A Machine Learning-Based Parameterized Tropical Cyclone Precipitation Model

Abstract

Current simulation models considerably underestimate local-scale, short-duration extreme precipitation induced by tropical cyclones (TCs). This problem needs to be addressed to establish active response policies for TC-induced disasters. Taking Shanghai, a coastal megacity, as a study area and based on the observations from 192 meteorological stations in the city during 2005–2018, this study optimized the parameterized Tropical Cyclone Precipitation Model (TCPM) initially designed for TCs at the national scale (China) to the local or regional scales by using machine learning (ML) methods, including the random forest (RF), extreme gradient boosting (XGBoost), and ensemble learning (EL) algorithms. The TCPM-ML was applied for multiple temporal scale hazard assessment. The results show that: (1) The TCPM-ML not only improved TCPM performance for simulating hourly extreme precipitations, but also preserved the physical meaning of the results, contrary to ML methods; (2) Machine learning algorithms enhanced the TCPM ability to reproduce observations, although the hourly extreme precipitations remained slightly underestimated; (3) Best performance was obtained with the XGBoost or EL algorithms. Combining the strengths of both XGBoost and RF, the EL algorithm yielded the best overall performance. This study provides essential model support for TC disaster risk assessment and response at the local and regional scales in China.

References

[] ChenJ, ChangC, LiT. Annual cycle of the South China Sea surface temperature using the NCEP/NCAR reanalysis. Journal of the Meteorological Society of Japan, 2003, 81(4): 879-884

[] Chen, L., Z. Meng, and C. Cong. 2017. An overview on the research of typhoon rainfall distribution. Journal of Marine Meteorology 37(4): 1–7 (in Chinese).

[] Chen, P.Y., H. Yu, K.K.W. Cheung, J. Xin, and Y. Lu. 2021. A potential risk index dataset for landfalling tropical cyclones over the Chinese mainland (PRITC dataset V1.0). Advances in Atmospheric Sciences 38(10): Article 12.

[] EmanuelKA. Downscaling CMIP5 climate models shows increased tropical cyclone activity over the 21st century. Proceedings of the National Academy of Sciences of the United States of America, 2013, 110(30): 12219-12224

[] EmanuelKA. Assessing the present and future probability of hurricane Harvey’s rainfall. Proceedings of the National Academy of Sciences of the United States of America, 2017, 114(48): 12681-12684

[] EmanuelKA. Response of global tropical cyclone activity to increasing CO₂: Results from downscaling CMIP6 models. Journal of Climate, 2021, 34(1): 57-70

[] Emanuel, K.A. 2024. Cyclone Jasper’s rains in the context of climate change. Proceedings of the National Academy of Sciences 121(15): Article e2400292121.

[] EmanuelK, SundararajanR, WilliamsJ. Hurricanes and global warming: Results from downscaling IPCC AR4 simulations. Bulletin of the American Meteorological Society, 2008, 89(3): 347-367

[] Fang, W., and X. Shi. 2012. A review of stochastic modeling of tropical cyclone track and intensity for disaster risk assessment. Advances in Earth Science 27(8): 866–875 (in Chinese).

[] Fang, H., S. Wang, X. Wang, J. Tan, and L. Lu. 2024. A grid temperature forecast correction method based on machine learning. Meteorology 50(1): 103–114 (in Chinese).

[] Galea, D. 2022. Meteorological data reduction for tropical cyclones using deep learning techniques. University of Reading, Reading, UK.

[] GoriA, LinN, XiD, EmanuelK. Tropical cyclone climatology change greatly exacerbates US extreme rainfall-surge hazard. Nature Climate Change, 2022, 12: 171-178

[] GrieserJ, JewsonS. The RMS TC-rain model. Meteorologische Zeitschrift, 2012, 21(1): 79-88

[] He, L., Q. Li, J. Zhang, X. Deng, Z. Wu, Y. Wang, P.W. Chan, and N. Li. 2024. Enhanced tropical cyclone precipitation prediction in the Northwest Pacific using deep learning models and ensemble techniques. Water 16(5): Article 671.

[] Higa, M., S. Tanahara, Y. Adachi, N. Ishiki, S. Nakama, H. Yamada, K. Ito, A. Kitamoto, and R. Miyata. 2021. Domain knowledge integration into deep learning for typhoon intensity classification. Scientific Reports 11(1): Article 12972.

[] JiangH, HuZ, ZhengJ, WangL, ZhuY. Study on quantitative precipitation estimation by polarimetric radar using deep learning. Advances in Atmospheric Sciences, 2024, 41(6): 1147-1160

[] Kim, D., Y. Choi, M. Seo, S. Shin, and H. Jeong. 2023. Short-term forecasting of typhoon rainfall with a deep-learning-based disaster monitoring model. Environmental Data Science 2: Article e28.

[] Knight, D.B., and R.E. Davis. 2009. Contribution of tropical cyclones to extreme rainfall events in the southeastern United States. Journal of Geophysical Research 114: Article D23102.

[] LangousisA, VenezianoD. ElsnerJ, JaggerT. Boundary layer model for moving tropical cyclones. Hurricanes and climate change, 2008 Boston Springer 265-286

[] Langousis, A., and D. Veneziano. 2009. Theoretical model of rainfall in tropical cyclones for the assessment of long-term risk. Journal of Geophysical Research 114(D2): Article D02106.

[] Li, H., J. Wu, Q. Wang, C. Yang, and S. Pan. 2021. A study on rainstorm waterlogging disaster prediction models in Shanghai based on machine learning. Journal of Natural Disasters 30(1): 191–200 (in Chinese).

[] LiD, YangL, LiuS, TanR. Multi-attribute decision making for deep learning-based typhoon disaster assessment. Journal of Intelligent & Fuzzy Systems, 2024, 46(3): 6657-6677

[] Lian, J., S. Wu, S. Huang, and Q. Zhao. 2024. A novel sequence-to-sequence based deep learning model for satellite cloud image time series prediction. Atmospheric Research 306: Article 107457.

[] Lin, P., P. Lin, J. Wang, and N. Wang. 2023. Typhoon disaster risk assessment and dynamic risk forecast in Zhejiang Province based on machine learning methods. Journal of Natural Disasters 32(4): 13–24 (in Chinese).

[] LuXQ, YuH, YingM, ZhaoBK, ZhangS, LinLM, BaiLN, WanRJ. Western North Pacific tropical cyclone database created by the China Meteorological Administration. Advances in Atmospheric Sciences, 2021, 38(4): 690-699

[] LuY, ChenP, YuH, FangP, GongT, WangX, SongS. Parameterized tropical cyclone precipitation model for catastrophe risk assessment in China. Journal of Applied Meteorology and Climatology, 2022, 61(9): 1291-1303

[] LuY, RenF, ZhuW. Risk zoning of typhoon disasters in Zhejiang Province, China. Natural Hazards and Earth System Sciences, 2018, 18: 2921-2932

[] Moya, L., E. Mas, and S. Koshimura. 2020. Learning from the 2018 western Japan heavy rains to detect floods during the 2019 Hagibis Typhoon. Remote Sensing 12(14): Article 2244.

[] Peng, M.S., J. Bao-Fong, and R.T. Williams. 1999. A numerical study on tropical cyclone intensification. Part I: Beta effect and mean flow effect. Journal of the Atmospheric Sciences 56(10): 1404–1423.

[] PielkeR, GratzJ, LandseaC, CollinsD, SaundersM, MusulinR. Normalized hurricane damage in the United States: 1900–2005. Natural Hazards Review, 2008, 9(1): 29-42

[] QiaoB, WuJ, WangR, HaoY, WangP, HanD, WuG. A parallel feature selection method based on NMI-XGBoost and distance correlation for typhoon trajectory prediction. Journal of Supercomputing, 2024, 80: 11293-11321

[] Ren, F., L. Jia, C. Wu, C. Ding, D. Zhang, Z. Jia, Y. Ma, and W. Qiu. 2023. Advances in dynamic-statistical analog ensemble forecasting and its application to precipitation prediction of landfalling typhoons: A renewed understanding. Acta Meteorologica Sinica 81(2): 193–204 (in Chinese).

[] RodgersEB, ChangSW, PierceHF. A satellite observational and numerical study of precipitation characteristics in western North Atlantic tropical cyclones. Journal of Applied Meteorology, 1994, 33(2): 129-139

[] Shepherd, J.M., A. Grundstein, and T.L. Mote. 2007. Quantifying the contribution of tropical cyclones to extreme rainfall along the coastal southeastern United States. Geophysical Research Letters 34: Article L23810.

[] SmithAB, KatzRW. US billion-dollar weather and climate disasters: Data sources, trends, accuracy and biases. Natural Hazards, 2013, 67: 387-410

[] SunY, DengK, RenK, LiuJ, DengC, JinY. Deep learning in statistical downscaling for deriving high spatial resolution gridded meteorological data: A systematic review. ISPRS Journal of Photogrammetry and Remote Sensing, 2024, 208: 14-38

[] Sun, Q., R. Jiao, J. Xia, Z. Yan, H. Li, J. Sun, L. Wang, and Z. Liang. 2019. Adjusting wind speed prediction of numerical weather forecast model based on machine learning methods. Meteorological Monthly 45(3): 426–436 (in Chinese).

[] Tuleya, R.E., M. DeMaria, and R.J. Kuligowski. 2007. Evaluation of GFDL and simple statistical model rainfall forecasts for U.S. landfalling tropical storms. Weather & Forecasting 22(1): 56–70.

[] VickeryPJ, SkerjlPF, TwisdaleLA. Simulation of hurricane risk in the U.S. using empirical track model. Journal of Structural Engineering, 2000, 126: 1222-1237

[] World Meteorological Organization. World’s deadliest tropical cyclone was 50 years ago, 2020 Geneva WMO

[] XiD, LinN, SmithJ. Evaluation of a physics-based tropical cyclone rainfall model for risk assessment. Journal of Hydrometeorology, 2020, 21(9): 2197-2218

[] Yang, C., J. Xu, and J. Yin. 2021. Stochastic simulation of tropical cyclones for risk assessment at one go: A multivariate functional PCA approach. Earth and Space Science 8(8): Article e2021EA001748.

[] Yang, X., L. Zhang, and Z. Wang. 2022. Risk assessment for typhoon economic losses in county-based units using machine learning. Journal of Tropical Meteorology 38(5): 651–661 (in Chinese).

[] YinJ, YuD, YinZ, WangJ, XuS. Modelling the anthropogenic impacts on fluvial flood risks in a coastal mega-city: A scenario-based case study in Shanghai, China. Landscape and Urban Planning, 2015, 136: 144-155

[] YingM, ZhangW, YuH, LuX, FengJ, FanY, ZhuY, ChenD. An overview of the China Meteorological Administration tropical cyclone database. Journal of Atmospheric and Oceanic Technology, 2014, 31: 287-301

[] Zhou, H. 2017. Rainfall intensities simulation based on boundary model and rainfall risk analysis of typhoon. Harbin Institute of Technology, Harbin, China (in Chinese).

[] Zhu, L., K. Emanuel, and S.M. Quiring. 2021. Elevated risk of tropical cyclone precipitation and pluvial flood in Houston under global warming. Environmental Research Letters 16(9): Article 94030.

[] ZhuL, QuiringSM, EmanuelK. Estimating tropical cyclone precipitation risk in Texas. Geophysical Research Letters, 2013, 40(23): 6225-6230

[] Zhu, L., Y. Wang, D. Chavas, M. Johncox, and Y.L. Yung. 2024. Leading role of Saharan dust on tropical cyclone rainfall in the Atlantic basin. Science Advances 10(30): Article eadn6106.