TY - JOUR
T1 - Using spatial point process models, clustering and space partitioning to reconfigure fire stations layout
AU - Bispo, Regina
AU - Vieira, Francisca G.
AU - Yokochi, Clara
AU - Marques, Filipe J.
AU - Espadinha-Cruz, Pedro
AU - Penha, Alexandre
AU - Grilo, António
N1 - Funding Information:
info:eu-repo/grantAgreement/FCT/Concurso de Projetos de Investigação Científica e Desenvolvimento Tecnológico em Ciência dos dados e inteligência artificial na Administração Pública - 2019/DSAIPA%2FDS%2F0088%2F2019/PT#
info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F00667%2F2020/PT#
info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F00297%2F2020/PT#
info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDP%2F00297%2F2020/PT#
Publisher Copyright:
© 2023, The Author(s).
PY - 2023/10/4
Y1 - 2023/10/4
N2 - Fire stations (FS) are typically non-uniformly distributed across space, and their service area is, in general, defined based on administrative boundaries. Since the location of FS may considerably influence the readiness and the effectiveness of the provided services, national and regional governments need research-based information to adequately plan where to establish firefighting facilities. In this study, we propose a method to reconfigure the fire stations layout using spatial point process models, clustering and space partitioning. First, modelling fire intensity variation across space through a point process model enables to replicate the process independently by simulation. Subsequently, for each simulation, the k-means algorithm is used to define a siting location, minimizing the total within distance between the fire occurrences and the new position. This method allows to obtain a set of locations from which the respective distribution is inferred. Assuming a bivariate normal spatial distribution, we further define confidence siting regions. Ultimately, new FS service areas are defined by Voronoi tessellation. To exemplify the application of the method, we apply it to reconfigure the fire station layout at Aveiro, Portugal.
AB - Fire stations (FS) are typically non-uniformly distributed across space, and their service area is, in general, defined based on administrative boundaries. Since the location of FS may considerably influence the readiness and the effectiveness of the provided services, national and regional governments need research-based information to adequately plan where to establish firefighting facilities. In this study, we propose a method to reconfigure the fire stations layout using spatial point process models, clustering and space partitioning. First, modelling fire intensity variation across space through a point process model enables to replicate the process independently by simulation. Subsequently, for each simulation, the k-means algorithm is used to define a siting location, minimizing the total within distance between the fire occurrences and the new position. This method allows to obtain a set of locations from which the respective distribution is inferred. Assuming a bivariate normal spatial distribution, we further define confidence siting regions. Ultimately, new FS service areas are defined by Voronoi tessellation. To exemplify the application of the method, we apply it to reconfigure the fire station layout at Aveiro, Portugal.
KW - Fire
KW - Fire stations
KW - k-means
KW - Poisson point process
KW - Voronoi tessellation
UR - http://www.scopus.com/inward/record.url?scp=85173095736&partnerID=8YFLogxK
U2 - 10.1007/s41060-023-00455-z
DO - 10.1007/s41060-023-00455-z
M3 - Article
AN - SCOPUS:85173095736
SN - 2364-415X
JO - International Journal of Data Science and Analytics
JF - International Journal of Data Science and Analytics
ER -