Articles | Volume 13, issue 6
Geosci. Model Dev., 13, 2631–2644, 2020
https://doi.org/10.5194/gmd-13-2631-2020
Geosci. Model Dev., 13, 2631–2644, 2020
https://doi.org/10.5194/gmd-13-2631-2020

Model description paper 11 Jun 2020

Model description paper | 11 Jun 2020

RainNet v1.0: a convolutional neural network for radar-based precipitation nowcasting

Georgy Ayzel et al.

Related authors

Optical flow models as an open benchmark for radar-based precipitation nowcasting (rainymotion v0.1)
Georgy Ayzel, Maik Heistermann, and Tanja Winterrath
Geosci. Model Dev., 12, 1387–1402, https://doi.org/10.5194/gmd-12-1387-2019,https://doi.org/10.5194/gmd-12-1387-2019, 2019
Short summary
Climate change impact on streamflow in large-scale river basins: projections and their uncertainties sourced from GCMs and RCP scenarios
Olga N. Nasonova, Yeugeniy M. Gusev, Evgeny E. Kovalev, and Georgy V. Ayzel
Proc. IAHS, 379, 139–144, https://doi.org/10.5194/piahs-379-139-2018,https://doi.org/10.5194/piahs-379-139-2018, 2018
Short summary
Coupling physically based and data-driven models for assessing freshwater inflow into the Small Aral Sea
Georgy Ayzel and Alexander Izhitskiy
Proc. IAHS, 379, 151–158, https://doi.org/10.5194/piahs-379-151-2018,https://doi.org/10.5194/piahs-379-151-2018, 2018
Short summary
Impact of possible climate changes on river runoff under different natural conditions
Yeugeniy M. Gusev, Olga N. Nasonova, Evgeny E. Kovalev, and Georgy V. Ayzel
Proc. IAHS, 379, 293–300, https://doi.org/10.5194/piahs-379-293-2018,https://doi.org/10.5194/piahs-379-293-2018, 2018
Short summary

Related subject area

Atmospheric Sciences
Implementation of a synthetic inflow turbulence generator in idealised WRF v3.6.1 large eddy simulations under neutral atmospheric conditions
Jian Zhong, Xiaoming Cai, and Zheng-Tong Xie
Geosci. Model Dev., 14, 323–336, https://doi.org/10.5194/gmd-14-323-2021,https://doi.org/10.5194/gmd-14-323-2021, 2021
Short summary
Numerical study of the effects of initial conditions and emissions on PM2.5 concentration simulations with CAMx v6.1: a Xi'an case study
Han Xiao, Qizhong Wu, Xiaochun Yang, Lanning Wang, and Huaqiong Cheng
Geosci. Model Dev., 14, 223–238, https://doi.org/10.5194/gmd-14-223-2021,https://doi.org/10.5194/gmd-14-223-2021, 2021
Short summary
A multi-year short-range hindcast experiment with CESM1 for evaluating climate model moist processes from diurnal to interannual timescales
Hsi-Yen Ma, Chen Zhou, Yunyan Zhang, Stephen A. Klein, Mark D. Zelinka, Xue Zheng, Shaocheng Xie, Wei-Ting Chen, and Chien-Ming Wu
Geosci. Model Dev., 14, 73–90, https://doi.org/10.5194/gmd-14-73-2021,https://doi.org/10.5194/gmd-14-73-2021, 2021
Short summary
Ground-based lidar processing and simulator framework for comparing models and observations (ALCF 1.0)
Peter Kuma, Adrian J. McDonald, Olaf Morgenstern, Richard Querel, Israel Silber, and Connor J. Flynn
Geosci. Model Dev., 14, 43–72, https://doi.org/10.5194/gmd-14-43-2021,https://doi.org/10.5194/gmd-14-43-2021, 2021
Development of an Ozone Monitoring Instrument (OMI) aerosol index (AI) data assimilation scheme for aerosol modeling over bright surfaces – a step toward direct radiance assimilation in the UV spectrum
Jianglong Zhang, Robert J. D. Spurr, Jeffrey S. Reid, Peng Xian, Peter R. Colarco, James R. Campbell, Edward J. Hyer, and Nancy L. Baker
Geosci. Model Dev., 14, 27–42, https://doi.org/10.5194/gmd-14-27-2021,https://doi.org/10.5194/gmd-14-27-2021, 2021
Short summary

Cited articles

Agrawal, S., Barrington, L., Bromberg, C., Burge, J., Gazen, C., and Hickey, J.: Machine Learning for Precipitation Nowcasting from Radar Images, available at: https://arxiv.org/abs/1912.12132 (last access: 28 January 2020), 2019. a, b
Austin, G. L. and Bellon, A.: The use of digital weather radar records for short-term precipitation forecasting, Q. J. Roy. Meteor. Soc., 100, 658–664, https://doi.org/10.1002/qj.49710042612, 1974. a
Ayzel, G.: hydrogo/rainnet: RainNet v1.0-gmdd, Zenodo, https://doi.org/10.5281/zenodo.3631038, 2020a. a, b, c
Ayzel, G.: RainNet: pretrained model and weights, Zenodo, https://doi.org/10.5281/zenodo.3630429, 2020b. a, b, c
Ayzel, G.: RYDL: the sample data of the RY product for deep learning applications, Zenodo, https://doi.org/10.5281/zenodo.3629951, 2020c. a, b
Download
Short summary
In this study, we present RainNet, a deep convolutional neural network for radar-based precipitation nowcasting, which was trained to predict continuous precipitation intensities at a lead time of 5 min. RainNet significantly outperformed the benchmark models at all lead times up to 60 min. Yet, an undesirable property of RainNet predictions is the level of spatial smoothing. Obviously, RainNet learned an optimal level of smoothing to produce a nowcast at 5 min lead time.