Encyclopedia topics Nupur Bhatnagar Spatial storage and indexing: The R-tree and the quad tree are commonly used multi-dimensional index structures in spatial databases. R-tree uses minimum bounding rectangles and operations like insertion, deletion, and searching are based on the position of MBR’s.I n this article I would write the different storage structures and space filling curves that are supported by the spatial databases. I would also discuss index structures including R tree family and grids. At the near end of the article I would like to mention some of the interesting properties of the storage and indexing structures. Key Words: range queries, data clustering, Hilbert curve, space filling curves.RTree family, Quad tree Spatial Database: A tour – Shashi Shekhar, Sanjaya Chawala The spatial database book provides a detailed and comprehensive explanation of Spatial Storage along with the SDBMS physical model and spatial data and operations. The author has also discussed common spatial Queries and Operation along with description of common file structure and Space filling curves like Z curve and Hilbert curve. Later in the chapter there is a comprehensive description of Index structures like grid files and R tree family. Wikipedia: www.wikipedia.org/ It gives a easy to understand description about Spatial indexes and spatial index methods like Grid, R-tree and its variants like R* tree and R+ tree. It also discusses quad trees-the region quad tree point quad tree , edge quad tree. It also contains a description of search and insertion algorithms. Interesting topics related to “Spatial storage and indexing” Space filling Curves: Analysis of the Clustering Properties of the Hilbert Space-Filling Curve. http://www.spatial.cs.umn.edu/CS8715/SA2_moon_jagadish_faloutsos_saltz.pdf This paper exploits the clustering property of the Hilbert space-filling of different shapes like polygons,polyhedras.It states the clustering property of the Hilbert space-filling curve as a linear mapping of a multidimensional space. There is also a performance comparison between z curve and Hilbert curve wrt to the clustering property. Object-Based Selective Materialization for Efficient Implementation of Spatial Data Cubes. www-faculty.cs.uiuc.edu/~hanj/pdf/tkde00.pdf Key Words: Data warehouse, data mining, online analytical processing (OLAP), spatial databases, spatial data analysis This paper highlights the spatial OLAP, spatial data warehouse models, spatial cubes. The author has proposed a new terminology “Object-based selective materialization” that exploits the granularity at the level of a single cell of a cuboid. Spatial Data Mining: Key Words: Spatial Data Mining, Classification. Clustering, Spatial Autocorrelation, , Spatial Outliers, Hot Spots, collocation mining Spatial Data Mining is a process of finding interesting hidden pattern in large spatial database. Examples include population census data, weather data. The process involves many phases that includes data cleaning, data pre-processing, feature selection, model building, evaluating a model. This article would revolve around the need of spatial data mining, different classification techniques – Spatial regression, Association rule mining, Clustering algorithms and outlier detection. The different key sources that I would refer are: Spatial Database: A tour – Shashi Shekhar ,Sanjaya Chawala This book provides a in depth discussion of concepts of pattern and spatial data mining. It motivates the readers about the interesting features of SDM explaining data mining process and novel spatial data mining techniques. The book covers topics like families of SDM including Location prediction, Spatial interaction, Hot spots. It also explains clustering, Auto correlation, spatial auto regression, classification, Association rule techniques, outlier detection technique and mapping SDM pattern families to spatial patterns. http://www-cse.uta.edu/~cook/dm/lectures/l13/index.htm It the course website of university of Texas at Arlington. It has a decent material giving an overview of spatial data mining and few interesting examples like weather pattern analysis. It describes Spatial OLAP, Spatial Associations and Hierarchy of Spatial Relationships. Coming along the way of SDM algorithms it discusses Spatial Classification, Spatial prediction and trend analysis, spatial primitives, spatial trend detection. Some special topics like time-series data mining, mining surprising temporal pattern are also useful. Some Articles ,tutorials and special topics: www.giscience.org/GIScience2000/papers/232-Peuquet.pdf This is an interesting article named Mining Spatial data using an interactive rule based approach. The author tries to integrate C4.5 algorithm with geographic visualization capabilities. It discusses the need of the the geographic visualization capabilities to become an integral part of the data mining process. http://www.spatial.cs.umn.edu/sdm.html This tutorial is a subset of topics covers in the Spatial database books but still its relevant to read as it highlights some important details of spatial data types, spatial relationships, and spatial autocorrelation and introduces spatial data mining in the following categories: location prediction, spatial outlier detection, and co-location mining. http://www.spatial.cs.umn.edu/CS8715/SDM9_cao.pdf Mining Frequent Spatio-temporal Sequential Patterns: The movement of mobile objects can be represented as a sequence of timestampped locations. This paper discusses an innovative algorithm to find patterns by a improved version of Apriori Algorithm.