[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119923-en":3,"doc-seo-119923-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},119923,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Hybrid machine learning model based on feature decomposition and entropy optimization for higher accuracy flood forecasting","Machine learning methods are widely used for flood forecasting, yet accuracy depends on selecting the most informative features from high-dimensional, nonlinear time series collected across multiple stations. This work integrates ANN, ANFIS, and LSTM with time-series decomposition techniques—empirical mode decomposition, ensemble EMD, and discrete wavelet transform—to produce a hybrid model for monthly water-level forecasting using rainfall from the Kelantan River Basin. Mutual information-based entropy ranks and selects rainfall features by measuring uncertainty among stations. Experiments with RMSE, MAE, and NSE show improved forecasting accuracy, supporting better flood risk management for citizens.","Hybrid machine learning model based on feature decomposition and entropy optimization for higher accuracy flood forecasting  \nNazli Mohd Khairudin a, 1,*, Norwati Mustapha a,2, Teh Noranis Mohd Aris a,3, Maslina Zolkepli a,4  \na Faculty of Computer Sciences and Information Technology, Universiti Putra Malaysia, 43400 UPM Serdang, Selangor, Malaysia  \n[1](1 nazmkhair@gmail.com)[ nazmkhair@gmail.com](1 nazmkhair@gmail.com); [2](2 norwati@upm.edu.my)[ norwati@upm.edu.my](2 norwati@upm.edu.my); [3](3 nuranis@upm.edu.my)[ nuranis@upm.edu.my](3 nuranis@upm.edu.my); [4](4 masz@upm.edu.my)[ masz@upm.edu.my](4 masz@upm.edu.my)  \n* corresponding author  \nARTICLE INFO ABSTRACT  \n\n| Article history\u003Cbr>Received May 31, 2023\u003Cbr>Revised July 1, 2023\u003Cbr>Accepted July 8, 2023\u003Cbr>Available online December 29, 2023\u003Cbr>Keywords\u003Cbr>Discrete wavelet transform Empirical mode decomposition Ensemble EMD\u003Cbr>Entropy\u003Cbr>Mutual information | The advancement of the machine learning model has widely been adopted to provide flood forecasts. However, the model must deal with the challenges of determining the most important features to be used in flood forecasts with high-dimensional non-linear time series when involving data from various stations. Decomposition of time-series data such as empirical mode decomposition, ensemble empirical mode decomposition, and discrete wavelet transform are widely used for optimization of input; however, they have been done for single dimension time-series data which are unable to determine relationships between data in high dimensional time series. In this study, machine learning models, which are Artificial Neural Network (ANN), Adaptive Neuro Fuzzy Inferences System (ANFIS), and Long-Short Term Memory (LSTM), are integrated with decomposition methods to provide a hybrid model to forecast the monthly water level using monthly rainfall data from Kelantan River Basin. To effectively select the best rainfall data from the multi-stations that provide higher accuracy, these rainfall data are analyzed with entropy called Mutual Information that measures the uncertainty of random variables from various stations. Mutual information acts as an optimization method to help the researcher select the appropriate features to score a higher accuracy for the model. The experimental evaluations using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Nash-Sutcliffe Efficiency (NSE) proved that the hybrid machine learning model based on the feature decomposition and ranked by Mutual Information can increase the accuracy of water level forecasting. This outcome will help citizens manage the risk of floods.\u003Cbr>\u003Cbr>This is an open access article under the CC–BY-SA license\u003Cbr> |\n| --- | --- |\n\n1. Introduction  \nThe advancement of machine learning model has proved it potential in providing accurate forecasts for hydrological data such as rainfall. In many literatures, the development of machine learning models for long-term flood forecasting such as monthly water level can be categorized as single or hybrid model. Single models have been applied only one machine learning method to produce the forecast. Among the widely used single machine learning models are Support Vector regression (SVR), Artificial Neural Networks (ANN), Decision Tree (DT), Random Forest (RF), and Support Vector Machine (SVM) . Hybrid models also often used in long-term flood forecasting.  \nHybrid models have become a growing interest to the researcher in developing model for longterm flood forecast. Multiple machine learning techniques are integrated, combined, or used in  \nensembles to create models. Hybrid machine learning models can also be developed by combining input optimization into the models that can give forecasts with acceptable performance and accuracy. In certain studies, hybrid machine learning is used with more traditional techniques like physical approaches to improve the performance of the models.  \nIn most machine learning model either it is singl","cbCaihae1q5pP30N","https://ap.wps.com/l/cbCaihae1q5pP30N","pdf",973840,1,12,"English","en",105,"# Introduction\n## Machine learning for flood forecasting\n## Hybrid model development\n## Importance of input selection and preprocessing\n## Discrete wavelet transform and its limitations\n## Empirical mode decomposition and intrinsic mode functions","[{\"question\":\"What problem does the study address in flood forecasting?\",\"answer\":\"It addresses how to select the most important features from high-dimensional, nonlinear time-series data from multiple stations to improve forecast accuracy.\"},{\"question\":\"How is the hybrid model constructed in this research?\",\"answer\":\"It combines machine learning models (ANN, ANFIS, and LSTM) with time-series decomposition methods such as EMD, ensemble EMD, and discrete wavelet transform to generate a hybrid forecasting approach.\"},{\"question\":\"How does mutual information support feature selection?\",\"answer\":\"Mutual information measures uncertainty across stations and is used to rank rainfall features, helping choose inputs that lead to higher accuracy.\"}]","Hybrid machine learning model based on feature decomposition and entropy optimization for higher accuracy flood forecasting | PDF",1785727018,30,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"hybrid-machine-learning-model-based-on-feature-decomposition-and-entropy-optimization-for-higher-accuracy-flood-forecasting","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/hybrid-machine-learning-model-based-on-feature-decomposition-and-entropy-optimization-for-higher-accuracy-flood-forecasting/119923/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the study address in flood forecasting?","Question",{"text":75,"@type":76},"It addresses how to select the most important features from high-dimensional, nonlinear time-series data from multiple stations to improve forecast accuracy.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the hybrid model constructed in this research?",{"text":80,"@type":76},"It combines machine learning models (ANN, ANFIS, and LSTM) with time-series decomposition methods such as EMD, ensemble EMD, and discrete wavelet transform to generate a hybrid forecasting approach.",{"name":82,"@type":73,"acceptedAnswer":83},"How does mutual information support feature selection?",{"text":84,"@type":76},"Mutual information measures uncertainty across stations and is used to rank rainfall features, helping choose inputs that lead to higher accuracy.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":29,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]