Dataset

Smart City Digital Twin Ecosystem Dataset

Contains 3 years of synthetic multi-table smart-city data across 20 districts for forecasting, classification, regression, and causal analysis.

Kaggle ↗Aug 29, 2026

  • time_series
  • synthetic data
  • relational tables
  • causal dynamics
cover
cover

What it is

Synthetic 3-year smart-city digital twin with 9 linked tables across mobility, weather, power, air quality, and incidents, including causal cascades and dirty telemetry. 3 years of synthetic urban telemetry across 20 districts in 9 relational tables: traffic, transit, weather, air quality, power, events, emergencies, geography, and schema metadata.

Key results

  • 9 relational CSV tables + 1 data dictionary
  • Covers Jan 2023 to Dec 2025
  • 20 urban districts with injected missingness and 0.2% duplicates

Useful for testing cross-table urban forecasting, outage prediction, and robust pipelines under realistic sensor failures.

One useful ML email a week.

Worth your time, not all of your time.

We track new ML work across papers, code, and data, then keep only the pieces worth a closer look. Selected, not collected.

Papers.Data.Code

The Weekly ML Signal

Selected, not collected.

One useful ML email a week: the papers, repos and datasets worth your attention.

Worth your time, not all of your time.