Flood Forecast

Last updated: 2026-10-31 07:00:00 SAST
EN ZU XH
Home Lite View

Weather Models

Statistics

Min—
Mean—
Max—
Total—
Max Hourly—
Mean Hourly—
Wet Hours—

Forecast Accuracy

MAE (m) by forecast horizon
Model 1-6h 7-12h 13-24h 25-48h 49-72h 73h+
Ensemble Mean 0.0303 0.0327 0.0349 0.0380 0.0398 0.0447
Best Match 0.0314 0.0342 0.0390 0.0384 0.0435 0.0494
CMA GRAPES 0.0285 0.0333 0.0358 0.0435 0.0472 0.0460
ECMWF AIFS 0.0333 0.0372 0.0378 0.0417 0.0421 0.0481
ECMWF IFS 0.0314 0.0342 0.0390 0.0384 0.0435 0.0494
ECMWF IFS 0.25° 0.0310 0.0344 0.0368 0.0360 0.0413 0.0456
GFS Global 0.0327 0.0349 0.0363 0.0406 0.0415 0.0480
GFS Seamless 0.0327 0.0349 0.0363 0.0406 0.0415 0.0480
MET Norway 0.0314 0.0342 0.0390 0.0384 0.0435 0.0494
NCEP AI-GFS 0.0332 0.0352 0.0381 0.0415 0.0385 0.0503
NCEP HGEFS 0.0325 0.0350 0.0365 0.0409 0.0423 0.0453
UKMO Global 0.0317 0.0384 0.0403 0.0418 0.0501 0.0768
Based on 693,480 prediction-observation comparisons (all-time). Updates every hour as new observations verify past predictions.
How is this calculated?

Each hour, the system generates water level predictions for the next 7 days using each weather model's rainfall forecast. Once real observations come in, the predicted values are compared against what actually happened. MAE (Mean Absolute Error) is the average difference between predicted and observed levels — lower is better. Columns group predictions by how far ahead they were made: a "1-6h" prediction is easier to get right than a "73h+" one. Values are colour-coded: green < 0.02m, yellow < 0.05m, orange < 0.1m, red ≥ 0.1m.