Assessment of multi-temporal, multi-sensor radar and ancillary spatial data for grasslands monitoring in Ireland using machine learning approaches

Abstract

Accurate inventories of grasslands are important for studies of carbon dynamics, biodiversity conservation and agricultural management. For regions with persistent cloud cover the use of multi-temporal synthetic aperture radar (SAR) data provides an attractive solution for generating up-to-date inventories of grasslands. This is even more appealing considering the data that will be available from upcoming missions such as Sentinel-1 and ALOS-2. In this study, the performance of three machine learning algorithms; Random Forests (RF), Support Vector Machines (SVM) and the relatively underused Extremely Randomised Trees (ERT) is evaluated for discriminating between grassland types over two large heterogeneous areas of Ireland using multi-temporal, multi-sensor radar and ancillary spatial datasets. A detailed accuracy assessment shows the efficacy of the three algorithms to classify different types of grasslands. Overall accuracies≥88.7% (with kappa coefficient of 0.87) were achieved for the single frequency classifications and maximum accuracies of 97.9% (kappa coefficient of 0.98) for the combined frequency classifications. For most datasets, the ERT classifier outperforms SVM and RF.