Detection and classification of rainfall in South America using satellite images and machine learning techniques

Autores
Andelsman, Federico; Masuelli, Sergio; Tamarit, Francisco
Año de publicación
2023
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
The study of precipitation is one of the most intriguing areas in atmospheric sciences, with significant implications for our daily lives and climate change projections. This paper explores the estimation of rainfall trends in South American regions using convolutional neural networks (CNNs). The study focuses on the application of Cloud-Net, a CNNbased model with a format similar to an autoencoder, to obtain qualitative estimates of precipitation patterns. The employed loss functions, Categorical Cross Entropy and Categorical Focal Loss, address the challenges of classifying minority categories in unbalanced data. Regional analysis was conducted, identifying days with high rainfall intensity and the predominant intensities in 25 regions. The CNN model’s performance was compared with the XGBoost algorithm, showing excellent results for extreme rainfall categories and challenging intermediate categories. Furthermore, a comparison was made with Quantitative Precipitation Estimation (QPE) data and ground measurements from rain gauges. While the CNN model provided a valuable qualitative estimate of precipitation trends, achieving precise quantitative estimation would require an extensive data set of in-situ measurements. Overall, this research demonstrates the potential of CNNs for estimating rainfall trends and understanding precipitation patterns in South American regions. The findings offer valuable insights for further applications in meteorology and environmental studies.
Fil: Andelsman, Federico. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina
Fil: Masuelli, Sergio. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina
Fil: Tamarit, Francisco. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba. Instituto de Física Enrique Gaviola. Universidad Nacional de Córdoba. Instituto de Física Enrique Gaviola; Argentina
Materia
Machine learning
Rainfall estimation
Convolutional Neural Networks
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/255688
Acceder
id CONICETDig_a4e8e38af3031d39b714e2c91218b6ae
oai_identifier_str oai:ri.conicet.gov.ar:11336/255688
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Detection and classification of rainfall in South America using satellite images and machine learning techniquesAndelsman, FedericoMasuelli, SergioTamarit, FranciscoMachine learningRainfall estimationConvolutional Neural Networkshttps://purl.org/becyt/ford/1.3https://purl.org/becyt/ford/1The study of precipitation is one of the most intriguing areas in atmospheric sciences, with significant implications for our daily lives and climate change projections. This paper explores the estimation of rainfall trends in South American regions using convolutional neural networks (CNNs). The study focuses on the application of Cloud-Net, a CNNbased model with a format similar to an autoencoder, to obtain qualitative estimates of precipitation patterns. The employed loss functions, Categorical Cross Entropy and Categorical Focal Loss, address the challenges of classifying minority categories in unbalanced data. Regional analysis was conducted, identifying days with high rainfall intensity and the predominant intensities in 25 regions. The CNN model’s performance was compared with the XGBoost algorithm, showing excellent results for extreme rainfall categories and challenging intermediate categories. Furthermore, a comparison was made with Quantitative Precipitation Estimation (QPE) data and ground measurements from rain gauges. While the CNN model provided a valuable qualitative estimate of precipitation trends, achieving precise quantitative estimation would require an extensive data set of in-situ measurements. Overall, this research demonstrates the potential of CNNs for estimating rainfall trends and understanding precipitation patterns in South American regions. The findings offer valuable insights for further applications in meteorology and environmental studies.Fil: Andelsman, Federico. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; ArgentinaFil: Masuelli, Sergio. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; ArgentinaFil: Tamarit, Francisco. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba. Instituto de Física Enrique Gaviola. Universidad Nacional de Córdoba. Instituto de Física Enrique Gaviola; ArgentinaInstituto de Física de Líquidos y Sistemas Biológicos2023-12info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/255688Andelsman, Federico; Masuelli, Sergio; Tamarit, Francisco; Detection and classification of rainfall in South America using satellite images and machine learning techniques; Instituto de Física de Líquidos y Sistemas Biológicos; Papers In Physics; 15; 150006; 12-2023; 1-141852-4249CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://www.papersinphysics.org/papersinphysics/article/view/920info:eu-repo/semantics/altIdentifier/doi/10.4279/PIP.150006info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-03T09:48:11Zoai:ri.conicet.gov.ar:11336/255688instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-03 09:48:11.866CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Detection and classification of rainfall in South America using satellite images and machine learning techniques
title Detection and classification of rainfall in South America using satellite images and machine learning techniques
spellingShingle Detection and classification of rainfall in South America using satellite images and machine learning techniques
Andelsman, Federico
Machine learning
Rainfall estimation
Convolutional Neural Networks
title_short Detection and classification of rainfall in South America using satellite images and machine learning techniques
title_full Detection and classification of rainfall in South America using satellite images and machine learning techniques
title_fullStr Detection and classification of rainfall in South America using satellite images and machine learning techniques
title_full_unstemmed Detection and classification of rainfall in South America using satellite images and machine learning techniques
title_sort Detection and classification of rainfall in South America using satellite images and machine learning techniques
dc.creator.none.fl_str_mv Andelsman, Federico
Masuelli, Sergio
Tamarit, Francisco
author Andelsman, Federico
author_facet Andelsman, Federico
Masuelli, Sergio
Tamarit, Francisco
author_role author
author2 Masuelli, Sergio
Tamarit, Francisco
author2_role author
author
dc.subject.none.fl_str_mv Machine learning
Rainfall estimation
Convolutional Neural Networks
topic Machine learning
Rainfall estimation
Convolutional Neural Networks
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.3
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv The study of precipitation is one of the most intriguing areas in atmospheric sciences, with significant implications for our daily lives and climate change projections. This paper explores the estimation of rainfall trends in South American regions using convolutional neural networks (CNNs). The study focuses on the application of Cloud-Net, a CNNbased model with a format similar to an autoencoder, to obtain qualitative estimates of precipitation patterns. The employed loss functions, Categorical Cross Entropy and Categorical Focal Loss, address the challenges of classifying minority categories in unbalanced data. Regional analysis was conducted, identifying days with high rainfall intensity and the predominant intensities in 25 regions. The CNN model’s performance was compared with the XGBoost algorithm, showing excellent results for extreme rainfall categories and challenging intermediate categories. Furthermore, a comparison was made with Quantitative Precipitation Estimation (QPE) data and ground measurements from rain gauges. While the CNN model provided a valuable qualitative estimate of precipitation trends, achieving precise quantitative estimation would require an extensive data set of in-situ measurements. Overall, this research demonstrates the potential of CNNs for estimating rainfall trends and understanding precipitation patterns in South American regions. The findings offer valuable insights for further applications in meteorology and environmental studies.
Fil: Andelsman, Federico. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina
Fil: Masuelli, Sergio. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina
Fil: Tamarit, Francisco. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba. Instituto de Física Enrique Gaviola. Universidad Nacional de Córdoba. Instituto de Física Enrique Gaviola; Argentina
description The study of precipitation is one of the most intriguing areas in atmospheric sciences, with significant implications for our daily lives and climate change projections. This paper explores the estimation of rainfall trends in South American regions using convolutional neural networks (CNNs). The study focuses on the application of Cloud-Net, a CNNbased model with a format similar to an autoencoder, to obtain qualitative estimates of precipitation patterns. The employed loss functions, Categorical Cross Entropy and Categorical Focal Loss, address the challenges of classifying minority categories in unbalanced data. Regional analysis was conducted, identifying days with high rainfall intensity and the predominant intensities in 25 regions. The CNN model’s performance was compared with the XGBoost algorithm, showing excellent results for extreme rainfall categories and challenging intermediate categories. Furthermore, a comparison was made with Quantitative Precipitation Estimation (QPE) data and ground measurements from rain gauges. While the CNN model provided a valuable qualitative estimate of precipitation trends, achieving precise quantitative estimation would require an extensive data set of in-situ measurements. Overall, this research demonstrates the potential of CNNs for estimating rainfall trends and understanding precipitation patterns in South American regions. The findings offer valuable insights for further applications in meteorology and environmental studies.
publishDate 2023
dc.date.none.fl_str_mv 2023-12
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/255688
Andelsman, Federico; Masuelli, Sergio; Tamarit, Francisco; Detection and classification of rainfall in South America using satellite images and machine learning techniques; Instituto de Física de Líquidos y Sistemas Biológicos; Papers In Physics; 15; 150006; 12-2023; 1-14
1852-4249
CONICET Digital
CONICET
url http://hdl.handle.net/11336/255688
identifier_str_mv Andelsman, Federico; Masuelli, Sergio; Tamarit, Francisco; Detection and classification of rainfall in South America using satellite images and machine learning techniques; Instituto de Física de Líquidos y Sistemas Biológicos; Papers In Physics; 15; 150006; 12-2023; 1-14
1852-4249
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://www.papersinphysics.org/papersinphysics/article/view/920
info:eu-repo/semantics/altIdentifier/doi/10.4279/PIP.150006
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
application/pdf
dc.publisher.none.fl_str_mv Instituto de Física de Líquidos y Sistemas Biológicos
publisher.none.fl_str_mv Instituto de Física de Líquidos y Sistemas Biológicos
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1842268909412024320
score 13.13397

Publicaciones similares