Search

Tsunamis are natural phenomena that, although occasional, can have large impacts on coastal environments and settlements, especially in terms of loss of life. An accurate, detailed and timely assessment of the hazard is essential as input for mitigation strategies both in the long term and during emergencies. This goal is compounded by the high computational cost of simulating an adequate number of scenarios to make robust assessments. To reduce this handicap, alternative methods could be used. Here, an enhanced method for estimating tsunami time series using a one-dimensional convolutional neural network model (1D CNN) is considered. While the use of deep learning for this problem is not new, most of existing research has focused on assessing the capability of a network to reproduce inundation metrics extrema. However, for the context of Tsunami Early Warning, it is equally relevant to assess whether the networks can accurately predict whether inundation would occur or not, and its time series if it does. Hence, a set of 6776 scenarios with magnitudes in the range Mw 8.0–9.2 were used to design several 1D CNN models at two bays that have different hydrodynamic behavior, that would use as input inexpensive low-resolution numerical modeling of tsunami propagation to predict inundation time series at pinpoint locations. In addition, different configuration parameters were also analyzed to outline a methodology for model testing and design, that could be applied elsewhere. The results show that the network models are capable of reproducing inundation time series well, either for small or large flow depths, but also when no inundation was forecast, with minimal instances of false alarms or missed alarms. To further assess the performance, the model was tested with two past tsunamis and compared with actual inundation metrics. The results obtained are promising, and the proposed model could become a reliable alternative for the calculation of tsunami intensity measures i, Tide gauge data were obtained from the Sea Level Station Monitoring Facility of the Intergovernmental Oceanographic Commission (http://www.ioc-sealevelmonitoring.org/list.php). The coarser bathymetric and topographic data from the General Bathymetric Chart of the Ocean (https://www.gebco.net/data_and_products/gridded_bathymetry_data/). The authors acknowledge SHOA for providing nautical charts and coastal zone plans used to generate high resolution topo-bathymetric grids for research purposes. We are deeply grateful with A. Gubler that prepared a first version of the high resolution bathymetry grids. The authors acknowledge the computer resources at CTE-POWER (https://www.bsc.es/supportkc/docs/CTE-POWER/overview) and the technical support provided by BSC. We are greatly thankful the EDANYA Group at Málaga University for sharing the Tsunami-HySEA code. Most figures were generated with Python91,92,93 and Global Mapping Tools94. JN deeply thanks support of Mitiga Solutions during his secondment. PAC would like to thank funding by ANID, Chile Grants FONDEF ID19I10048, Centro de Investigación para la Gestión Integrada del Riesgo de Desastres (CIGIDEN) ANID/FONDAP/15110017, and Centro Científico Tecnológico de Valparaíso, ANID PIA/APOYO AFB180002. NZ has received funding from the Marie Skłodowska-Curie grant agreement H2020-MSCA-COFUND-2016-75443., Peer Reviewed, Postprint (published version)

Maritime hub : Blue Economy Innovation Forum, 9-10 de noviembre de 2021

Tsunami hazard is typically assessed from inundation flow depths estimated from one or many earthquake scenarios. However, information about the exact time when such inundation occurs is seldom considered, yet it is crucial for pedestrian evacuation planning. Here, we propose an approach to estimating tsunami hazard by combining tsunami flow depths and arrival times to produce a nine-level, qualitative hazard scale that is translated into a simple tsunami hazard map. To do this, one of the most populated regions of the coast of Chile is considered as the sample site, using a large set of 2,800 tsunamigenic sources from earthquakes with magnitudes in the range Mw8.6−9.2, modeled from generation to inundation at high resolution. Main outcomes show great dependency of the hazard categorization on the tsunami time arrival, and less to the flow depths. Also, these results demonstrate that incorporating different sources of variability such as different earthquake magnitudes and locations as well as stochastic slip distributions is essential. Moreover, this proof-of-concept exercise clearly shows that the qualitative hybrid categorization of the tsunami hazard allows for its more effective understanding, which can be beneficial for designing mitigation strategies such as evacuation planning, and its management., The authors acknowledge SHOA’s support to this work, particularly making available nautical charts and coastal zone plans used to generate high resolution terrain models. PC, NZ and AG were partially funded by ANID through its grants ANID/FONDAP/15110017 (CIGIDEN), and ANID/FONDEF/ID19I10048. PAC also thanks ANID PIA/APOYO AFB180002. MC acknowledges the support from ‘Millennium Nucleus CYCLO: The Seismic Cycle Along Subduction Zones’ and Chile’s Fondo Nacional de Desarrollo Científico y Tecnológico, FONDECYT Projects N°1190258 and N° 1181479. The authors also acknowledge C. Sippl for discussion about asperities offshore Valparaíso and corrections to the manuscript. The authors thankfully acknowledges the computer resources at CTE-POWER and the technical support provided by BSC (RES-AECT-2020-2-0001), and the EDANYA Group at Málaga university for providing the HySEA code. We acknowledge D. Melgar for making available the MudPy code at: https://github.com/dmelgarm/MudPy. J. León is acknowledge for sharing the evacuation results. We are very grateful to the editor S. Lorito and the comments of K. Goda, A. Armigliato and W. Power, for a thoughtful and insightful discussion that helped us to greatly improve this work. NZ has received funding from the STARS programme part of the Marie Skłodowska-Curie grant agreement H2020-MSCA-COFUND-2016-754433., Peer Reviewed, Postprint (published version)