Unlocking vegetation health: optimizing GEDI data for accurate chlorophyll content estimation DOI Creative Commons
Cuifen Xia, Wenwu Zhou, Qingtai Shu

et al.

Frontiers in Plant Science, Journal Year: 2024, Volume and Issue: 15

Published: Nov. 29, 2024

Chlorophyll content is a vital indicator for evaluating vegetation health and estimating productivity. This study addresses the issue of Global Ecosystem Dynamics Investigation (GEDI) data discreteness explores its potential in chlorophyll content. used empirical Bayesian Kriging regression prediction (EBKRP) method to obtain continuous distribution GEDI spot parameters an unknown space. Initially, 52 measured sample were employed screen modeling with Pearson RF methods. Next, optimization (BO) algorithm was applied optimize KNN model, RFR Gradient Boosting Regression Tree (GBRT) model. These steps taken establish most effective RS estimation model

Language: Английский

Assessing Above-Ground Biomass Dynamics and Carbon Sequestration Potential Using Machine Learning and Spaceborne LiDAR in Hilly Conifer Forests of Mansehra District, Pakistan DOI Open Access
Muhammad Imran, Guanhua Zhou,

Guifei Jing

et al.

Forests, Journal Year: 2025, Volume and Issue: 16(2), P. 330 - 330

Published: Feb. 13, 2025

Consistent and accurate data on forest biomass carbon dynamics are essential for optimizing sequestration, advancing sustainable management, developing natural climate solutions in various ecosystems. This study quantifies the designated forests based GEDI LiDAR datasets with a unique compartment-level monitoring of unexplored hilly areas Mansehra. The integration multisource explanatory variables, employing machine learning models, adds further innovation to reliable above ground (AGB) estimation. Integrating Landsat-9 vegetation indices ancillary improved estimation, random algorithm yielding best performance (R2 = 0.86, RMSE 28.03 Mg/ha, MAE 19.54 Mg/ha). Validation field point-to-point basis estimated mean above-ground 224.61 closely aligning measurement 208.13 Mg/ha 0.71). overall AGB model 189.42 moist temperate area. A critical deficit sequestration potential was analysed, 2022, at 19.94 thousand tons, 0.83 tons nullify CO2 emissions (20.77 tons). proposes estimation reliability offers insights into potential, suggesting policy shift decision-making change mitigation policies.

Language: Английский

Citations

0
Unlocking vegetation health: optimizing GEDI data for accurate chlorophyll content estimation DOI Creative Commons
Cuifen Xia, Wenwu Zhou, Qingtai Shu

et al.

Frontiers in Plant Science, Journal Year: 2024, Volume and Issue: 15

Published: Nov. 29, 2024

Chlorophyll content is a vital indicator for evaluating vegetation health and estimating productivity. This study addresses the issue of Global Ecosystem Dynamics Investigation (GEDI) data discreteness explores its potential in chlorophyll content. used empirical Bayesian Kriging regression prediction (EBKRP) method to obtain continuous distribution GEDI spot parameters an unknown space. Initially, 52 measured sample were employed screen modeling with Pearson RF methods. Next, optimization (BO) algorithm was applied optimize KNN model, RFR Gradient Boosting Regression Tree (GBRT) model. These steps taken establish most effective RS estimation model

Language: Английский

Citations

0