TAE Predict: An Ensemble Methodology for Multivariate Time Series Forecasting of Climate Variables in the Context of Climate Change

Climate change presents significant challenges due to the increasing frequency and intensity of extreme weather events. Mexico, with its diverse climate and geographic position, is particularly vulnerable, underscoring the need for robust strategies to predict atmospheric variables. This work presen...

Full description

Saved in:
Bibliographic Details
Main Authors: Juan Frausto Solís, Erick Estrada-Patiño, Mirna Ponce Flores, Juan Paulo Sánchez-Hernández, Guadalupe Castilla-Valdez, Javier González-Barbosa
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Mathematical and Computational Applications
Subjects:
Online Access:https://www.mdpi.com/2297-8747/30/3/46
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849432319049334784
author Juan Frausto Solís
Erick Estrada-Patiño
Mirna Ponce Flores
Juan Paulo Sánchez-Hernández
Guadalupe Castilla-Valdez
Javier González-Barbosa
author_facet Juan Frausto Solís
Erick Estrada-Patiño
Mirna Ponce Flores
Juan Paulo Sánchez-Hernández
Guadalupe Castilla-Valdez
Javier González-Barbosa
author_sort Juan Frausto Solís
collection DOAJ
description Climate change presents significant challenges due to the increasing frequency and intensity of extreme weather events. Mexico, with its diverse climate and geographic position, is particularly vulnerable, underscoring the need for robust strategies to predict atmospheric variables. This work presents TAE Predict (Time series Analysis and Ensemble-based Prediction with relevant feature selection) based on relevant feature selection and ensemble models of machine learning. Dimensionality in multivariate time series is reduced through Principal Component Analysis, ensuring interpretability and efficiency. Additionally, data remediation techniques improve data set quality. The ensemble combines Long Short-Term Memory neural networks, Random Forest regression, and Support Vector Machines, optimizing their contributions using heuristic algorithms such as Particle Swarm Optimization. Experimental results from meteorological time series in key Mexican cities demonstrate that the proposed strategy outperforms individual models in accuracy and robustness. This methodology provides a replicable framework for climate variable forecasting, delivering analytical tools that support decision-making in critical sectors, such as agriculture and water resource management. The findings highlight the potential of integrating modern techniques to address complex, high-dimensional problems. By combining advanced prediction models and feature selection strategies, this study advances the reliability of climate forecasts and contributes to the development of effective adaptation and mitigation measures in response to climate change challenges.
format Article
id doaj-art-ef6b8f3198c94fccb7b22b80f17efeca
institution Kabale University
issn 1300-686X
2297-8747
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Mathematical and Computational Applications
spelling doaj-art-ef6b8f3198c94fccb7b22b80f17efeca2025-08-20T03:27:24ZengMDPI AGMathematical and Computational Applications1300-686X2297-87472025-04-013034610.3390/mca30030046TAE Predict: An Ensemble Methodology for Multivariate Time Series Forecasting of Climate Variables in the Context of Climate ChangeJuan Frausto Solís0Erick Estrada-Patiño1Mirna Ponce Flores2Juan Paulo Sánchez-Hernández3Guadalupe Castilla-Valdez4Javier González-Barbosa5Graduate Program Division, Tecnológico Nacional de México/Instituto Tecnológico de Ciudad Madero, Ciudad Madero 89440, MexicoGraduate Program Division, Tecnológico Nacional de México/Instituto Tecnológico de Ciudad Madero, Ciudad Madero 89440, MexicoGraduate Program Division, Tecnológico Nacional de México/Instituto Tecnológico de Ciudad Madero, Ciudad Madero 89440, MexicoDirección de Informático, Electrónica y Telecomunicaciones, Universidad Politécnica del Estado de Morelos, Boulevard Cuauhnáhuac 566, Jiutepec 62574, MexicoGraduate Program Division, Tecnológico Nacional de México/Instituto Tecnológico de Ciudad Madero, Ciudad Madero 89440, MexicoGraduate Program Division, Tecnológico Nacional de México/Instituto Tecnológico de Ciudad Madero, Ciudad Madero 89440, MexicoClimate change presents significant challenges due to the increasing frequency and intensity of extreme weather events. Mexico, with its diverse climate and geographic position, is particularly vulnerable, underscoring the need for robust strategies to predict atmospheric variables. This work presents TAE Predict (Time series Analysis and Ensemble-based Prediction with relevant feature selection) based on relevant feature selection and ensemble models of machine learning. Dimensionality in multivariate time series is reduced through Principal Component Analysis, ensuring interpretability and efficiency. Additionally, data remediation techniques improve data set quality. The ensemble combines Long Short-Term Memory neural networks, Random Forest regression, and Support Vector Machines, optimizing their contributions using heuristic algorithms such as Particle Swarm Optimization. Experimental results from meteorological time series in key Mexican cities demonstrate that the proposed strategy outperforms individual models in accuracy and robustness. This methodology provides a replicable framework for climate variable forecasting, delivering analytical tools that support decision-making in critical sectors, such as agriculture and water resource management. The findings highlight the potential of integrating modern techniques to address complex, high-dimensional problems. By combining advanced prediction models and feature selection strategies, this study advances the reliability of climate forecasts and contributes to the development of effective adaptation and mitigation measures in response to climate change challenges.https://www.mdpi.com/2297-8747/30/3/46climate changemultivariate time seriesdeep learningprincipal component analysisensemble methodsparticle swarm optimization
spellingShingle Juan Frausto Solís
Erick Estrada-Patiño
Mirna Ponce Flores
Juan Paulo Sánchez-Hernández
Guadalupe Castilla-Valdez
Javier González-Barbosa
TAE Predict: An Ensemble Methodology for Multivariate Time Series Forecasting of Climate Variables in the Context of Climate Change
Mathematical and Computational Applications
climate change
multivariate time series
deep learning
principal component analysis
ensemble methods
particle swarm optimization
title TAE Predict: An Ensemble Methodology for Multivariate Time Series Forecasting of Climate Variables in the Context of Climate Change
title_full TAE Predict: An Ensemble Methodology for Multivariate Time Series Forecasting of Climate Variables in the Context of Climate Change
title_fullStr TAE Predict: An Ensemble Methodology for Multivariate Time Series Forecasting of Climate Variables in the Context of Climate Change
title_full_unstemmed TAE Predict: An Ensemble Methodology for Multivariate Time Series Forecasting of Climate Variables in the Context of Climate Change
title_short TAE Predict: An Ensemble Methodology for Multivariate Time Series Forecasting of Climate Variables in the Context of Climate Change
title_sort tae predict an ensemble methodology for multivariate time series forecasting of climate variables in the context of climate change
topic climate change
multivariate time series
deep learning
principal component analysis
ensemble methods
particle swarm optimization
url https://www.mdpi.com/2297-8747/30/3/46
work_keys_str_mv AT juanfraustosolis taepredictanensemblemethodologyformultivariatetimeseriesforecastingofclimatevariablesinthecontextofclimatechange
AT erickestradapatino taepredictanensemblemethodologyformultivariatetimeseriesforecastingofclimatevariablesinthecontextofclimatechange
AT mirnaponceflores taepredictanensemblemethodologyformultivariatetimeseriesforecastingofclimatevariablesinthecontextofclimatechange
AT juanpaulosanchezhernandez taepredictanensemblemethodologyformultivariatetimeseriesforecastingofclimatevariablesinthecontextofclimatechange
AT guadalupecastillavaldez taepredictanensemblemethodologyformultivariatetimeseriesforecastingofclimatevariablesinthecontextofclimatechange
AT javiergonzalezbarbosa taepredictanensemblemethodologyformultivariatetimeseriesforecastingofclimatevariablesinthecontextofclimatechange