Abstract
General Circulation Models (GCMs) are established numerical models for simulating multiple climate variables, decades into the future. GCMs produce such simulations at coarse resolution (100 to 600 km), making them inappropriate to monitor climate change at the local regional level. Downscaling approaches are usually adopted to infer the statistical relationship between the coarse simulations of GCMs and local observations and use the relationship to evaluate the simulations at a finer scale. In this paper, we propose a novel deep learning framework for forecasting daily precipitation values via downscaling. Our framework, named Precipitation CNN or PCNN, employs multi-head convolutional neural networks (CNNs) followed by Bahdanau attention blocks and an uncertainty quantification component with Bayesian inference. We apply PCNN to downscale the daily precipitation above the New Jersey portion of the Hackensack-Passaic watershed. Experiments show that PCNN is suitable for this task, reproducing the daily variability of precipitation. Moreover, we produce local-scale precipitation projections for multiple periods into the future (up to year 2100).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ahmed, K., Shahid, S., Haroon, S.B., Xiao-Jun, W.: Multilayer perceptron neural network for downscaling rainfall in arid region: a case study of Baluchistan, Pakistan. J. Earth Syst. Sci. 124(6), 1325–1341 (2015). https://doi.org/10.1007/s12040-015-0602-9
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: 3rd International Conference on Learning Representations (2015)
Blei, D.M., Kucukelbir, A., McAuliffe, J.D.: Variational inference: a review for statisticians. J. Am. Stat. Assoc. 112(518), 859–877 (2017)
Fang, J., Zhu, J., Wang, S., Yue, C., Shen, H.: Global warming, human-induced carbon emissions, and their uncertainties. Sci. China Earth Sci. 54(10), 1458–1468 (2011). https://doi.org/10.1007/s11430-011-4292-0
Gerges, F., Boufadel, M.C., Bou-Zeid, E., Nassif, H., Wang, J.T.L.: A novel deep learning approach to the statistical downscaling of temperatures for monitoring climate change. In: The 6th International Conference on Machine Learning and Soft Computing. ACM (2022). https://doi.org/10.1145/3523150.3523151
Gerges, F., Boufadel, M.C., Bou-Zeid, E., Nassif, H., Wang, J.T.: A novel Bayesian deep learning approach to the downscaling of wind speed with uncertainty quantification. In: Gama, J., Li, T., Yu, Y., Chen, E., Zheng, Y., Teng, F. (eds.) Advances in Knowledge Discovery and Data Mining, PAKDD 2022. LNCS, vol. 13282, pp. 55–66. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-05981-0_5
Gerges, F., Shih, F., Azar, D.: Automated diagnosis of acne and rosacea using convolution neural networks. In: 2021 4th International Conference on Artificial Intelligence and Pattern Recognition, pp. 607–613 (2021)
Gerges, F., Shih, F.Y.: A convolutional deep neural network approach for skin cancer detection using skin lesion images. Int. J. Electr. Comput. Eng. 15(8), 475–478 (2021)
Ghosh, S.: SVM-PGSL coupled approach for statistical downscaling to predict rainfall from GCM output. J, Geophys. Res. Atmos. 115(D22) (2010)
Goodfellow, I., Bengio, Y., Courville, A., Bengio, Y.: Deep Learning, vol. 1. MIT press, Cambridge (2016)
Griffies, S.M., et al.: The GFDL CM3 coupled climate model: characteristics of the ocean and sea ice simulations. J. Clim. 24(13), 3520–3544 (2011)
Hu, W., Scholz, Y., Yeligeti, M., von Bremen, L., Schroedter-Homscheidt, M.: Statistical downscaling of wind speed time series data based on topographic variables. In: EGU General Assembly Conference Abstracts, pp. EGU21-12734 (2021)
Jiang, H., et al.: Tracing h alpha fibrils through Bayesian deep learning. Astrophys. J. Suppl. Ser. 256(1), 20 (2021)
Khan, Z.N., Ahmad, J.: Attention induced multi-head convolutional neural network for human activity recognition. Appl. Soft Comput. 110, 107671 (2021)
Kwon, Y., Won, J.H., Kim, B.J., Paik, M.C.: Uncertainty quantification using Bayesian neural networks in classification: application to biomedical image segmentation. Comput. Stat. Data Anal. 142, 106816 (2020)
Linmans, J., van der Laak, J., Litjens, G.: Efficient out-of-distribution detection in digital pathology using multi-head convolutional neural networks. In: MIDL, pp. 465–478 (2020)
Liu, J.: Variable selection with rigorous uncertainty quantification using deep Bayesian neural networks: posterior concentration and Bernstein-von mises phenomenon. In: International Conference on Artificial Intelligence and Statistics, pp. 3124–3132. PMLR (2021)
Liu, Z., Wan, M., Guo, S., Achan, K., Yu, P.S.: Basconv: aggregating heterogeneous interactions for basket recommendation with graph convolutional neural network. In: Proceedings of the 2020 SIAM International Conference on Data Mining, pp. 64–72. SIAM (2020)
Livneh, B., et al.: A spatially comprehensive, hydrometeorological data set for Mexico, the us, and southern Canada 1950–2013. Sci. Data 2(1), 1–12 (2015)
Misra, S., Sarkar, S., Mitra, P.: Statistical downscaling of precipitation using long short-term memory recurrent neural networks. Theor. Appl. Climatol. 134(3), 1179–1196 (2018)
Myojin, T., Hashimoto, S., Ishihama, N.: Detecting uncertain BNN outputs on FPGA using monte Carlo dropout sampling. In: Farkaš, I., Masulli, P., Wermter, S. (eds.) ICANN 2020. LNCS, vol. 12397, pp. 27–38. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-61616-8_3
Myojin, T., Hashimoto, S., Mori, K., Sugawara, K., Ishihama, N.: Improving reliability of object detection for lunar craters using monte Carlo dropout. In: Tetko, I.V., Kůrková, V., Karpov, P., Theis, F. (eds.) ICANN 2019. LNCS, vol. 11729, pp. 68–80. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30508-6_6
Pan, X., Shi, J., Luo, P., Wang, X., Tang, X.: Spatial as deep: spatial CNN for traffic scene understanding. In: 32nd AAAI Conference on Artificial Intelligence (2018)
Pang, B., Yue, J., Zhao, G., Xu, Z.: Statistical downscaling of temperature with the random forest model. Adv. Meteorol. 2017 (2017)
Sun, L., Lan, Y.: Statistical downscaling of daily temperature and precipitation over china using deep learning neural models: Localization and comparison with other methods. Int.l J. Climatol. 41(2), 1128–1147 (2021)
Wang, Y., Rocková, V.: Uncertainty quantification for sparse deep learning. In: International Conference on Artificial Intelligence and Statistics, pp. 298–308. PMLR (2020)
Xu, R., Chen, N., Chen, Y., Chen, Z.: Downscaling and projection of multi-cmip5 precipitation using machine learning methods in the upper HAN river Basin. Adv. Meteorol. 2020, 1–17 (2020)
Acknowledgements
This work was supported by the Bridge Resource Program (BRP) from the New Jersey Department of Transportation. We acknowledge the Working Group on Coupled Modelling of the World Climate Research Program, responsible for CMIP, and we thank the Geophysical Fluid Dynamics Laboratory of NOAA for producing and making available their model output via Earth System Grid Federation.
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
Gerges, F., Boufadel, M.C., Bou-Zeid, E., Darekar, A., Nassif, H., Wang, J.T.L. (2023). Bayesian Multi-head Convolutional Neural Networks with Bahdanau Attention for Forecasting Daily Precipitation in Climate Change Monitoring. In: Amini, MR., Canu, S., Fischer, A., Guns, T., Kralj Novak, P., Tsoumakas, G. (eds) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2022. Lecture Notes in Computer Science(), vol 13717. Springer, Cham. https://doi.org/10.1007/978-3-031-26419-1_34
Download citation
DOI: https://doi.org/10.1007/978-3-031-26419-1_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-26418-4
Online ISBN: 978-3-031-26419-1
eBook Packages: Computer ScienceComputer Science (R0)