Loading...
Probabilistic sunspot predictions with a gated recurrent units-based combined model guided by pinball loss
Cui, Zhesen Ding, Zhe Xu, Jing Zhang, Shaotong Wu, Jinran Lian, Wei
Cui, Zhesen
Ding, Zhe
Xu, Jing
Zhang, Shaotong
Wu, Jinran
Lian, Wei
Abstract
Sunspots play a crucial role in both weather forecasting and the monitoring of solar storms. In this work, we propose a novel combined model for sunspot prediction using improved gated recurrent units (GRU) guided by pinball loss for probabilistic forecasts. Specifically, we optimize the GRU parameters using the slime mould algorithm and employ a seasonal-trend decomposition procedure based on loess to tackle challenges related to sequence prediction, such as self-correlations and non-stationarity. To address prediction uncertainty, we replace the traditional l_2-norm loss with pinball loss. This modification extends the conventional GRU-based point forecasting to a probabilistic framework expressed as quantiles. We apply our proposed model to analyze a well-established historical sunspot dataset for both single- and multi-step ahead forecasting. The results demonstrate the effectiveness of our combined model in predicting sunspot values, surpassing the performance of other existing methods.
Keywords
Date
2024
Type
Journal article
Journal
Scientific Reports
Book
Volume
14
Issue
1
Page Range
1-16
Article Number
Article 13601
ACU Department
Institute for Positive Psychology and Education
Faculty of Education and Arts
Faculty of Education and Arts
Relation URI
Source URL
Event URL
Open Access Status
Published as ‘gold’ (paid) open access
License
CC BY 4.0
File Access
Open
Notes
© The Author(s) 2024
This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.