---

Journal of Vibration Testing and System Dynamics 10(2) (2026) 105--117 | DOI:10.5890/JVTSD.2026.06.001

Hai Zeng$^1$, Yunxia Xie$^{1}$, Tianming Xiang$^{2}$

$^1$ Institute of Physics and Electronic Engineering, Sichuan University of Science and Engineering, China

$^2$ Institute of Automation and Information Engineering, Sichuan University of Science and Engineering, China

Download Full Text PDF

 

Abstract

Medium- and long-term precipitation prediction has always been a major challenge in precipitation prediction. This research proposes a generalizable Physics-guided Artificial Intelligence (PAI) framework for precipitation prediction. First, By using multifractal detrended fluctuation analysis(MFDFA)method, multifractal characteristic of precipitation is analyzed to identify complexity of the precipitation series. Second, for each precipitation regime, a BP Neural Network prediction model is trained by employing precipitation metrics at monthly scale combining the multifractal characteristic of precipitation as input and subsequently used to predict estimation precipitation for IMERG(Integrated Multi-satellite Retrievals for GPM). The PAI framework is demonstrated in the 18 cities in Sichuan province using the monthly precipitation over 2000--2023.And as the comparison, BP neural network and LSTM(Long Short-Term Memory) neural network were used to predict monthly precipitation in various cities in Sichuan Province. Results show that compared with other machine learning precipitation prediction model the MFDFA-BP prediction model performs better. The MFDFA-BP prediction model can then be used for hydrologic simulations and precipitation prediction.

References

1. [1]	An, B.J. (2019), Comprehensive meteorological observation techniques and quality improvement strategies, Decision Exploration (Central Edition), (4), 70.

2. [2]	Cui, L.J. (2021), Application of BP neural network in reservoir inflow prediction during dry season, Haihe Water Resources, 40(1), 61-63.

3. [3]	Fu, Z.L., Li, G.P., Jiang, F.Y., and et al (2022), Dynamic process analysis and local circulation numerical simulation of a warm-zone mountainous rainstorm event in the western Sichuan Basin, Chinese Journal of Atmospheric Sciences, 46(6), 1366-1380.

4. [4]	Jiang, P., Hu, Y.J., Zhong, Z., Sun, Y., and L\"{u}, S. (2023), Prediction of summer precipitation in China using convolutional neural network model based on interannual increment method, Meteorological Science, 43(5), 569-577.

5. [5]	Kantelhardt, J.W. (2011), Fractal and multifractal time series, Springer.

6. [6]	Li, Y.P., Zhu, C., Ma, C.M., and Zhang, G.S. (2015), Study on the changes of precipitation of different intensity levels in the Pihe River Basin, Resources and Environment in the Yangtze Basin, 24(9), 1477-1482.

7. [7]	Liu, W., Wang, Y.L., and Song, J.J. (2022), Neural network prediction model for daily precipitation values in Yining County, Ili River Valley, Water Resources Development and Management, 8(12), 20-24+19.

8. [8]	Qin, X.W., Wang, Q.J., Wang, X.M., and et al (2022), Short-term PM2.5 prediction in Beijing based on VMD and LSTM methods, Journal of Jilin University (Earth Science Edition), 52(1), 214-221.

9. [9]	Tao, L.Z., He, X.G., Li, J.J., and Yang, D. (2021), A multiscale long short-term memory model with attention mechanism for improving monthly precipitation prediction, Journal of Hydrology, 602, 126815.

10. [10]	Wang, H.B. (2022), Research on rainfall prediction technology in Qiqihar City, Heilongjiang Province, Groundwater, 44(4), 223-224.

11. [11]	Wang, W.Z., Wei, W.H., and Wei, D.L. (2023), Research and application of a precipitation prediction model based on EMD-DBO-GRU, Gansu Water Resources and Hydropower Technology, 59(9), 9-13.

12. [12]	Wu, L. and Feng, L.H. (2014), Precipitation prediction in Yiwu City based on BP neural network, Zhejiang Hydrotechnics, 42(2), 52-54.

13. [13]	Wu, X.H., Hua, Y.J., Guan, Y.H., Wang, W.W., and Liu, D.Y. (2022), Research on precipitation occurrence prediction based on CNN-Attention-BP, Journal of Nanjing University of Information Science and Technology (Natural Science Edition), 14(2), 148-155.

14. [14]	Xie, S.F., Zhao, Y., Li, G.H., and et al (2020), GPS precipitable water vapor prediction using GA-BP neural network, Science of Surveying and Mapping, 45(3), 33-38.

15. [15]	Xu, D.M., Wang, Y.Q., and Wang, W.C. (2022), Monthly precipitation prediction model based on VMD-TCN, Hydrology, 42(2), 13-18.

16. [16]	Yin, J.F., Wang, D.H., Xu, H.B., Zhai, G.Q., and Jiang, X.L. (2015), Research on the impact of ice nuclei on cloud physical properties and precipitation, Advances in Earth Science, 30(3), 323-333.

17. [17]	Yu, R., Sun, L.Y., Wang, M., Zhang, L., and Hou, L. (2023), Multifractal characteristics of daily precipitation series in Guangdong based on ICEEMDAN-MFDFA, Water Resources and Hydropower Engineering (Chinese and English), 54(2), 85-95.

18. [18]	Yu, W.H., Jia, K.L., Pan, X.P., Liang, Q.S., and Chen, Y.M. (2015), Analysis of non-trend fluctuations in precipitation and temperature in Hebei Province, Journal of Arid Land Resources and Environment, 29(1), 134-139.

19. [19]	Zhou, K.H., Zheng, Y.G., and Wang, T.B. (2021), A short-term forecasting method for lightning strike locations using deep learning to integrate NWP and multi-source observational data, Acta Meteorologica Sinica, 79(1), 1-14.

20. [20]	Zhou, T.X. and Chen, J. (2021), Multifractal characteristic analysis of precipitation time series in Altay region, Journal of Shaoxing University (Natural Science), 41(2), 45-50.