Earthquake magnitude estimation using an optimized CNN-DNN-GRU model with binary differential evolution and firefly algorithm
Nada Ahmed, Safia Abbas, Yasser Fouad, Ahmed M Osman, Hazem M El-Bakry, Ahmed M Elshewey · 2026
Read Earthquake magnitude estimation using an optimized CNN-DNN-GRU model with binary differential evolution and firefly algorithm by Nada Ahmed, Safia Abbas, Yasser Fouad, Ahmed M Osman, Hazem M El-Bakry, Ahmed M Elshewey (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13500689.txt.
Description
Nada Ahmed and co-authors stack three kinds of neural network into one system that estimates earthquake magnitude, in a 2026 study. Fast, accurate magnitude reads feed early warning. Quake data are nonlinear and shift over time, which strains simple models. Their stack pairs a pattern-spotting network for shape, a deep network for layered traits, and a memory network for long time spans. Two search algorithms tune it: one picks the input features, the other sets the dials.
The training set held three and a half million quake records from 1990 to 2023, split by time into training, check, and test parts. The final scores were strong, with errors near a tenth of a magnitude unit and a fit close to perfect. The authors offer the system as a magnitude component for future warning systems, once live station data are wired in.
Catalog record
| CREATOR | Nada Ahmed, Safia Abbas, Yasser Fouad, Ahmed M Osman, Hazem M El-Bakry, Ahmed M Elshewey |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 97 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |