Name in original language
Tampere Pulssi
Initiative overview
Tampere Pulse is an AI-enabled urban analytics initiative developed by the City of Tampere to improve evidence-based decision-making related to visitor flows in the city centre. The initiative addresses a common challenge faced by cities: limited real-time and forward-looking insight into how people move through urban environments, particularly during events, seasonal changes, or extreme weather conditions. By transforming anonymised sensor data into predictive insights, Tampere Pulse enables public authorities and local stakeholders to better anticipate demand, manage public spaces, and optimise services while respecting privacy and ethical standards.
The primary objective of the initiative is to support smarter, more responsive urban governance through reliable short- and medium-term forecasts of pedestrian volumes. The system combines AI-based predictive models with multiple data sources, including anonymised camera-based counts, weather data, temporal patterns, and event information. The resulting forecasts help city departments, local businesses, and other stakeholders to plan resources, staffing, maintenance, safety measures, and mobility services more effectively. A key objective is to strengthen human-AI collaboration by presenting predictions through an intuitive, map-based interface that supports interpretation and informed decision-making rather than automated action.
The key stakeholders include companies, which act as both customers and co-creators of the service; city residents and visitors, who can use the service to plan routes during peak hours and identify quieter or livelier areas of the city; maintenance teams, for whom the service supports more efficient scheduling and allocation of work; and security teams, which can use the insights to prepare for high-traffic periods and ensure appropriate staffing and readiness. Importantly, the solution is designed in line with principles of trustworthy and human-centric AI: data is anonymised at source, model limitations are communicated transparently, and the system is used as a decision-support tool rather than a substitute for human judgement. Additionally, the AI-forecast data can be leveraged for security and risk-preparedness purposes, with scalable potential to create a safer city ecosystem.
