Assessing the Impact of Meteorological and Infrastructure Factors on Internet Performance Using Machine Learning
摘要
Internet resilience has become a critical policy concern, as connectivity is increasingly disrupted by both environmental shocks and infrastructural failures. Recent events in Egypt—including severe storms in Alexandria and a major fire at Cairo’s Ramses Central exchange—illustrate these dual vulnerabilities. This paper assesses how meteorological and infrastructure factors jointly shape internet performance across Cairo, Alexandria, and Al Buhayrah. We integrate user-observed throughput and latency from Ookla Speedtest, meteorological reanalysis from ERA5-Land, tower infrastructure from OpenCelliD, and night-time lights from VIIRS into a harmonized, grid-based monthly panel. Ensemble classifiers (Random Forest and XGBoost) were trained on discretized download-speed quartiles, achieving accuracies above 95% under spatial–temporal cross-validation. Results reveal paradoxical patterns: Alexandria exhibited dense 4G infrastructure yet high instability, while Cairo achieved stability with sparse towers, highlighting the decisive role of operator practices and redundancy. Operator-level disparities were marked, with Vodafone outperforming competitors, and adverse weather amplified instability by nearly 50% despite only modest reductions in average speed. These findings demonstrate that resilience cannot be explained by tower density alone, but emerges from the interaction of environment, infrastructure, and operator strategies. The study provides novel evidence from an underrepresented regional context and underscores the need for redundancy investments, operator accountability, and climate-aware digital infrastructure planning.