Integrating Remotely Sensed Data to Reconcile Gaps in Growing Stock Volume Accounting for National Forest Inventory

National forest inventory (NFI) data are often collected over a 5-year or 10-year period, meaning some are already outdated by the time the complete results are available. This study assesses changes in growing stock volume (GSV, m3/ha) using hybrid estimation supported by Sentinel-2 metrics. It focuses on constructing a model for estimating the change in GSV using NFI plot data and bitemporal remotely sensed auxiliary data, where such data are available for both points in time (t1 and t2), and unitemporal data for which remotely sensed auxiliary data are available only for t2. A machine-learning approach based on the random forests (RFs) algorithm was used to predict plot-level GSV change. The original data for t2 and t3 were first used to evaluate the accuracy of the change prediction at the plot level, after which the predicted changes were applied to update the plot-level GSV to predict plot-level GSV at t3, which was then assessed against the observed plot-level GSV at t3. Predicted change was assessed with the Mean Average Annual Volume Change (MAAVC) method, representing the average annual change in GSV over a given period. The results indicate that at the plot level, the bitemporal model produced GSV change estimates with low accuracy (R2 = 0.26, RMSE = 4.06 m3/ha, and MAE = 3.26 m3/ha), while the unitemporal model achieved R2 = 0.40, RMSE = 3.64 m3/ha, and MAE = 2.65 m3/ha when predicting the t1− t2 GSV change. Using the predicted change to predict plot-level GSV at t3, the MAAVC based on field data yielded R2 = 0.91 and RMSE = 45.11 m3/ha, while the RS unitemporal yielded R2 = 0.73 and RMSE = 83.79 m3/ha, and the bitemporal yielded R2 = 0.72 and RMSE = 83.61 m3/ha. Mean population GSV at t3, estimated from the RF models, was 254.61 and 255.19 m3/ha for the unitemporal and bitemporal models, respectively. Monte Carlo simulations with a novel stopping criterion were then used to estimate total standard errors, which were 10.48 and 10.40 m3/ha for the unitemporal and bitemporal models, respectively, incorporating both model prediction uncertainty and sampling variability. A test of significance revealed a significant effect of the proposed method on the estimated mean population GSV at t3 (p < 0.001). Conclusively, MAAVC and spatiotemporal RS methods provide a robust framework for predicting GSV at t3 using Estonian NFI and Sentinel-2 data.