Theoretical foundations and methodological advancements in geospatial big data analytics and challenges

The rapid development of spatial data and management technologies has led to a paradigm shift from static GIS to dynamic and data-intensive frameworks, known as geospatial big data frameworks. The evolution of big data is driven by the rapid expansion and development of the Earth observation system, IoT, mobile based geolocation data. Accordingly, this literature review aims to provide a structured narrative review of existing literature on geospatial big data, its main features, theoretical foundations, and the challenges and opportunities in handling this multidimensional and heterogeneous dataset. To achieve this, existing literature from 2015 to 2026 is considered in this literature review. The literature review covers the main features of geospatial big data through the 5Vs framework, such as volume, velocity, variety, veracity, and value. Furthermore, it highlights the theoretical and methodological foundation of geospatial big data. Since geospatial datasets are increasing in size and heterogeneous, the traditional theoretical foundations need to be extended to incorporate scalability, automation, and data-driven discovery. This resulted in the emergence of a new hybrid scientific paradigm in geospatial data. One of the main advancements of geospatial big data is the emergence of GeoAI, which integrates geospatial data with advanced algorithms such as machine learning and deep learning. This enables automated knowledge discovery and extraction of complex datasets. Furthermore, recent platforms allow high computational power, storage, and analytical tools needed to handle and process large-scale datasets, including cloud computing platforms. However, though advanced computational platforms have emerged, geospatial big data analytics are challenged by data heterogeneity, bias, and ethical issues. The finding highlights the need for an innovative paradigm in geospatial big data analytics that integrates spatial data with AI to enhance robustness and transferability. The review will serve as a bridge to fill the gap between large data availability and knowledge production for solving complex global challenges. By filling the gap between diverse and massive geospatial data with actionable knowledge, the review shows how geospatial big data could serve as an engine for achieving the sustainable development goals (SDGs), such as monitoring environmental change and climate, urban resilience, and planning, where traditional data sources and computational methods failed to address them.