Regional Forest Volume Estimation by Expanding LiDAR Samples Using Multi-Sensor Satellite Data

Abstract

Accurate information regarding forest volume plays an important role in estimating afforestation, timber harvesting, and forest ecological services. Traditionally, operations on forest growing stock volume using field measurements are labor-intensive and time-consuming. Recently, remote sensing technology has emerged as a time-cost efficient method for forest inventory. In the present study, we have adopted three procedures, including samples expanding, feature selection, and results generation and evaluation. Extrapolating the samples from Light Detection and Ranging (LiDAR) scanning is the most important step in satisfying the requirement of sample size for nonparametric methods operation and result in accuracy improvement. Besides, mean decrease Gini (MDG) methodology embedded into Random Forest (RF) algorithm served as a selector for feature measure; afterwards, RF and K-Nearest Neighbor (KNN) were adopted in subsequent forest volume prediction. The results show that the retrieval of Forest volume in the entire area was in the range of 50–360 m3/ha, and the results from the two models show a better consistency while using the sample combination extrapolated by the optimal threshold value (2 × 10−4), leading to the best performances of RF (R2 = 0.618, root mean square error, RMSE = 43.641 m3/ha, mean absolute error, MAE = 33.016 m3/ha), followed by KNN (R2 = 0.617, RMSE = 43.693 m3/ha, MAE = 32.534 m3/ha). The detailed analysis that is discussed in the present paper clearly shows that expanding image-derived LiDAR samples helps in refining the prediction of regional forest volume while using satellite data and nonparametric models.

Mapping Aboveground Woody Biomass on Abandoned Agricultural Land Based on Airborne Laser Scanning Data

“…(3) The authors' algorithm implemented in the reFLex software was capable of providing relevant point cloud metrics (i.e., height) at the reference plot level (75 reference plots) as well as at forest management unit level (85,648 cells). (4) ALS data, despite a slight underestimation (bias from −2% to −6%), allowed more accurate prediction of AGB (RMSE < 33%) using ABA and the RF models than did other RS platforms [69][70][71][72][73][74][75].…”

“…Although the application of ALS data in this study demonstrated sufficient applicability for mapping AGB on AAL, it is generally accepted that data fusion methods using multi-sensor RS data sources allow AGB predictions for large areas while maintaining accuracy and reducing the associated costs. For example, ALS-based AGB estimations could be expanded through data from Landsat-8 and Sentinel-1 [73,74], Landsat-7 [75], Sentinel-2 [76][77][78], as well as MODIS [79] sensors. The overall accuracy of AGB prediction varied from 25% [73] to 49% [79] in these studies.…”

“…For example, ALS-based AGB estimations could be expanded through data from Landsat-8 and Sentinel-1 [73,74], Landsat-7 [75], Sentinel-2 [76][77][78], as well as MODIS [79] sensors. The overall accuracy of AGB prediction varied from 25% [73] to 49% [79] in these studies. However, in all cases, the study area did not contain AAL.…”

Estimating the Growing Stem Volume of Coniferous Plantations Based on Random Forest Using an Optimized Variable Selection Method

“…The RF method can evaluate the importance of feature variables based on non-linear relationships, allowing for the selection of feature variables with high importance for modeling [ 28 , 38 ]. Xie et al [ 58 ] used an RF algorithm to measure the importance of all candidate feature variables and then selected the predictors for regional GSV prediction and mapping, and the obtained results were acceptable (R 2 = 0.618). This implies that RF algorithms can be used to select robust and stable predictors based on importance measures.…”

“…However, their estimation accuracy of forest parameters in complex forest ecosystems is limited [ 51 ]. In contrast, non-parametric methods can model non-linear relationships and result in more accurate results in GSV estimation [ 27 , 35 , 57 , 58 , 59 ]. In our analysis, the SRF-RFR achieved the minimum rRMSE of 28.0% in the GSV estimation of Wangyedian forests, while the LSR-RFR, RF-RFR, Boruta-RFR, and VSURF-RFR resulted in the rRMSE values of 33.5%, 32.7%, 33.5%, and 31.3%, respectively.…”