Improving post-fire GEDI canopy height accuracy and canopy height mapping through convolutional neural network model

Abstract

ABSTRACT The Global Ecosystem Dynamics Investigation (GEDI) LiDAR data have been widely used to measure tree canopy heights. However, due to the altered GEDI waveform geometry in the fire-consumed canopy layers, it is challenging to accurately detect diminished signals with the original GEDI threshold settings, which may lead to underestimation of canopy height under extreme fire conditions. In this study, we delve into the relationship between the accuracy of post-fire GEDI canopy height and front thresholds applied to GEDI waveforms. Notably, thresholds 3σ and 6σ from the GEDI settings proved too high to detect burnt canopy signals, resulting in the lowest accuracy and substantial underestimation. In contrast, the 1σ threshold achieved the highest accuracy. Subsequently, a 1D CNN model was developed to calibrate post-fire GEDI canopy height, utilizing L1B waveforms as input, resulting in a significant reduction of RMSE from 12.2 m to 6.7 m and the elimination of canopy height underestimation in high and extreme fire severity scenarios. In the third experiment, a 2D CNN model was constructed for mapping calibrated canopy height with Sentinel-2 images, revealing a noteworthy drop in RMSE from 14.6 m to 8.5 m compared to the same model using original GEDI canopy height.