An Attention-Based Stochastic Simulator for Multisite Extremes to Evaluate Nonstationary, Cascading Flood Risk
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917409078640640 |
|---|---|
| author | Nayak, Adam Gentine, Pierre Lall, Upmanu |
| author_facet | Nayak, Adam Gentine, Pierre Lall, Upmanu |
| contents | Flood risk is correlated in space and time, challenging insurance systems that rely on diversification across assets. Financial instruments governing flood coverage are typically structured as 1 to 5-year contracts, exposing portfolios to climate-driven risk at interannual-to-decadal scales. Yet existing tools address climate risk either through seasonal forecasts extending only months or multidecadal projections misaligned with fiscal horizons, leaving a critical gap in actionable flood risk simulation. We introduce a multisite flood simulation framework combining attention-based analog retrieval with stochastic generation of multivariate flood frequency, intensity, and duration sequences. Applied to over 100 sites in the Mississippi River Basin, the model produces spatiotemporally coherent flood portfolios conditioned on interannual climate variability. Explainable AI attribution paired with wavelet analysis links simulated clustering to large-scale climate drivers, yielding physically interpretable flood clusters for portfolio-scale loss simulation. The framework provides plausible, out-of-sample flood risk catalogs for interannual-to-decadal insurance risk assessment and financial planning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_14162 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An Attention-Based Stochastic Simulator for Multisite Extremes to Evaluate Nonstationary, Cascading Flood Risk Nayak, Adam Gentine, Pierre Lall, Upmanu Geophysics Atmospheric and Oceanic Physics Data Analysis, Statistics and Probability Flood risk is correlated in space and time, challenging insurance systems that rely on diversification across assets. Financial instruments governing flood coverage are typically structured as 1 to 5-year contracts, exposing portfolios to climate-driven risk at interannual-to-decadal scales. Yet existing tools address climate risk either through seasonal forecasts extending only months or multidecadal projections misaligned with fiscal horizons, leaving a critical gap in actionable flood risk simulation. We introduce a multisite flood simulation framework combining attention-based analog retrieval with stochastic generation of multivariate flood frequency, intensity, and duration sequences. Applied to over 100 sites in the Mississippi River Basin, the model produces spatiotemporally coherent flood portfolios conditioned on interannual climate variability. Explainable AI attribution paired with wavelet analysis links simulated clustering to large-scale climate drivers, yielding physically interpretable flood clusters for portfolio-scale loss simulation. The framework provides plausible, out-of-sample flood risk catalogs for interannual-to-decadal insurance risk assessment and financial planning. |
| title | An Attention-Based Stochastic Simulator for Multisite Extremes to Evaluate Nonstationary, Cascading Flood Risk |
| topic | Geophysics Atmospheric and Oceanic Physics Data Analysis, Statistics and Probability |
| url | https://arxiv.org/abs/2509.14162 |