GEOID-Flood: A Large-Scale Multi-Modal Benchmark Dataset for Flood Segmentation

Hugging Face Daily Papers Papers
geospatial flood-segmentation benchmark multi-modal sar dataset

Summary

Introduces GEOID-Flood, a large-scale multi-modal benchmark dataset for flood segmentation with over 14,000 tiles from 219 events across 65 countries, evaluating foundation models against conventional encoders across single-image, multi-temporal, and multi-modal protocols.

Geospatial foundation models aim to learn representations that transfer across regions and sensors, yet evaluating them on specific tasks requires large, high-quality, multi-modal benchmarks that measure how well such models extract value from data. Concerning flood mapping, existing datasets rarely combine bi-temporal SAR and co-registered optical imagery at scale, leaving the value of foundation models for this downstream task largely untested. We introduce GEOID-Flood, a large-scale multi-modal flood segmentation benchmark, derived from Copernicus Emergency Management Service activations, spanning 219 events across 65 countries over ten years. The dataset provides more than 14,000 tiles with co-registered pre- and post-event Sentinel-1, in GRD and RTC format, pre-event Sentinel-2 composite, and DEM, including manually validated labels that separate background from permanent water and flooded water. Using this benchmark, we evaluate foundation models against conventional encoders across single-image, multi-temporal, and multi-modal protocols. We report three main findings: foundation models offer a consistent but modest advantage; optical-SAR fusion with finetuning best resolves transient flooding; and models trained on GEOID-Flood transfer to unseen events better than those trained on existing datasets. Dataset and code available at https://github.com/links-ads/geoid-flood.
Original Article
View Cached Full Text

Cached at: 08/04/26, 01:39 PM

Paper page - GEOID-Flood: A Large-Scale Multi-Modal Benchmark Dataset for Flood Segmentation

Source: https://huggingface.co/papers/2608.02315

Abstract

Geospatialfoundationmodelsaimtolearnrepresentationsthattransferacrossregionsandsensors,yetevaluatingthemonspecifictasksrequireslarge,high-quality,multi-modalbenchmarksthatmeasurehowwellsuchmodelsextractvaluefromdata.Concerningfloodmapping,existingdatasetsrarelycombinebi-temporalSARandco-registeredopticalimageryatscale,leavingthevalueoffoundationmodelsforthisdownstreamtasklargelyuntested.WeintroduceGEOID-Flood,alarge-scalemulti-modalfloodsegmentationbenchmark,derivedfromCopernicusEmergencyManagementServiceactivations,spanning219eventsacross65countriesovertenyears.Thedatasetprovidesmorethan14,000tileswithco-registeredpre-andpost-eventSentinel-1,inGRDandRTCformat,pre-eventSentinel-2composite,andDEM,includingmanuallyvalidatedlabelsthatseparatebackgroundfrompermanentwaterandfloodedwater.Usingthisbenchmark,weevaluatefoundationmodelsagainstconventionalencodersacrosssingle-image,multi-temporal,andmulti-modalprotocols.Wereportthreemainfindings:foundationmodelsofferaconsistentbutmodestadvantage;optical-SARfusionwithfinetuningbestresolvestransientflooding;andmodelstrainedonGEOID-Floodtransfertounseeneventsbetterthanthosetrainedonexistingdatasets.Datasetandcodeavailableathttps://github.com/links-ads/geoid-flood.

View arXiv pageView PDFProject pageGitHub1Add to collection

Get this paper in your agent:

hf papers read 2608\.02315

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2608.02315 in a model README.md to link it from this page.

Datasets citing this paper1

#### links-ads/geoid-flood Updatedabout 1 hour ago • 54 • 2

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.02315 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles