Application of machine learning algorithms for flood susceptibility assessment and risk management

Assessing floods and their likely impact in climate change scenarios will enable the facilitation of sustainable management strategies. In this study, five machine learning (ML) algorithms, namely (i) Logistic Regression, (ii) Support Vector Machine, (iii) K-nearest neighbor, (iv) Adaptive Boosting...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	R. Madhuri, S. Sistla, K. Srinivasa Raju
Formato:	article
Lenguaje:	EN
Publicado:	IWA Publishing 2021
Materias:	flood risk hyderabad hyperparameters machine learning rcps Environmental technology. Sanitary engineering TD1-1066 Environmental sciences GE1-350
Acceso en línea:	https://doaj.org/article/3aee8eec651f4f93b535825cfc338841
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:3aee8eec651f4f93b535825cfc338841
record_format	dspace
spelling	oai:doaj.org-article:3aee8eec651f4f93b535825cfc3388412021-11-05T19:07:49ZApplication of machine learning algorithms for flood susceptibility assessment and risk management2040-22442408-935410.2166/wcc.2021.051https://doaj.org/article/3aee8eec651f4f93b535825cfc3388412021-09-01T00:00:00Zhttp://jwcc.iwaponline.com/content/12/6/2608https://doaj.org/toc/2040-2244https://doaj.org/toc/2408-9354Assessing floods and their likely impact in climate change scenarios will enable the facilitation of sustainable management strategies. In this study, five machine learning (ML) algorithms, namely (i) Logistic Regression, (ii) Support Vector Machine, (iii) K-nearest neighbor, (iv) Adaptive Boosting (AdaBoost) and (v) Extreme Gradient Boosting (XGBoost), were tested for Greater Hyderabad Municipal Corporation (GHMC), India, to evaluate their clustering abilities to classify locations (flooded or non-flooded) for climate change scenarios. A geo-spatial database, with eight flood influencing factors, namely, rainfall, elevation, slope, distance from nearest stream, evapotranspiration, land surface temperature, normalised difference vegetation index and curve number, was developed for 2000, 2006 and 2016. XGBoost performed the best, with the highest mean area under curve score of 0.83. Hence, XGBoost was adopted to simulate the future flood locations corresponding to probable highest rainfall events under four Representative Concentration Pathways (RCPs), namely, 2.6, 4.5, 6.0 and 8.5 along with other flood influencing factors for 2040, 2056, 2050 and 2064, respectively. The resulting ranges of flood risk probabilities are predicted as 39–77%, 16–39%, 42–63% and 39–77% for the respective years. HIGHLIGHTS Comparative assessment of ML algorithms to identify the most suitable algorithm for Greater Hyderabad Municipal Corporation (GHMC), India, to classify locations as either flooded or non-flooded.; The most reliable ML algorithm (in this case XGBoost) is employed to predict flood risk probabilities for extreme rainfall situations in four different RCPs in association with other flood influencing factors.;R. MadhuriS. SistlaK. Srinivasa RajuIWA Publishingarticleflood riskhyderabadhyperparametersmachine learningrcpsEnvironmental technology. Sanitary engineeringTD1-1066Environmental sciencesGE1-350ENJournal of Water and Climate Change, Vol 12, Iss 6, Pp 2608-2623 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	flood risk hyderabad hyperparameters machine learning rcps Environmental technology. Sanitary engineering TD1-1066 Environmental sciences GE1-350
spellingShingle	flood risk hyderabad hyperparameters machine learning rcps Environmental technology. Sanitary engineering TD1-1066 Environmental sciences GE1-350 R. Madhuri S. Sistla K. Srinivasa Raju Application of machine learning algorithms for flood susceptibility assessment and risk management
description	Assessing floods and their likely impact in climate change scenarios will enable the facilitation of sustainable management strategies. In this study, five machine learning (ML) algorithms, namely (i) Logistic Regression, (ii) Support Vector Machine, (iii) K-nearest neighbor, (iv) Adaptive Boosting (AdaBoost) and (v) Extreme Gradient Boosting (XGBoost), were tested for Greater Hyderabad Municipal Corporation (GHMC), India, to evaluate their clustering abilities to classify locations (flooded or non-flooded) for climate change scenarios. A geo-spatial database, with eight flood influencing factors, namely, rainfall, elevation, slope, distance from nearest stream, evapotranspiration, land surface temperature, normalised difference vegetation index and curve number, was developed for 2000, 2006 and 2016. XGBoost performed the best, with the highest mean area under curve score of 0.83. Hence, XGBoost was adopted to simulate the future flood locations corresponding to probable highest rainfall events under four Representative Concentration Pathways (RCPs), namely, 2.6, 4.5, 6.0 and 8.5 along with other flood influencing factors for 2040, 2056, 2050 and 2064, respectively. The resulting ranges of flood risk probabilities are predicted as 39–77%, 16–39%, 42–63% and 39–77% for the respective years. HIGHLIGHTS Comparative assessment of ML algorithms to identify the most suitable algorithm for Greater Hyderabad Municipal Corporation (GHMC), India, to classify locations as either flooded or non-flooded.; The most reliable ML algorithm (in this case XGBoost) is employed to predict flood risk probabilities for extreme rainfall situations in four different RCPs in association with other flood influencing factors.;
format	article
author	R. Madhuri S. Sistla K. Srinivasa Raju
author_facet	R. Madhuri S. Sistla K. Srinivasa Raju
author_sort	R. Madhuri
title	Application of machine learning algorithms for flood susceptibility assessment and risk management
title_short	Application of machine learning algorithms for flood susceptibility assessment and risk management
title_full	Application of machine learning algorithms for flood susceptibility assessment and risk management
title_fullStr	Application of machine learning algorithms for flood susceptibility assessment and risk management
title_full_unstemmed	Application of machine learning algorithms for flood susceptibility assessment and risk management
title_sort	application of machine learning algorithms for flood susceptibility assessment and risk management
publisher	IWA Publishing
publishDate	2021
url	https://doaj.org/article/3aee8eec651f4f93b535825cfc338841
work_keys_str_mv	AT rmadhuri applicationofmachinelearningalgorithmsforfloodsusceptibilityassessmentandriskmanagement AT ssistla applicationofmachinelearningalgorithmsforfloodsusceptibilityassessmentandriskmanagement AT ksrinivasaraju applicationofmachinelearningalgorithmsforfloodsusceptibilityassessmentandriskmanagement
_version_	1718444032163577856

Application of machine learning algorithms for flood susceptibility assessment and risk management

Ejemplares similares