# Flood Mapping from RGB imagery using a Vision Foundation Model

arXiv: https://arxiv.org/abs/2606.24120 · HTML: https://mlsanity.com/paper/2606.24120/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 42 references that are in the map.
- First posted on arXiv 23 Jun 2026.

## Builds on (most cited first, 17 of 17)

- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery](https://mlsanity.com/paper/2207.08051/) (2022)
- [FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understanding](https://mlsanity.com/paper/2012.02951/) (2020)
- [Foundation Models for Generalist Geospatial Artificial Intelligence](https://mlsanity.com/paper/2310.18660/) (2023)
- [Prithvi-EO-2.0: A Versatile Multi-Temporal Foundation Model for Earth Observation Applications](https://mlsanity.com/paper/2412.02732/) (2024)
- [GEO-Bench: Toward Foundation Models for Earth Monitoring](https://mlsanity.com/paper/2306.03831/) (2023)
- [Segment Anything Model for Road Network Graph Extraction](https://mlsanity.com/paper/2403.16051/) (2024)
- [Assessment of a new GeoAI foundation model for flood inundation mapping](https://mlsanity.com/paper/2309.14500/) (2023)
- [When Geoscience Meets Foundation Models: Towards General Geoscience Artificial Intelligence System](https://mlsanity.com/paper/2309.06799/) (2023)
- [Fully Convolutional Network for Automatic Road Extraction from Satellite Imagery](https://mlsanity.com/paper/1806.05182/) (2018)
- [UrbanSARFloods: Sentinel-1 SLC-Based Benchmark Dataset for Urban and Open-Area Flood Mapping](https://mlsanity.com/paper/2406.04111/) (2024)
- [Evaluating and Benchmarking Foundation Models for Earth Observation and Geospatial AI](https://mlsanity.com/paper/2406.18295/) (2024)
- [AI-based Drone Assisted Human Rescue in Disaster Environments: Challenges and Opportunities](https://mlsanity.com/paper/2406.15875/) (2024)
- [BlessemFlood21: Advancing Flood Analysis with a High-Resolution Georeferenced Dataset for Humanitarian Aid Support](https://mlsanity.com/paper/2407.05007/) (2024)
- [Rapid Adaptation of Earth Observation Foundation Models for Segmentation](https://mlsanity.com/paper/2409.09907/) (2024)

## Built on by (most cited first, 2 of 2)

- [Earth Observation Foundation Models for Terrestrial Ecohydrology: From Representation Learning to Process Inference](https://mlsanity.com/paper/2608.15282/) (2026)
- [Cross-Architecture Foundation-Model Distillation for Edge Flood Segmentation](https://mlsanity.com/paper/2609.20441/) (2026)

## Abstract (arXiv)

Timely, high-resolution maps of flood extent around settlements are essential for emergency response and damage assessment. We consider airborne RGB imagery for flood mapping as it can be collected rapidly at low cost. To produce flood maps, deep learning models for water segmentation are often used. CNN based and small vision transformer models are used. However, they need much data for adaptation to a change of scenery, i.e., another flooding event. Vision foundation models or large vision transformers are known to generalize across domains. Recently, foundation models for Earth observation became available. They are pretrained on satellite data, whose spatial resolution, viewing geometry, and radiometry differ from nadir RGB imagery. Thus, adaptation is required. We investigate how a satellite-pretrained Earth observation foundation model can be adapted to centimeter-scale floodwater mapping from RGB imagery. Specifically, we fine-tune a model we call Prithvi-2.0-UPN consisting of the Prithvi-EO-2.0-600M Vision Transformer combined with a UPerNet decoder for binary water segmentation on two RGB datasets (BlessemFlood21, NeuenahrFlood). In a first experiment we observe that Prithvi-2.0-UPN reaches state-of-the-art results on BlessemFlood21 and NeuenahrFlood, when trained on their datasets. In a second experiment we show that Prithvi-2.0-UPN performs better than state-of-the-art baseline models for transfer to a new flood event (trained on BlessemFlood21, tested on NeuenahrFlood) in a zero-shot setting. However, the performance indicates room for improvement. In this respect, we investigate in a third experiment how performance improves when further fine-tuning the models with small shares of NeuenahrFlood training data: Prithvi-2.0-UPN improves the fastest and reaches almost the performance level when fully trained on NeuenahrFlood, indicating transfer capabilities.