Research · operator view · build 2026.06.06

Model health &
deployment traceability.

The operator view tracks production model status, source freshness, and current public coverage. Shorelife is a daily forecast product and does not detect intra-day spills.

Production model
xgb-undersample-ensemble-curated-v0
Test AUCPR
0.3894
Test Brier
0.0733
Coverage
148 / 328
45% of California beaches
Public release
Eligible
Spatial backtests

Performance on unobserved counties

spatial beach persistence
AUCPR
0.579
Brier
0.249
50 folds · 6266 samples
spatial county persistence
AUCPR
0.370
Brier
0.185
12 folds · 20065 samples
spatial beach xgb undersample ensemble
AUCPR
0.872
Brier
0.113
50 folds · 6266 samples
spatial county xgb undersample ensemble
AUCPR
0.503
Brier
0.115
12 folds · 20065 samples
spatial beach hist gbm
AUCPR
0.853
Brier
0.121
50 folds · 6266 samples
spatial county hist gbm
AUCPR
0.474
Brier
0.118
12 folds · 20065 samples
spatial beach hist gbm positive persistence guard
AUCPR
0.624
Brier
0.226
50 folds · 6266 samples
spatial county hist gbm positive persistence guard
AUCPR
0.438
Brier
0.176
12 folds · 20065 samples
spatial beach hist gbm persistence blend
AUCPR
0.835
Brier
0.147
50 folds · 6266 samples
spatial county hist gbm persistence blend
AUCPR
0.489
Brier
0.117
12 folds · 20065 samples
spatial beach hist gbm no bacteria weather delta
AUCPR
0.783
Brier
0.170
50 folds · 6266 samples
spatial county hist gbm no bacteria weather delta
AUCPR
0.201
Brier
0.150
12 folds · 20065 samples
Deep dives

Transparency documentation

Labels · Thresholds

Risk Labels

How exceedance probability maps to the four public bands, legal basis, and what the model can and cannot predict.

READ →
Provenance · Cadence

Data Sources

The six primary datasets feeding the pipeline — BeachWatch, NDBC, CDIP, Open-Meteo, USGS NWIS, and CEDEN — with freshness status.

READ →
AUCPR · Brier · Spatial CV

Calibration

Live production metrics, spatial backtest results, and candidate model registry from the latest CI run.

READ →
Scientific artifacts

Open data & methodology

Technical Methodology

Model design, coverage limits, risk-band calibration, spatial holdout protocol, and known limitations.

Shorelife Team
READ →

Source Code & Data

Full pipeline, training scripts, and curated datasets available on GitHub under an open-source license.

Automated Pipeline
GITHUB →