfonline.com/doi/10.1080/21580103.2025.2481122
work_keys_str_mv AT chiranjitsingha predictingforestabovegroundbiomassusingsarimageryandgedidatathroughmachinelearningingeecloud
AT kishorechandraswain predictingforestabovegroundbiomassusingsarimageryandgedidatathroughmachinelearningingeecloud
AT satiprasadsahoo predictingforestabovegroundbiomassusingsarimageryandgedidatathroughmachinelearningingeecloud
AT ayadmfadhilalquraishi predictingforestabovegroundbiomassusingsarimageryandgedidatathroughmachinelearningingeecloud
AT josephomeizaalao predictingforestabovegroundbiomassusingsarimageryandgedidatathroughmachinelearningingeecloud
AT husseinalmohamad predictingforestabovegroundbiomassusingsarimageryandgedidatathroughmachinelearningingeecloud
AT mohamedfatahallamohamedahmed predictingforestabovegroundbiomassusingsarimageryandgedidatathroughmachinelearningingeecloud
AT hazemghassanabdo predictingforestabovegroundbiomassusingsarimageryandgedidatathroughmachinelearningingeecloud