{"title":"Discharge estimation in compound channels with converging and diverging floodplains an using an optimised Gradient Boosting Algorithm","authors":"Shashank Shekhar Sandilya, Bhabani Shankar Das, Dr. Sébastien Proust, Divyanshu Shekhar","doi":"10.2166/hydro.2024.292","DOIUrl":null,"url":null,"abstract":"\n River discharge estimation is vital for effective flood management and infrastructure planning. River systems consist of a main channel and floodplains, collectively forming a compound channel, posing challenges in discharge calculation, particularly when floodplains converge or diverge. Numerical models for discharge prediction require the solution of complex non-linear equations while traditional approaches often yield unreliable results with significant errors. To solve these complex non-linear problems, various machine learning (ML) approaches becoming popular. In the present study, ML algorithms, such as XGBoost, CatBoost and LightGBM, were developed to predict discharge in a compound channel. The PSO algorithm is applied for the optimisThe eesults show that all three gradient boosting algorithms effectively predict discharge in compound channels and are further enhanced by the application of the PSO algorithm. The R2 values for XGBoost, PSO-XGBoost, CatBoost and PSO-CatBoost exceed 0.95, whereas they are above 0.85 for LightBoost and PSO-LightBoost.The findings of this study validate the suitability of the proposed models, especially optimised with PSO is recommended for predicting discharge in a compound channel.","PeriodicalId":2,"journal":{"name":"ACS Applied Bio Materials","volume":"14 1","pages":""},"PeriodicalIF":4.6000,"publicationDate":"2024-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACS Applied Bio Materials","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.2166/hydro.2024.292","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MATERIALS SCIENCE, BIOMATERIALS","Score":null,"Total":0}
引用次数: 0
Abstract
River discharge estimation is vital for effective flood management and infrastructure planning. River systems consist of a main channel and floodplains, collectively forming a compound channel, posing challenges in discharge calculation, particularly when floodplains converge or diverge. Numerical models for discharge prediction require the solution of complex non-linear equations while traditional approaches often yield unreliable results with significant errors. To solve these complex non-linear problems, various machine learning (ML) approaches becoming popular. In the present study, ML algorithms, such as XGBoost, CatBoost and LightGBM, were developed to predict discharge in a compound channel. The PSO algorithm is applied for the optimisThe eesults show that all three gradient boosting algorithms effectively predict discharge in compound channels and are further enhanced by the application of the PSO algorithm. The R2 values for XGBoost, PSO-XGBoost, CatBoost and PSO-CatBoost exceed 0.95, whereas they are above 0.85 for LightBoost and PSO-LightBoost.The findings of this study validate the suitability of the proposed models, especially optimised with PSO is recommended for predicting discharge in a compound channel.
期刊介绍:
ACS Applied Bio Materials is an interdisciplinary journal publishing original research covering all aspects of biomaterials and biointerfaces including and beyond the traditional biosensing, biomedical and therapeutic applications.
The journal is devoted to reports of new and original experimental and theoretical research of an applied nature that integrates knowledge in the areas of materials, engineering, physics, bioscience, and chemistry into important bio applications. The journal is specifically interested in work that addresses the relationship between structure and function and assesses the stability and degradation of materials under relevant environmental and biological conditions.