ABSTRACT
Beach Surface Moisture (BSM) is a key attribute in the coastal investigations of land-atmospheric water and energy fluxes, groundwater resource budgets and coastal beach/dune development. In this study, an attempt has been made for the first time to estimate BSM from terrestrial LiDAR intensity data based on the Support Vector Regression (SVR). A long-range static terrestrial LiDAR (Riegl VZ-2000) was adopted to collect point cloud data of high spatiotemporal resolution on the Ostend-Mariakerke beach, Belgium. Based on the field moisture samples, SVR models were developed to retrieve BSM, using the backscattered intensity, scanning ranges and incidence angles as input features. The impacts of the training samples' size and density on the predictive accuracy and generalization capability of the SVR models were fully investigated based on simulated BSM-intensity samples. Additionally, we compared the performance of the SVR models for BSM estimation with the traditional Stepwise Regression (SR) method and the Artificial Neural Network (ANN). Results show that SVR could accurately retrieve the BSM from the backscattered intensity with high reproducibility (average test RMSE of 0.71% ± 0.02% and R2 of 0.98% ± 0.002%). The Radial Basis Function (RBF) was the most suitable kernel for SVR model development in this study. The impacts of scanning geometry on the intensity could also be accurately corrected in the process of estimating BSM by the SVR models. However, compared to the SR method, the predictive accuracy and generalization performance of SVR models were significantly dependent on the training samples' coverage, size and distribution, suggesting the need for the training samples of uniform distribution and representativeness. The minimum size of training samples required for SVR model development was 54. Under this condition, SVR performed similarly to ANN with a test RMSE of 1.06%, but SVR still performed acceptably (with an RMSE of 1.83%) even using extremely few training samples (only 16 field samples of uniform distribution), far better than the ANN (with an RMSE of 4.02%).
ABSTRACT
Obtaining information about the spatial distribution of desert plants is considered as a serious challenge for ecologists and environmental modeling due to the required intensive field work and infrastructures in harsh and remote arid environments. A new method was applied for assessing the spatial distribution of the halophytic species (HS) in an arid coastal environment. This method was based on the object-based image analysis for a high-resolution Google Earth satellite image. The integration of the image processing techniques and field work provided accurate information about the spatial distribution of HS. The extracted objects were based on assumptions that explained the plant-pixel relationship. Three different types of digital image processing techniques were implemented and validated to obtain an accurate HS spatial distribution. A total of 2703 individuals of the HS community were found in the case study, and approximately 82% were located above an elevation of 2 m. The micro-topography exhibited a significant negative relationship with pH and EC (r = -0.79 and -0.81, respectively, p < 0.001). The spatial structure was modeled using stochastic point processes, in particular a hybrid family of Gibbs processes. A new model is proposed that uses a hard-core structure at very short distances, together with a cluster structure in short-to-medium distances and a Poisson structure for larger distances. This model was found to fit the data perfectly well.
