Improved Rainfall Prediction through Nonlinear Autoregressive Network with Exogenous Variables: A Case Study in Andes High Mountain Region

Precipitation is the most relevant element in the hydrological cycle and vital for the biosphere. However, when extreme precipitation events occur, the consequences could be devastating for humans (droughts or floods). An accurate prediction of precipitation helps decision-makers to develop adequate...

Full description

Saved in:
Bibliographic Details
Main Authors: Mario Peña, Angel Vázquez-Patiño, Darío Zhiña, Martin Montenegro, Alex Avilés
Format: Article
Language:English
Published: Wiley 2020-01-01
Series:Advances in Meteorology
Online Access:http://dx.doi.org/10.1155/2020/1828319
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849468128283590656
author Mario Peña
Angel Vázquez-Patiño
Darío Zhiña
Martin Montenegro
Alex Avilés
author_facet Mario Peña
Angel Vázquez-Patiño
Darío Zhiña
Martin Montenegro
Alex Avilés
author_sort Mario Peña
collection DOAJ
description Precipitation is the most relevant element in the hydrological cycle and vital for the biosphere. However, when extreme precipitation events occur, the consequences could be devastating for humans (droughts or floods). An accurate prediction of precipitation helps decision-makers to develop adequate mitigation plans. In this study, linear and nonlinear models with lagged predictors and the implementation of a nonlinear autoregressive model with exogenous variables (NARX) network were used to predict monthly rainfall in Labrado and Chirimachay meteorological stations. To define a suitable model, ridge regression, lasso, random forest (RF), support vector machine (SVM), and NARX network were used. Although the results were “unsatisfactory” with the linear models, the specific direct influences of variables such as Niño 1 + 2, Sahel rainfall, hurricane activity, North Pacific Oscillation, and the same delayed rainfall signal were identified. RF and SVM also demonstrated poor performance. However, RF had a better fit than linear models, and SVM has a better fit than RF models. Instead, the NARX model was trained using several architectures to identify an optimal one for the best prediction twelve months ahead. As an overall evaluation, the NARX model showed “good” results for Labrado and “satisfactory” results for Chirimachay. The predictions yielded by NARX models, for the first six months ahead, were entirely accurate. This study highlighted the strengths of NARX networks in the prediction of chaotic and nonlinear signals such as rainfall in regions that obey complex processes. The results would serve to make short-term plans and give support to decision-makers in the management of water resources.
format Article
id doaj-art-fb0be423dd0546dfb5a5ee74a970a2f9
institution Kabale University
issn 1687-9309
1687-9317
language English
publishDate 2020-01-01
publisher Wiley
record_format Article
series Advances in Meteorology
spelling doaj-art-fb0be423dd0546dfb5a5ee74a970a2f92025-08-20T03:25:56ZengWileyAdvances in Meteorology1687-93091687-93172020-01-01202010.1155/2020/18283191828319Improved Rainfall Prediction through Nonlinear Autoregressive Network with Exogenous Variables: A Case Study in Andes High Mountain RegionMario Peña0Angel Vázquez-Patiño1Darío Zhiña2Martin Montenegro3Alex Avilés4Dirección de Investigación (DIUC), Universidad de Cuenca, Campus Central, Av. 12 de Abril s/n y Loja 010203, Cuenca, EcuadorFacultad de Ingeniería, Universidad de Cuenca, Av. 12 de Abril S/n y Loja 010203, Cuenca, EcuadorCarrera de Ingeniería Ambiental, Facultad de Ciencias Químicas, Universidad de Cuenca, Campus Central, Av. 12 de Abril S/n y Loja 010203, Cuenca, EcuadorCarrera de Ingeniería Ambiental, Facultad de Ciencias Químicas, Universidad de Cuenca, Campus Central, Av. 12 de Abril S/n y Loja 010203, Cuenca, EcuadorCarrera de Ingeniería Ambiental, Facultad de Ciencias Químicas, Universidad de Cuenca, Campus Central, Av. 12 de Abril S/n y Loja 010203, Cuenca, EcuadorPrecipitation is the most relevant element in the hydrological cycle and vital for the biosphere. However, when extreme precipitation events occur, the consequences could be devastating for humans (droughts or floods). An accurate prediction of precipitation helps decision-makers to develop adequate mitigation plans. In this study, linear and nonlinear models with lagged predictors and the implementation of a nonlinear autoregressive model with exogenous variables (NARX) network were used to predict monthly rainfall in Labrado and Chirimachay meteorological stations. To define a suitable model, ridge regression, lasso, random forest (RF), support vector machine (SVM), and NARX network were used. Although the results were “unsatisfactory” with the linear models, the specific direct influences of variables such as Niño 1 + 2, Sahel rainfall, hurricane activity, North Pacific Oscillation, and the same delayed rainfall signal were identified. RF and SVM also demonstrated poor performance. However, RF had a better fit than linear models, and SVM has a better fit than RF models. Instead, the NARX model was trained using several architectures to identify an optimal one for the best prediction twelve months ahead. As an overall evaluation, the NARX model showed “good” results for Labrado and “satisfactory” results for Chirimachay. The predictions yielded by NARX models, for the first six months ahead, were entirely accurate. This study highlighted the strengths of NARX networks in the prediction of chaotic and nonlinear signals such as rainfall in regions that obey complex processes. The results would serve to make short-term plans and give support to decision-makers in the management of water resources.http://dx.doi.org/10.1155/2020/1828319
spellingShingle Mario Peña
Angel Vázquez-Patiño
Darío Zhiña
Martin Montenegro
Alex Avilés
Improved Rainfall Prediction through Nonlinear Autoregressive Network with Exogenous Variables: A Case Study in Andes High Mountain Region
Advances in Meteorology
title Improved Rainfall Prediction through Nonlinear Autoregressive Network with Exogenous Variables: A Case Study in Andes High Mountain Region
title_full Improved Rainfall Prediction through Nonlinear Autoregressive Network with Exogenous Variables: A Case Study in Andes High Mountain Region
title_fullStr Improved Rainfall Prediction through Nonlinear Autoregressive Network with Exogenous Variables: A Case Study in Andes High Mountain Region
title_full_unstemmed Improved Rainfall Prediction through Nonlinear Autoregressive Network with Exogenous Variables: A Case Study in Andes High Mountain Region
title_short Improved Rainfall Prediction through Nonlinear Autoregressive Network with Exogenous Variables: A Case Study in Andes High Mountain Region
title_sort improved rainfall prediction through nonlinear autoregressive network with exogenous variables a case study in andes high mountain region
url http://dx.doi.org/10.1155/2020/1828319
work_keys_str_mv AT mariopena improvedrainfallpredictionthroughnonlinearautoregressivenetworkwithexogenousvariablesacasestudyinandeshighmountainregion
AT angelvazquezpatino improvedrainfallpredictionthroughnonlinearautoregressivenetworkwithexogenousvariablesacasestudyinandeshighmountainregion
AT dariozhina improvedrainfallpredictionthroughnonlinearautoregressivenetworkwithexogenousvariablesacasestudyinandeshighmountainregion
AT martinmontenegro improvedrainfallpredictionthroughnonlinearautoregressivenetworkwithexogenousvariablesacasestudyinandeshighmountainregion
AT alexaviles improvedrainfallpredictionthroughnonlinearautoregressivenetworkwithexogenousvariablesacasestudyinandeshighmountainregion