Machine Learning Based Modeling for Forest Aboveground Biomass Retrieval

This study aims at evaluating the potential of Support Vector Machine (SVM) and Random Forest (RF) algorithm for the prediction of forest aboveground biomass. In this study, mean forest aboveground biomass density (AGBD) data obtained from GEDI L4B product, Normalized Difference Vegetation Index (NDVI) and Enhanced Vegetation Index (EVI) from Moderate Resolution Imaging Spectroradiometer (MODIS) at 1km spatial resolution for Uttarakhand region. Uttarakhand falls under biodiversity rich region and consists of enormous resources such as forests, glaciers, river etc. The machine learning algorithm SVM and RF was trained using AGBD GEDI, NDVI and EVI data. RF achieved an absolute training accuracy having root mean square error (RMSE) of 38.95 Mg/ha, Pearson correlation coefficient (r) of 0.89 and bias as -0.01 whereas testing conveyed RMSE, r and bias as 71.09Mg/ha,0.45 and -0.02 respectively. On the basis of correlation derived from RF model between biomass, NDVI and EVI, a potential biomass map was generated using raster prediction in R software package. The predicted biomass map has biomass ranging from 67.05Mg/ha to 348.65Mg/ha as compared to the GEDI L4B product biomass map provided which ranges from 52.64 to 400.43Mg/h. These biomass datasets show a moderate correlation (r=0.41), but, show a similar pattern of distribution across the study area. RF outperformed the SVM (polynomial) and SVM (RBF) but further need to explore the biomass estimation using some deep learning (i.e., CNN) and ensemble models.

• Publication year

  2023

• Venue

  2023 International Conference on Machine Intelligence for GeoAnalytics and Remote Sensing (MIGARS)

• Publication date

  2023-01-27

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1109/MIGARS57353.2023.10064607
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Logistics Distribution Path Optimization Using Support Vector Machine Algorithm under Different Constraints

  2022cited by this paper
• Forest above-ground woody biomass estimation using multi-temporal space-borne LiDAR data in a managed forest at Haldwani, India

  2022cited by this paper
• Estimation of aboveground biomass from PolSAR and PolInSAR using regression-based modelling techniques

  2021cited by this paper
• Forest microclimates and climate change: Importance, drivers and future research agenda

  2021cited by this paper
• Global Change and Forest Disturbances in the Mediterranean Basin: Breakthroughs, Knowledge Gaps, and Recommendations

  2021cited by this paper
• Highly Local Model Calibration with a New GEDI LiDAR Asset on Google Earth Engine Reduces Landsat Forest Height Signal Saturation

  2020cited by this paper
• Prediction of discharge coefficient of combined weir-gate using ANN, ANFIS and SVM

  2019cited by this paper
• An assessment of global satellite‐based precipitation datasets in capturing precipitation extremes: A comparison with observed precipitation dataset in India

  2019cited by this paper
• Quantifying Forest Biomass Carbon Stocks From Space

  2017cited by this paper
• Comparison of three modeling methods for estimating forest biomass using TM, GLAS and field measurement data

  2017cited by this paper
• Random forest regression modelling for forest aboveground biomass estimation using RISAT-1 PolSAR and terrestrial LiDAR data

  2016cited by this paper
• Learning Deep Features for Discriminative Localization

  2015cited by this paper
• POLINSAR Coherence-Based Regression Analysis of Forest Biomass Using RADARSAT-2 Datasets

  2014cited by this paper
• Using satellite radar backscatter to predict above‐ground woody biomass: A consistent relationship across four different African landscapes

  2009cited by this paper
• Importance of biomass in the global carbon cycle

  2009cited by this paper
• Properties of ERS-1/2 coherence in the Siberian boreal forest and implications for stem volume retrieval

  2007cited by this paper
• Monitoring and estimating tropical forest carbon stocks: making REDD a reality

  2007cited by this paper
• Remote Sensing and Spatial Information Sciences

  2005cited by this paper

• Advancing fire regime assessment in the Indian Himalayan forests using GEDI LiDAR

  2026cites this paper
• Enhanced aboveground biomass density estimation in Central Vietnamese forests

  2025cites this paper
• Mapping forest above-ground biomass of coniferous forest in northern China by integrating simultaneous multi-angle spectral and full-waveform observations using the TECIS system

  2025cites this paper
• Time-series reconstruction and mapping of forest aboveground biomass in the Great Xing’an Mountains of China using GEDI, MODIS, and machine learning

  2025cites this paper
• Forest aboveground biomass estimation by GEDI and multi-source EO data fusion over Indian forest

  2024cites this paper
• Forest Aboveground Biomass Estimation Using GEDI Observations Over Indian Forest

  2024cites this paper
• AGBUNet: an enhanced CNN-UNET architecture for the prediction of above ground biomass using deep learning

  2024cites this paper
• Total and component forest aboveground biomass inversion via LiDAR-derived features and machine learning algorithms

  2023cites this paper