2016
DOI: 10.2139/ssrn.2828069
|View full text |Cite
|
Sign up to set email alerts
|

Multimodal Optimization: An Effective Framework for Model Calibration

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
14
0

Year Published

2017
2017
2021
2021

Publication Types

Select...
6

Relationship

5
1

Authors

Journals

citations
Cited by 6 publications
(14 citation statements)
references
References 64 publications
0
14
0
Order By: Relevance
“…Finally, Machine Learning should capitalize on bio-inspired solvers for multimodal optimization, in problems related to feature selection [179] or model calibration [180]. We do think that this is an extremely interesting research line that spans far beyond multimodal optimization, which we expect will be further growing in the near future.…”
Section: Multimodal Optimizationmentioning
confidence: 99%
“…Finally, Machine Learning should capitalize on bio-inspired solvers for multimodal optimization, in problems related to feature selection [179] or model calibration [180]. We do think that this is an extremely interesting research line that spans far beyond multimodal optimization, which we expect will be further growing in the near future.…”
Section: Multimodal Optimizationmentioning
confidence: 99%
“…The environmental impact, en v j ( t ) , of province agent j at time t is computed based on two components, namely the intensity of extreme weather events and the vulnerability of agent j to each event, vu l j . The intensity of climatic hazard component is produced by a Poisson distribution function P ( x , λ ) , where x is the observed occurrence of hazards and λ is the expected number of hazard events in a given time interval 20 :…”
Section: Agent-based Modeling Of Inter-provincial Migrationmentioning
confidence: 99%
“…The GA 17 has been proven to be a useful tool for automated calibration of different kinds of non-linear models, including agent-based models. 1821 The GA also has advantages in terms of its capability to conduct automated sensitivity analysis 18 and explore wider ranges of parameter settings. 22…”
Section: Introductionmentioning
confidence: 99%
“…This sensitivity analysis can be directly run by studying the output of the different simulation runs. Although a complete sensitivity analysis requires more advanced methods and specific tools to this end (Saltelli et al 2008, Chica et al 2017, the simheuristic learning process can give the modeler a first approach to a deeper sensitivity analysis of the system whose optimization is sought.…”
Section: Advantages Of Using Simheuristics In Optimizationmentioning
confidence: 99%
“…Thus, for instance, validation and stakeholders' discussion of the simulation model used within the simheuristic are encouraged. As simulation can tolerate far less restrictive modeling assumptions, even simple simulations must be correctly validated (Sargent 2005, Oliva 2003, Chica et al 2017 and agreed to by as many decision makers as possible, in order to lead to better decisions (Voinov and Bousquet 2010). These guidelines promote use of different stages to avoid jeopardizing the optimization process itself, and obtain the best possible results with reduced computing time.…”
Section: Introductionmentioning
confidence: 99%