{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T01:52:03Z","timestamp":1760233923363,"version":"build-2065373602"},"reference-count":35,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2021,3,8]],"date-time":"2021-03-08T00:00:00Z","timestamp":1615161600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["51861125203","U1911204"],"award-info":[{"award-number":["51861125203","U1911204"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>It has become increasingly difficult in recent years to predict precipitation scientifically and accurately due to the dual effects of human activities and climatic conditions. This paper focuses on four aspects to improve precipitation prediction accuracy. Five decomposition methods (time-varying filter-based empirical mode decomposition (TVF-EMD), robust empirical mode decomposition (REMD), complementary ensemble empirical mode decomposition (CEEMD), wavelet transform (WT), and extreme-point symmetric mode decomposition (ESMD) combined with the Elman neural network (ENN)) are used to construct five prediction models, i.e., TVF-EMD-ENN, REMD-ENN, CEEMD-ENN, WT-ENN, and ESMD-ENN. The variance contribution rate (VCR) and Pearson correlation coefficient (PCC) are utilized to compare the performances of the five decomposition methods. The wavelet transform coherence (WTC) is used to determine the reason for the poor prediction performance of machine learning algorithms in individual years and the relationship with climate indicators. A secondary decomposition of the TVF-EMD is used to improve the prediction accuracy of the models. The proposed methods are used to predict the annual precipitation in Guangzhou. The subcomponents obtained from the TVF-EMD are the most stable among the four decomposition methods, and the North Atlantic Oscillation (NAO) index, the Nino 3.4 index, and sunspots have a smaller influence on the first subcomponent (Sc-1) than the other subcomponents. The TVF-EMD-ENN model has the best prediction performance and outperforms traditional machine learning models. The secondary decomposition of the Sc-1 of the TVF-EMD model significantly improves the prediction accuracy.<\/jats:p>","DOI":"10.3390\/rs13051018","type":"journal-article","created":{"date-parts":[[2021,3,8]],"date-time":"2021-03-08T12:12:18Z","timestamp":1615205538000},"page":"1018","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Performance Comparison of Machine Learning Models for Annual Precipitation Prediction Using Different Decomposition Methods"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5117-9501","authenticated-orcid":false,"given":"Chao","family":"Song","sequence":"first","affiliation":[{"name":"Center for Water Resources and Environment, Sun Yat-sen University, Guangzhou 510275, China"},{"name":"Guangdong Engineering Technology Research Center of Water Security Regulation and Control for Southern China, Sun Yat-sen University, Guangzhou 510275, China"},{"name":"Key Laboratory of Water Cycle and Water Security in Southern China of Guangdong High Education Institute, Sun Yat-sen University, Guangzhou 510275, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0809-5297","authenticated-orcid":false,"given":"Xiaohong","family":"Chen","sequence":"additional","affiliation":[{"name":"Center for Water Resources and Environment, Sun Yat-sen University, Guangzhou 510275, China"},{"name":"Guangdong Engineering Technology Research Center of Water Security Regulation and Control for Southern China, Sun Yat-sen University, Guangzhou 510275, China"},{"name":"Key Laboratory of Water Cycle and Water Security in Southern China of Guangdong High Education Institute, Sun Yat-sen University, Guangzhou 510275, China"}]}],"member":"1968","published-online":{"date-parts":[[2021,3,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Swain, S., Patel, P., and Nandi, S. (2017, January 1). A multiple linear regression model for precipitation forecasting over Cuttack district, Odisha, India. Proceedings of the 2nd International Conference for Convergence in Technology (I2CT), Mumbai, India.","DOI":"10.1109\/I2CT.2017.8226150"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1007\/s00703-016-0479-4","article-title":"Analysis and prediction of rainfall trends over Bangladesh using Mann\u2013Kendall, Spearman\u2019s rho tests and ARIMA model. Meteorol","volume":"129","author":"Rahman","year":"2017","journal-title":"Atmos. Phys."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1016\/j.enbuild.2015.09.073","article-title":"Using multiple regression analysis to develop energy consumption indicators for commercial buildings in the US","volume":"109","author":"Amiri","year":"2015","journal-title":"Energy Build."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1016\/j.jhydrol.2004.06.028","article-title":"Artificial neural network technique for rainfall forecasting applied to the so Paulo region","volume":"301","author":"Ramirez","year":"2005","journal-title":"J. Hydrol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"3697","DOI":"10.1007\/s11269-013-0374-4","article-title":"Monthly Rainfall Prediction Using Wavelet Neural Network Analysis","volume":"27","author":"Ramana","year":"2013","journal-title":"Water Resour. Manag."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1016\/j.procs.2015.07.528","article-title":"Rainfall monthly prediction based on artificial neural network: A case study in Tenggarong station, east Kalimantan-Indonesia","volume":"59","author":"Mislan","year":"2015","journal-title":"Procedia Comput. Sci."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1016\/j.jhydrol.2010.05.040","article-title":"Prediction of rainfall time series using modular artificial neural networks coupled with data-preprocessing techniques","volume":"389","author":"Wu","year":"2010","journal-title":"J. Hydrol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2057","DOI":"10.1002\/hyp.6047","article-title":"Multireservoir system optimization in the Han River basin using multi-objective genetic algorithms","volume":"20","author":"Kim","year":"2006","journal-title":"Hydrol. Process."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1515\/jwld-2016-0003","article-title":"A wavelet-sarima-ann hybrid model for precipitation forecasting","volume":"28","author":"Maryam","year":"2016","journal-title":"J. Water Land Devt."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"458","DOI":"10.2166\/hydro.2010.032","article-title":"A hybrid model coupled with singular spectrum analysis for daily rainfall prediction","volume":"12","author":"Chau","year":"2010","journal-title":"J. Hydroinform."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"767","DOI":"10.1016\/j.jhydrol.2018.01.015","article-title":"An adaptive middle and long-term runoff forecast model using EEMD-ANN hybrid approach","volume":"567","author":"Tan","year":"2018","journal-title":"J. Hydrol."},{"key":"ref_12","unstructured":"Chen, R., Jia, H., Xie, X., and Wen, G. (2017). Sparsity-Promoting Adaptive Coding with Robust Empirical Mode Decomposition for Image Restoration. Pacific Rim Conference on Multimedia, Springer."},{"key":"ref_13","first-page":"124674","article-title":"Complete ensemble empirical mode decomposition hybridized with random forest and kernel ridge regression model for monthly rainfall forecasts","volume":"584","author":"Mumtaz","year":"2020","journal-title":"J. Hydrol."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Ji, Y., Dong, H.T., Xing, Z.X., Sun, M.X., Fu, Q., and Liu, D. (2020). Application of the decomposition prediction reconstruction framework to middle and long-term runoff forecasting. Water Supply.","DOI":"10.2166\/ws.2020.337"},{"key":"ref_15","first-page":"1","article-title":"Spatial and temporal monthly precipitation forecasting using wavelet transform and neural networks, Qara-Qum catchment. Iran","volume":"9","author":"Arab","year":"2016","journal-title":"Arab. J. Geosci."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1623\/hysj.54.2.234","article-title":"Prediction of daily precipitation using wavelet\u2014neural networks","volume":"54","author":"Partal","year":"2009","journal-title":"Hydrol. Sci. J."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1556","DOI":"10.1080\/02626667.2019.1662023","article-title":"Nonlinear response of runoff to atmospheric freezing level height variation based on hybrid prediction models","volume":"64","author":"Qin","year":"2019","journal-title":"Hydrol. Sci. J."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1016\/j.sigpro.2017.03.019","article-title":"A time varying filter approach for empirical mode decomposition","volume":"138","author":"Li","year":"2017","journal-title":"Signal Process."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.jsv.2017.12.028","article-title":"An optimized time varying filtering based empirical mode decomposition method with grey wolf optimizer for machinery fault diagnosis","volume":"418","author":"Zhang","year":"2018","journal-title":"J. Sound Vib."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2573","DOI":"10.1007\/s12206-019-0505-9","article-title":"An enhanced multipoint optimal minimum entropy deconvolution approach for bearing fault detection of spur gearbox","volume":"33","author":"Xu","year":"2019","journal-title":"J. Mech. Sci. Technol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1016\/j.jhydrol.2016.12.001","article-title":"Comparison of methods for non-stationary hydrologic frequency analysis: Case study using annual maximum daily precipitation in Taiwan","volume":"545","author":"Chen","year":"2017","journal-title":"J. Hydrol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1142\/S1793536910000422","article-title":"Complementary ensemble empirical mode decomposition: A novel noise enhanced data analysis method","volume":"2","author":"Yeh","year":"2010","journal-title":"Adv. Adapt. Data Anal."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"903","DOI":"10.1098\/rspa.1998.0193","article-title":"The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis","volume":"454","author":"Huang","year":"1998","journal-title":"Proc. R. Soc. A Math. Phys. Eng. Sci."},{"key":"ref_24","first-page":"764","article-title":"Elevation of wavelet denoising performance via an ANN-based streamflow forecasting model","volume":"1","author":"Nejad","year":"2012","journal-title":"Int. J. Comput. Sci. Manag. Res."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.jhydrol.2010.06.033","article-title":"Development of a coupled wavelet transform and neural network method for flow forecasting of non-perennial rivers in semi-arid watersheds","volume":"390","author":"Adamowski","year":"2010","journal-title":"J. Hydrol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"466","DOI":"10.1016\/j.engappai.2008.09.003","article-title":"A combined neural-wavelet model for prediction of Ligvanchai watershed precipitation","volume":"22","author":"Nourani","year":"2009","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1016\/j.neucom.2006.04.005","article-title":"Wavelet-based nonlinear multiScale decomposition model for electricity load forecasting","volume":"70","author":"Benaouda","year":"2006","journal-title":"Neurocomputing"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1142\/S1793536913500155","article-title":"Extreme-point symmetric mode decomposition method for data analysis","volume":"5","author":"Wang","year":"2013","journal-title":"Adv. Adapt. Data Anal."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2239","DOI":"10.1002\/joc.5330","article-title":"Spatio-temporal variations of nonlinear trends of precipitation over an arid region of northwest China according to the extreme-point symmetric mode decomposition method","volume":"38","author":"Qin","year":"2018","journal-title":"Int. J. Climatol."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1207\/s15516709cog1402_1","article-title":"Finding structure in time","volume":"14","author":"Elman","year":"1990","journal-title":"Cogn. Sci."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"125","DOI":"10.5004\/dwt.2019.23458","article-title":"Research on a coupling model for groundwater depth forecasting","volume":"142","author":"Song","year":"2019","journal-title":"Desalin. Water Treat."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1177\/1687814017744473","article-title":"New approach of friction model and identification for hydraulic system based on MAPSO-NMDS optimization Elman neural network","volume":"9","author":"Pan","year":"2017","journal-title":"Adv. Mech. Eng."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"2540","DOI":"10.1016\/j.neucom.2010.06.004","article-title":"Chaotic time series prediction with residual analysis method using hybrid Elman\u2013NARX neural networks","volume":"73","author":"Zolfaghari","year":"2010","journal-title":"Neurocomputing"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"4932","DOI":"10.1029\/2018JD029842","article-title":"Multiple-wavelet coherence of world\u2019s large rivers with meteorological factors and ocean signals","volume":"124","author":"Su","year":"2019","journal-title":"J. Geophys. Res. Atmos."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"561","DOI":"10.5194\/npg-11-561-2004","article-title":"Application of the cross wavelet transform and wavelet coherence to geophysical time series","volume":"11","author":"Grinsted","year":"2004","journal-title":"Nonlinear Process. Geophys."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/5\/1018\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:34:52Z","timestamp":1760160892000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/5\/1018"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,8]]},"references-count":35,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2021,3]]}},"alternative-id":["rs13051018"],"URL":"https:\/\/doi.org\/10.3390\/rs13051018","relation":{},"ISSN":["2072-4292"],"issn-type":[{"type":"electronic","value":"2072-4292"}],"subject":[],"published":{"date-parts":[[2021,3,8]]}}}