Machine Learning for Climate Precipitation Prediction Modeling over South America
Many natural disasters in South America are linked to meteorological phenomena. Therefore, forecasting and monitoring climatic events are fundamental issues for society and various sectors of the economy. In the last decades, machine learning models have been developed to tackle different issues in...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-06-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/13/13/2468 |
_version_ | 1797528848971071488 |
---|---|
author | Juliana Aparecida Anochi Vinícius Albuquerque de Almeida Haroldo Fraga de Campos Velho |
author_facet | Juliana Aparecida Anochi Vinícius Albuquerque de Almeida Haroldo Fraga de Campos Velho |
author_sort | Juliana Aparecida Anochi |
collection | DOAJ |
description | Many natural disasters in South America are linked to meteorological phenomena. Therefore, forecasting and monitoring climatic events are fundamental issues for society and various sectors of the economy. In the last decades, machine learning models have been developed to tackle different issues in society, but there is still a gap in applications to applied physics. Here, different machine learning models are evaluated for precipitation prediction over South America. Currently, numerical weather prediction models are unable to precisely reproduce the precipitation patterns in South America due to many factors such as the lack of region-specific parametrizations and data availability. The results are compared to the general circulation atmospheric model currently used operationally in the National Institute for Space Research (INPE: Instituto Nacional de Pesquisas Espaciais), Brazil. Machine learning models are able to produce predictions with errors under 2 mm in most of the continent in comparison to satellite-observed precipitation patterns for different climate seasons, and also outperform INPE’s model for some regions (e.g., reduction of errors from 8 to 2 mm in central South America in winter). Another advantage is the computational performance from machine learning models, running faster with much lower computer resources than models based on differential equations currently used in operational centers. Therefore, it is important to consider machine learning models for precipitation forecasts in operational centers as a way to improve forecast quality and to reduce computation costs. |
first_indexed | 2024-03-10T10:05:09Z |
format | Article |
id | doaj.art-0020586ba1304537be0189b0c9e4bb99 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-10T10:05:09Z |
publishDate | 2021-06-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-0020586ba1304537be0189b0c9e4bb992023-11-22T01:35:33ZengMDPI AGRemote Sensing2072-42922021-06-011313246810.3390/rs13132468Machine Learning for Climate Precipitation Prediction Modeling over South AmericaJuliana Aparecida Anochi0Vinícius Albuquerque de Almeida1Haroldo Fraga de Campos Velho2National Institute for Space Research, São José dos Campos 12227-010, BrazilLaboratory for Applied Meteorology, Federal University of Rio de Janeiro, Rio de Janeiro 21941-901, BrazilNational Institute for Space Research, São José dos Campos 12227-010, BrazilMany natural disasters in South America are linked to meteorological phenomena. Therefore, forecasting and monitoring climatic events are fundamental issues for society and various sectors of the economy. In the last decades, machine learning models have been developed to tackle different issues in society, but there is still a gap in applications to applied physics. Here, different machine learning models are evaluated for precipitation prediction over South America. Currently, numerical weather prediction models are unable to precisely reproduce the precipitation patterns in South America due to many factors such as the lack of region-specific parametrizations and data availability. The results are compared to the general circulation atmospheric model currently used operationally in the National Institute for Space Research (INPE: Instituto Nacional de Pesquisas Espaciais), Brazil. Machine learning models are able to produce predictions with errors under 2 mm in most of the continent in comparison to satellite-observed precipitation patterns for different climate seasons, and also outperform INPE’s model for some regions (e.g., reduction of errors from 8 to 2 mm in central South America in winter). Another advantage is the computational performance from machine learning models, running faster with much lower computer resources than models based on differential equations currently used in operational centers. Therefore, it is important to consider machine learning models for precipitation forecasts in operational centers as a way to improve forecast quality and to reduce computation costs.https://www.mdpi.com/2072-4292/13/13/2468machine learningclimate precipitation predictionneural networksoptimal neural architecturedeep learning |
spellingShingle | Juliana Aparecida Anochi Vinícius Albuquerque de Almeida Haroldo Fraga de Campos Velho Machine Learning for Climate Precipitation Prediction Modeling over South America Remote Sensing machine learning climate precipitation prediction neural networks optimal neural architecture deep learning |
title | Machine Learning for Climate Precipitation Prediction Modeling over South America |
title_full | Machine Learning for Climate Precipitation Prediction Modeling over South America |
title_fullStr | Machine Learning for Climate Precipitation Prediction Modeling over South America |
title_full_unstemmed | Machine Learning for Climate Precipitation Prediction Modeling over South America |
title_short | Machine Learning for Climate Precipitation Prediction Modeling over South America |
title_sort | machine learning for climate precipitation prediction modeling over south america |
topic | machine learning climate precipitation prediction neural networks optimal neural architecture deep learning |
url | https://www.mdpi.com/2072-4292/13/13/2468 |
work_keys_str_mv | AT julianaaparecidaanochi machinelearningforclimateprecipitationpredictionmodelingoversouthamerica AT viniciusalbuquerquedealmeida machinelearningforclimateprecipitationpredictionmodelingoversouthamerica AT haroldofragadecamposvelho machinelearningforclimateprecipitationpredictionmodelingoversouthamerica |