Reliability based management of coastal aquifers using heterogeneous ensemble of meta-models

Roy, Dilip Kumar, and Datta, Bithin (2018) Reliability based management of coastal aquifers using heterogeneous ensemble of meta-models. In: Proceedings of the IEEE Conference on Technologies for Sustainability (1) From: SusTech 2018: 6th IEEE Conference on Technologies for Sustainability, 11-13 November 2018, Long Beach, CA, USA.

[img] PDF (Published Version) - Published Version
Restricted to Repository staff only

View at Publisher Website: https://doi.org/10.1109/SusTech.2018.867...
 
1


Abstract

This study proposes a weighted average heterogeneous ensemble of meta-models for approximating seawater intrusion phenomena in coastal aquifer systems. Root mean square error criterion of standalone meta-models is used to assign the corresponding weight to each meta-model. Results indicate that the ensemble model's prediction is better than all considered meta-models except the best model in the ensemble. In the next step, individual meta-models are combined with a multiple objective optimization algorithm within the framework of multiple realization optimization to develop reliability based management models for coastal aquifers. Four different reliability levels (0.99, 0.83, 0.67, and 0.5) are considered. It is observed from the Pareto optimal fronts of the management models that total objective function value (total production well pumping for beneficial purposes) decreases as the reliability increases. A demonstrative multilayered coastal aquifer system is selected for assessing the suitability of the evaluated methodology. Results obtained demonstrate the capability of this approach to develop a reliable management strategy in mitigating the extent salinity intrusion in coastal aquifer systems.

Item ID: 57880
Item Type: Conference Item (Research - E1)
ISBN: 978-1-5386-7791-9
Keywords: coastal aquifer; saltwater intrusion; heterogeneous emsemble; reliability; multi-objective management
Date Deposited: 11 Apr 2019 05:21
FoR Codes: 09 ENGINEERING > 0905 Civil Engineering > 090509 Water Resources Engineering @ 100%
SEO Codes: 96 ENVIRONMENT > 9609 Land and Water Management > 960999 Land and Water Management of Environments not elsewhere classified @ 100%
Downloads: Total: 1
More Statistics

Actions (Repository Staff Only)

Item Control Page Item Control Page