All Issue

2024 Vol.57, Issue 12S

Review

Rainfall nowcasting with Deep Neural Networks: trends and strategies to overcome limitations

딥 뉴럴 네트워크를 활용한 강우 나우캐스팅의 최신 동향과 한계 극복을 위한 향후 과제

Hyojeong Choia
,
Yongchan Kimb
,
Dongkyun Kimc*
최 효정a
,
김 용찬b
,
김 동균c*
aMaster's Student, Department of Civil Engineering, Hongik University, Seoul, Korea
bPh.D. Student, Department of Civil Engineering, Hongik University, Seoul, Korea
cProfessor, Department of Civil Engineering, Hongik University, Seoul, Korea
a홍익대학교 토목공학과 석사과정
b홍익대학교 토목공학과 박사과정
c홍익대학교 건설환경공학과 교수
*Corresponding Author
31 December 2024. pp. 1161-1175
PDF XML Citation
Abstract

Deep learning models have demonstrated remarkable performance in short-term rainfall prediction by effectively capturing the complex spatiotemporal patterns of rainfall systems using vast datasets. This has helped to address the limitations of traditional Numerical Weather Prediction (NWP) models and radar echo extrapolation methods, such as computational speed and nonlinear precipitation dynamics. In this paper, we systematically review deep learning-based rainfall nowcasting models, categorizing them into three main groups: Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Generative Adversarial Networks (GANs). We also conduct an in-depth analysis of the common limitations identified in these models and explore strategies to overcome them. Innovative approaches, such as the application of diverse loss functions, transfer learning, sampling techniques, and ensemble models, are discussed in terms of their impact on enhancing model performance. Based on these findings, we propose future research directions for rainfall nowcasting. This review aims to provide a comprehensive understanding of the current state of deep learning-based technologies for rainfall nowcasting and serve as a guide for future research and technological advancements in the field.

Keywords
Nowcasting
Deep neural networks
Convolutional neural networks
Recurrent neural networks
Generative adversarial networks
Extreme rainfall

딥러닝 모델은 방대한 데이터를 활용하여 강우 시스템의 복잡한 시공간 패턴을 효과적으로 포착함으로써, 기존 수치예보(Numerical Weather Prediction, NWP) 모델과 레이더 에코 외삽법의 계산 속도 및 비선형 강수 동역학 처리의 한계를 보완하여 단기 강우 예측에서 뛰어난 성과를 보이고 있다. 이에 따라, 본 논문에서는 딥러닝 기반 강우 나우캐스팅 모델을 체계적으로 리뷰하고, 합성곱 신경망(Convolutional Neural Networks, CNN), 순환 신경망(Recurrent Neural Networks, RNN), 생성적 적대 신경망(Generative Adversarial Networks, GAN) 기반의 세 가지 주요 그룹으로 분류하여 분석하였다. 또한, 각 모델에서 나온 공통적인 한계점과 이들 문제를 해결하기 위한 전략을 심도 있게 조사하였다. 다양한 손실함수의 적용, 전이학습, 샘플링, 그리고 앙상블 모델의 활용과 같은 혁신적인 접근법이 모델 성능 개선에 미치는 영향을 논의하며, 이를 바탕으로 강우 나우캐스팅의 향후 연구 방향을 제시한다. 본 리뷰는 강우 나우캐스팅에 대한 딥러닝 기반 기술의 현재 상태를 이해하고, 향후 연구 및 기술 발전을 위한 지침을 제공하는 데 기여하고자 한다.

키워드
나우캐스팅
딥 뉴럴 네트워크
합성곱 신경망
순환 신경망
생성적 적대 신경망
극한 강우
References
1

Agrawal, S., Barrington, L., Bromberg, C., Burge, J., Gazen, C., and Hickey, J. (2019). "Machine learning for precipitation nowcasting from radar images." arXiv Preprint, arXiv:1912.12132

2

Alfieri, L., Salamon, P., Pappenberger, F., Wetterhall, F., and Thielen, J. (2012). "Operational early warning systems for water-related hazards in Europe." Environmental Science & Policy, Vol. 21, pp. 35-49.

10.1016/j.envsci.2012.01.008
3

Amini, A., Dolatshahi, M., and Kerachian, R. (2022). "Adaptive precipitation nowcasting using deep learning and ensemble modeling." Journal of Hydrology, Vol. 612, 128197.

10.1016/j.jhydrol.2022.128197
4

Ashesh, A., Chang, C.-T., Chen, B.-F., Lin, H.-T., Chen, B., and Huang, T.-S. (2022). "Accurate and clear quantitative precipitation nowcasting based on a deep learning model with consecutive attention and rain-map discrimination." Artificial Intelligence for the Earth Systems, Vol. 1, No. 3, e210005.

10.1175/AIES-D-21-0005.1
5

Ayzel, G., Heistermann, M., and Winterrath, T. (2019a). "Optical flow models as an open benchmark for radar-based precipitation nowcasting (rainymotion v0.1)." Geoscientific Model Development, Vol. 12, No. 4, pp. 1387-1402.

10.5194/gmd-12-1387-2019
6

Ayzel, G., Heistermann, M., Sorokin, A., Nikitin, O., and Lukyanova, O. (2019b). "All convolutional neural networks for radar-based precipitation nowcasting." Procedia Computer Science, Vol. 150, pp. 186-192.

10.1016/j.procs.2019.02.036
7

Ayzel, G., Scheffer, T., and Heistermann, M. (2020). "RainNet v1.0: a convolutional neural network for radar-based precipitation nowcasting." Geoscientific Model Development, Vol. 13, No. 6, pp. 2631-2644.

10.5194/gmd-13-2631-2020
8

Ballas, N., Yao, L., Pal, C., Courville, A. (2015). "Delving deeper into convolutional networks for learning video representations." arXiv preprint, arXiv:1511.06432.

9

Bellos, V., Costanzo, C., Kalogiros, J., Ahmadian, R., Rozos, E., and Costabile, P. (2024). "Nowcasting floods in detailed scales considering the uncertainties associated with impact-based practical applications." Water Resources Management, pp. 1-21.

10.1007/s11269-024-03988-5
10

Bouget, V., Béréziat, D., Brajard, J., Charantonis, A., and Filoche, A. (2021). "Fusion of rain radar images and wind forecasts in a deep learning model applied to rain nowcasting." Remote Sensing, Vol. 13, No. 2, 246.

10.3390/rs13020246
11

Bowler, N.E., Pierce, C.E., and Seed, A. (2004). "Development of a precipitation nowcasting algorithm based upon optical flow techniques." Journal of Hydrology, Vol. 288, No. 1-2, pp. 74-91.

10.1016/j.jhydrol.2003.11.011
12

Caseri, A.N., Santos, L.B.L., and Stephany, S. (2022). "A convolutional recurrent neural network for strong convective rainfall nowcasting using weather radar data in Southeastern Brazil." Artificial Intelligence in Geosciences, Vol. 3, pp. 8-13.

10.1016/j.aiig.2022.06.001
13

Chen, L., Cao, Y., Ma, L., and Zhang, J. (2020). "A deep learning- based methodology for precipitation nowcasting with radar." Earth and Space Science, Vol. 7, No. 2, e2019EA000812.

10.1029/2019EA000812
14

Csáji, B.C. (2001). Approximation with artificial neural networks. Master Thesis, Faculty of Sciences, Eötvös Loránd University, Hungary.

15

Dao, D.A., Kim, D., Kim, S., and Park, J. (2020a). "Determination of flood-inducing rainfall and runoff for highly urbanized area based on high-resolution radar-gauge composite rainfall data and flooded area GIS data." Journal of Hydrology, Vol. 584, 124704.

10.1016/j.jhydrol.2020.124704
16

Dao, D.A., Kim, D., Park, J., and Kim, T. (2020b). "Precipitation threshold for urban flood warning-an analysis using the satellite-based flooded area and radar-gauge composite rainfall data." Journal of Hydro-Environment Research, Vol. 32, pp. 48-61.

10.1016/j.jher.2020.08.001
17

De Luca, D.L., and Capparelli, G. (2022). "Rainfall nowcasting model for early warning systems applied to a case over Central Italy." Natural Hazards, Vol. 112, No. 1, pp. 501-520.

10.1007/s11069-021-05191-w
18

Diakakis, M., Boufidis, N., Grau, J.M.S., Andreadakis, E., and Stamos, I. (2020). "A systematic assessment of the effects of extreme flash floods on transportation infrastructure and circulation: The example of the 2017 Mandra flood." International Journal of Disaster Risk Reduction, Vol. 47, 101542.

10.1016/j.ijdrr.2020.101542
19

Eini, M., Kaboli, H.S., Rashidian, M., and Hedayat, H. (2020). "Hazard and vulnerability in urban flood risk mapping: Machine learning techniques and considering the role of urban districts." International Journal of Disaster Risk Reduction, Vol. 50, 101687.

10.1016/j.ijdrr.2020.101687
20

Fortelli, A., Scafetta, N., and Mazzarella, A. (2019). "Nowcasting and real-time monitoring of heavy rainfall events inducing flash-floods: An application to Phlegraean area (Central- Southern Italy)." Natural Hazards, Vol. 97, pp. 861-889.

10.1007/s11069-019-03680-7
21

Fowler, H.J., Lenderink, G., Prein, A.F., Westra, S., Allan, R.P., Ban, N., Barbero, R., Berg, P., Blenkinsop, S., and Do, H.X. (2021). "Anthropogenic intensification of short-duration rainfall extremes." Nature Reviews Earth & Environment, Vol. 2, No. 2, pp. 107-122.

10.1038/s43017-020-00128-6
22

Franch, G., Nerini, D., Pendesini, M., Coviello, L., Jurman, G., and Furlanello, C. (2020). "Precipitation nowcasting with orographic enhanced stacked generalization: Improving deep learning predictions on extreme events." Atmosphere, Vol. 11, No. 3, 267.

10.3390/atmos11030267
23

Geng, H., Ge, X., Xie, B., Min, J., and Zhuang, X. (2023). "LSTMAtU- Net: A precipitation nowcasting model based on ECSA module." Sensors, Vol. 23, No. 13, 5785.

10.3390/s2313578537447634PMC10346408
24

Gong, A., Li, R., Pan, B., Chen, H., Ni, G., and Chen, M. (2023). "Enhancing spatial variability representation of radar nowcasting with generative adversarial networks." Remote Sensing, Vol. 15, No. 13, 3306.

10.3390/rs15133306
25

Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep learning. MIT Press, Cambridge, MA, U.S., pp. 1-4.

26

Han, L., Liang, H., Chen, H., Zhang, W., and Ge, Y. (2021). "Convective precipitation nowcasting using U-Net model." IEEE Transactions on Geoscience and Remote Sensing, Vol. 60, pp. 1-8.

10.1109/TGRS.2021.3100847
27

Harlim, J. (2006). Errors in the initial conditions for numerical weather prediction: A study of error growth patterns and error reduction with ensemble filtering. Ph. D. Dissertation, University of Maryland, College Park, MD, U.S., pp. 1-99.

28

Huggel, C., Khabarov, N., Obersteiner, M., and Ramírez, J. M. (2010). "Implementation and integrated numerical modeling of a landslide early warning system: A pilot study in Colombia." Natural Hazards, Vol. 52, pp. 501-518.

10.1007/s11069-009-9393-0
29

Inoue, T., and Misumi, R. (2022). "Learning from precipitation events in the wider domain to improve the performance of a deep learning-based precipitation nowcasting model." Weather and Forecasting, Vol. 37, No. 6, pp. 1013-1026.

10.1175/WAF-D-21-0078.1
30

Ji, Y., Gong, B., Langguth, M., Mozaffari, A., and Zhi, X. (2023). "CLGAN: A generative adversarial network (GAN)-based video prediction model for precipitation nowcasting." Geoscientific Model Development, Vol. 16, No. 10, pp. 2737-2752.

10.5194/gmd-16-2737-2023
31

Kim, S., Hong, S., Joh, M., and Song, S. (2017). "Deeprain: Convlstm network for precipitation prediction using multichannel radar data." arXiv Preprint, arXiv:1711.02316.

32

Ko, J., Lee, K., Hwang, H., Oh, S.-G., Son, S.-W., and Shin, K. (2022). "Effective training strategies for deep-learning-based precipitation nowcasting and estimation." Computers & Geosciences, Vol. 161, 105072.

10.1016/j.cageo.2022.105072
33

Kumar, A., Islam, T., Sekimoto, Y., Mattmann, C., and Wilson, B. (2020). "Convcast: An embedded convolutional LSTM based architecture for precipitation nowcasting using satellite data." Plos One, Vol. 15, No. 3, e0230114.

10.1371/journal.pone.023011432160237PMC7065808
34

Li, D., Deng, K., Zhang, D., Liu, Y., Leng, H., Yin, F., Ren, K., and Song, J. (2023). "LPT-QPN: A lightweight physics-informed transformer for quantitative precipitation nowcasting." IEEE Transactions on Geoscience and Remote Sensing, Vol. 61, pp. 1-20.

10.1109/TGRS.2023.3328945
35

Li, D., Liu, Y., and Chen, C. (2021). "MSDM v1.0: A machine learning model for precipitation nowcasting over eastern China using multisource data." Geoscientific Model Development, Vol. 14, No. 6, pp. 4019-4034.

10.5194/gmd-14-4019-2021
36

Ma, Z., Zhang, H., and Liu, J. (2022a). "Focal frame loss: A simple but effective loss for precipitation nowcasting." IEEE Transactions on Geoscience and Remote Sensing, Vol. 15, pp. 6781-6788.

10.1109/JSTARS.2022.3194522
37

Ma, Z., Zhang, H., and Liu, J. (2022b). "Preciplstm: A meteorological spatiotemporal lstm for precipitation nowcasting." IEEE Transactions on Geoscience and Remote Sensing, Vol. 60, pp. 1-8.

10.1109/TGRS.2022.3198222
38

Ma, Z., Zhang, H., and Liu, J. (2023). "MM-RNN: A multimodal RNN for precipitation nowcasting." IEEE Transactions on Geoscience and Remote Sensing, Vol. 61, pp. 1-14.

10.1109/TGRS.2023.3264545
39

Oh, M., Lee, D., Kwon, H., and Kim, D. (2016). "Development of flood inundation area GIS database for Samsung-1 drainage sector, Seoul, Korea." Journal of Korea Water Resources Association, Vol. 49, No. 12, pp. 981-993.

10.3741/JKWRA.2016.49.12.981
40

Papagiannaki, K., Lagouvardos, K., Kotroni, V., and Bezes, A. (2015). "Flash flood occurrence and relation to the rainfall hazard in a highly urbanized area." Natural Hazards and Earth System Science, Vol. 15, No. 8, pp. 1859-1871.

10.5194/nhess-15-1859-2015
41

Púčik, T., Francová, M., Rýva, D., Kolář, M., and Ronge, L. (2011). "Forecasting challenges during the severe weather outbreak in Central Europe on 25 June 2008." Atmospheric Research, Vol. 100, No. 4, pp. 680-704.

10.1016/j.atmosres.2010.11.014
42

Pulkkinen, S., Nerini, D., Pérez Hortal, A.A., Velasco-Forero, C., Seed, A., Germann, U., and Foresti, L. (2019). "Pysteps: An open-source Python library for probabilistic precipitation nowcasting (v1.0)." Geoscientific Model Development, Vol. 12, No. 10, pp. 4185-4219.

10.5194/gmd-12-4185-2019
43

Ravuri, S., Lenc, K., Willson, M., Kangin, D., Lam, R., Mirowski, P., Fitzsimons, M., Athanassiadou, M., Kashem, S., and Madge, S. (2021). "Skilful precipitation nowcasting using deep generative models of radar." Nature, Vol. 597, No. 7878, pp. 672-677.

10.1038/s41586-021-03854-z34588668PMC8481123
44

Ronneberger, O., Fischer, P., and Brox, T. (2015). "U-net: Convolutional networks for biomedical image segmentation." Medical Image Computing and Computer-Assisted intervention - MICCAI 2015: 18th International Conference, Munich, Germany, Part III, No. 18, pp. 234-241.

10.1007/978-3-319-24574-4_28
45

Sämann, R., Graf, T., and Neuweiler, I. (2022). "Performance of nearest neighbour metrics for pluvial flood nowcasts in urban catchments." Journal of Hydrology, Vol. 604, 127225.

10.1016/j.jhydrol.2021.127225
46

Shi, X., Chen, Z., Wang, H., Yeung, D.-Y., Wong, W.-K., and Woo, W. (2015). "Convolutional LSTM network: A machine learning approach for precipitation nowcasting." Advances in Neural Information Processing Systems, Vol. 28.

47

Shi, X., Gao, Z., Lausen, L., Wang, H., Yeung, D.-Y., Wong, W., and Woo, W. (2017). "Deep learning for precipitation nowcasting: A benchmark and a new model." Advances in Neural Information Processing Systems, Vol. 30.

48

Szura, K. (2018). "The big data project: Enhancing public access to NOAA's open data." AGU Fall Meeting Abstracts, Vol. 2018, PA32C-34.

49

Talebi, A., Dolatshahi, M., and Kerachian, R. (2024). "A framework for real-time operation of urban detention reservoirs: Application of the cellular automata and rainfall nowcasting." Journal of Environmental Management, Vol. 350, 119638.

10.1016/j.jenvman.2023.11963838029498
50

Tan, J., Huang, Q., and Chen, S. (2024a). "Deep learning model based on multi-scale feature fusion for precipitation nowcasting." Geoscientific Model Development, Vol. 17, No. 1, pp. 53-69.

10.5194/gmd-17-53-2024
51

Tan, Y., Zhang, T., Li, L., and Li, J. (2024b). "Radar-based precipitation nowcasting based on improved U-Net model." Remote Sensing, Vol. 16, No. 10, 1681.

10.3390/rs16101681
52

Tian, L., Li, X., Ye, Y., Xie, P., and Li, Y. (2019). "A generative adversarial gated recurrent unit model for precipitation nowcasting." IEEE Geoscience and Remote Sensing Letters, Vol. 17, No. 4, pp. 601-605.

10.1109/LGRS.2019.2926776
53

Tran, Q.-K., and Song, S. (2019). "Computer vision in precipitation nowcasting: Applying image quality assessment metrics for training deep neural networks." Atmosphere, Vol. 10, No. 5, 244.

10.3390/atmos10050244
54

Tuyen, D.N., Tuan, T.M., Le, X.-H., Tung, N.T., Chau, T.K., Van Hai, P., Gerogiannis, V.C., and Son, L.H. (2022). "RainPredRNN: A new approach for precipitation nowcasting with weather radar echo images based on deep learning." Axioms, Vol. 11, No. 3, 107.

10.3390/axioms11030107
55

Wang, R., Su, L., Wong, W.K., Lau, A.K., and Fung, J.C. (2023). "Skillful radar-based heavy rainfall nowcasting using task- segmented generative adversarial network." IEEE Transactions on Geoscience and Remote Sensing, Vol. 15, pp. 7400-7413.

10.1109/TGRS.2023.3295211
56

Wang, Y., Gao, Z., Long, M., Wang, J., and Philip, S.Y. (2018). "Predrnn: Towards a resolution of the deep-in-time dilemma in spatiotemporal predictive learning." Proceedings of the International Conference on Machine Learning (ICML), Stockholm, Sweden, pp. 5123-5132.

57

Wang, Y., Long, M., Wang, J., Gao, Z., and Yu, P.S. (2017). "Predrnn: Recurrent neural networks for predictive learning using spatiotemporal LSTMs." Advances in Neural Information Processing Systems, Vol. 30.

58

Wang, Y., Wu, H., Zhang, J., Gao, Z., Wang, J., Philip, S.Y., and Long, M. (2022). "Predrnn: A recurrent neural network for spatiotemporal predictive learning." IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 45, No. 2, pp. 2208-2225.

10.1109/TPAMI.2022.316515335380958
59

Xu, L., Li, X., Yu, H., Du, W., Chen, Z., and Chen, N. (2024). "PP- Loss: An imbalanced regression loss based on plotting position for improved precipitation nowcasting." Theoretical and Applied Climatology, Vol. 155, pp. 5909-5923.

10.1007/s00704-024-04984-w
60

Yao, S., Chen, H., Thompson, E.J., and Cifelli, R. (2022). "An improved deep learning model for high-impact weather nowcasting." IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol. 15, pp. 7400-7413.

10.1109/JSTARS.2022.3203398
61

Yin, J., Gao, Z., and Han, W. (2021). "Application of a radar echo extrapolation-based deep learning method in strong convection nowcasting." Earth and Space Science, Vol. 8, No. 8, e2020EA001621.

10.1029/2020EA001621
62

Yu, W., Wang, S., Zhang, C., Chen, Y., Sheng, X., Yao, Y., Liu, J., and Liu, G. (2023). "Integrating spatio-temporal and generative adversarial networks for enhanced nowcasting performance." Remote Sensing, Vol. 15, No. 15, 3720.

10.3390/rs15153720
63

Zhu, H., and Thorpe, A. (2006). "Predictability of extratropical cyclones: The influence of initial condition and model uncertainties." Journal of the Atmospheric Sciences, Vol. 63, No. 5, pp. 1483-1497.

10.1175/JAS3688.1
Information
  • Publisher :KOREA WATER RESOURECES ASSOCIATION
  • Publisher(Ko) :한국수자원학회
  • Journal Title :Journal of Korea Water Resources Association
  • Journal Title(Ko) :한국수자원학회 논문집
  • Volume : 57
  • No :12
  • Pages :1161-1175
  • Received Date : 2024-10-15
  • Revised Date : 2024-12-02
  • Accepted Date : 2024-12-03
  • DOI :https://doi.org/10.3741/JKWRA.2024.57.S-1.1161
Journal Informaiton Journal of Korea Water Resources Association Journal of Korea Water Resources Association
Online Submission
Archives
  • scopus
  • KCI-수자원
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close