Combining Seasonal and Trend Decomposition Using LOESS With a Gated Recurrent Unit for Climate Time Series Forecasting
Temperature, as a key indicator of climate change, is a constant object of research focus due to its importance in accurate forecasting. Traditional meteorological models have limitations in handling complex temperature data, and deep recurrent network techniques, known for their excellent performan...
| Published in: | IEEE Access |
|---|---|
| Main Authors: | , |
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10559488/ |
| _version_ | 1850303934080483328 |
|---|---|
| author | Xiao Liu Qianqian Zhang |
| author_facet | Xiao Liu Qianqian Zhang |
| author_sort | Xiao Liu |
| collection | DOAJ |
| container_title | IEEE Access |
| description | Temperature, as a key indicator of climate change, is a constant object of research focus due to its importance in accurate forecasting. Traditional meteorological models have limitations in handling complex temperature data, and deep recurrent network techniques, known for their excellent performance in capturing long-term dependencies in time series, offer new possibilities for climate prediction. This paper adopts a decomposition strategy to address the temporal features of meteorological data and proposes a decomposition-prediction model combining seasonal and trend decomposition using LOESS and gated recurrent unit (STL-GRU) neural networks. By applying this model to datasets from three different regions in Gansu Province, China, the effectiveness of the model is demonstrated. The results show that the combination of decomposition methods and deep learning techniques improves the accuracy of seasonal variations and long-term prediction trends of temperature data, and the root-mean-square errors of the proposed model in the prediction of three real surface temperature datasets are 1.7707, 1.2681, and 1.4166, respectively. |
| format | Article |
| id | doaj-art-8e8287c84dfb4cf7a7442543948e606d |
| institution | Directory of Open Access Journals |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| spelling | doaj-art-8e8287c84dfb4cf7a7442543948e606d2025-08-19T23:29:58ZengIEEEIEEE Access2169-35362024-01-0112852758529010.1109/ACCESS.2024.341534910559488Combining Seasonal and Trend Decomposition Using LOESS With a Gated Recurrent Unit for Climate Time Series ForecastingXiao Liu0https://orcid.org/0009-0007-1671-7590Qianqian Zhang1Department of Software Engineering, Tongji University, Shanghai, ChinaCollege of Physics and Electronic Engineering, Northwest Normal University, Lanzhou, ChinaTemperature, as a key indicator of climate change, is a constant object of research focus due to its importance in accurate forecasting. Traditional meteorological models have limitations in handling complex temperature data, and deep recurrent network techniques, known for their excellent performance in capturing long-term dependencies in time series, offer new possibilities for climate prediction. This paper adopts a decomposition strategy to address the temporal features of meteorological data and proposes a decomposition-prediction model combining seasonal and trend decomposition using LOESS and gated recurrent unit (STL-GRU) neural networks. By applying this model to datasets from three different regions in Gansu Province, China, the effectiveness of the model is demonstrated. The results show that the combination of decomposition methods and deep learning techniques improves the accuracy of seasonal variations and long-term prediction trends of temperature data, and the root-mean-square errors of the proposed model in the prediction of three real surface temperature datasets are 1.7707, 1.2681, and 1.4166, respectively.https://ieeexplore.ieee.org/document/10559488/Gated recurrent unitseasonal and trend decomposition using LOESSclimate predictiondeep learning |
| spellingShingle | Xiao Liu Qianqian Zhang Combining Seasonal and Trend Decomposition Using LOESS With a Gated Recurrent Unit for Climate Time Series Forecasting Gated recurrent unit seasonal and trend decomposition using LOESS climate prediction deep learning |
| title | Combining Seasonal and Trend Decomposition Using LOESS With a Gated Recurrent Unit for Climate Time Series Forecasting |
| title_full | Combining Seasonal and Trend Decomposition Using LOESS With a Gated Recurrent Unit for Climate Time Series Forecasting |
| title_fullStr | Combining Seasonal and Trend Decomposition Using LOESS With a Gated Recurrent Unit for Climate Time Series Forecasting |
| title_full_unstemmed | Combining Seasonal and Trend Decomposition Using LOESS With a Gated Recurrent Unit for Climate Time Series Forecasting |
| title_short | Combining Seasonal and Trend Decomposition Using LOESS With a Gated Recurrent Unit for Climate Time Series Forecasting |
| title_sort | combining seasonal and trend decomposition using loess with a gated recurrent unit for climate time series forecasting |
| topic | Gated recurrent unit seasonal and trend decomposition using LOESS climate prediction deep learning |
| url | https://ieeexplore.ieee.org/document/10559488/ |
| work_keys_str_mv | AT xiaoliu combiningseasonalandtrenddecompositionusingloesswithagatedrecurrentunitforclimatetimeseriesforecasting AT qianqianzhang combiningseasonalandtrenddecompositionusingloesswithagatedrecurrentunitforclimatetimeseriesforecasting |