Exploring the ZTBus Dataset

Discover urban mobility in Zurich with our newly released ZTBus dataset, consisting of a vast amount of data collected over 13,000 hours of operation of electric buses. Find out about the story of the dataset, how it enabled past projects, and the potential it holds for further research.
Published in Research Data
Exploring the ZTBus Dataset
Like

Share this post

Choose a social network to share with, or copy the URL to share elsewhere

This is a representation of how your post may appear on social media. The actual post will vary between social networks

Context

In 2015, we kicked off our program for electrified public transport research at the Institute for Dynamic Systems and Control (IDSC) of ETH Zürich. Thus far, this program has given rise to several projects, each involving a collaborative effort between academic, industrial, and public transportation partners. In the project "SwissTrolley plus", a first prototype of a battery-assisted trolley bus was developed. As of 2016, this prototype served as a platform for our research work. The collaborative exchange with our partners, i.e., the bus manufacturer Carrosserie HESS AG and VBZ, the transport operator of the city of Zurich, quickly turned out to be an ideal playground for applied research: Thanks to the diverse competences united in the partnership consortium, it was possible to quickly develop and deploy a software platform on the prototype vehicle, which is able to interface with the bus's central computer. This platform simultaneously supports the collection of data on the one hand and the testing of algorithms in real time on the other. Having continuous access to the bus in close proximity to our office in the center of Zurich proved to be not only very practical but also a source of great motivation. For example, it was easy to arrange test drives for students who were involved in the project in terms of a bachelor's or master's thesis . Naturally, these test drives provided a lot of fun and hence a great motivational boost. The uniqueness and the synergetic potential of the collaborative partnership was quickly recognized by all involved and led to the launch of further projects in this area from 2021 onwards, when another vehicle was available as a platform.

ETH research team at the SwissTrolley plus rollout
A part of ETH’s research team at the rollout of the “SwissTrolley plus” in 2017.

Exploring the dataset

In recent years, the data collected on the two vehicles has always formed the basis for our research work. For example, we have been able to use the data for the development and evaluation of a self-learning map algorithm and a passenger mass estimator. In addition, the data has been useful for large-scale simulation studies involving bus HVAC systems. As we became more and more aware of the value of the data in this way, we decided to make the data available to the public earlier this year. In doing so, we compiled the ZTBus data set, which consists of measurements from 1409 individual driving missions. Added together, the data includes a distance traveled of over 200,000 km in over 13,000 h.

The following sample graphs are intended to provide a first glimpse into the nature and content of the data set:

Heatmap of the trips in Zurich
“Heat map” of the 1409 driving missions, shown on a map of the city of Zurich. The filled circles mark the bus stops, which are colored according to the number of visits in the dataset. Map data ©2023 Google.
Energy consumption variations throughout the year
The histograms show the recorded mean energy consumption values of all the missions throughout the different seasons. The red lines indicate the mean value for each month. In winter months, the overall energy consumption is significantly higher.
Influence of COVID-19 measures on passenger load
The dots represent the maximum, mean, and minimum passenger load for each of the 1409 missions. The influence of the COVID-19 pandemic on the observed passenger load is evident. The vertical lines indicate a few of the most prominent Swiss national measures with regards to the pandemic.

Even more visualizations can be found in the original data descriptor paper.

What's next?

Even after more than seven years of working with the collected data, we strongly believe that the data still offers a lot of potential for further research. For example, the large amount of data could be used to feed machine learning algorithms, which could then provide real-time predictions of the expected speed profile or the passenger load. On the other hand, we see great potential to use the empirical data to support the development and validation of control algorithms – for example, in the area of load strategy planning or operational optimization. If this sounds as exciting to you as it does to us, we encourage you to download the data set and start exploring it right now!

(Poster image © Carrosserie HESS AG, 2017)

Please sign in or register for FREE

If you are a registered user on Research Communities by Springer Nature, please sign in

Follow the Topic

Research Data
Research Communities > Community > Research Data

Related Collections

With collections, you can get published faster and increase your visibility.

Text and speech corpora for natural language processing and corpus linguistics

This Collection presents a series of annotated text and speech corpora alongside linguistic models tailored for CL and NLP applications. These resources aim to enrich the arsenals of CL and NLP users and facilitate interdisciplinary research.

Publishing Model: Open Access

Deadline: Apr 24, 2025

Data for epigenetics research

This Collection presents data within epigenetics research including, but not limited to, data generated through techniques such as ChIP, bisulphite, nanopore and RNA sequencing, single-cell epigenetics/epigenomics, spatial genomics/epigenomics, and the role of non-coding RNAs in epigenetic modulation.

Publishing Model: Open Access

Deadline: Dec 28, 2024