An Introduction to Spatial Data Science with GeoDa: Volume 2: Clustering Spatial Data

The book "Spatial Data Science: The Analysis of Geospatial Patterns" is the second in a two-volume series that explores spatial clustering, a crucial aspect of unsupervised learning. It introduces methods to spatialize classic clustering methods through linked maps and graphs and incorporates spatial contiguity constraints into algorithms. With real-world empirical illustrations, it provides an understanding of the main concepts and techniques, their advantages, and disadvantages. It is organized into three major parts and serves as a definitive users guide for these methods as implemented in the GeoDa open-source software. The book is intended for readers interested in gaining insight into patterns expressed in spatial clusters of observations.

Format: Hardback
Length: 210 pages
Publication date: 29 May 2024
Publisher: Taylor & Francis Ltd

This captivating two-volume series delves into the realm of spatial data science, presenting a comprehensive exploration of the field. It ventures beyond mere data exploration, venturing into the organization of observations into meaningful groups known as spatial clustering. This pivotal component is a significant facet of modern machine learning, known as unsupervised learning.

What sets this book apart is its unique approach to spatializing classic clustering methods through linked maps and graphs, while also incorporating spatial contiguity constraints into clustering algorithms. Through a wealth of real-world empirical illustrations, readers will gain a deep understanding of the key concepts and techniques, their relative advantages, and disadvantages. Moreover, this book serves as an invaluable user guide for these methods, as implemented in the GeoDa open source software for spatial analysis.

The book is meticulously organized into three major parts, covering dimension reduction, classic clustering methods, and spatially constrained clustering methods. The first part delves into dimension reduction techniques such as principal components, multidimensional scaling, and stochastic network embedding. The second part explores classic clustering methods, including hierarchical clustering, k-means, k-medians, k-medoids, and spectral clustering. The third part explores spatially constrained clustering methods, encompassing both hierarchical and partitioning approaches.

To conclude, this book is a must-read for readers who seek to transcend the realm of simple geographical data mapping and unlock the fascinating patterns concealed within spatial clusters of observations. A solid foundation in Volume 1, particularly in the analysis of local spatial autocorrelation and a wide array of visualization methods, is assumed. Prepare to embark on an insightful journey into the world of spatial data science!

Weight: 664g
Dimension: 184 x 261 x 21 (mm)
ISBN-13: 9781032713021