STFM: Accurate Spatio-Temporal Fusion Model for Weather Forecasting

Liu, Jun; Wu, Li; Zhang, Tao; Huang, Jianqiang; Wang, Xiaoying; Tian, Fang

doi:10.3390/atmos15101176

STFM: Accurate Spatio-Temporal Fusion Model for Weather Forecasting

Journal Article · Mon Sep 30 00:00:00 EDT 2024 · Atmosphere (Basel)

DOI:https://doi.org/10.3390/atmos15101176· OSTI ID:2500909

Liu, Jun; Wu, Li; Zhang, Tao; Huang, Jianqiang; ; Tian, Fang

Meteorological prediction is crucial for various sectors, including agriculture, navigation, daily life, disaster prevention, and scientific research. However, traditional numerical weather prediction (NWP) models are constrained by their high computational resource requirements, while the accuracy of deep learning models remains suboptimal. In response to these challenges, we propose a novel deep learning-based model, the Spatiotemporal Fusion Model (STFM), designed to enhance the accuracy of meteorological predictions. Our model leverages Fifth-Generation ECMWF Reanalysis (ERA5) data and introduces two key components: a spatiotemporal encoder module and a spatiotemporal fusion module. The spatiotemporal encoder integrates the strengths of convolutional neural networks (CNNs) and recurrent neural networks (RNNs), effectively capturing both spatial and temporal dependencies. Meanwhile, the spatiotemporal fusion module employs a dual attention mechanism, decomposing spatial attention into global static attention and channel dynamic attention. This approach ensures comprehensive extraction of spatial features from meteorological data. The combination of these modules significantly improves prediction performance. Experimental results demonstrate that STFM excels in extracting spatiotemporal features from reanalysis data, yielding predictions that closely align with observed values. In comparative studies, STFM outperformed other models, achieving a 7% improvement in ground and high-altitude temperature predictions, a 5% enhancement in the prediction of the u/v components of 10 m wind speed, and an increase in the accuracy of potential height and relative humidity predictions by 3% and 1%, respectively. This enhanced performance highlights STFM’s potential to advance the accuracy and reliability of meteorological forecasting.

View Journal Article

Sponsoring Organization:: USDOE

Grant/Contract Number:: SC0012704

OSTI ID:: 2500909

Alternate ID(s):: OSTI ID: 2475960

Journal Information:: Atmosphere (Basel), Journal Name: Atmosphere (Basel) Journal Issue: 10 Vol. 15; ISSN 2073-4433; ISSN ATMOCZ

Publisher:: MDPI AGCopyright Statement

Country of Publication:: Switzerland

Language:: English

References (29)

Communicating forecast uncertainty: public perception of weather forecast uncertainty Joslyn, Susan; Savelli, Sonia Meteorological Applications, Vol. 17, Issue 2 https://doi.org/10.1002/met.190	journal	April 2010
Predicting weather forecast uncertainty with machine learning Scher, Sebastian; Messori, Gabriele Quarterly Journal of the Royal Meteorological Society, Vol. 144, Issue 717 https://doi.org/10.1002/qj.3410	journal	October 2018
Analysis methods for numerical weather prediction Lorenc, A. C. Quarterly Journal of the Royal Meteorological Society, Vol. 112, Issue 474 https://doi.org/10.1002/qj.49711247414	journal	October 1986
Deep learning-based effective fine-grained weather forecasting model Hewage, Pradeep; Trovati, Marcello; Pereira, Ella Pattern Analysis and Applications, Vol. 24, Issue 1 https://doi.org/10.1007/s10044-020-00898-1	journal	June 2020
Deep Learning-Based Weather Prediction: A Survey Ren, Xiaoli; Li, Xiaoyong; Ren, Kaijun Big Data Research, Vol. 23 https://doi.org/10.1016/j.bdr.2020.100178	journal	February 2021
Curved splicing of copulas Jwaid, T.; Meyer, H. De; Ismail, A. Haj Information Sciences, Vol. 556 https://doi.org/10.1016/j.ins.2020.12.053	journal	May 2021
A spatio-temporal sequence-to-sequence network for traffic flow prediction Cao, Shuqin; Wu, Libing; Wu, Jia Information Sciences, Vol. 610 https://doi.org/10.1016/j.ins.2022.07.125	journal	September 2022
Spatio-temporal fusion for daily Sentinel-2 images Wang, Qunming; Atkinson, Peter M. Remote Sensing of Environment, Vol. 204 https://doi.org/10.1016/j.rse.2017.10.046	journal	January 2018
Computation of optimal unstable structures for a numerical weather prediction model Buizza, R.; Tribbia, J.; Molteni, F. Tellus A, Vol. 45, Issue 5 https://doi.org/10.1034/j.1600-0870.1993.t01-4-00005.x	journal	October 1993
The quiet revolution of numerical weather prediction Bauer, Peter; Thorpe, Alan; Brunet, Gilbert Nature, Vol. 525, Issue 7567 https://doi.org/10.1038/nature14956	journal	September 2015
Estimation of mean monthly global solar radiation using sunshine hours for Nairobi City, Kenya Onyango, A. Omondi; Ongoma, Victor Journal of Renewable and Sustainable Energy, Vol. 7, Issue 5 https://doi.org/10.1063/1.4930530	journal	September 2015
Neural networks and physical systems with emergent collective computational abilities. Hopfield, J. J. Proceedings of the National Academy of Sciences, Vol. 79, Issue 8 https://doi.org/10.1073/pnas.79.8.2554	journal	April 1982
Can deep learning beat numerical weather prediction? Schultz, M. G.; Betancourt, C.; Gong, B. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 379, Issue 2194 https://doi.org/10.1098/rsta.2020.0097	journal	February 2021
Bidirectional recurrent neural networks Schuster, M.; Paliwal, K. K. IEEE Transactions on Signal Processing, Vol. 45, Issue 11 https://doi.org/10.1109/78.650093	journal	January 1997
What's going on? Discovering spatio-temporal dependencies in dynamic scenes Kuettel, Daniel; Breitenstein, Michael D.; Van Gool, Luc 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition https://doi.org/10.1109/CVPR.2010.5539869	conference	June 2010
Temporal Convolutional Networks for Action Segmentation and Detection Lea, Colin; Flynn, Michael D.; Vidal, Rene 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) https://doi.org/10.1109/CVPR.2017.113	conference	July 2017
Squeeze-and-Excitation Networks Hu, Jie; Shen, Li; Sun, Gang 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) https://doi.org/10.1109/CVPR.2018.00745	conference	June 2018
Memory in Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity From Spatiotemporal Dynamics Wang, Yunbo; Zhang, Jianjin; Zhu, Hongyu 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) https://doi.org/10.1109/CVPR.2019.00937	conference	June 2019
Weather forecasting using deep learning techniques Salman, Afan Galih; Kanigoro, Bayu; Heryadi, Yaya 2015 International Conference on Advanced Computer Science and Information Systems (ICACSIS) https://doi.org/10.1109/ICACSIS.2015.7415154	conference	October 2015
Towards Understanding Action Recognition Jhuang, Hueihan; Gall, Juergen; Zuffi, Silvia 2013 IEEE International Conference on Computer Vision https://doi.org/10.1109/ICCV.2013.396	conference	December 2013
A Review on Deep Learning Techniques for Video Prediction Oprea, Sergiu; Martinez-Gonzalez, Pablo; Garcia-Garcia, Alberto IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 44, Issue 6 https://doi.org/10.1109/TPAMI.2020.3045007	journal	June 2022
PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning Wang, Yunbo; Wu, Haixu; Zhang, Jianjin IEEE Transactions on Pattern Analysis and Machine Intelligence https://doi.org/10.1109/TPAMI.2022.3165153	journal	January 2022
UniFormer: Unifying Convolution and Self-Attention for Visual Recognition Li, Kunchang; Wang, Yali; Zhang, Junhao IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 45, Issue 10 https://doi.org/10.1109/TPAMI.2023.3282631	journal	October 2023
A Decision Tree Framework for Spatiotemporal Sequence Prediction Kim, Taehwan; Yue, Yisong; Taylor, Sarah Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining https://doi.org/10.1145/2783258.2783356	conference	August 2015
Preserving Dynamic Attention for Long-Term Spatial-Temporal Prediction Lin, Haoxing; Bai, Rufan; Jia, Weijia Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining https://doi.org/10.1145/3394486.3403046	conference	August 2020
Long Short-Term Memory Hochreiter, Sepp; Schmidhuber, Jürgen Neural Computation, Vol. 9, Issue 8 https://doi.org/10.1162/neco.1997.9.8.1735	journal	November 1997
Text feature extraction based on deep learning: a review Liang, Hong; Sun, Xiao; Sun, Yunlei EURASIP Journal on Wireless Communications and Networking, Vol. 2017, Issue 1 https://doi.org/10.1186/s13638-017-0993-1	journal	December 2017
Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction Zhang, Junbo; Zheng, Yu; Qi, Dekang Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 31, Issue 1 https://doi.org/10.1609/aaai.v31i1.10735	journal	February 2017
A Convolutional Encoder Model for Neural Machine Translation Gehring, Jonas; Auli, Michael; Grangier, David Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) https://doi.org/10.18653/v1/P17-1012	conference	January 2017

Similar Records

Wind Speed Prediction with Spatio–Temporal Correlation: A Deep Learning Approach

Journal Article · Wed Mar 21 00:00:00 EDT 2018 · Energies · OSTI ID:1474549

Predictive Skill of Deep Learning Models Trained on Limited Sequence Data

Technical Report · Thu Oct 01 00:00:00 EDT 2020 · OSTI ID:1688570

STFM: Accurate Spatio-Temporal Fusion Model for Weather Forecasting

Citation Formats

References (29)

Similar Records

Related Subjects