Research & the Operational Service
The relationship between the peer-reviewed Bikos (2024) methodology and the live prediction system.
The Research Foundation
Seismikon's prediction methodology is grounded in peer-reviewed work: Bikos, A.N. (2024). Seismic Nowcasting: A Systemic Artificial Neural Network Predictive Model. Geoinformatics & Geostatistics: An Overview, 12:4.
The paper describes the natural time framework, the sliding window feature extraction technique, the LSTM architecture, the Earthquake Potential Score definition, and retrospective validation on California seismic data (2000–2023). This is the scientific basis for all operational claims. Download the paper (PDF).
From Paper to Production
Translating a research methodology into a live operational service involves engineering decisions not fully specified in the original paper:
- Data source: the operational service uses USGS/FDSN real-time catalogue data rather than the historical catalogue used in the research.
- Update cadence: predictions are issued on a defined schedule; the paper describes a batch analysis rather than a real-time pipeline.
- Evaluation protocol: the paper's retrospective analysis uses internal validation; the operational service uses a publicly-published, versioned evaluation protocol that is fixed before predictions are issued.
- Geographic scope: both paper and service focus on California; the paper notes the methodology is generalisable to other regions.
Where They Agree
The core algorithmic pipeline - natural time preprocessing, EPS calculation, sliding window feature extraction, LSTM prediction, and 4-tuple output (lat, lon, depth, magnitude) - is implemented in the operational service as described in the paper. Changes to this pipeline from the published specification are versioned and disclosed on the Research Methodology page.
Where More Work Is Needed
The paper demonstrates retrospective validation. The operational service is the first large-scale prospective test of the methodology in real-time conditions. Results may differ from retrospective figures due to non-stationarity in the seismic system, distributional shift between training and deployment data, or aspects of the pipeline not fully captured in the paper.
Seismikon's scientific co-founder (Dr. Bikos) is directly involved in the operational service, and any significant divergence from paper predictions prompts methodology review.