Modeling with Artificial Neural Networks to estimate daily precipitation in the Brazilian Legal Amazon.
Saved in:
| Title: | Modeling with Artificial Neural Networks to estimate daily precipitation in the Brazilian Legal Amazon. |
|---|---|
| Authors: | Pinheiro Gomes, Evanice1 (AUTHOR) gomesevanice@ufpa.br, Progênio, Mayke Feitosa2 (AUTHOR), da Silva Holanda, Patrícia3 (AUTHOR) |
| Source: | Climate Dynamics. Jul2024, Vol. 62 Issue 7, p6219-6233. 15p. |
| Subjects: | Stochastic learning models, Machine learning, Artificial neural networks, Atmospheric circulation, Water supply, Rain gauges |
| Abstract: | Hydrological analyses carried out based on precipitation in the Brazilian Legal Amazon (BLA) are essential due to their importance in climate regulation and regional and global atmospheric circulation. However, data series with short periods and many gaps, especially at the daily scale, are a limitation in this region. In order to improve precipitation analysis, a non-parametric stochastic model based on Artificial Neural Networks (ANNs) was used to estimate daily precipitation in the BLA. For this purpose, 22 rain gauge stations were adopted and organized, taking into account the complete series and the seasonal periods (rainy and dry).The results obtained showed a good performance of the model, with ranges of MSE (0.0022–0.2665), MAPE (0.0083–1.5343) and RMSE (0.0017–0.0214), which characterize an acceptable estimate for the estimation daily precipitation, especially in those with a wetter climate and more frequent precipitation during the year, as is the case in those located in the Amazon Biome. However, in regions that suffer from droughts, such as the Amazon-Cerrado ecotone areas, the results were less satisfactory due to the greater recurrence of zeros in the historical series. The seasonal division into dry and rainy periods did not provide better estimates for the model, except for some rain gauge stations located at latitudes close to the equator. However, this study could support future research on the estimation of daily precipitation in the region. [ABSTRACT FROM AUTHOR] |
| Copyright of Climate Dynamics is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Hydrological analyses carried out based on precipitation in the Brazilian Legal Amazon (BLA) are essential due to their importance in climate regulation and regional and global atmospheric circulation. However, data series with short periods and many gaps, especially at the daily scale, are a limitation in this region. In order to improve precipitation analysis, a non-parametric stochastic model based on Artificial Neural Networks (ANNs) was used to estimate daily precipitation in the BLA. For this purpose, 22 rain gauge stations were adopted and organized, taking into account the complete series and the seasonal periods (rainy and dry).The results obtained showed a good performance of the model, with ranges of MSE (0.0022–0.2665), MAPE (0.0083–1.5343) and RMSE (0.0017–0.0214), which characterize an acceptable estimate for the estimation daily precipitation, especially in those with a wetter climate and more frequent precipitation during the year, as is the case in those located in the Amazon Biome. However, in regions that suffer from droughts, such as the Amazon-Cerrado ecotone areas, the results were less satisfactory due to the greater recurrence of zeros in the historical series. The seasonal division into dry and rainy periods did not provide better estimates for the model, except for some rain gauge stations located at latitudes close to the equator. However, this study could support future research on the estimation of daily precipitation in the region. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 09307575 |
| DOI: | 10.1007/s00382-024-07200-7 |
