Land cover and flood type govern the detection limits of satellite-based flood mapping across diverse global flood events

arXiv cs.AI Papers

Summary

A study evaluating the Prithvi-EO-2.0 foundation model for satellite-based flood mapping across 19 diverse global flood events, finding that detection accuracy is jointly governed by land cover and flood type.

arXiv:2606.07780v1 Announce Type: new Abstract: Floods are among the most destructive natural hazards, and their increasing frequency under climate change makes satellite-based inundation mapping essential for disaster response. Geospatial foundation models pretrained on satellite archives offer geographic transferability, but their operational reliability across diverse, unseen events remains uncharacterized. Here we deploy Prithvi-EO-2.0 across 19 out-of-distribution flood events (2017-2025) spanning six continents, eight climate zones, and six flood mechanisms, validating against two independent reference products. Detection accuracy depended jointly on land cover and flood type, with cropland yielding the highest agreement (IoU=52%) and riverine events the strongest detection (F1=0.69), while tree cover and built-up areas showed near-zero detection (IoU=4%) regardless of flood mechanism. Dual-reference validation revealed that apparent model error partly reflects definitional inconsistency between reference products rather than detection failure. Iterative pipeline testing identified 23 failure modes, with pipeline engineering dominating initial error over model capacity. These findings establish environment-dependent detection boundaries for operational satellite flood mapping.
Original Article
View Cached Full Text

Cached at: 06/09/26, 08:52 AM

# Land cover and flood type govern the detection limits of satellite-based flood mapping across diverse global flood events
Source: [https://arxiv.org/abs/2606.07780](https://arxiv.org/abs/2606.07780)
[View PDF](https://arxiv.org/pdf/2606.07780)

> Abstract:Floods are among the most destructive natural hazards, and their increasing frequency under climate change makes satellite\-based inundation mapping essential for disaster response\. Geospatial foundation models pretrained on satellite archives offer geographic transferability, but their operational reliability across diverse, unseen events remains uncharacterized\. Here we deploy Prithvi\-EO\-2\.0 across 19 out\-of\-distribution flood events \(2017\-2025\) spanning six continents, eight climate zones, and six flood mechanisms, validating against two independent reference products\. Detection accuracy depended jointly on land cover and flood type, with cropland yielding the highest agreement \(IoU=52%\) and riverine events the strongest detection \(F1=0\.69\), while tree cover and built\-up areas showed near\-zero detection \(IoU=4%\) regardless of flood mechanism\. Dual\-reference validation revealed that apparent model error partly reflects definitional inconsistency between reference products rather than detection failure\. Iterative pipeline testing identified 23 failure modes, with pipeline engineering dominating initial error over model capacity\. These findings establish environment\-dependent detection boundaries for operational satellite flood mapping\.

## Submission history

From: Venkatesh Kolluru Dr \[[view email](https://arxiv.org/show-email/63fe4c07/2606.07780)\] **\[v1\]**Fri, 5 Jun 2026 18:46:03 UTC \(7,964 KB\)

Similar Articles

Do Foundation Model Embeddings Improve Cross-Country Crop Yield Generalisation? A Leave-One-Country-Out Evaluation in Sub-Saharan Africa

arXiv cs.LG

This paper evaluates whether geospatial foundation model embeddings like Prithvi-EO improve cross-country crop yield prediction in Sub-Saharan Africa compared to traditional Sentinel-2 features. The study finds that frozen embeddings do not significantly outperform spectral medians under rigorous Leave-One-Country-Out validation, suggesting country-level distribution shift is the primary bottleneck rather than feature representation quality.

Physics-Informed Machine Learning for Short-Term Flood Prediction

arXiv cs.LG

Researchers propose a Physics-Informed Machine Learning (PIML) framework that integrates hydrological constraints into an LSTM loss function to improve short-term flood forecasting, particularly in data-scarce regimes. A 'Trend Alignment' constraint enforcing consistency between precipitation and discharge trends improves Nash-Sutcliffe Efficiency and eliminates unphysical predictions during extreme events.