Continental-scale ICESat canopy height modelling sensitivity and random forest simulations in Australia and Canada

Wednesday, 17 December 2014
Craig Mahoney1, Chris Hopkinson1, Andre Alexander Held2 and Ron Hall3, (1)University of Lethbridge, Lethbridge, AB, Canada, (2)CSIRO Canberra, Canberra, ACT, Australia, (3)Natural Resources Canada - Canadian Forest Service, Northern Forestry Centre, Edmonton, AB, Canada
The Geoscience Laser Altimeter System (GLAS), previously onboard the Ice, Cloud, and land Elevation Satellite (ICESat) uniquely offers near global waveform LiDAR coverage, however, data quality are subject to system, temporal, and spatial issues. These subtleties are investigated here with respect to canopy height comparisons with 3 airborne LiDAR sites in Australia. Optimal GLAS results were obtained from high energy laser transmissions from laser 3 during leaf-on conditions; GLAS data best corresponded with 95th percentile heights from an all return airborne LiDAR point cloud. In addition, best GLAS results were obtained over relatively open canopies, where prominent ground returns can be retrieved.

Optimized GLAS data within Australian forests were employed as canopy height observations, and related to 6 predictor variables (landcover, cover fraction, elevation, slope, soils, and species) by random forest (RF) models. Fifty seven RF models were trained, varying by binomial combinations of predictor data, from 2 to 6 inputs. Trained models were separately utilized to predict Australia wide canopy heights; RF canopy height outputs were validated against spatially concurrent airborne LiDAR 95th percentile canopy heights from an all return point cloud for 10 sites, encompassing multiple ecosystems.

The best RF output was obtained from predictor data inputs: landcover, cover fraction, elevation soils, and species, yielding a RMSE=7.98 m, and R2=0.97. Results indicate inherent issues (noted in existing literature) in GLAS observations that propagate through RF algorithms, manifested as canopy height underestimations for taller vegetation (>45 m).

To extend this research to the Canadian boreal forest context, research is also targeting canopy height model development in the Northwest Territories, allowing investigations of time-variant phenology and landcover sensitivity due to wetland extent and growth, snow cover and other land cover changes common within boreal forest ecosystems.