DeepBioFusion: Multi-modal deep learning based above ground biomass estimation using SAR and optical satellite images

Accurate estimation of forest above-ground biomass (AGB) is essential for ecosystem conservation, sustainable forest management, and mitigating climate change and wildfire risks. Traditional methods, such as manual field surveys, are labor-intensive and limited in scope. This study presents DeepBioF...

Full description

Saved in:
Bibliographic Details
Main Authors: Abdul Hanan, Mehak Khan, Nieves Fernandez-Anez, Reza Arghandeh
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:Ecological Informatics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1574954125002869
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849233618209079296
author Abdul Hanan
Mehak Khan
Nieves Fernandez-Anez
Reza Arghandeh
author_facet Abdul Hanan
Mehak Khan
Nieves Fernandez-Anez
Reza Arghandeh
author_sort Abdul Hanan
collection DOAJ
description Accurate estimation of forest above-ground biomass (AGB) is essential for ecosystem conservation, sustainable forest management, and mitigating climate change and wildfire risks. Traditional methods, such as manual field surveys, are labor-intensive and limited in scope. This study presents DeepBioFusion, a multi-modal deep learning framework that first estimates AGB for validation as ground truth generation by using LiDAR-derived tree heights and a Tree Species map, employing allometry equations to relate tree height to Diameter at Breast Height (DBH). After this initial estimation, the framework is trained to predict AGB using high-resolution optical imagery and multiple bands of Synthetic Aperture Radar (SAR), including X, C, and L bands. The use of SAR bands enables improved canopy penetration, particularly in dense and cloud-covered forests. DeepBioFusion leverages the complementary strengths of SAR and optical data to enhance the accuracy of biomass predictions. Benchmarking against models like ResNet50 and Transformer, the proposed model demonstrates superior performance in AGB estimation across diverse forest environments. This study offers a scalable, cutting-edge approach to biomass monitoring, advancing efforts in climate change mitigation and sustainable forest management.
format Article
id doaj-art-e0096455a5964be8a26b99b87c3a6150
institution Kabale University
issn 1574-9541
language English
publishDate 2025-12-01
publisher Elsevier
record_format Article
series Ecological Informatics
spelling doaj-art-e0096455a5964be8a26b99b87c3a61502025-08-20T05:05:31ZengElsevierEcological Informatics1574-95412025-12-019010327710.1016/j.ecoinf.2025.103277DeepBioFusion: Multi-modal deep learning based above ground biomass estimation using SAR and optical satellite imagesAbdul Hanan0Mehak Khan1Nieves Fernandez-Anez2Reza Arghandeh3Department of Computer Science, Electrical Engineering and Mathematical Sciences, Western Norway University of Applied Sciences, Bergen, 5020, Norway; Corresponding author.Department of Computer Science, Electrical Engineering and Mathematical Sciences, Western Norway University of Applied Sciences, Bergen, 5020, NorwayDepartment of Safety, Chemistry and Biomedical Laboratory Sciences, Western Norway University of Applied Sciences, Haugesund, 5528, NorwayDepartment of Computer Science, Electrical Engineering and Mathematical Sciences, Western Norway University of Applied Sciences, Bergen, 5020, NorwayAccurate estimation of forest above-ground biomass (AGB) is essential for ecosystem conservation, sustainable forest management, and mitigating climate change and wildfire risks. Traditional methods, such as manual field surveys, are labor-intensive and limited in scope. This study presents DeepBioFusion, a multi-modal deep learning framework that first estimates AGB for validation as ground truth generation by using LiDAR-derived tree heights and a Tree Species map, employing allometry equations to relate tree height to Diameter at Breast Height (DBH). After this initial estimation, the framework is trained to predict AGB using high-resolution optical imagery and multiple bands of Synthetic Aperture Radar (SAR), including X, C, and L bands. The use of SAR bands enables improved canopy penetration, particularly in dense and cloud-covered forests. DeepBioFusion leverages the complementary strengths of SAR and optical data to enhance the accuracy of biomass predictions. Benchmarking against models like ResNet50 and Transformer, the proposed model demonstrates superior performance in AGB estimation across diverse forest environments. This study offers a scalable, cutting-edge approach to biomass monitoring, advancing efforts in climate change mitigation and sustainable forest management.http://www.sciencedirect.com/science/article/pii/S1574954125002869Above Ground BiomassSynthetic Aperture Radar (SAR)Machine learningMulti-modalDiameter at Breast Height (DBH)Optical and SAR fusion
spellingShingle Abdul Hanan
Mehak Khan
Nieves Fernandez-Anez
Reza Arghandeh
DeepBioFusion: Multi-modal deep learning based above ground biomass estimation using SAR and optical satellite images
Ecological Informatics
Above Ground Biomass
Synthetic Aperture Radar (SAR)
Machine learning
Multi-modal
Diameter at Breast Height (DBH)
Optical and SAR fusion
title DeepBioFusion: Multi-modal deep learning based above ground biomass estimation using SAR and optical satellite images
title_full DeepBioFusion: Multi-modal deep learning based above ground biomass estimation using SAR and optical satellite images
title_fullStr DeepBioFusion: Multi-modal deep learning based above ground biomass estimation using SAR and optical satellite images
title_full_unstemmed DeepBioFusion: Multi-modal deep learning based above ground biomass estimation using SAR and optical satellite images
title_short DeepBioFusion: Multi-modal deep learning based above ground biomass estimation using SAR and optical satellite images
title_sort deepbiofusion multi modal deep learning based above ground biomass estimation using sar and optical satellite images
topic Above Ground Biomass
Synthetic Aperture Radar (SAR)
Machine learning
Multi-modal
Diameter at Breast Height (DBH)
Optical and SAR fusion
url http://www.sciencedirect.com/science/article/pii/S1574954125002869
work_keys_str_mv AT abdulhanan deepbiofusionmultimodaldeeplearningbasedabovegroundbiomassestimationusingsarandopticalsatelliteimages
AT mehakkhan deepbiofusionmultimodaldeeplearningbasedabovegroundbiomassestimationusingsarandopticalsatelliteimages
AT nievesfernandezanez deepbiofusionmultimodaldeeplearningbasedabovegroundbiomassestimationusingsarandopticalsatelliteimages
AT rezaarghandeh deepbiofusionmultimodaldeeplearningbasedabovegroundbiomassestimationusingsarandopticalsatelliteimages