Geospatial Big Data: Survey and Challenges

TL;DR

This paper surveys the evolution, techniques, and challenges of geospatial big data (GBD), highlighting its integration with AI, new technologies, and its applications in urban and environmental management.

Contribution

It provides a comprehensive overview of GBD mining, categorizes data sources, discusses integration with AI and emerging tech, and addresses current challenges and future directions.

Findings

GBD includes satellite, sensor, mobile, and GIS data.

AI and new tech like LLMs enhance GBD analysis.

Challenges include data retrieval and security issues.

Abstract

In recent years, geospatial big data (GBD) has obtained attention across various disciplines, categorized into big earth observation data and big human behavior data. Identifying geospatial patterns from GBD has been a vital research focus in the fields of urban management and environmental sustainability. This paper reviews the evolution of GBD mining and its integration with advanced artificial intelligence (AI) techniques. GBD consists of data generated by satellites, sensors, mobile devices, and geographical information systems, and we categorize geospatial data based on different perspectives. We outline the process of GBD mining and demonstrate how it can be incorporated into a unified framework. Additionally, we explore new technologies like large language models (LLM), the Metaverse, and knowledge graphs, and how they could make GBD even more useful. We also share examples of GBD helping with city management and protecting the environment. Finally, we discuss the real challenges that come up when working with GBD, such as issues with data retrieval and security. Our goal is to give readers a clear view of where GBD mining stands today and where it might go next.