Multi-objective optimization of typhoon inundation forecast models with
cross-site structures for a water-level gauging network by integrating ARMAX
with a genetic algorithm

Ouyang, Huei-Tau

doi:https://doi.org/10.5194/nhess-16-1897-2016

Articles | Volume 16, issue 8

https://doi.org/10.5194/nhess-16-1897-2016

© Author(s) 2016. This work is distributed under
the Creative Commons Attribution 3.0 License.

https://doi.org/10.5194/nhess-16-1897-2016

© Author(s) 2016. This work is distributed under
the Creative Commons Attribution 3.0 License.

Articles | Volume 16, issue 8

Research article

|

16 Aug 2016

Research article |

| 16 Aug 2016

Multi-objective optimization of typhoon inundation forecast models with cross-site structures for a water-level gauging network by integrating ARMAX with a genetic algorithm

Huei-Tau Ouyang

Data sets

Disaster Prevention Information Service Network Taiwan Water Resources Agency http://fhy.wra.gov.tw/fhy/Alert/Water

Short summary

Typhoon inundation forecast model for a gauging network is proposed. Model inputs are identified by cross-correlation and mutual information analysis. Optimal ARMAX model structures are searched for considering three objective functions, including the forecasting capacity in water level throughout the event, the accuracy in forecasting peak water levels and the time at which peak water levels are likely to occur. Characteristics of the resultant models subject to various objectives are examined.