Discriminating the occurrence of inundation in tsunami early warning with one-dimensional convolutional neural networks
Abstract 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...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-06-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-13788-9 |
| _version_ | 1818219033555632128 |
|---|---|
| author | Jorge Núñez Patricio A. Catalán Carlos Valle Natalia Zamora Alvaro Valderrama |
| author_facet | Jorge Núñez Patricio A. Catalán Carlos Valle Natalia Zamora Alvaro Valderrama |
| author_sort | Jorge Núñez |
| collection | DOAJ |
| description | Abstract 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 $$M_w$$ M w 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 in a faster than real time manner. This could complement existing early warning system, by means of an approximate and fast procedure that could allow simulating a larger number of scenarios within the always restricting time frame of tsunami emergencies. |
| first_indexed | 2024-12-12T07:33:13Z |
| format | Article |
| id | doaj.art-a237c09349bd4662a82c826295960373 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-12-12T07:33:13Z |
| publishDate | 2022-06-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-a237c09349bd4662a82c8262959603732022-12-22T00:32:58ZengNature PortfolioScientific Reports2045-23222022-06-0112112010.1038/s41598-022-13788-9Discriminating the occurrence of inundation in tsunami early warning with one-dimensional convolutional neural networksJorge Núñez0Patricio A. Catalán1Carlos Valle2Natalia Zamora3Alvaro Valderrama4Departamento de Obras Civiles, Universidad Técnica Federico Santa MaríaDepartamento de Obras Civiles, Universidad Técnica Federico Santa MaríaDepartamento de Ciencia de Datos e Informática, Universidad de Playa Ancha ValparaísoComputer Applications in Science and Engineering Department, Barcelona Supercomputing Center (BSC)Universidad Técnica Federico Santa MaríaAbstract 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 $$M_w$$ M w 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 in a faster than real time manner. This could complement existing early warning system, by means of an approximate and fast procedure that could allow simulating a larger number of scenarios within the always restricting time frame of tsunami emergencies.https://doi.org/10.1038/s41598-022-13788-9 |
| spellingShingle | Jorge Núñez Patricio A. Catalán Carlos Valle Natalia Zamora Alvaro Valderrama Discriminating the occurrence of inundation in tsunami early warning with one-dimensional convolutional neural networks Scientific Reports |
| title | Discriminating the occurrence of inundation in tsunami early warning with one-dimensional convolutional neural networks |
| title_full | Discriminating the occurrence of inundation in tsunami early warning with one-dimensional convolutional neural networks |
| title_fullStr | Discriminating the occurrence of inundation in tsunami early warning with one-dimensional convolutional neural networks |
| title_full_unstemmed | Discriminating the occurrence of inundation in tsunami early warning with one-dimensional convolutional neural networks |
| title_short | Discriminating the occurrence of inundation in tsunami early warning with one-dimensional convolutional neural networks |
| title_sort | discriminating the occurrence of inundation in tsunami early warning with one dimensional convolutional neural networks |
| url | https://doi.org/10.1038/s41598-022-13788-9 |
| work_keys_str_mv | AT jorgenunez discriminatingtheoccurrenceofinundationintsunamiearlywarningwithonedimensionalconvolutionalneuralnetworks AT patricioacatalan discriminatingtheoccurrenceofinundationintsunamiearlywarningwithonedimensionalconvolutionalneuralnetworks AT carlosvalle discriminatingtheoccurrenceofinundationintsunamiearlywarningwithonedimensionalconvolutionalneuralnetworks AT nataliazamora discriminatingtheoccurrenceofinundationintsunamiearlywarningwithonedimensionalconvolutionalneuralnetworks AT alvarovalderrama discriminatingtheoccurrenceofinundationintsunamiearlywarningwithonedimensionalconvolutionalneuralnetworks |