Big Data Analytics for Geospatial Application Using Python

Numerous organizations regularly produce enormous volumes of geospatial data due to the widespread use of sensors and location-based services. However, traditionally collecting, storing, managing, exploring, analyzing, and visualization of geospatial data has been a complex and time-consuming task. This study proposed a big data analytics approach to collect, store, manage, explore, process, and analyze massive amounts of geospatial data. A comprehensive literature review, various Python libraries for geospatial big data, challenges in geospatial big data analytics, and big data analytics techniques such as spatial clustering, spatial regression analysis, and spatial-temporal analysis, were presented. In addition, geospatial big data analytics algorithms like K-means clustering, ordinary least squares (OLS), geographically weighted regression (GWR), Spatio-temporal clustering algorithms, Spatio-temporal regression models, and others were discussed. Finally, case studies on performing geospatial big data analytics using Pyspark were addressed.