Non-linear methods for inferring lidar metrics using SPOT-5 textural data

Abstract. Although many studies have demonstrated the utility of airborne lidar for forest inventory, the acquisition and processing of the data can be cost prohibitive for small areas. In such cases, it may be possible to emulate lidar metrics using more affordable optical data. This study explored processing methods for predicting lidar metrics using SPOT-5 textural data. Multiple-linear regression (MLR) was compared with non-linear machine learning techniques including multi-layer perceptron (MLP) artificial neural networks (ANN), rational basis function (RBF) ANN and regression tree (RT). For this purpose, 11 grey level co-occurrence matrix (GLCM) indices were calculated for bands, band ratios and principal components (PCs) of SPOT-5 multispectral image. SPOT-5 metrics were correlated with 25 lidar metrics collected over a Pinus radiata plantation. After dimensionality reduction, random forest feature selection was applied to select the most relevant SPOT-5 textural attributes for inferring each lidar metric. The results showed that the non-linear methods including MLP and RBF methods are more promising for modelling lidar metrics using SPOT-5 data than MLR and RT.