Peak Spotting

nand_bracket

Visual tools for managing the capacity of Germany’s rail traffic network

Client

Deutsche Bahn

Scope of Work

  • Data Visualization
  • Software Development

Credits

More and more people travel by train in Germany. How can we combine machine learning and visual analytics methods to help manage the passenger loads?

Peak Spotting provides yield and capacity managers with rich visual tools to identify potential bottlenecks early on and react through price management, communications or logistic solutions.

Based on passenger load predictions from neural nets and random forest models, the web application integrates millions of datapoints over 100 days into the future, allowing to inspect the data on custom developed visual tools such as animated maps, stacked histograms, path-time-diagrams and powerful lists with miniature visualizations.

Special emphasis was put on providing actionable information and collaborative features, so that insights can be transformed immediately into improvements in planning and management.

The application provides deep integration of task management features bound to individual trains. This directly supports calls to action from the data exploration and helps to optimize workflows significantly. Trains can be annotated and managed via task and status items shared by the team of yield and capacity managers.

A calendar view with histograms provides a effective overview to spot peaks (obfuscated data).
Details in the calendar provide context for expected peak travel days (obfuscated data).
Various annotations, tasks and their statuses
The full application from the timeline macro view on the left to the very detailed train-level information and tasks on the right (obfuscated data).
Visualizing estimated loads along corridors by the hour (obfuscated data).
Trains are visualized in groups of main corridors across Germany (obfuscated data).
Path-Time diagrams for individual corridors allow spotting estimated loads along parallel paths (obfuscated data).
Sophisticated lists, which can be sorted and grouped based on many criteria, allow rapid drill down to individual trains (obfuscated data).

Video

Studio NAND
Screen cast of the application in use. Produced by Moritz Stefaner (obfuscated data).

Credits & References

Studio NAND

Directed by Christian Au; in collaboration with Moritz Stefaner (creative direction, data visualization); Christian Laesser (design); Kevin Wang (Analytics) Technical Lead Stephan Thiel Design Technologists Gabriel Credico, Lennart Hildebrandt;