Measuring the Impact of Natural Hazards with Citizen Science: The Case of Flooded Area Estimation Using Twitter

Abstract

Twitter has significant potential as a source of Volunteered Geographic Information (VGI), as its content is updated at high frequency, with high availability thanks to dedicated interfaces. However, the diversity of content types and the low average accuracy of geographic information attached to individual tweets remain obstacles in this context. The contributions in this paper relate to the general goal of extracting actionable information regarding the impact of natural hazards on a specific region from social platforms, such as Twitter. Specifically, our contributions describe the construction of a model classifying whether given spatio-temporal coordinates, materialized by raster cells in a remote sensing context, lie in a flooded area. For training, remotely sensed data are used as the target variable, and the input covariates are built on the sole basis of textual and spatial data extracted from a Twitter corpus. Our contributions enable the use of trained models for arbitrary new Twitter corpora collected for the same region, but at different times, allowing for the construction of a flooded area measurement proxy available at a higher temporal frequency. Experimental validation uses true data that were collected during Hurricane Harvey, which caused significant flooding in the Houston urban area between mid-August and mid-September 2017. Our experimental section compares several spatial information extraction methods, as well as various textual representation and aggregation techniques, which were applied to the collected Twitter data. The best configuration yields a F1 score of 0.425, boosted to 0.834 if restricted to the 10% most confident predictions.

Supervised Machine Learning Approaches on Multispectral Remote Sensing Data for a Combined Detection of Fire and Burned Area

“…Another approach to further enhance our proposed combined detection would be to include crowdsourced data that are freely available and up-to-date. Such approaches have been used in several studies on various natural hazards, e.g., [90,91]. One disadvantage of such data is that the needed geo-location is not always present; see, e.g., [92].…”

Understanding Discussions of Citizen Science Around Sustainable Development Goals in Twitter

“…Topic modelling is an unsupervised learning technique that aims to identify patterns and relationships among text documents [39] and widely adopted within a variety of domains such as bioinformatics, politics, transportation, etc. [40]. For this research, we have used Latent Dirichlet Allocation (LDA) as topic modelling method for understanding topics of discussion.…”

Earth Observation for Land Cover and Human-Environment Interactions

“…Apart from soil quality sampling, field sampling has been applied for water quality testing (Sun et al, 2016) (Ristea et al, 2020). Nowadays, this new data type has been applied for hazard monitoring purposes (Bruneau et al, 2021).…”

“…Among these topics, numerous issues, covering biology, environmental engineering, spatial engineering, urban planning and social science, are discussed based on datasets generated from earth observation and spatial techniques. Generalised earth observation includes data generated from monitoring stations and mobile technologies, which could represent natural factors (Gellrich and Zimmermann, 2007), social behaviours (Ristea et al, 2020) and natural hazards (Bruneau et al, 2021). Apart from academic benefits from the earth surface properties disclosure, the value of earth observation can be added with the help of analytical methods with innovations.…”