Abstract
Scientific prediction of precipitation changes has important guiding value and significance for revealing regional spatial and temporal patterns of precipitation changes, flood climate prediction, etc. Based on the fact that CEEMD can effectively overcome the interference of modal aliasing and white noise, fine composite multi-scale entropy can reorganize the same FCMSE value to reduce the modal component and improve the computational efficiency, and Stacking ensemble learning can effectively and conveniently improve the fitting effect of machine learning, a rainfall prediction method based on CEEMD-fine composite multi-scale entropy and Stacking ensemble learning is constructed, and it is applied to the prediction of monthly precipitation in the Xixia. The results show that, under the same conditions, the CEEMD-FCMSE-Stacking model reduces the root mean square error by 83.48% and 62.08%, and the mean absolute error by 83.25% and 61.84%, respectively, compared with the single Stacking model and CEEMD-LSTM, while the goodness-of-fit coefficients improve by 11.28% and 6.50%, respectively, which means that the CEEMD-FCMSE-Stacking model has higher prediction performance. The CEEMD-FCMSE-Stacking model has higher prediction performance.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Data availability
Data and materials are available from the corresponding author upon request.
References
Bidroha B, Maria N, Alan OC (2020) New Approach to Multisite Downscaling of Precipitation by Identifying Different Set of Atmospheric Predictor Variables. J Hydrol Eng 25(5). https://doi.org/10.1061/(ASCE)HE.1943-5584.0001900
Dong N, Ke KW, Li JS (2020) Short-term photovoltaic power generation forecasting based on random forest feature selection and CEEMD: A case study[J]. Appl Soft Comput J 93:combined model based on ensemble EMD106389
Fethi O, Mourad L, Soltane A (2018) Improvement of rainfall estimation from MSG data using Random Forests classification and regression[J]. Atmos Res 211:62–72
Gorai AK, Himanshu VK, Santi C (2021) Development of ANN-Based Universal Predictor for Prediction of Blast-Induced Vibration Indicators and its Performance Comparison with Existing Empirical Models[J]. Mining Metall Explor 38(5)
Guo J, Guo SL, Chen H (2010) ANN statistical downscaling method for predicting precipitation changes in the Han River basin[J]. J Wuhan Univ (Engineering Edition) 43(02):148–152
Kang WH, Xu TQ, Wang SL, Deng SL, Li Y (2022) Short-term wind power prediction based on CEEMDAN-fine composite multiscale entropy and Stacking integrated learning[J]. Water Resources and Hydropower Technology (in Chinese and English) 53(02):163–172. https://doi.org/10.13928/j.cnki.wrahe.2022.02.016
Kavya J, Pai ML, Adarsh S (2020) Adaptive EEMD-ANN hybrid model for Indian summer monsoon rainfall forecasting[J]. Theor Appl Climatol
Khan Md, Munir H, Muhammad NS (2020) Wavelet based hybrid ANN-ARIMA models for meteorological drought forecasting[J]. J Hydrol 590:125380
Lin Yongen Du, Yi Meng Yue, Hehai Xie, Dagang Wang (2021) Study on the influence of different integrated models on short time runoff forecasting in small watersheds[J]. China Rural Water Conservancy and Hydropower 11:97–102
Liu X, Zhao N, Guo JY (2020) Monthly precipitation prediction on the Tibetan Plateau based on LSTM neural network[J]. Journal of Geoinformation Science 22(08):1617–1629
Liu S, Liu R, Tan NZ (2021) A spatial Improved-kNN-Based flood inundation risk framework for urban tourism under two rainfall scenarios[J]. Sustainability 13(5):2859
Lu K, Wu W, Lin GR (2021) Combined prediction method of passenger hub aggregation based on KNN regression[J]. J Jilin Univ (Engineering Edition) 51(04):1241–1250
Qing H, Miao BX, Pan HW (2019) Improving monsoon precipitation prediction using combined convolutional and long short term memory neural network[J]. Water 11(5):977
Shi JQ, Zhang JH (2019) Load forecasting method based on multi-model fusion Stacking integrated learning approach[J]. Chin J Electr Eng 39(14):4032–4042
Song YT, Zhao XH, Zhu XP, Xi DJ (2019) Monthly runoff prediction of the upper Fen River based on CEEMD-BP model[J]. People’s Yellow River 41(08):1–5
Sun A, Li JZ, Feng P (2021) Applicability of RF-SVR downscaling model in the Luan River basin[J]. J Water Resour Water Eng 32(02):31–37
Xiao SG, Mo L, Zhang X (2020) Short-term load forecasting based on CEEMDAN+RF+AdaBoost[J]. Hydropower Energy Sci 38(04):181-184+175
Xiong WL, Xu BG (2006) Study on the optimal selection method of SVR parameters based on PSO[J]. J Syst Simul 09:2442–2445
Yu X, Ling G, Lihua H, Shoulu X, Wenyong W (2018) A SVR–ANN combined model based on ensemble EMD for rainfall prediction[J]. Applied Soft Computing Journal 73
Funding
This work was supported by the Key Scientific Research Project of Colleges and Universities in Henan Province (CN) [grant numbers 17A570004].
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and design. writing and editing: Xianqi Zhang and Kai Wang; chart editing: Tao Wang; preliminary data collection: Kai Wang. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Ethical approval and consent to participate
Not applicable.
Consent for publication
Written informed consent for publication was obtained from all participants.
Competing interests
The authors declare no competing interests.
Additional information
Communicated by: H. Babaie
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zhang, X., Wang, K. & Zheng, Z. A novel integrated learning model for rainfall prediction CEEMD- FCMSE -Stacking. Earth Sci Inform 15, 1995–2005 (2022). https://doi.org/10.1007/s12145-022-00819-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12145-022-00819-2