MétaCan
Menu
Back to cohort
Record W4408483698 · doi:10.5194/egusphere-egu25-20668

Early Warning Tsunami Prediction Using Neural Networks: A Case Study in Vancouver Island, Canada

2025· preprint· en· W4408483698 on OpenAlexaffabout
Ilias Chamatidis, Denis Istrati, Katsuichiro Goda, Nikos D. Lagaros

Bibliographic record

Venuenot available
Typepreprint
Languageen
FieldComputer Science
TopicSeismology and Earthquake Studies
Canadian institutionsWestern University
Fundersnot available
KeywordsWarning systemArtificial neural networkGeographyEarly warning systemCartographySeismologyGeologyComputer scienceArtificial intelligenceTelecommunications

Abstract

fetched live from OpenAlex

Tsunamis are one of the most devastating natural hazards, with the potential to cause extensive loss of life, property damage and socioeconomic disruptions. Developing robust and accurate early warning systems is critical to mitigating these impacts. In this study, a neural network-based early warning system is proposed to predict tsunami wave heights nearshore, focusing on the Vancouver Island area on the western coast of Canada.  The Vancouver Island region, which is extremely susceptible to tsunami hazards because of its closeness to the Cascadia Subduction Zone, is the area used to generate the synthetic data. In tsunami research, synthetic data are essential because they enable the investigation of a variety of possible earthquake and tsunami scenarios, including uncommon but highly consequential occurrences. The dataset, which contains 5000 simulation scenarios, used includes parameters such as fault slip parameters, bathymetry, hypocenter position, and earthquake magnitude, as well as the related tsunami wave heights at particular nearshore locations. The parameters used to train the model are the maximum wave heights off shore at different stations and the parameter that the model is trained to predict is the maximum wave height near shore in different depth zones (0 m, 5 m, 10 m, and 100 m). The neural network architecture was designed to model the nonlinear relationships between input parameters (maximum wave heights off shore at different stations) and resulting tsunami wave heights (near shore at different depths). By training, validating, and testing the neural network, the model demonstrated a high level of accuracy in predicting wave heights nearshore. The performance metrics, including mean absolute error and correlation coefficients, indicate that the neural network effectively captures the complexities of tsunami wave dynamics, making it suitable for early warning applications. According to the results, the neural network can accurately forecast tsunami heights close to shore, facilitating prompt evacuation preparation and disaster relief. This method is a major improvement over conventional physics-based models, which frequently demand a large amount of time and resources, by providing a computationally effective and scalable solution. Overall, this study demonstrates how machine learning, and in particular neural networks, might improve early warning systems for tsunamis.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.232
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.002
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.020
GPT teacher head0.250
Teacher spread0.230 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes2
Has abstractyes

Explore more

Same topicSeismology and Earthquake StudiesFrench-language works237,207