Estimation of coppice forest characteristics using spatial and non-spatial models and Landsat data

Accurate spatial modelling of forest characteristics is one of the most important challenges in remote sensing applications. In this study, we compared the ability of Multiple Linear Regression (MLR), Geographically weighted regression (GWR), and Random Forest (RF) to estimate different forest attributes based on field sample data and Landsat 8 image. CA was modelled with the highest accuracy compared to other variables using GWR. GWR outperformed other methods. The highest and the lowest values of RMSE were for BA using RF (31.0%) and CA using GWR (12.0%), respectively.

Automated summary

Accurate spatial modelling of forest characteristics is essential in remote sensing applications. This study compared the performance of Multiple Linear Regression (MLR), Geographically Weighted Regression (GWR), and Random Forest (RF) in estimating different forest attributes. GWR outperformed the other methods, with the highest accuracy in modelling canopy area (CA).