Large data spatial data (SBD) has the potential to transform many major social challenges such as water resource management, food security, disaster response and transport. However, there are significant computational challenges in the SBD analysis because of the unique spatial characteristics including the spatial self-correlation, the heterogeneity, the heterogeneity, the multiple scales and the resolutions that are described in this book.

This book also discusses the current techniques of spatial large-scale data science with particular emphasis on classification techniques for large Earth observation data. Specifically, the authors introduced many new spatial classification techniques, such as spatial resolution trees and spatial group learning.

Several possible future research trends are also discussed. This book targets a multidisciplinary audience that includes computer scientists, practitioners, researchers working in the field of data mining and mass data, as well as field scientists working in earth sciences (eg, hydrology and disasters), public safety and public health.

Advanced level students in computer science will also find this book useful as a reference.