Deep learning models for generation of precipitation maps based on numerical weather prediction

Author:

Rojas-Campos Adrian,Langguth MichaelORCID,Wittenbrink Martin,Pipa Gordon

Abstract

Abstract. Numerical weather prediction (NWP) models are atmospheric simulations that imitate the dynamics of the atmosphere and provide high-quality forecasts. One of the most significant limitations of NWP is the elevated amount of computational resources required for its functioning, which limits the spatial and temporal resolution of the outputs. Traditional meteorological techniques to increase the resolution are uniquely based on information from a limited group of interest variables. In this study, we offer an alternative approach to the task where we generate precipitation maps based on the complete set of variables of the NWP to generate high-resolution and short-time precipitation predictions. To achieve this, five different deep learning models were trained and evaluated: a baseline, U-Net, two deconvolution networks and one conditional generative model (Conditional Generative Adversarial Network; CGAN). A total of 20 independent random initializations were performed for each of the models. The predictions were evaluated using skill scores based on mean absolute error (MAE) and linear error in probability space (LEPS), equitable threat score (ETS), critical success index (CSI) and frequency bias after applying several thresholds. The models showed a significant improvement in predicting precipitation, showing the benefits of including the complete information from the NWP. The algorithms doubled the resolution of the predictions and corrected an over-forecast bias from the input information. However, some new models presented new types of bias: U-Net tended to mid-range precipitation events, and the deconvolution models favored low rain events and generated some spatial smoothing. The CGAN offered the highest-quality precipitation forecast, generating realistic outputs and indicating possible future research paths.

Funder

Bundesministerium für Bildung und Forschung

Publisher

Copernicus GmbH

Subject

General Medicine

Reference40 articles.

1. Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Mané, D., Monga, R., Moore, S., Murray, D., Olah, C., Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P., Vanhoucke, V., Vasudevan, V., Viégas, F., Vinyals, O., Warden, P., Wattenberg, M., Wicke, M., Yu, Y., and Zheng, X.: TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems, Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI '16), 2–4 November 2016, Savannah, GA, USA, USENIX, ISBN 978-1-931971-33-1, https://www.usenix.org/system/files/conference/osdi16/osdi16-abadi.pdf (last access: 6 March 2023), 2015. a, b

2. Agrawal, S., Barrington, L., Bromberg, C., Burge, J., Gazen, C., and Hickey, J.: Machine Learning for Precipitation Nowcasting from Radar Images, arXiv [preprint], https://doi.org/10.48550/arXiv.1912.12132, 11 December 2019. a

3. Ayzel, G., Heistermann, M., Sorokin, A., Nikitin, O., and Lukyanova, O.: All convolutional neural networks for radar-based precipitation nowcasting, proceedings of the 13th International Symposium “Intelligent Systems 2018” (INTELS’18), 22–24 October 2018, St. Petersburg, Russia, Procedia Comput. Sci., 150, 186–192, https://doi.org/10.1016/j.procs.2019.02.036, 2019. a

4. Ayzel, G., Scheffer, T., and Heistermann, M.: RainNet v1.0: a convolutional neural network for radar-based precipitation nowcasting, Geosci. Model Dev., 13, 2631–2644, https://doi.org/10.5194/gmd-13-2631-2020, 2020. a, b, c, d, e, f

5. Bartels, H., Weigl, E., Reich, T., Lang, P., Wagner, A., Kohler, O., and Gerlach, N.: Projekt RADOLAN–Routineverfahren zur Online-Aneichung der Radarniederschlagsdaten mit Hilfe von automatischen Bodenniederschlagsstationen (Ombrometer), Deutscher Wetterdienst, Hydrometeorologie, 5, 265–283, https://www.dwd.de/DE/leistungen/radolan/radolan_info/abschlussbericht_pdf (last access: 6 March 2023), 2004. a

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3