Combining social media data and meteorological sensors for urban flood detection: a statistical analysis in São Paulo City

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.contributorBrazilian Center for Early Warning and Monitoring for Natural Disasters (CEMADEN)-
Autor(es): dc.creatorHossaki, Vitor Yuichi-
Autor(es): dc.creatorNegri, Rogério Galante-
Autor(es): dc.creatorSantos, Leonardo Bacelar Lima-
Autor(es): dc.creatorMendes, Tatiana Sussel Gonçalves-
Autor(es): dc.creatorBressane, Adriano-
Data de aceite: dc.date.accessioned2025-08-21T17:37:19Z-
Data de disponibilização: dc.date.available2025-08-21T17:37:19Z-
Data de envio: dc.date.issued2025-04-29-
Data de envio: dc.date.issued2025-03-01-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.1007/s12145-025-01802-3-
Fonte completa do material: dc.identifierhttps://hdl.handle.net/11449/306607-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/306607-
Descrição: dc.descriptionFloods are among the most frequent and costly natural disasters in urban areas, often resulting from intense precipitation. Leveraging geospatial data from social media and physical sensors offers a valuable opportunity for effective flood detection. This study conducts a statistical analysis employing Anderson-Darling and Shapiro-Wilk tests to assess the normality of the data distributions. Correlation analyses were conducted to evaluate the relationships between rainfall levels, river levels, and Twitter (currently X), while the Mann-Whitney U test was used to compare data from flood and non-flood events. Meteorological variables, such as rainfall data from rain gauges and radar, proved critical in establishing a link between precipitation levels and flooding events. River level data from the São Paulo Flood Alert System revealed a strong correlation between river levels and flood conditions, particularly during “Warning” and “Emergency” situations. Additionally, the analysis of social media data demonstrated a significant correlation between the frequency of flood-related keywords in tweets and the occurrence of actual flood events. This finding highlights the potential of Twitter data as an alternative source for urban flood detection. By leveraging real-time, user-generated content, this approach offers a novel methodology for early warning systems, enhancing situational awareness and improving flood monitoring capabilities. The findings underscore the effectiveness of integrating multiple data sources for comprehensive flood monitoring, offering practical insights for improving flood detection and management in urban environments.-
Descrição: dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)-
Descrição: dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)-
Descrição: dc.descriptionInstitute of Science and Technology São Paulo State University (UNESP)-
Descrição: dc.descriptionBrazilian Center for Early Warning and Monitoring for Natural Disasters (CEMADEN) Graduate Program in Natural Disasters São Paulo State University (UNESP)-
Descrição: dc.descriptionBrazilian Center for Early Warning and Monitoring for Natural Disasters (CEMADEN)-
Descrição: dc.descriptionGraduate Program in Civil and Environmental Engineering São Paulo State University (UNESP)-
Descrição: dc.descriptionInstitute of Science and Technology São Paulo State University (UNESP)-
Descrição: dc.descriptionBrazilian Center for Early Warning and Monitoring for Natural Disasters (CEMADEN) Graduate Program in Natural Disasters São Paulo State University (UNESP)-
Descrição: dc.descriptionGraduate Program in Civil and Environmental Engineering São Paulo State University (UNESP)-
Descrição: dc.descriptionFAPESP: 2021/01305-6-
Descrição: dc.descriptionCNPq: 305220/2022-5-
Descrição: dc.descriptionCNPq: 446053/2023-6-
Idioma: dc.languageen-
Relação: dc.relationEarth Science Informatics-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subjectRain gauge-
Palavras-chave: dc.subjectRiver level-
Palavras-chave: dc.subjectTwitter-
Palavras-chave: dc.subjectUrban flood-
Título: dc.titleCombining social media data and meteorological sensors for urban flood detection: a statistical analysis in São Paulo City-
Tipo de arquivo: dc.typelivro digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.