Forest stand height predicted from ICESat-2 ATLAS data for forest inventory and comparison to airborne laser scanning metrics

The study analysed 2019–2022 summertime canopy height predictions (H_ICESat) given in ICESat-2 ATLAS dataset ATL08 for hemiboreal forests growing on an area of 40,000 km² in Estonia around 25.6° E, 58.8° N. In total 12,711 ATL08 20×20 m pixel observations were used from 3,065 forest stands with homogenous canopy structure. Regression modelling was used to explain variability in ground surface elevation estimates, and relationships of H_ICESat to basal area weighted mean tree height given in the forest inventory database (H_FI) and to the 95th percentile of the vertical distribution of airborne laser scanning pulse return (H_ALS). The other explanatory variables were the ICESat-2 ATLAS observation geographic location, ICESat-2 ATLAS track and beam energy indicators, forest canopy cover, evergreen coniferous tree dominance indicator, and deep peat soil indicator. The linear model between the Estonian digital terrain model elevation and ATL08 ground elevation had a determination coefficient of R²=99.97% and residual standard error of δ=0.51 m when a geographic location was included. The H_FI can be predicted from H_ICESat with R²=85% and δ=2.7 m. A comparison of means indicated that, on average, H_ICESat was about 0.3 m greater than H_FI. All the predictive variables (except the geographic location) were significant in canopy height models, and the best models fitted H_ICESat with R²=95% and δ=1.6 m, however, there was no notable increase in R² if more predictors than H_ALS were added in the models. In practical applications using ATL08 data for forest inventories, the inclusion of weak energy beam observations increases the number of observations, but the beam energy indicator has to be included in the models.