Regional forest above-ground biomass retrieval by optimized k-NN algorithm in Northeast China

This study explores retrieval of wall-to-wall forest above-ground biomass (AGB) over Jilin province in Northeast China, using the optimized non-parametric k-NN method, the 7
^th
National Forest Inventory (NFI) data, and the remote sensing data: Landsat-TM/ETM+ images. For pixel-based validation, the estimated result was compared to the NFI data by leave-one-out process and R
²
= 0.40 and RMSE = 54.29 tons/hm
²
. For county-scale validation, the result was verified by the intensive forest sub-compartment data of eight county and R
²
= 0.80 and RMSE = 34.26 tons/hm
²
.