Search for: All records

Neural networks (NNs) enable precise modeling of complicated geophysical phenomena but can be sensitive to small input changes. In this work, we present a new method for analyzing this instability in NNs. We focus our analysis on adversarial examples, test‐time inputs with carefully crafted human‐imperceptible perturbations that expose the worst‐case instability in a model's predictions. Our stability analysis is based on a low‐rank expansion of NNs on a fixed input, and we apply our analysis to a NN model for tsunami early warning which takes geodetic measurements as the input and forecasts tsunami waveforms. The result is an improved description of local stability that explains adversarial examples generated by a standard gradient‐based algorithm, and allows the generation of other comparable examples. Our analysis can predict whether noise in the geodetic input will produce an unstable output, and identifies a potential approach to filtering the input that enable more robust forecasting 

Continuous-time dynamics models, e.g., neural ordinary differential equations, enable accurate modeling of underlying dynamics in time-series data. However, employing neural networks for parameterizing dynamics makes it challenging for humans to identify dependence structures, especially in the presence of delayed effects. In consequence, these models are not an attractive option when capturing dependence carries more importance than accurate modeling, e.g., in tsunami forecasting. In this paper, we present a novel method for identifying dependence structures in continuous-time dynamics models. We take a two-step approach: (1) During training, we promote weight sparsity in the model’s first layer during training. (2) We prune the sparse weights after training to identify dependence structures. In evaluation, we test our method in scenarios where the exact dependence structures of time-series are known. Compared to baselines, our method is more effective in uncovering dependence structures in data even when there are delayed effects. Moreover, we evaluate our method to a real-world tsunami forecasting, where the exact dependence structures are unknown beforehand. Even in this challenging scenario, our method still effective learns physically-consistent dependence structures and achieves high accuracy in forecasting. 

We investigate the potential of using Global Navigation Satellite System (GNSS) observations to directly forecast full tsunami waveforms in real time. We train convolutional neural networks to use less than 9 min of GNSS data to forecast the full tsunami waveforms over 6 hr at select locations, and obtain accurate forecasts on a test data set. Our training and test data consists of synthetic earthquakes and associated GNSS data generated for the Cascadia Subduction Zone using the MudPy software, and corresponding tsunami waveforms in Puget Sound computed using GeoClaw. We use the same suite of synthetic earthquakes and waveforms as in earlier work where tsunami waveforms were used for forecasting, and provide a comparison. We also explore varying the number of GNSS stations, their locations, and their observation durations.