A decision support tool for optimising groundwater-level monitoring networks using an adaptive genetic algorithm

Mapping of the spatial variability of sparse groundwater-level measurements is usually achieved by means of geostatistical methods. This work tackles the problem of deficient sampling of an aquifer, by employing an innovative integer adaptive genetic algorithm (iaGA) coupled with geostatistical mode...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Antonios Parasyris, Katerina Spanoudaki, Emmanouil A. Varouchakis, Nikolaos A. Kampanis
Formato:	article
Lenguaje:	EN
Publicado:	IWA Publishing 2021
Materias:	adaptive genetic algorithm geostatistical modelling groundwater monitoring network optimisation kriging-based genetic algorithm optimisation Information technology T58.5-58.64 Environmental technology. Sanitary engineering TD1-1066
Acceso en línea:	https://doaj.org/article/b94d138f748b4f1399be784eda5d8718
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b94d138f748b4f1399be784eda5d8718
record_format	dspace
spelling	oai:doaj.org-article:b94d138f748b4f1399be784eda5d87182021-11-05T17:51:27ZA decision support tool for optimising groundwater-level monitoring networks using an adaptive genetic algorithm1464-71411465-173410.2166/hydro.2021.045https://doaj.org/article/b94d138f748b4f1399be784eda5d87182021-09-01T00:00:00Zhttp://jh.iwaponline.com/content/23/5/1066https://doaj.org/toc/1464-7141https://doaj.org/toc/1465-1734Mapping of the spatial variability of sparse groundwater-level measurements is usually achieved by means of geostatistical methods. This work tackles the problem of deficient sampling of an aquifer, by employing an innovative integer adaptive genetic algorithm (iaGA) coupled with geostatistical modelling by means of ordinary kriging, to optimise the monitoring network. Fitness functions based on three different errors are used for removing a constant number of boreholes from the monitoring network. The developed methodology has been applied to the Mires basin in Crete, Greece. The methodological improvement proposed concerns the adaptive method for the GA, which affects the crossover–mutation fractions depending on the stall parameter, aiming at higher accuracy and faster convergence of the GA. The initial dataset consists of 70 monitoring boreholes and the applied methodology shows that as many as 40 boreholes can be removed, while still retaining an accurate mapping of groundwater levels. The proposed scenario for optimising the monitoring network consists of removing 30 boreholes, in which case the estimated uncertainty is considerably smaller. A sensitivity analysis is conducted to compare the performance of the standard GA with the proposed iaGA. The integrated methodology presented is easily replicable for other areas for efficient monitoring networks design. HIGHLIGHTS Development of an innovative adaptive genetic algorithm for optimising groundwater-level monitoring networks.; Coupling of evolutionary algorithms with geostatistics for monitoring network optimisation.; Development of a monitoring network design optimisation tool, easily applicable to any area, which considerably reduces sampling efforts, while achieving accurate mapping of groundwater levels.;Antonios ParasyrisKaterina SpanoudakiEmmanouil A. VarouchakisNikolaos A. KampanisIWA Publishingarticleadaptive genetic algorithmgeostatistical modellinggroundwater monitoring network optimisationkriging-based genetic algorithm optimisationInformation technologyT58.5-58.64Environmental technology. Sanitary engineeringTD1-1066ENJournal of Hydroinformatics, Vol 23, Iss 5, Pp 1066-1082 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	adaptive genetic algorithm geostatistical modelling groundwater monitoring network optimisation kriging-based genetic algorithm optimisation Information technology T58.5-58.64 Environmental technology. Sanitary engineering TD1-1066
spellingShingle	adaptive genetic algorithm geostatistical modelling groundwater monitoring network optimisation kriging-based genetic algorithm optimisation Information technology T58.5-58.64 Environmental technology. Sanitary engineering TD1-1066 Antonios Parasyris Katerina Spanoudaki Emmanouil A. Varouchakis Nikolaos A. Kampanis A decision support tool for optimising groundwater-level monitoring networks using an adaptive genetic algorithm
description	Mapping of the spatial variability of sparse groundwater-level measurements is usually achieved by means of geostatistical methods. This work tackles the problem of deficient sampling of an aquifer, by employing an innovative integer adaptive genetic algorithm (iaGA) coupled with geostatistical modelling by means of ordinary kriging, to optimise the monitoring network. Fitness functions based on three different errors are used for removing a constant number of boreholes from the monitoring network. The developed methodology has been applied to the Mires basin in Crete, Greece. The methodological improvement proposed concerns the adaptive method for the GA, which affects the crossover–mutation fractions depending on the stall parameter, aiming at higher accuracy and faster convergence of the GA. The initial dataset consists of 70 monitoring boreholes and the applied methodology shows that as many as 40 boreholes can be removed, while still retaining an accurate mapping of groundwater levels. The proposed scenario for optimising the monitoring network consists of removing 30 boreholes, in which case the estimated uncertainty is considerably smaller. A sensitivity analysis is conducted to compare the performance of the standard GA with the proposed iaGA. The integrated methodology presented is easily replicable for other areas for efficient monitoring networks design. HIGHLIGHTS Development of an innovative adaptive genetic algorithm for optimising groundwater-level monitoring networks.; Coupling of evolutionary algorithms with geostatistics for monitoring network optimisation.; Development of a monitoring network design optimisation tool, easily applicable to any area, which considerably reduces sampling efforts, while achieving accurate mapping of groundwater levels.;
format	article
author	Antonios Parasyris Katerina Spanoudaki Emmanouil A. Varouchakis Nikolaos A. Kampanis
author_facet	Antonios Parasyris Katerina Spanoudaki Emmanouil A. Varouchakis Nikolaos A. Kampanis
author_sort	Antonios Parasyris
title	A decision support tool for optimising groundwater-level monitoring networks using an adaptive genetic algorithm
title_short	A decision support tool for optimising groundwater-level monitoring networks using an adaptive genetic algorithm
title_full	A decision support tool for optimising groundwater-level monitoring networks using an adaptive genetic algorithm
title_fullStr	A decision support tool for optimising groundwater-level monitoring networks using an adaptive genetic algorithm
title_full_unstemmed	A decision support tool for optimising groundwater-level monitoring networks using an adaptive genetic algorithm
title_sort	decision support tool for optimising groundwater-level monitoring networks using an adaptive genetic algorithm
publisher	IWA Publishing
publishDate	2021
url	https://doaj.org/article/b94d138f748b4f1399be784eda5d8718
work_keys_str_mv	AT antoniosparasyris adecisionsupporttoolforoptimisinggroundwaterlevelmonitoringnetworksusinganadaptivegeneticalgorithm AT katerinaspanoudaki adecisionsupporttoolforoptimisinggroundwaterlevelmonitoringnetworksusinganadaptivegeneticalgorithm AT emmanouilavarouchakis adecisionsupporttoolforoptimisinggroundwaterlevelmonitoringnetworksusinganadaptivegeneticalgorithm AT nikolaosakampanis adecisionsupporttoolforoptimisinggroundwaterlevelmonitoringnetworksusinganadaptivegeneticalgorithm AT antoniosparasyris decisionsupporttoolforoptimisinggroundwaterlevelmonitoringnetworksusinganadaptivegeneticalgorithm AT katerinaspanoudaki decisionsupporttoolforoptimisinggroundwaterlevelmonitoringnetworksusinganadaptivegeneticalgorithm AT emmanouilavarouchakis decisionsupporttoolforoptimisinggroundwaterlevelmonitoringnetworksusinganadaptivegeneticalgorithm AT nikolaosakampanis decisionsupporttoolforoptimisinggroundwaterlevelmonitoringnetworksusinganadaptivegeneticalgorithm
_version_	1718444121482330112

A decision support tool for optimising groundwater-level monitoring networks using an adaptive genetic algorithm

Ejemplares similares