Abstract
Temperature prediction is a critical component of weather forecasting, impacting human life, safety, and property. Compared to traditional numerical weather prediction models, data-driven deep learning methods have more advantages in terms of computational time and resource consumption. However, existing deep learning methods also have inherent drawbacks, such as producing more ambiguous and diffused forecast results. To address these limitations, we introduce a novel model composed of a Spatiotemporal Perception Module (SPM) and an enhanced diffusion model. The SPM captures the long-term dependency information, serving as the generation condition for the diffusion model, and thereby endowing it with forecasting capabilities. We also introduce a new equilibrium loss function that balances the generation abilities of the diffusion model and the spatiotemporal information extraction capabilities of the SPM. Our model demonstrates superior performance on Weatherbench temperature prediction. It achieves a 13.3%.
Supported by the National Natural Science Foundation of China (Grant No.42075007) and the Open Project of Provincial Key Laboratory for Computer Information Processing Technology under Grant KJS2275, Soochow University.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Castro, R., Souto, Y.M., Ogasawara, E., et al.: STConvS2S: spatiotemporal convolutional sequence to sequence network for weather forecasting. Neurocomputing 426, 285–298 (2021)
Hewage, P., Trovati, M., Pereira, E., et al.: Deep learning-based effective fine-grained weather forecasting model. Pattern Anal. Appl. 24(1), 343–366 (2021)
Hewage, P., Behera, A., Trovati, M., et al.: Temporal convolutional neural (TCN) network for an effective weather forecasting using time-series data from the local weather station. Soft. Comput. 24, 16453–16482 (2020)
Meti, G., GK, R.K.: Analogousness enhanced rainfall predictor using XGBoost backbone. Int. J. Intell. Syst. Appl. Eng. 11(2), 329–335 (2023)
Quan Q, Hao Z, Xi feng H, et al.: Research on water temperature prediction based on improved support vector regression. Neural Comput. Appl., 1–10 (2020)
Ayzel, G., Heistermann, M., Sorokin, A., et al.: All convolutional neural networks for radar-based precipitation nowcasting. Procedia Comput. Sci. 150, 186–192 (2019)
Sari, A.P., Suzuki, H., Kitajima, T., et al.: Short-term wind speed and direction forecasting by 3DCNN and deep convolutional LSTM. IEEJ Trans. Electrical Electron. Eng. 17(11), 1620–1628 (2022)
Fernández, J.G., Mehrkanoon, S.: Broad-UNet: multi-scale feature learning for nowcasting tasks. Neural Netw. 144, 419–427 (2021)
Trebing, K., Stanczyk, T., Mehrkanoon, S.: SmaAt-UNet: precipitation nowcasting using a small attention-UNet architecture. Pattern Recogn. Lett. 145, 178–186 (2021)
Xie, W.H., Xu, G.J., Dong, C.M.: Research on storm surge floodplain prediction based on ConvL STM machine learning. Trans. At-mos Sci. 45(5), 674–687 (2022)
Luo, C., Li, X., Ye, Y.: PFST-LSTM: a spatiotemporal LSTM model with pseudoflow prediction for precipitation nowcasting. IEEE J. Selected Top. Appl. Earth Observ. Remote Sens. 14, 843–857 (2020)
Ravuri, S., Lenc, K., Willson, M., et al.: Skilful precipitation nowcasting using deep generative models of radar. Nature 597(7878), 672–677 (2021)
Xu, Z., Du, J., Wang, J., et al.: Satellite image prediction relying on GAN and LSTM neural networks. In: ICC 2019–2019 IEEE International Conference on Communications (ICC), pp. 1–6. IEEE, Shanghai (2019)
Shi, X., Chen, Z., Wang, H., et al.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting. Adv. Neural. Inf. Process. Syst. 28, 802–810 (2015)
Wang, Y., Long, M., Wang, J., et al.: PredRNN: recurrent neural networks for predictive learning using spatiotemporal LSTMs. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 879–888. Curran Associates, California (2017)
Wang, Y., Zhang, J., Zhu, H., et al.: Memory in memory: a predictive neural network for learning higher-order non-stationarity from spatiotemporal dynamics. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9154–9162. IEEE, California (2019)
Wang, Y., Jiang, L., Yang, M.H., et al.: Eidetic 3D LSTM: a model for video prediction and beyond. In: International Conference on Learning Representations, OpenReview.net, New Orleans (2018)
Guen, V.L., Thome, N.: Disentangling physical dynamics from unknown factors for unsupervised video prediction. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11474–11484. IEEE, Seattle (2020)
Lin, Z., Li, M., Zheng, Z., et al.: Self-attention ConvLSTM for spatiotemporal prediction. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 11531–11538, AAAI Press, New York (2020)
Wang, Y., Gao, Z., Long, M., et al.: PredRNN++: towards a resolution of the deep-in-time dilemma in spatiotemporal predictive learning. In: International Conference on Machine Learning, pp. 5123–5132. PMLR, Stockholm (2018)
Yu, W., Lu, Y., Easterbrook, S., et al.: Efficient and information-preserving future frame prediction and beyond. In: International Conference on Learning Representations, OpenReview.net, Addis Ababa (2019)
Cemgil, T., Ghaisas, S., Dvijotham, K., et al.: The autoencoding variational autoencoder. Adv. Neural. Inf. Process. Syst. 33, 15077–15087 (2020)
Goodfellow, I., Pouget-Abadie, J., Mirza, M., et al.: Generative adversarial networks. Commun. ACM 63(11), 139–144 (2020)
Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840–6851 (2020)
Kingma, D., Salimans, T., Poole, B., et al.: Variational diffusion models. Adv. Neural. Inf. Process. Syst. 34, 21696–21707 (2021)
Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: International Conference on Machine Learning, pp. 8162–8171. PMLR, Virtually (2021)
Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780–8794 (2021)
Wang, Y., Wu, H., Zhang, J., et al.: PredRNN: a recurrent neural network for spatiotemporal predictive learning. IEEE Trans. Pattern Anal. Mach. Intell. (2022)
Rasp, S., Dueben, P.D., Scher, S., et al.: WeatherBench: a benchmark data set for data-driven weather forecasting. J. Adv. Model. Earth Syst. 12(11), e2020MS002203 (2020)
Gao, Z., Tan, C., Wu, L., et al.: SimVP: simpler yet better video prediction. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3170–3180. IEEE/CVF, New York (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Fang, W., Yuan, Z., Xue, Q. (2023). SPM-Diffusion for Temperature Prediction. In: Iliadis, L., Papaleonidas, A., Angelov, P., Jayne, C. (eds) Artificial Neural Networks and Machine Learning – ICANN 2023. ICANN 2023. Lecture Notes in Computer Science, vol 14262. Springer, Cham. https://doi.org/10.1007/978-3-031-44201-8_31
Download citation
DOI: https://doi.org/10.1007/978-3-031-44201-8_31
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44200-1
Online ISBN: 978-3-031-44201-8
eBook Packages: Computer ScienceComputer Science (R0)