A Comparison of Imputation Approaches for Estimating Forest Biomass Using Landsat Time-Series and Inventory Data

Abstract

The prediction of forest biomass at the landscape scale can be achieved by integrating data from field plots with satellite imagery, in particular data from the Landsat archive, using k-nearest neighbour (kNN) imputation models. While studies have demonstrated different kNN imputation approaches for estimating forest biomass from remote sensing data and forest inventory plots, there is no general agreement on which approach is most appropriate for biomass estimation across large areas. In this study, we compared several imputation approaches for estimating forest biomass using Landsat time-series and inventory plot data. We evaluated 18 kNN models to impute three aboveground biomass (AGB) variables (total AGB, AGB of live trees and AGB of dead trees). These models were developed using different distance techniques (Random Forest or RF, Gradient Nearest Neighbour or GNN, and Most Similar Neighbour or MSN) and different combinations of response variables (model scenarios). Direct biomass imputation models were trained according to the biomass variables while indirect biomass imputation models were trained according to combinations of forest structure variables (e.g., basal area, stem density and stem volume of live and dead-standing trees). We also assessed the ability of our imputation method to spatially predict biomass variables across large areas in relation to a forest disturbance history over a 30-year period (1987-2016). Our results show that RF consistently outperformed MSN and GNN distance techniques across different model scenarios and biomass variables. The lowest error rates were achieved by RF-based models with generalized root mean squared difference (gRMSD, RMSE divided by the standard deviation of the observed values) ranging from 0.74 to 1.24. Whereas gRMSD associated with MSN-based and GNN-based models ranged from 0.92 to 1.36 and from 1.04 to 1.42, respectively. The indirect imputation method generally achieved better biomass predictions than the direct imputation method. In particular, the kNN model trained with the combination of basal area and stem density variables was the most robust for estimating forest biomass. This model reported a gRMSD of 0.89, 0.95 and 1.08 for total AGB, AGB of live trees and AGB of dead trees, respectively. In addition, spatial predictions of biomass showed relatively consistent trends with disturbance severity and time since disturbance across the time-series. As the kNN imputation method is increasingly being used by land managers and researchers to map forest biomass, this work helps those using these methods ensure their modelling and mapping practices are optimized.

Spatiotemporal Variations of Aboveground Biomass under Different Terrain Conditions

“…In terms of tasseled cap, its components have been widely used in biomass estimation [14,21,39]. Brightness, greenness, and wetness were successively selected as important predictor variables, similar to other Landsat-related biomass estimation research [40]. However, it has been stated that Landsat 8 has a refined near-infrared spectral band for more accurate spectral acquisition when compared to the Landsat former series [11], but the advantage in the near-infrared band of OLI Band 5 over TM Band 4 remains to be further investigated.…”

Improving Aboveground Forest Biomass Maps: From High-Resolution to National Scale

“…Our MODIS model relative RMSE (48.47%) was consistent with other studies such as that of Reference [79], which revealed an RMSE% of 69% for aboveground tree biomass estimated by NFI ground plots and 250 m MODIS data. However, other studies, which a large amount of Landsat data, provided lower RMSE% at regional scale [80].…”

Landsat Time-Series for Estimating Forest Aboveground Biomass and Its Dynamics across Space and Time: A Review

“…For example, Matasci, Hermosilla [51] and Nguyen, Jones [52] used this method for large area predictions of AGB dynamics through 30-year periods in Canada and southeast Australia, respectively. Studies comparing different kNN distance techniques used for imputing forest attributes often indicated the outperformance of RF [8,56,96].…”

“…The accuracy of AGB predictions can be enhanced as it is imputed based on another variable (or group of variables) that has higher correlation with predictors. Nguyen, Jones [56] found that AGB can be better predicted using an indirect imputation approach combining a group of basal area and stem density variables with LTS. In addition, other forest attributes, along with AGB, can be mapped directly without new model developments.…”