Machine learning meets big spatial data

Abstract

The proliferation in amounts of generated data has propelled the rise of scalable machine learning solutions to efficiently analyze and extract useful insights from such data. Meanwhile, spatial data has become ubiquitous, e.g., GPS data, with increasingly sheer sizes in recent years. The applications of big spatial data span a wide spectrum of interests including tracking infectious disease, climate change simulation, drug addiction, among others. Consequently, major research efforts are exerted to support efficient analysis and intelligence inside these applications by either providing spatial extensions to existing machine learning solutions or building new solutions from scratch. In this 90-minutes tutorial, we comprehensively review the state-of-the-art work in the intersection of machine learning and big spatial data. We cover existing research efforts and challenges in three major areas of machine learning, namely, data analysis, deep learning and statistical inference, as well as two advanced spatial machine learning tasks, namely, spatial features extraction and spatial sampling. We also highlight open problems and challenges for future research in this area.

Review on Integrating Geospatial Big Datasets and Open Research Issues

“…infection tracking, climate change simulations, disaster management, etc. ), research has been focused on supplying geospatial extensions to current ML solutions or formulating entirely new solutions to enable effective analysis and intelligence for existing applications [99]. Nevertheless, further research is needed to determine which geospatial applications are most influential as well as to integrate geospatial techniques and parallelization in this age of big data [100].…”

Applications of geospatial big data in the Internet of Things

“…The intelligent analysis of IoT objects trajectories can be applied in many ways, such as traffic analysis and trip time estimation (Erdelić et al, 2021;Yi, Liu, Markovic, & Phillips, 2021), route prediction, and trajectory patterns learning (Sabek & Mokbel, 2019;Solomon, Livne, Katz, Shapira, & Rokach, 2021). All of this stimulates the creation of spatial data systems with APIs to support real-time ML operations in massive volumes of geospatial data (Sarwat, 2020) and frameworks and inference models for spatial ML (Sabek & Mokbel, 2019). Current ML solutions could also benefit from new geospatial extensions and specific applications embedded with intelligent analysis methods (Al-Yadumi et al, 2021).…”

Spatial data science for sustainable mobility

“…From the perspective of analysing mobility data, the integration of machine learning methods into spatio-temporal analysis has already commenced [22,23]. But truly spatiallyaware machine learning methods are for the large part still missing.…”