Spatiotemporal Datasets

Spatiotemporal datasets collected for network science, deep learning and general machine learning research.

Contents

1. Chickenpox Cases in Hungary
2. PedalMe London Bicycle Deliveries

Chickenpox Cases in Hungary

Description

A spatio-temporal dataset of weekly chickenpox (childhood disease) cases from Hungary. The dataset consists of a county-level adjacency matrix and time series of the county-level reported cases between 2005 and 2015. There are 2 specific related tasks:

• County level case count prediction.
• National level case count prediction.

Links

• Chickenpox Cases in Hungary Edges
• Chickenpox Cases in Hungary Time Series

Properties

• Directed: No.
• Node features: Yes.
• Temporal: Yes.

Possible tasks

• Count data regression

Citing

@misc{rozemberczki2021chickenpox,
      title={{Chickenpox Cases in Hungary: a Benchmark Dataset for Spatiotemporal Signal Processing with Graph Neural Networks}}, 
      author={Benedek Rozemberczki and Paul Scherer and Oliver Kiss and Rik Sarkar and Tamas Ferenci},
      year={2021},
      eprint={2102.08100},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}

PedalMe London Bicycle Deliveries

Description

A spatio-temporal dataset of weekly PedalMe bicycle deliveries in London. The dataset consists of a proximity based weighted adjacency matrix and time series of the weekly demands in 2020 and 2021. There are 2 specific related tasks:

• Locality level demand prediction.
• London level demand prediction.

Links

• PedalMe London Bicycle Deliveries Edges
• PedalMe London Bicycle Deliveries Time Series

Properties

• Directed: No.
• Node features: Yes.
• Temporal: Yes.

Possible tasks

• Count data regression

Citing

@inproceedings{rozemberczki2021pytorch,
               author = {Benedek Rozemberczki and Paul Scherer and Yixuan He and George Panagopoulos and Alexander Riedel and Maria Astefanoaei and Oliver Kiss and Ferenc Beres and Guzman Lopez and Nicolas Collignon and Rik Sarkar},
               title = {{PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models}},
               year = {2021},
               booktitle={Proceedings of the 30th ACM International Conference on Information and Knowledge Management},
}