Sismik Analiz
Can earthquake magnitude be predicted from its own past time series? My answer was no — and I am not hiding it.
Earthquake records form a time series, and time-series forecasting has well-known architectures. The question was whether those architectures could predict the next magnitude from past magnitudes alone.
- I split a 31,915-record dataset into 20-step windows.
- I built two models in PyTorch: a bidirectional LSTM and an attention-based LSTM.
- I measured success with R² rather than accuracy — accuracy is a meaningless metric when predicting a continuous value.
My own notebook in this four-person team is PyTorch-based. The TensorFlow and Bi-GRU work in the team repository belongs to other members; I do not present it as mine.
Bi-LSTM R² = 0.10, attention LSTM R² = 0.02. Both models fail to explain nearly any of the variance. Conclusion: a univariate setup cannot predict earthquake magnitude.
Inflating these numbers would have been easy — overlap the windows and let train and test leak into each other, or swap the metric for accuracy. Either would have produced a handsome chart, and either would have been a lie. Showing that a model does not work is itself a finding; the real engineering is refusing to dress up a null result as a success.
Python · PyTorch · Jupyter · Bi-LSTM · Attention