Spatial Big Data Science

Emerging Spatial Big Data (SBD) has transformative potential in solving many grand societal challenges such as water resource management, food security, disaster response, and transportation. However, significant computational challenges exist in analyzing SBD due to the unique spatial characteristics including spatial autocorrelation, anisotropy, heterogeneity, multiple scales and resolutions which is illustrated in this book.

This book also discusses current techniques for, spatial big data science with a particular focus on classification techniques for earth observation imagery big data. Specifically, the authors introduce several recent spatial classification techniques, such as spatial decision trees and spatial ensemble learning. Several potential future research directions are also discussed.

This book targets an interdisciplinary audience including computer scientists, practitioners and researchers working in the field of data mining, big data, as well as domain scientists working in earth science (e.g., hydrology, disaster), public safety and public health. Advanced level students in computer science will also find this book useful as a reference.

Introduces four unique properties related to the nature of spatial data that must be accounted for in any data analysis Covers Spatial Autocorrelation Discusses Spatial Dependency in Multiple Spatial Scales Includes supplementary material: sn.pub/extras

Inhalt
Part I Overview of Spatial Big Data Analytics.- 1 Spatial Big.- 2 Spatial and Spatiotemporal Big Data science.- Part II Classification of Earth Observation Imagery Big Data.- 3 Overview of Earth Imagery Classification.- 4 Spatial Information Gain Based Spatial Decision Tree.- 5 Focal-Test-Based Spatial Decision Tree.- 6 Spatial Ensemble Learning.- Part III Future Research Needs.- 7 Future Research Needs.- References.<p