Search

Complexity of forest structure is an important factor contributing to uncertainty in aboveground biomass estimates. In this study, we present a new method for reducing uncertainty in forest aboveground biomass (AGB) estimation based on plot-level terrestrial laser scanner (TLS) point clouds reconstruction. The method estimates the total AGB of plots with complex structures after automatically performing the steps of ground point filtering, single tree segmentation, and three-dimensional (3D) structure reconstruction. We used plot data from temperate and tropical forest ecosystems to verify the effectiveness of the method, reconstructing a 1300 m2 temperate plantation plot and a 5000 m2 mingled forest plot, respectively. The total biomass of 153 trees in the plantation plot was overestimated by 17.12 %, and the total biomass of 61 trees in the mingled forest plot was underestimated by 10.88 %. We found that the uncertainty of aboveground biomass estimation in tropical forests with more complex structures is not necessarily greater than in plantations. Therefore, in large-scale remote sensing observations of forest biomass, the number or area of plots can be increased to reduce the uncertainty of the results caused by the complex structure. The focus of this study is to explore TLS point clouds modeling methods to reduce the uncertainty in AGB estimation caused by the complexity of forest structures, and to provide reference cases for plot-level point clouds reconstruction methods. Forest ecologists can use this method to regularly observe forest growth and obtain indicators related to forest ecology without destroying trees.

• Twelve machine learning algorithms are compared to construct a retrieval model. • The TN concentration is retrieved using the UAV Hyper Spectral Remote Sensing data. • Spatial distribution of TN concentration is retrieved with high resolution. • Providing scientific references for water quality monitoring and management. Monitoring the water pollution level in real time is the most critical issue for protecting the water quality of water reservoirs. Due to the restrictions on flight areas of Unmanned Arial Vehicles (UAV), four sensitive regions with the area of 1–2 km2 were first selected in this study based on the spatial distribution of total nitrogen (TN) concentration changes estimated by the Landsat remote sensing data. And then twelve machine learning algorithms including Support Vector Machine (SVM), Artificial Neural Networks (ANN), Bayesian Ridge Regression (BRR), Lasso Regression (Lasso), Elastic Net (EN), Linear Regression (LR), Decision Tree Regression (DTR), K Neighbors Regression (KNR), Random Forest Regression (RFR), Extra Trees Regression (ETR), AdaBoost Regression (ABR) and Gradient Boosting Regression (GBR) were compared to construct a more accurate retrieval model by using the UAV hyper spectral remote sensing and ground monitoring data. And then the TN concentration was estimated after the process of dimensionality reduction and compressed sensing denoing. Finally, spatial heterogeneity of the TN concentration was analyzed in four sensitive areas of the Miyun reservoir. The results demonstrated that among the tested algorithms the Extra Trees Regression was best suitable for the construction of a TN concentration retrieval model on the basis of UAV hyper spectral data, and its absolute squared error was 0.000065. The spatial distribution of the TN showed that the concentration was highest within the water area of the Bulaotun village and the Houbajiazhuang village, while it was relatively low for the Chao river dam and Bai river dam. Additionally, no significant differences regarding the concentrations were shown in the single UAV flight area except the Houbajia village, which indicated that the water quality in Miyun reservoir was relatively stable and changed in a small interval. These conclusions can provide scientific references for water quality monitoring and management in the water reservoir. [ABSTRACT FROM AUTHOR]