Rain garden infiltration rate modeling using gradient boosting machine and deep learning techniques

Rain garden is effective in reducing storm water runoff, whose efficiency depends upon several parameters such as soil type, vegetation and meteorological factors. Evaluation of rain gardens has been done by various researchers. However, knowledge for sound design of rain gardens is still very limit...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Sandeep Kumar, K. K. Singh
Formato:	article
Lenguaje:	EN
Publicado:	IWA Publishing 2021
Materias:	deep learning gradient boosting machine philip's model rain garden simulation of infiltration rate Environmental technology. Sanitary engineering TD1-1066
Acceso en línea:	https://doaj.org/article/3acb241d87f846e5888e7ad2a466fc88
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:3acb241d87f846e5888e7ad2a466fc88
record_format	dspace
spelling	oai:doaj.org-article:3acb241d87f846e5888e7ad2a466fc882021-11-23T18:40:56ZRain garden infiltration rate modeling using gradient boosting machine and deep learning techniques0273-12231996-973210.2166/wst.2021.444https://doaj.org/article/3acb241d87f846e5888e7ad2a466fc882021-11-01T00:00:00Zhttp://wst.iwaponline.com/content/84/9/2366https://doaj.org/toc/0273-1223https://doaj.org/toc/1996-9732Rain garden is effective in reducing storm water runoff, whose efficiency depends upon several parameters such as soil type, vegetation and meteorological factors. Evaluation of rain gardens has been done by various researchers. However, knowledge for sound design of rain gardens is still very limited, particularly the accurate modeling of infiltration rate and how much it differs from infiltration of natural ground surface. The present study uses experimentally observed infiltration rate of rain gardens with different types of vegetation (grass, candytuft, marigold and daisy with different plant densities) and flow conditions. After that, modeling has been done by the popular infiltration model i.e. Philip's model (which is valid for natural ground surface) and soft computing tools viz. Gradient Boosting Machine (GBM) and Deep Learning (DL). Results suggest a promising performance (in terms of CC, RMSE, MAE, MSE and NSE) by GBM and DL in comparison to the relation proposed by Philip's model (1957). Most of the values predicted by both GBM and DL are within scatter limits of ±5%, whereas the values by Philips model are within the range of ±25% error lines and even outside. GBM performs better than DL as the values of the correlation coefficients and Nash-Sutcliffe model efficiency (NSE) coefficient are the highest and the root mean square error is the lowest. The results of the study will be useful in selection of plant type and its density in the rain garden of the urban area. HIGHLIGHTS Performance of rain garden for different vegetation has been studied.; Soft computing techniques has been used to analyze the performance of rain garden.; Results suggest that soft computing techniques model better than existing conventional models.;Sandeep KumarK. K. SinghIWA Publishingarticledeep learninggradient boosting machinephilip's modelrain gardensimulation of infiltration rateEnvironmental technology. Sanitary engineeringTD1-1066ENWater Science and Technology, Vol 84, Iss 9, Pp 2366-2379 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	deep learning gradient boosting machine philip's model rain garden simulation of infiltration rate Environmental technology. Sanitary engineering TD1-1066
spellingShingle	deep learning gradient boosting machine philip's model rain garden simulation of infiltration rate Environmental technology. Sanitary engineering TD1-1066 Sandeep Kumar K. K. Singh Rain garden infiltration rate modeling using gradient boosting machine and deep learning techniques
description	Rain garden is effective in reducing storm water runoff, whose efficiency depends upon several parameters such as soil type, vegetation and meteorological factors. Evaluation of rain gardens has been done by various researchers. However, knowledge for sound design of rain gardens is still very limited, particularly the accurate modeling of infiltration rate and how much it differs from infiltration of natural ground surface. The present study uses experimentally observed infiltration rate of rain gardens with different types of vegetation (grass, candytuft, marigold and daisy with different plant densities) and flow conditions. After that, modeling has been done by the popular infiltration model i.e. Philip's model (which is valid for natural ground surface) and soft computing tools viz. Gradient Boosting Machine (GBM) and Deep Learning (DL). Results suggest a promising performance (in terms of CC, RMSE, MAE, MSE and NSE) by GBM and DL in comparison to the relation proposed by Philip's model (1957). Most of the values predicted by both GBM and DL are within scatter limits of ±5%, whereas the values by Philips model are within the range of ±25% error lines and even outside. GBM performs better than DL as the values of the correlation coefficients and Nash-Sutcliffe model efficiency (NSE) coefficient are the highest and the root mean square error is the lowest. The results of the study will be useful in selection of plant type and its density in the rain garden of the urban area. HIGHLIGHTS Performance of rain garden for different vegetation has been studied.; Soft computing techniques has been used to analyze the performance of rain garden.; Results suggest that soft computing techniques model better than existing conventional models.;
format	article
author	Sandeep Kumar K. K. Singh
author_facet	Sandeep Kumar K. K. Singh
author_sort	Sandeep Kumar
title	Rain garden infiltration rate modeling using gradient boosting machine and deep learning techniques
title_short	Rain garden infiltration rate modeling using gradient boosting machine and deep learning techniques
title_full	Rain garden infiltration rate modeling using gradient boosting machine and deep learning techniques
title_fullStr	Rain garden infiltration rate modeling using gradient boosting machine and deep learning techniques
title_full_unstemmed	Rain garden infiltration rate modeling using gradient boosting machine and deep learning techniques
title_sort	rain garden infiltration rate modeling using gradient boosting machine and deep learning techniques
publisher	IWA Publishing
publishDate	2021
url	https://doaj.org/article/3acb241d87f846e5888e7ad2a466fc88
work_keys_str_mv	AT sandeepkumar raingardeninfiltrationratemodelingusinggradientboostingmachineanddeeplearningtechniques AT kksingh raingardeninfiltrationratemodelingusinggradientboostingmachineanddeeplearningtechniques
_version_	1718416146461360128

Rain garden infiltration rate modeling using gradient boosting machine and deep learning techniques

Ejemplares similares