Fill the gaps in your sensor data.

Loggers fail, batteries die, telemetry drops out. What is left is a time series full of holes — and every analysis downstream inherits them. Deleting the gappy stretch wastes real data; naive interpolation invents data that never happened.

How it works

Gaplad learns the relationship between your broken series and the streams that kept working — plus time-of-day and seasonal structure — then fills the gaps and proves the fill quality on synthetic gaps carved from your own observed data.

• 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 sensor time series, 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

Everything runs in your browser. The file never uploads anywhere, which means confidential monitoring data needs no clearance to use it. 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.