Water level prediction based on improved WMCP-ARIMA model

Fei-hu Wang; Xue-chun Liang; Xue-bin lv

doi:10.1117/12.2627470

22 April 2022 Water level prediction based on improved WMCP-ARIMA model

Fei-hu Wang, Xue-chun Liang, Xue-bin lv

Proceedings Volume 12163, International Conference on Statistics, Applied Mathematics, and Computing Science (CSAMCS 2021); 121631V (2022) https://doi.org/10.1117/12.2627470
Event: International Conference on Statistics, Applied Mathematics, and Computing Science (CSAMCS 2021), 2021, Nanjing, China

Abstract

To solve the problem of medium and long-term water level prediction of Hongze Lake with small samples, strong fluctuations, and nonlinearity, a statistical model is proposed to predict the water level. The weighed Markov chain (WMCP) is introduced to predict the residual sequence generated by the ARIMA model. The prediction result is converted from the state value to the specific value under the action of the state feature value combined with the linear interpolation method to compensate for the prediction result of the ARIMA model. Taking into account the directivity of the ARIMA model to the trend of water level changes, and improving the conversion process of the residual state, the experimental results show that the improved combined model reduces the water level prediction error by 7.02% and 3.66%, respectively, compared with the single model and the unimproved combined model.

Citation Download Citation

Fei-hu Wang, Xue-chun Liang, and Xue-bin lv "Water level prediction based on improved WMCP-ARIMA model", Proc. SPIE 12163, International Conference on Statistics, Applied Mathematics, and Computing Science (CSAMCS 2021), 121631V (22 April 2022); https://doi.org/10.1117/12.2627470

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available