Seismic Risk Analysis

Java

Select Region
-6.00°N, 110.00°E R = 300 km — —

— Java bölgesel fay/subdüksiyon sistemi. Kayma hızı —; son büyük olay: —.

01Instant Risk Assessment
Talivio Engine·[TAL-401]render per-band ML risk cards

5 Magnitude Band Forecast

02Regional Model v2
Eren Bostan·[TAL-402]wire pretrained regional band models

Bölgeye Özel Band Tahminleri

Koordinata en yakın önceden eğitilmiş bölgesel model kullanılır. Her band ayrı stratejiyle eğitilmiştir (zor negatifler, temporal validation).

Yükleniyor…
03Physical Framework
Talivio Engine·[TAL-403]summarize seismic cycle metrics

Seismic Cycle Summary

Seismic Gap
—
Son kırılmadan beri
Slip Deficit
—
Birikmiş plastik deformasyon
Slip Rate
—
Jeodezik GNSS ölçümü
Max. Moment
—
Segment potansiyeli
b-Value Trend
—
Model çıktısından
Dominant Band
—
En yüksek risk skoru
05Tidal & Lunar Cycle
Talivio Engine·[TAL-405]overlay celestial tidal stress window

Celestial Alignment Window

06Historical Seismic Activity
Eren Bostan·[TAL-406]chart historical magnitude frequency

Magnitude Band Catalog Distribution

Kaynak: USGS, AFAD, ISC Bulletin (1900–2026) — Java, R=300 km. Değerler 100 yıllık normalize sıklığı temsil eder.

07Spatial Risk Distribution
Talivio Engine·[TAL-407]render spatial risk heatmap grid

Region Risk Heatmap

300 km yarıçap içinde 12×12 ızgara üzerinde ML risk skoru. Yeşil → düşük, sarı → orta, kırmızı → yüksek.

Detailed Risk Analysis Report
High-resolution grid, fault proximity scores, and 5-year probability forecasts.
Get Full Report
08Regional Geology
Eren Bostan·[TAL-408]list regional fault geology details

Fault System Details

Fault systemJava bölgesel fay/subdüksiyon sistemi
Fault type—
Slip rate—
Last major event—
Segment potential—
Seismic Gap—
Slip Deficit—
09ML Model Metrics
Talivio Engine·[TAL-409]surface per-band ROC-AUC scores

Band-Level ROC-AUC Accuracy

M3–4 (CalibratedFrozenEstimator) 1.000
M4–5 (CalibratedRandomForestClassifier) 0.860
M5–6 (CalibratedLGBMClassifier) 0.808
M6–7 (CalibratedFrozenEstimator) 0.827
M7+ (CalibratedRandomForestClassifier) 0.862
10Model Validation
Eren Bostan·[TAL-410]report walk-forward backtest accuracy

Backtest & Forecast Accuracy

Walk-forward backtest from 1990 to present — at every time slice the model is trained only on past data and tested on future events.

—
Avg. ROC-AUC
—
Brier Score
—
ECE (Calibration)
—
Test Windows
—
Skill Score (Poisson)
Prospective Forecast Accuracy

Every forecast is stored and verified against the USGS catalog when its window closes. Real performance — not retrospective.

Loading accuracy…
11Prospective Validation
Talivio Engine·[TAL-411]list past forecast hit/miss outcomes

Past Forecasts (Last 60 Days)

Forecasts issued by the system and their outcomes. Each forecast window is automatically matched against the USGS catalog when it closes.

Loading accuracy…
Forecasts are automatically saved and verified against the USGS catalog.