Fill gaps in streamflow records.

A gauging station that dropped out for a week leaves a hole in the discharge record right where the annual statistics, flow-duration curves and model calibrations need it to be continuous.

How it works

Gaplad reconstructs the missing span from correlated series — a neighbouring gauge, rainfall, stage at another section — and reports NSE and KGE against held-out data per gap-duration class, with linear interpolation as the baseline, so the filled record can be defended in front of a reviewer.

• Quality scan first — error codes, spikes, frozen sensors and re-installed sensors are found before anything is modelled.
• Validated before filled — synthetic gaps are carved from your observed streamflow or stage record, filled blind, and scored against held-out truth. The winning method per gap length fills the real gaps.
• Honest by construction — short gaps use interpolation because it wins there; unfillable gaps stay unfilled with the reason stated; every filled value is flagged, with uncertainty bands from measured residuals.

Your data never leaves your browser

Extreme-event honesty is built in: filled points where the predictors leave their observed range are flagged as extrapolation, and the tool will not silently reconstruct a flood peak it never saw. The model trains in a background thread on your machine — there is no upload, no account, and nothing to get security clearance for.

Free tier runs the full pipeline on up to 20,000 time steps (about two years of hourly data) with a watermark line on exports. A one-time licence lifts the size limit and cleans the exports. Exported CSVs flag every filled value; the trust report is a single HTML file you can attach to a deliverable.