Moderate evidence
Published recordClimateGood Space
More
A GEFS-Ensemble-Driven Dual-Gate Machine Learning System for 3-Hourly Quantitative Precipitation Forecasting over Brazil: Independent Dual-Reference Verification and Calibration for Flood Early Warning
- Truvace record
- TRV-2026-3004raw data (JSON)
- Version
- v1Published
- First published
- Evidence type
- Controlled or validated comparison
- Sources
- 1 sourcePeer-reviewed
- sha256
- 052db749e408…check it
Abstract Subdaily quantitative precipitation forecasts (QPFs) are a primary input to flood early warning, yet over Brazil, they are hampered by convective, intermittent rainfall and a sparse observing network. We present a machine learning postprocessing system (V2.0C) producing 3-hourly QPF on a 0.25° grid by coupling a light gradient-boosting machine (LightGBM) precipitation-occurrence classifier with a Tweedie amount regressor and a dual-gate routing scheme with a physically guarded heavy-rain (≥5 mm) hard ro…
The gain
In a verification over two windows in 2025–2026 against satellite estimates, a machine learning postprocessing system for Brazil reached a heavy-rain (≥10 mm) critical success index of 0.063–0.071, 3.3–4.4 times that of the raw GFS model.
What this doesn’t fix
The absolute heavy-rain critical success index remains low, and the authors say the product is a detection aid rather than a stand-alone warning trigger.
Sources
1 on file- Journal of Hydrometeorologydoi:10.1175/jhm-d-26-0116.1
Cite this record
v1Truvace Impact Record TRV-2026-3004, v1: “A GEFS-Ensemble-Driven Dual-Gate Machine Learning System for 3-Hourly Quantitative Precipitation Forecasting over Brazil: Independent Dual-Reference Verification and Calibration for Flood Early Warning.” Truvace, 2026-11-17. /record/TRV-2026-3004 (accessed on the day you copy it). sha256 052db749e4082c0c…
Change history
1 versionEvery change made to this record since it was first published, and why. Nothing has changed since it went up.
Certified into the record
Check this record hasn’t been altered
How to check it yourself, without trusting this page
Download any version from /api/record/TRV-2026-3004 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.
ace