ABSTRACT. The purpose of this study is to examine smart city digital twins, geospatial data mining and predictive maintenance tools, and deep learning-based remote sensing and image recognition technologies in urban simulated environments and immersive hyper-connected virtual spaces. In this research, previous findings were cumulated showing that intelligent sensor and blockchain-enabled Internet of Things networks, predictive modeling techniques, virtual simulation and digital twin modeling tools, smart infrastructure sensors, and urban simulation and virtualization technologies optimize digital urban governance and Internet of Things-enabled smart cities. Evidence map visualization tools, machine learning classifiers, and reference management software harnessed include Abstrackr, CASP, R package and Shiny app citationchaser, DistillerSR, Eppi-Reviewer, JBI SUMARI, Litstream, MMAT, PICO Portal, ROBIS, and SluRp. The case study covers how Oslo’s Internet of Things sensors and actuators further vulnerable socio-economical areas, clean energy generation, green transport and shared mobility, and emission-free construction equipment.

Keywords: smart city; digital twin; geospatial data mining; deep learning-based remote sensing; urban simulated environments; immersive hyper-connected virtual spaces

How to cite: Pârvu, I. A., Uçan, O. N., AlAkoum, A., Pațurcă, R. N., and Papić-Blagojević, N. (2025). “Smart City Digital Twins, Geospatial Data Mining and Predictive Maintenance Tools, and Deep Learning-based Remote Sensing and Image Recognition Technologies in Urban Simulated Environments and Immersive Hyper-connected Virtual Spaces,” Geopolitics, History, and International Relations 17(2): 53–64. doi: 10.22381/GHIR17220254.

Received 12 July 2025 • Received in revised form 24 October 2025
Accepted 28 October 2025 • Available online 30 October 2025