Patch-aware Long-term Weather Forecasting

DOI

10.2991/978-94-6463-276-7_50How to use a DOI?

Keywords

Time series prediction; PatchTST; weather

Abstract

This paper explores the prediction of weather condition and employs long-sequence time-series forecasting techniques, specifically the Transformer model. Contrary to traditional methods that examined the model based on prediction length, we focus on the analysis of the relationship between patch value and prediction accuracy of the PatchTST Transformer model. The statistical analysis involves identifying specific words or phrases in news titles and correlating them with view counts. Through experiments, we demonstrate that the Transformer model effectively predicts the popularity of news articles based on weather information, yielding accurate results. We hope this work illuminates the untapped potential of utilizing weather data to forecast public engagement with news content and uncovers novel insights into the intricate relationship between weather conditions and public attention.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial 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 license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Aslan Feng
PY  - 2023
DA  - 2023/10/27
TI  - Patch-aware Long-term Weather Forecasting
BT  - Proceedings of the 2023 4th International Conference on Big Data and Social Sciences (ICBDSS 2023)
PB  - Atlantis Press
SP  - 475
EP  - 484
SN  - 2667-128X
UR  - https://doi.org/10.2991/978-94-6463-276-7_50
DO  - 10.2991/978-94-6463-276-7_50
ID  - Feng2023
ER  -