Multi-City Meteorological Trends & Correlation Dashboard
An end-to-end meteorological analytics project analyzing long-term climate patterns, temperature extremes, humidity variations, and wind dynamics across global cities using SQL data modeling and interactive Power BI dashboards.
Critical friction and failure modes observed in existing workflows
Raw meteorological datasets are often high-volume, multi-dimensional, and contain missing or noisy readings across disparate city sensors, making holistic trend analysis and correlation discovery difficult for researchers.
Engineering methodology, model selection, and pipeline design
Designed a comprehensive SQL schema to clean, normalize, and aggregate hourly weather records across cities (humidity, air pressure, temperature, wind vectors). Built star-schema data models in Power BI with custom DAX measures for seasonal decomposition, rolling averages, and cross-variable correlations.
Validated benchmarks, latency figures, and operational efficiency
Synthesized over 500,000 hourly weather records into an intuitive dashboard, enabling instant identification of micro-climate variations and meteorological anomalies.
Multi-city climate comparison with geographical mapping and coordinates
Hourly and seasonal trend analysis with dynamic date slicing
Cross-variable correlation matrix (Temperature vs Pressure vs Humidity)
Wind rose and velocity distribution modeling across seasons
Custom DAX measures for anomalies and historical percentile ranks
Interactive filtering by climate zones, seasons, and city clusters
The Power BI dashboard provides comprehensive insights into weather patterns, seasonal variations, and correlations between different weather attributes. Users can interactively explore data trends, visualize historical weather data, and derive actionable insights.
Production libraries, architectural components, and runtimes used in this system:
Let's discuss architecture, production deployment, or building high-performance intelligence solutions.