Pittsburgh (PA, USA) floods at street-segment level from open data (2015-2024)

The dataset provides fine-grained spatiotemporal information on urban floods occurring inside the city of Pittsburgh, PA, USA, from 2015 to 2024 by integrating publicly available data sources. The data sources include NOAA storm events database and Pittsburgh 311 flooding requests. Each row corresponds to one segment flood event, characterized by street segment defined by distinct combination of "u_node", "v_node", "length_m", and time. Each flood event was mapped to the street segments using the provided location information (one-to-many). For NOAA storm events, we followed the reporting mechanism and matched segments following the order of event narratives, bounding box defined by begin/end coordinates, and azimuth/range information. For 311 flood events, we mapped the segments connecting the reported intersection, or the segment closest to the event coordinates if only a single street is provided. Mapping was performed with street-level information over OSMnx driving network (directed, Boeing 2025). Deduplication was performed by removing duplicate reports of a segment flood event if the reports on the same street segment (defined by (u_node, v_node, length_m)) were submitted less than 1 hour apart. We have another dataset of New York City published on Zenodo (https://zenodo.org/records/18062104) and Hugging Face (https://huggingface.co/datasets/yueq92/nyc_floods_street_level) following the similar data collection and processing procedures. Please cite this dataset with its DOI (10.5281/zenodo.17562033) if you are using it. Reference Boeing, G. (2025). Modeling and Analyzing Urban Networks and Amenities with OSMnx. Geographical Analysis 57 (4), 567-577. doi:10.1111/gean.70009