Podcast
Urban Data Science: Transport Analytics, Sensors and Liveable Cities
Open original DataTalks.Club episode
Urban Data Science: Transport Analytics, Sensors and Liveable Cities
Original Episode
Use these links for the canonical episode and media sources.
- Open the original DataTalks.Club podcast page
- Watch on YouTube
- Listen on Spotify
- Listen on Apple Podcasts
Episode Overview
How can cities use transport analytics, sensors and AI to become more liveable? In this episode Rachel Lim, an urban data scientist with a geography background and a master’‘s in urban data science, walks through practical ways data informs transport planning and placemaking. We cover core data sources—GPS, sensors, fare card systems, ride-hailing logs and computer vision for passenger flow—plus travel demand forecasting, real-time monitoring (including event analytics like F1), and operational responses such as.
People
Use these links to connect the episode to guest notes.
Chapter Summary
Use these checkpoints to decide whether to open the source transcript.
- 0:00 - Episode Introduction
- 1:56 - Guest Introduction: Rachel Lim, urban data scientist
- 2:52 - Career Path: Geography to urban informatics and data engineering
- 4:47 - Transport Scientist Role: public sector and consultancy applications
- 5:34 - Planning Horizons: short-term operations vs long-term infrastructure
- 6:47 - Data Sources for Transport: GPS, sensors, fare cards, ride-hailing
- 7:40 - Fare Card Systems: tap-in/tap-out travel data mechanics
- 8:20 - Computer Vision for Passenger Flow where fare data is absent
- 8:55 - Professional Motivation: internships, World City Summit, master’s study
- 11:26 - Urban Design Principles: walkability, public spaces, human-scale streets
- 13:49 - Livability Criteria: transport, housing, green space, digital access
- 15:48 - Singapore Planning Practices: Master Plan and placemaking initiatives
- 18:24 - Open Data & Collaboration: public datasets enabling research and apps
- 21:09 - Travel Demand Forecasting: predicting movements for infrastructure planning
- 23:01 - Data Pipelines & Warehousing: aggregation of real-time and historical data
- 24:09 - Real-Time Monitoring: traffic management and event analytics (F1 example)
- 25:10 - Operational Response: cameras, recovery services, traffic marshals
- 27:59 - Generative AI in Data Engineering: natural-language access to data
- 33:19 - Text-to-SQL Architecture: metadata, vector DB, RAG and LLMs
- 35:18 - Prompt Engineering & Query Safety: reliability and SQL restrictions
- 36:32 - Dataset Scale: millions of fare card records and demand analytics
- 38:34 - Infrastructure Stack: Kafka, Apache Spark, sensors, real-time APIs
- 39:27 - Journey Logic & Aggregation: trip definition and fare computation
- 41:08 - Data Quality Management: anomaly detection and sensor reliability
- 42:17 - Generative AI Use Cases: synthetic data and conversational search
- 45:40 - Privacy & Publishing: masking sensitive data before release
- 46:00 - Singapore Open Data Portals: data.gov.sg and DataMall resources
- 47:05 - Project Ideas for Learning: car parking and real-time taxi datasets
- 49:16 - Recommended Resources: DataTalks.Club, Jane Jacobs, Happy City