GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion, pages 1583-1591

Deadline-driven approach for multi-fidelity surrogate-assisted environmental model calibration

Publication typeProceedings Article
Publication date2019-07-13
Abstract
This paper describes the approach for calibration of environmental models with the presence of time and quality restrictions. Advantages of the suggested strategy are based on two main concepts. The first advantage was provided by reducing the overall optimisation time due to the surrogate modelling of fitness function with the iterative gradual refinement of the environmental model fidelity (spatial and temporal resolution) for improving the fitness approximation. For the demonstration of the efficiency of surrogate-assisted multi-fidelity approach, it was compared with the baseline evolutionary calibration approach. The second advantage was assured by additional increasing of optimisation quality in the presence of strict deadline due to the building the strategy of multi-fidelity fitness approximation directly during the evolutionary algorithm execution. In order to prove the efficiency of the proposed dynamic strategy, it was compared with the preliminary meta-optimisation approach. As a case study, the wind wave model SWAN is used. The conducted experiments confirm the effectiveness of the proposed anytime approach and its applicability for the complex environmental models' parameters calibration.

Citations by journals

1
2
Journal of Computational Science
Journal of Computational Science, 2, 66.67%
Journal of Computational Science
2 publications, 66.67%
Applied Energy
Applied Energy, 1, 33.33%
Applied Energy
1 publication, 33.33%
1
2

Citations by publishers

1
2
3
Elsevier
Elsevier, 3, 100%
Elsevier
3 publications, 100%
1
2
3
  • We do not take into account publications that without a DOI.
  • Statistics recalculated only for publications connected to researchers, organizations and labs registered on the platform.
  • Statistics recalculated weekly.
Metrics
Share
Cite this
GOST |
Cite this
GOST Copy
Nikitin N. O. et al. Deadline-driven approach for multi-fidelity surrogate-assisted environmental model calibration // GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion. 2019. pp. 1583-1591.
GOST all authors (up to 50) Copy
Nikitin N. O., Vychuzhanin P., Hvatov A., Deeva I., Kalyuzhnaya A., Kovalchuk S. Deadline-driven approach for multi-fidelity surrogate-assisted environmental model calibration // GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion. 2019. pp. 1583-1591.
RIS |
Cite this
RIS Copy
TY - CPAPER
DO - 10.1145/3319619.3326876
UR - https://doi.org/10.1145%2F3319619.3326876
TI - Deadline-driven approach for multi-fidelity surrogate-assisted environmental model calibration
T2 - GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion
AU - Nikitin, Nikolay O
AU - Vychuzhanin, Pavel
AU - Hvatov, Alexander
AU - Deeva, Irina
AU - Kalyuzhnaya, Anna
AU - Kovalchuk, S.
PY - 2019
DA - 2019/07/13 00:00:00
SP - 1583-1591
ER -
BibTex
Cite this
BibTex Copy
@inproceedings{2019_Nikitin
author = {Nikolay O Nikitin and Pavel Vychuzhanin and Alexander Hvatov and Irina Deeva and Anna Kalyuzhnaya and S. Kovalchuk},
title = {Deadline-driven approach for multi-fidelity surrogate-assisted environmental model calibration},
year = {2019},
pages = {1583--1591},
month = {jul}
}
Found error?