Improving Forest Above-Ground Biomass Estimation by Integrating Individual Machine Learning Models

Forests, Journal Year: 2024, Volume and Issue: 15(6), P. 975 - 975

Published: June 1, 2024

The accurate estimation of forest above-ground biomass (AGB) is crucial for sustainable management and tracking the carbon cycle ecosystem. Machine learning algorithms have been proven to great potential in AGB with remote sensing data. Though many studies demonstrated that a single machine model can produce highly estimations situations, efforts are still required explore possible improvement specific scenario under study. This study aims investigate performance novel ensemble methods analyzes whether these affected by types, independent variables, spatial autocorrelation. Four well-known models (CatBoost, LightGBM, random (RF), XGBoost) were compared using eight scenarios devised on basis two regions, variable validation strategies. Subsequently, hybrid combining strengths individual was proposed estimation. findings indicated no outperforms others all scenarios. RF demonstrates superior 5, 6, 7, while CatBoost shows best remaining Moreover, consistently has spite some uncertainties. strategy developed this substantially improves accuracy exhibits greater stability, effectively addressing challenge selection encountered forecasting process.

Language: Английский

---

A multi-source approach combining GEDI LiDAR, satellite data, and machine learning algorithms for estimating forest aboveground biomass on Google Earth engine platform

Ecological Informatics, Journal Year: 2025, Volume and Issue: unknown, P. 103052 - 103052

Published: Jan. 1, 2025

Language: Английский

---

Progress and Limitations in Forest Carbon Stock Estimation Using Remote Sensing Technologies: A Comprehensive Review

Forests, Journal Year: 2025, Volume and Issue: 16(3), P. 449 - 449

Published: March 2, 2025

Forests play a key role in carbon sequestration and oxygen production. They significantly contribute to peaking neutrality goals. Accurate estimation of forest stocks is essential for precise understanding the capacity ecosystems. Remote sensing technology, with its wide observational coverage, strong timeliness, low cost, stock research. However, challenges data acquisition processing include variability, signal saturation dense forests, environmental limitations. These factors hinder accurate estimation. This review summarizes current state research on from two aspects, namely remote methods, highlighting both advantages limitations various sources models. It also explores technological innovations cutting-edge field, focusing deep learning techniques, optical vegetation thickness impact forest–climate interactions Finally, discusses including issues related quality, model adaptability, stand complexity, uncertainties process. Based these challenges, paper looks ahead future trends, proposing potential breakthroughs pathways. The aim this study provide theoretical support methodological guidance researchers fields.

Language: Английский

---

Estimation of above ground biomass in tropical heterogeneous forests in India using GEDI

Ecological Informatics, Journal Year: 2024, Volume and Issue: 82, P. 102712 - 102712

Published: June 30, 2024

Quantifying above ground biomass (AGB) and its spatial distribution can significantly contribute to monitor carbon stocks as well the storage dynamics in forests. For effective forest monitoring management case of complex tropical Indian forests, there is a need obtain reliable estimates amount sequestration at regional national levels, but estimation quite challenging. The main objective study validate usefulness gridded density (AGBD) (ton/ha) spaceborne LiDAR Global Ecosystem Dynamics Investigation data (GEDI L4B, Version 2) across two heterogeneous forests India, Betul Mudumalai Methodology includes, for each area, linear regression model which predicts AGB from Sentinel-2 MSI was developed using reference comparing it with GEDI AGBD values. Central India had RMSE 13.9 ton/ha, relative = 8.7% R2 0.88, bias −0.28 comparison between modelled 1 km resolution show relatively strong correlation (0.66) no or little bias. It also found that footprint value underestimated compared according model. southern an 29.1 10.8%, 0.79 −0.022. 0.84, field values lies 42.2 ton/ha 238.8 75.9 353.6 ton/ha. results indicates underestimates AGB, used produce product needs be adjusted provide information on balance changes over time type exists test areas.

Language: Английский

---

Improving aboveground biomass density mapping of arid and semi-arid vegetation by combining GEDI LiDAR, Sentinel-1/2 imagery and field data

Science of Remote Sensing, Journal Year: 2025, Volume and Issue: 11, P. 100204 - 100204

Published: Feb. 6, 2025

Language: Английский

---

Advances in Laser Scanning to Assess Carbon in Forests: From Ground-Based to Space-Based Sensors

Current Forestry Reports, Journal Year: 2025, Volume and Issue: 11(1)

Published: Jan. 22, 2025

Language: Английский

---

From Air to Space: A Comprehensive Approach to Optimizing Aboveground Biomass Estimation on UAV-Based Datasets

Forests, Journal Year: 2025, Volume and Issue: 16(2), P. 214 - 214

Published: Jan. 23, 2025

Estimating aboveground biomass (AGB) is vital for sustainable forest management and helps to understand the contributions of forests carbon storage emission goals. In this study, effectiveness plot-level AGB estimation using height crown diameter derived from UAV-LiDAR, calibration GEDI-L4A GEDI-L2A rh98 heights, spectral variables UAV-multispectral RGB data were assessed. These calibrated values UAV-derived used fit estimations a random (RF) regression model in Fuling District, China. Using Pearson correlation analysis, we identified 10 most important predictor prediction model, including GEDI height, Visible Atmospherically Resistant Index green (VARIg), Red Blue Ratio (RBRI), Difference Vegetation (DVI), canopy cover (CC), (ARVI), Red-Edge Normalized (NDVIre), Color (CIVI), elevation, slope. The results showed that, general, second based on Sentinel-2 indices, slope datasets with evaluation metric (for training: R2 = 0.941 Mg/ha, RMSE 13.514 MAE 8.136 Mg/ha) performed better than first prediction. result was between 23.45 Mg/ha 301.81 standard error 0.14 10.18 Mg/ha. This hybrid approach significantly improves accuracy addresses uncertainties modeling. findings provide robust framework enhancing stock assessment contribute global-scale monitoring, advancing methodologies ecological research.

Language: Английский

---

A data-driven, cloud-based approach for forest aboveground biomass mapping using GEDI and other earth observation data: an ecoregion-specific Investigation across the state of Alabama, USA

Geocarto International, Journal Year: 2025, Volume and Issue: 40(1)

Published: Feb. 19, 2025

Language: Английский

---

A scalable, annual aboveground biomass product for monitoring carbon impacts of ecosystem restoration projects

Remote Sensing of Environment, Journal Year: 2025, Volume and Issue: 327, P. 114774 - 114774

Published: May 22, 2025

Language: Английский

---

Quantifying forest stocking changes in Sundarbans mangrove using remote sensing data

Science of Remote Sensing, Journal Year: 2024, Volume and Issue: unknown, P. 100181 - 100181

Published: Dec. 1, 2024

Language: Английский

---