Reproduce “A Geometry-Informed Neural Operator surrogate of LISFLOOD-FP for rapid pluvial-fluvial flood forecasting: the case of Forlì, Italy” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Samuele Maria Garofalo, Fabio Limardo, Simonetta Bodojra, Mohammad Amin Nabian, Mehdi Taghizadeh
The authors develop a gauge-driven neural surrogate, GINO, to emulate LISFLOOD-FP flood forecasts for Forlì using river-stage and rainfall inputs. It predicts depth on 659 risk-product polygons and forecasts 72 hours ahead. Across 38 held-out forcing events, time-averaged CSI was 0.934 at 0.05 m and 0.844 at 0.3 m; these scores measure agreement with simulations, not observed depths.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.