Recently, rapid developments in remote sensing technologies have provided new ways of solving conventional problems. Advanced new remote sensing technologies and an urgent need to respond to some important environment problems have inspired researchers to develop and test more reliable approaches and to discover new knowledge for improvement of the applications of these new technologies. Traditional methods for forest classification were based either on the interpretation of aerial photographs or field work. These methods are labour intensive and time consuming. In past decades, remotely sensed data have been a valuable source of information in forest characterisation and classification. For example, high spatial resolution satellite imagery can be used to capture data relating to horizontal forest structure. However, it is unable to directly describe vertical forest structure. LiDAR, on the other hand, is able to describe the forest structure in three dimensions. This project aims to integrate the LiDAR data and satellite imagery data, along with the usage of object-based image analysis (OBIA) and machine learning based classifiers such as decision trees, random forests and support vector machines (SVMs) to improve the characterisation and classification of forest communities.

Dr Zhenyu Zhang

• Dr Xiaoye Liu

• International Centre for Applied Climate Sciences
• School of Engineering and Built Environment

• Environmental Science and Management
• Geomatic Engineering
• Statistics

• Doctor of Philosophy (DPHD)
• Master of Research (MRES)
• Master of Research (MRES)