A statistical and machine learning approach for monthly precipitation forecasting in an Amazon city
IntroductionCity-scale rainfall prediction is crucial for various essential services, such as transportation, supply chain logistics, and leisure activities, as well as for preventing risks associated with high volumes of rain. Belém is a city located in northern Brazil with distinct periods of prec...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-05-01
|
| Series: | Frontiers in Earth Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/feart.2025.1589753/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850278670686486528 |
|---|---|
| author | Ewerton Cristhian Lima de Oliveira Eduardo Costa de Carvalho Edmir dos Santos Jesus Rafael de Lima Rocha Rafael de Lima Rocha Helder Moreira Arruda Ronnie Cley de Oliveira Alves Ronnie Cley de Oliveira Alves Renata Gonçalves Tedeschi |
| author_facet | Ewerton Cristhian Lima de Oliveira Eduardo Costa de Carvalho Edmir dos Santos Jesus Rafael de Lima Rocha Rafael de Lima Rocha Helder Moreira Arruda Ronnie Cley de Oliveira Alves Ronnie Cley de Oliveira Alves Renata Gonçalves Tedeschi |
| author_sort | Ewerton Cristhian Lima de Oliveira |
| collection | DOAJ |
| description | IntroductionCity-scale rainfall prediction is crucial for various essential services, such as transportation, supply chain logistics, and leisure activities, as well as for preventing risks associated with high volumes of rain. Belém is a city located in northern Brazil with distinct periods of precipitation, including a rainy season that directly impacts the city’s dynamics and the quality of life of its citizens, often resulting in flooding and infrastructure accidents in several city zones.MethodsMeteorological studies generally use large volumes of data; however, our study is characterized by using a data source with fewer years to predict rainfall precipitation. Additionally, we use meteorological data from a set of sensors installed at a meteorological station located in Belém to train multivariate statistical and machine learning (ML) models to predict precipitation. Besides the use of algorithms, another evaluation was conducted on Feature Composition based on statistical methods to investigate the impact of variables on the prediction.ResultsThe results obtained in our investigation indicate that the vector autoregressive moving average with exogenous regressors (VARMAX) model achieved the best performance in rainfall forecasting, with an average root mean square error (RMSE) of 9.1833 in time series cross-validation, outperforming the other models.DiscussionThe climate-driven patterns directly influenced the performance of the rainfall forecasting models evaluated in this study. As cited above, the VARMAX had the lowest avRMSE, which was obtained using a lag-1 value of exogenous variables. This is particularly noteworthy, as this same configuration not only produced the lowest RMSE for forecasts in 2022 but also highlighted the importance of relative humidity and solar radiation in enhancing predictive accuracy, even in the presence of data anomalies related to solar radiation measurements. |
| format | Article |
| id | doaj-art-7fe2eb92da43493f96da1aec3a0e2dc6 |
| institution | OA Journals |
| issn | 2296-6463 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Earth Science |
| spelling | doaj-art-7fe2eb92da43493f96da1aec3a0e2dc62025-08-20T01:49:23ZengFrontiers Media S.A.Frontiers in Earth Science2296-64632025-05-011310.3389/feart.2025.15897531589753A statistical and machine learning approach for monthly precipitation forecasting in an Amazon cityEwerton Cristhian Lima de Oliveira0Eduardo Costa de Carvalho1Edmir dos Santos Jesus2Rafael de Lima Rocha3Rafael de Lima Rocha4Helder Moreira Arruda5Ronnie Cley de Oliveira Alves6Ronnie Cley de Oliveira Alves7Renata Gonçalves Tedeschi8Instituto Tecnologico Vale Desenvolvimento Sustentável, Belém, BrazilInstituto Tecnologico Vale Desenvolvimento Sustentável, Belém, BrazilInstituto Tecnologico Vale Desenvolvimento Sustentável, Belém, BrazilInstituto Tecnologico Vale Desenvolvimento Sustentável, Belém, BrazilUniversidade Federal do Pará, Computer Science Graduate Program, Belém, BrazilInstituto Tecnologico Vale Desenvolvimento Sustentável, Belém, BrazilInstituto Tecnologico Vale Desenvolvimento Sustentável, Belém, BrazilUniversidade Federal do Pará, Computer Science Graduate Program, Belém, BrazilInstituto Tecnologico Vale Desenvolvimento Sustentável, Belém, BrazilIntroductionCity-scale rainfall prediction is crucial for various essential services, such as transportation, supply chain logistics, and leisure activities, as well as for preventing risks associated with high volumes of rain. Belém is a city located in northern Brazil with distinct periods of precipitation, including a rainy season that directly impacts the city’s dynamics and the quality of life of its citizens, often resulting in flooding and infrastructure accidents in several city zones.MethodsMeteorological studies generally use large volumes of data; however, our study is characterized by using a data source with fewer years to predict rainfall precipitation. Additionally, we use meteorological data from a set of sensors installed at a meteorological station located in Belém to train multivariate statistical and machine learning (ML) models to predict precipitation. Besides the use of algorithms, another evaluation was conducted on Feature Composition based on statistical methods to investigate the impact of variables on the prediction.ResultsThe results obtained in our investigation indicate that the vector autoregressive moving average with exogenous regressors (VARMAX) model achieved the best performance in rainfall forecasting, with an average root mean square error (RMSE) of 9.1833 in time series cross-validation, outperforming the other models.DiscussionThe climate-driven patterns directly influenced the performance of the rainfall forecasting models evaluated in this study. As cited above, the VARMAX had the lowest avRMSE, which was obtained using a lag-1 value of exogenous variables. This is particularly noteworthy, as this same configuration not only produced the lowest RMSE for forecasts in 2022 but also highlighted the importance of relative humidity and solar radiation in enhancing predictive accuracy, even in the presence of data anomalies related to solar radiation measurements.https://www.frontiersin.org/articles/10.3389/feart.2025.1589753/fullmonthly precipitationstatistical learningmachine learningvariable correlationAmazon region |
| spellingShingle | Ewerton Cristhian Lima de Oliveira Eduardo Costa de Carvalho Edmir dos Santos Jesus Rafael de Lima Rocha Rafael de Lima Rocha Helder Moreira Arruda Ronnie Cley de Oliveira Alves Ronnie Cley de Oliveira Alves Renata Gonçalves Tedeschi A statistical and machine learning approach for monthly precipitation forecasting in an Amazon city Frontiers in Earth Science monthly precipitation statistical learning machine learning variable correlation Amazon region |
| title | A statistical and machine learning approach for monthly precipitation forecasting in an Amazon city |
| title_full | A statistical and machine learning approach for monthly precipitation forecasting in an Amazon city |
| title_fullStr | A statistical and machine learning approach for monthly precipitation forecasting in an Amazon city |
| title_full_unstemmed | A statistical and machine learning approach for monthly precipitation forecasting in an Amazon city |
| title_short | A statistical and machine learning approach for monthly precipitation forecasting in an Amazon city |
| title_sort | statistical and machine learning approach for monthly precipitation forecasting in an amazon city |
| topic | monthly precipitation statistical learning machine learning variable correlation Amazon region |
| url | https://www.frontiersin.org/articles/10.3389/feart.2025.1589753/full |
| work_keys_str_mv | AT ewertoncristhianlimadeoliveira astatisticalandmachinelearningapproachformonthlyprecipitationforecastinginanamazoncity AT eduardocostadecarvalho astatisticalandmachinelearningapproachformonthlyprecipitationforecastinginanamazoncity AT edmirdossantosjesus astatisticalandmachinelearningapproachformonthlyprecipitationforecastinginanamazoncity AT rafaeldelimarocha astatisticalandmachinelearningapproachformonthlyprecipitationforecastinginanamazoncity AT rafaeldelimarocha astatisticalandmachinelearningapproachformonthlyprecipitationforecastinginanamazoncity AT heldermoreiraarruda astatisticalandmachinelearningapproachformonthlyprecipitationforecastinginanamazoncity AT ronniecleydeoliveiraalves astatisticalandmachinelearningapproachformonthlyprecipitationforecastinginanamazoncity AT ronniecleydeoliveiraalves astatisticalandmachinelearningapproachformonthlyprecipitationforecastinginanamazoncity AT renatagoncalvestedeschi astatisticalandmachinelearningapproachformonthlyprecipitationforecastinginanamazoncity AT ewertoncristhianlimadeoliveira statisticalandmachinelearningapproachformonthlyprecipitationforecastinginanamazoncity AT eduardocostadecarvalho statisticalandmachinelearningapproachformonthlyprecipitationforecastinginanamazoncity AT edmirdossantosjesus statisticalandmachinelearningapproachformonthlyprecipitationforecastinginanamazoncity AT rafaeldelimarocha statisticalandmachinelearningapproachformonthlyprecipitationforecastinginanamazoncity AT rafaeldelimarocha statisticalandmachinelearningapproachformonthlyprecipitationforecastinginanamazoncity AT heldermoreiraarruda statisticalandmachinelearningapproachformonthlyprecipitationforecastinginanamazoncity AT ronniecleydeoliveiraalves statisticalandmachinelearningapproachformonthlyprecipitationforecastinginanamazoncity AT ronniecleydeoliveiraalves statisticalandmachinelearningapproachformonthlyprecipitationforecastinginanamazoncity AT renatagoncalvestedeschi statisticalandmachinelearningapproachformonthlyprecipitationforecastinginanamazoncity |