Evaluating different machine learning methods to simulate runoff from extensive green roofs

<p>Green roofs are increasingly popular measures to permanently reduce or delay storm-water runoff. The main objective of the study was to examine the potential of using machine learning (ML) to simulate runoff from green roofs to estimate their hydrological performance. Four machine learning...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	E. M. H. Abdalla, V. Pons, V. Stovin, S. De-Ville, E. Fassman-Beck, K. Alfredsen, T. M. Muthanna
Formato:	article
Lenguaje:	EN
Publicado:	Copernicus Publications 2021
Materias:	Technology T Environmental technology. Sanitary engineering TD1-1066 Geography. Anthropology. Recreation G Environmental sciences GE1-350
Acceso en línea:	https://doaj.org/article/646cf6d51e8544dbbb45cf9ead935d61
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:646cf6d51e8544dbbb45cf9ead935d61
record_format	dspace
spelling	oai:doaj.org-article:646cf6d51e8544dbbb45cf9ead935d612021-11-15T08:12:11ZEvaluating different machine learning methods to simulate runoff from extensive green roofs10.5194/hess-25-5917-20211027-56061607-7938https://doaj.org/article/646cf6d51e8544dbbb45cf9ead935d612021-11-01T00:00:00Zhttps://hess.copernicus.org/articles/25/5917/2021/hess-25-5917-2021.pdfhttps://doaj.org/toc/1027-5606https://doaj.org/toc/1607-7938<p>Green roofs are increasingly popular measures to permanently reduce or delay storm-water runoff. The main objective of the study was to examine the potential of using machine learning (ML) to simulate runoff from green roofs to estimate their hydrological performance. Four machine learning methods, artificial neural network (ANN), M5 model tree, long short-term memory (LSTM) and <span class="inline-formula"><i>k</i></span> nearest neighbour (kNN), were applied to simulate storm-water runoff from 16 extensive green roofs located in four Norwegian cities across different climatic zones. The potential of these ML methods for estimating green roof retention was assessed by comparing their simulations with a proven conceptual retention model. Furthermore, the transferability of ML models between the different green roofs in the study was tested to investigate the potential of using ML models as a tool for planning and design purposes. The ML models yielded low volumetric errors that were comparable with the conceptual retention models, which indicates good performance in estimating annual retention. The ML models yielded satisfactory modelling results (NSE <span class="inline-formula">>0.5</span>) in most of the roofs, which indicates an ability to estimate green roof detention. The variations in ML models' performance between the cities was larger than between the different configurations, which was attributed to the different climatic characteristics between the four cities. Transferred ML models between cities with similar rainfall events characteristics (Bergen–Sandnes, Trondheim–Oslo) could yield satisfactory modelling performance (Nash–Sutcliffe efficiency NSE <span class="inline-formula">>0.5</span> and percentage bias <span class="inline-formula">\|</span>PBIAS<span class="inline-formula">\|</span> <span class="inline-formula"><25</span> %) in most cases. However, we recommend the use of the conceptual retention model over the transferred ML models, to estimate the retention of new green roofs, as it gives more accurate volume estimates. Follow-up studies are needed to explore the potential of ML models in estimating detention from higher temporal resolution datasets.</p>E. M. H. AbdallaV. PonsV. StovinS. De-VilleE. Fassman-BeckK. AlfredsenT. M. MuthannaCopernicus PublicationsarticleTechnologyTEnvironmental technology. Sanitary engineeringTD1-1066Geography. Anthropology. RecreationGEnvironmental sciencesGE1-350ENHydrology and Earth System Sciences, Vol 25, Pp 5917-5935 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Technology T Environmental technology. Sanitary engineering TD1-1066 Geography. Anthropology. Recreation G Environmental sciences GE1-350
spellingShingle	Technology T Environmental technology. Sanitary engineering TD1-1066 Geography. Anthropology. Recreation G Environmental sciences GE1-350 E. M. H. Abdalla V. Pons V. Stovin S. De-Ville E. Fassman-Beck K. Alfredsen T. M. Muthanna Evaluating different machine learning methods to simulate runoff from extensive green roofs
description	<p>Green roofs are increasingly popular measures to permanently reduce or delay storm-water runoff. The main objective of the study was to examine the potential of using machine learning (ML) to simulate runoff from green roofs to estimate their hydrological performance. Four machine learning methods, artificial neural network (ANN), M5 model tree, long short-term memory (LSTM) and <span class="inline-formula"><i>k</i></span> nearest neighbour (kNN), were applied to simulate storm-water runoff from 16 extensive green roofs located in four Norwegian cities across different climatic zones. The potential of these ML methods for estimating green roof retention was assessed by comparing their simulations with a proven conceptual retention model. Furthermore, the transferability of ML models between the different green roofs in the study was tested to investigate the potential of using ML models as a tool for planning and design purposes. The ML models yielded low volumetric errors that were comparable with the conceptual retention models, which indicates good performance in estimating annual retention. The ML models yielded satisfactory modelling results (NSE <span class="inline-formula">>0.5</span>) in most of the roofs, which indicates an ability to estimate green roof detention. The variations in ML models' performance between the cities was larger than between the different configurations, which was attributed to the different climatic characteristics between the four cities. Transferred ML models between cities with similar rainfall events characteristics (Bergen–Sandnes, Trondheim–Oslo) could yield satisfactory modelling performance (Nash–Sutcliffe efficiency NSE <span class="inline-formula">>0.5</span> and percentage bias <span class="inline-formula">\|</span>PBIAS<span class="inline-formula">\|</span> <span class="inline-formula"><25</span> %) in most cases. However, we recommend the use of the conceptual retention model over the transferred ML models, to estimate the retention of new green roofs, as it gives more accurate volume estimates. Follow-up studies are needed to explore the potential of ML models in estimating detention from higher temporal resolution datasets.</p>
format	article
author	E. M. H. Abdalla V. Pons V. Stovin S. De-Ville E. Fassman-Beck K. Alfredsen T. M. Muthanna
author_facet	E. M. H. Abdalla V. Pons V. Stovin S. De-Ville E. Fassman-Beck K. Alfredsen T. M. Muthanna
author_sort	E. M. H. Abdalla
title	Evaluating different machine learning methods to simulate runoff from extensive green roofs
title_short	Evaluating different machine learning methods to simulate runoff from extensive green roofs
title_full	Evaluating different machine learning methods to simulate runoff from extensive green roofs
title_fullStr	Evaluating different machine learning methods to simulate runoff from extensive green roofs
title_full_unstemmed	Evaluating different machine learning methods to simulate runoff from extensive green roofs
title_sort	evaluating different machine learning methods to simulate runoff from extensive green roofs
publisher	Copernicus Publications
publishDate	2021
url	https://doaj.org/article/646cf6d51e8544dbbb45cf9ead935d61
work_keys_str_mv	AT emhabdalla evaluatingdifferentmachinelearningmethodstosimulaterunofffromextensivegreenroofs AT vpons evaluatingdifferentmachinelearningmethodstosimulaterunofffromextensivegreenroofs AT vstovin evaluatingdifferentmachinelearningmethodstosimulaterunofffromextensivegreenroofs AT sdeville evaluatingdifferentmachinelearningmethodstosimulaterunofffromextensivegreenroofs AT efassmanbeck evaluatingdifferentmachinelearningmethodstosimulaterunofffromextensivegreenroofs AT kalfredsen evaluatingdifferentmachinelearningmethodstosimulaterunofffromextensivegreenroofs AT tmmuthanna evaluatingdifferentmachinelearningmethodstosimulaterunofffromextensivegreenroofs
_version_	1718428501580709888

Evaluating different machine learning methods to simulate runoff from extensive green roofs

Ejemplares similares