Data-driven disaster management in a smart city

Detalhes bibliográficos
Autor(a) principal: Gonçalves, Sandra de Jesus Pereira
Data de Publicação: 2021
Tipo de documento: Dissertação
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10071/23563
Resumo: Disasters, both natural and man-made, are complex events that result in the loss of human life and/or the destruction of properties. The advances in Information Technology (IT) and Big Data Analysis represent an opportunity for the development of resilient environments, since from the application of Big Data (BD) technologies it is possible not only to extract patterns of occurrences of events, but also to predict them. The work carried out in this dissertation aims to apply the CRISP-DM methodology to conduct a descriptive and predictive analysis of the events that occurred in the city of Lisbon, with emphasis on the events that affected buildings. Through this research it was verified the existence of temporal and spatial patterns of occurrences with some events occurring in certain periods of the year, such as floods and collapses that are recorded more frequently in periods of high precipitation. The spatial analysis showed that the city center is the area most affected by the occurrences, and it is in these areas where the largest proportion of buildings with major repair needs are concentrated. Finally, machine learning models were applied to the data, and the Random Forest model obtained the best result with an accuracy of 58%. This research contributes to improve the resilience of the city since the analysis developed allowed to extract insights regarding the events and their occurrence patterns that will help the decision-making process.
id RCAP_a5602b9bb0678f4612cb7ee335c08579
oai_identifier_str oai:repositorio.iscte-iul.pt:10071/23563
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Data-driven disaster management in a smart cityDisaster managementData mining --Machine learningSmart CitiesGestão de desastresDisasters, both natural and man-made, are complex events that result in the loss of human life and/or the destruction of properties. The advances in Information Technology (IT) and Big Data Analysis represent an opportunity for the development of resilient environments, since from the application of Big Data (BD) technologies it is possible not only to extract patterns of occurrences of events, but also to predict them. The work carried out in this dissertation aims to apply the CRISP-DM methodology to conduct a descriptive and predictive analysis of the events that occurred in the city of Lisbon, with emphasis on the events that affected buildings. Through this research it was verified the existence of temporal and spatial patterns of occurrences with some events occurring in certain periods of the year, such as floods and collapses that are recorded more frequently in periods of high precipitation. The spatial analysis showed that the city center is the area most affected by the occurrences, and it is in these areas where the largest proportion of buildings with major repair needs are concentrated. Finally, machine learning models were applied to the data, and the Random Forest model obtained the best result with an accuracy of 58%. This research contributes to improve the resilience of the city since the analysis developed allowed to extract insights regarding the events and their occurrence patterns that will help the decision-making process.Os desastres, tanto naturais quanto as provocadas pelo homem, são eventos complexos que se traduzem em perdas de vidas e/ou destruição de propriedades. Os avanços na área de Tecnologias de Informação e Big Data Analysis representam uma oportunidade para o desenvolvimento de ambientes resilientes dado que, a partir da aplicação das tecnologias de Big Data (BD), é possível não só extrair padrões de ocorrências dos eventos, mas também fazer a previsão dos mesmos. O trabalho realizado nesta dissertação visa aplicar a metodologia CRISP-DM de forma a conduzir análises descritivas e preditivas sobre os eventos que ocorreram na cidade de Lisboa, com ênfase nos eventos que afetaram os edifícios. A investigação permitiu verificar a existência de padrões temporais e espaciais eventos a ocorrer em certos períodos do ano, como é o caso das cheias e inundações que são registados com maior frequência nos períodos de alta precipitação. A análise espacial permitiu verificar que a área do centro da cidade é a área mais afetada pelas ocorrências sendo nestas áreas onde se concentram a maior proporção de edifícios com grandes necessidades de reparação. Por fim, modelos de aprendizagem automática foram aplicados aos dados tendo o modelo Random Forest obtido o melhor resultado com accuracy de 58%. Esta pesquisa contribui para melhorar o aumento da resiliência da cidade pois, a análise desenvolvida permitiu extrair insights sobre os eventos e os seus padrões de ocorrência que irá ajudar os processos de tomada de decisão.2021-11-19T11:04:38Z2021-11-11T00:00:00Z2021-11-112021-10info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10071/23563TID:202787168engGonçalves, Sandra de Jesus Pereirainfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-11-09T17:49:35Zoai:repositorio.iscte-iul.pt:10071/23563Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T22:24:21.632582Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Data-driven disaster management in a smart city
title Data-driven disaster management in a smart city
spellingShingle Data-driven disaster management in a smart city
Gonçalves, Sandra de Jesus Pereira
Disaster management
Data mining --
Machine learning
Smart Cities
Gestão de desastres
title_short Data-driven disaster management in a smart city
title_full Data-driven disaster management in a smart city
title_fullStr Data-driven disaster management in a smart city
title_full_unstemmed Data-driven disaster management in a smart city
title_sort Data-driven disaster management in a smart city
author Gonçalves, Sandra de Jesus Pereira
author_facet Gonçalves, Sandra de Jesus Pereira
author_role author
dc.contributor.author.fl_str_mv Gonçalves, Sandra de Jesus Pereira
dc.subject.por.fl_str_mv Disaster management
Data mining --
Machine learning
Smart Cities
Gestão de desastres
topic Disaster management
Data mining --
Machine learning
Smart Cities
Gestão de desastres
description Disasters, both natural and man-made, are complex events that result in the loss of human life and/or the destruction of properties. The advances in Information Technology (IT) and Big Data Analysis represent an opportunity for the development of resilient environments, since from the application of Big Data (BD) technologies it is possible not only to extract patterns of occurrences of events, but also to predict them. The work carried out in this dissertation aims to apply the CRISP-DM methodology to conduct a descriptive and predictive analysis of the events that occurred in the city of Lisbon, with emphasis on the events that affected buildings. Through this research it was verified the existence of temporal and spatial patterns of occurrences with some events occurring in certain periods of the year, such as floods and collapses that are recorded more frequently in periods of high precipitation. The spatial analysis showed that the city center is the area most affected by the occurrences, and it is in these areas where the largest proportion of buildings with major repair needs are concentrated. Finally, machine learning models were applied to the data, and the Random Forest model obtained the best result with an accuracy of 58%. This research contributes to improve the resilience of the city since the analysis developed allowed to extract insights regarding the events and their occurrence patterns that will help the decision-making process.
publishDate 2021
dc.date.none.fl_str_mv 2021-11-19T11:04:38Z
2021-11-11T00:00:00Z
2021-11-11
2021-10
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10071/23563
TID:202787168
url http://hdl.handle.net/10071/23563
identifier_str_mv TID:202787168
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799134805988737024