en
Proceedings chapter
Open access
English

Computing flood probabilities using Twitter: application to the Houston urban area during Harvey

Presented at Paris (France), 2-4 October 2019
Publication date2019
Abstract

In this paper, we investigate the conversion of a Twitter corpus into geo-referenced raster cells holding the probability of the associated geographical areas of being flooded. We describe a baseline approach that combines a density ratio function, aggregation using a spatio-temporal Gaussian kernel function, and TFIDF textual features. The features are transformed to probabilities using a logistic regression model. The described method is evaluated on a corpus collected after the floods that followed Hurricane Harvey in the Houston urban area in August-September 2017. The baseline reaches a F1 score of 68%. We highlight research directions likely to improve these initial results.

Citation (ISO format)
BRANGBOUR, Etienne Alaric et al. Computing flood probabilities using Twitter: application to the Houston urban area during Harvey. In: 9th International Workshop on Climate Informatics. Paris (France). [s.l.] : [s.n.], 2019.
Main files (1)
Proceedings chapter (Published version)
accessLevelPublic
Identifiers
  • PID : unige:129070
250views
47downloads

Technical informations

Creation01/17/2020 5:02:00 PM
First validation01/17/2020 5:02:00 PM
Update time03/15/2023 6:47:35 PM
Status update03/15/2023 6:47:34 PM
Last indexation01/17/2024 8:49:22 AM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack