Self-Organizing Topological Multilayer Perceptron: A Hybrid Method to Improve the Forecasting of Extreme Pollution Values
Forecasting air pollutant levels is essential in regulatory plans focused on controlling and mitigating air pollutants, such as particulate matter. Focusing the forecast on air pollution peaks is challenging and complex since the pollutant time series behavior is not regular and is affected by sever...
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Artículo |
| Lenguaje: | inglés |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | Ver en el sistema de origen Enlace permanente (DOI o Handle) Enlace permanente (DOI o Handle) |
| Etiquetas: |
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1881508905276669952 |
|---|---|
| author | López Gonzales, Javier Linkolk Gómez Lamus, Ana María Torres, Romina Canas Rodrigues, Paulo Salas, Rodrigo |
| author_browse | Canas Rodrigues, Paulo Gómez Lamus, Ana María López Gonzales, Javier Linkolk Salas, Rodrigo Torres, Romina |
| author_facet | López Gonzales, Javier Linkolk Gómez Lamus, Ana María Torres, Romina Canas Rodrigues, Paulo Salas, Rodrigo |
| author_sort | López Gonzales, Javier Linkolk |
| collection | Producción científica |
| description | Forecasting air pollutant levels is essential in regulatory plans focused on controlling and mitigating air pollutants, such as particulate matter. Focusing the forecast on air pollution peaks is challenging and complex since the pollutant time series behavior is not regular and is affected by several environmental and urban factors. In this study, we propose a new hybrid method based on artificial neural networks to forecast daily extreme events of PM2.5 pollution concentration. The hybrid method combines self-organizing maps to identify temporal patterns of excessive daily pollution found at different monitoring stations, with a set of multilayer perceptron to forecast extreme values of PM2.5 for each cluster. The proposed model was applied to analyze five-year pollution data obtained from nine weather stations in the metropolitan area of Santiago, Chile. Simulation results show that the hybrid method improves performance metrics when forecasting daily extreme values of PM2.5. |
| format | Article |
| id | oai:cris.upeu.edu.pe:20.500.15037/424 |
| institution | UPeU |
| language | English |
| publishDate | 2023 |
| publishDateRange | 2023 |
| publishDateSort | 2023 |
| record_format | dspace |
| spelling | oai:cris.upeu.edu.pe:20.500.15037/4242026-10-30T16:14:37ZSelf-Organizing Topological Multilayer Perceptron: A Hybrid Method to Improve the Forecasting of Extreme Pollution ValuesLópez Gonzales, Javier LinkolkGómez Lamus, Ana MaríaTorres, RominaCanas Rodrigues, PauloSalas, Rodrigoair pollutionhybrid methodologyartificial neural networkstime series forecastingForecasting air pollutant levels is essential in regulatory plans focused on controlling and mitigating air pollutants, such as particulate matter. Focusing the forecast on air pollution peaks is challenging and complex since the pollutant time series behavior is not regular and is affected by several environmental and urban factors. In this study, we propose a new hybrid method based on artificial neural networks to forecast daily extreme events of PM2.5 pollution concentration. The hybrid method combines self-organizing maps to identify temporal patterns of excessive daily pollution found at different monitoring stations, with a set of multilayer perceptron to forecast extreme values of PM2.5 for each cluster. The proposed model was applied to analyze five-year pollution data obtained from nine weather stations in the metropolitan area of Santiago, Chile. Simulation results show that the hybrid method improves performance metrics when forecasting daily extreme values of PM2.5.Articlehttps://www.mdpi.com/2571-905X/6/4/77/pdf?version=1699693856https://doi.org/10.3390/stats604007710.3390/stats6040077https://hdl.handle.net/20.500.15037/424W4388629651enStats2571-905X2023-11-112026-06-13T08:13:17Z2026-06-13T08:13:17Z |
| spellingShingle | air pollution hybrid methodology artificial neural networks time series forecasting López Gonzales, Javier Linkolk Gómez Lamus, Ana María Torres, Romina Canas Rodrigues, Paulo Salas, Rodrigo Self-Organizing Topological Multilayer Perceptron: A Hybrid Method to Improve the Forecasting of Extreme Pollution Values |
| title | Self-Organizing Topological Multilayer Perceptron: A Hybrid Method to Improve the Forecasting of Extreme Pollution Values |
| title_full | Self-Organizing Topological Multilayer Perceptron: A Hybrid Method to Improve the Forecasting of Extreme Pollution Values |
| title_fullStr | Self-Organizing Topological Multilayer Perceptron: A Hybrid Method to Improve the Forecasting of Extreme Pollution Values |
| title_full_unstemmed | Self-Organizing Topological Multilayer Perceptron: A Hybrid Method to Improve the Forecasting of Extreme Pollution Values |
| title_short | Self-Organizing Topological Multilayer Perceptron: A Hybrid Method to Improve the Forecasting of Extreme Pollution Values |
| title_sort | self organizing topological multilayer perceptron a hybrid method to improve the forecasting of extreme pollution values |
| topic | air pollution hybrid methodology artificial neural networks time series forecasting |
| topic_facet | air pollution hybrid methodology artificial neural networks time series forecasting |
| url | https://www.mdpi.com/2571-905X/6/4/77/pdf?version=1699693856 https://doi.org/10.3390/stats6040077 https://hdl.handle.net/20.500.15037/424 |
| work_keys_str_mv | AT lopezgonzalesjavierlinkolk selforganizingtopologicalmultilayerperceptronahybridmethodtoimprovetheforecastingofextremepollutionvalues AT gomezlamusanamaria selforganizingtopologicalmultilayerperceptronahybridmethodtoimprovetheforecastingofextremepollutionvalues AT torresromina selforganizingtopologicalmultilayerperceptronahybridmethodtoimprovetheforecastingofextremepollutionvalues AT canasrodriguespaulo selforganizingtopologicalmultilayerperceptronahybridmethodtoimprovetheforecastingofextremepollutionvalues AT salasrodrigo selforganizingtopologicalmultilayerperceptronahybridmethodtoimprovetheforecastingofextremepollutionvalues |