Spatial–Temporal Temperature Forecasting Using Deep-Neural-Network-Based Domain Adaptation
-
Published:2024-01-10
Issue:1
Volume:15
Page:90
-
ISSN:2073-4433
-
Container-title:Atmosphere
-
language:en
-
Short-container-title:Atmosphere
Author:
Tran Vu1ORCID, Septier François2ORCID, Murakami Daisuke1ORCID, Matsui Tomoko1ORCID
Affiliation:
1. The Institute of Statistical Mathematics, Tokyo 190-8562, Japan 2. UMR CNRS 6205, LMBA, Université Bretagne Sud, F-56000 Vannes, France
Abstract
Accurate temperature forecasting is critical for various sectors, yet traditional methods struggle with complex atmospheric dynamics. Deep neural networks (DNNs), especially transformer-based DNNs, offer potential advantages, but face challenges with domain adaptation across different geographical regions. We evaluated the effectiveness of DNN-based domain adaptation for daily maximum temperature forecasting in experimental low-resource settings. We used an attention-based transformer deep learning architecture as the core forecasting framework and used kernel mean matching (KMM) for domain adaptation. Domain adaptation significantly improved forecasting accuracy in most experimental settings, thereby mitigating domain differences between source and target regions. Specifically, we observed that domain adaptation is more effective than exclusively training on a small amount of target-domain training data. This study reinforces the potential of using DNNs for temperature forecasting and underscores the benefits of domain adaptation using KMM. It also highlights the need for caution when using small amounts of target-domain data to avoid overfitting. Future research includes investigating strategies to minimize overfitting and to further probe the effect of various factors on model performance.
Funder
Research Organization of Information and Systems
Subject
Atmospheric Science,Environmental Science (miscellaneous)
Reference22 articles.
1. Lee, S., Lee, Y.S., and Son, Y. (2020). Forecasting daily temperatures with different time interval data using deep neural networks. Appl. Sci., 10. 2. Use of new variables based on air temperature for forecasting day-ahead spot electricity prices using deep neural networks: A new approach;Energy,2020 3. Neural networks for postprocessing ensemble weather forecasts;Rasp;Mon. Weather. Rev.,2018 4. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł., and Polosukhin, I. (2017, January 4–9). Attention is all you need. In Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA. 5. Zhao, W.X., Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y., Min, Y., Zhang, B., Zhang, J., and Dong, Z. (2023). A survey of large language models. arXiv.
|
|