# Beyond Backscatter: AlphaEarth Land-Cover Priors for Rapid SAR Flood Segmentation Across Foundation Backbones

arXiv: https://arxiv.org/abs/2606.29134 · HTML: https://mlsanity.com/paper/2606.29134/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 28 Jun 2026.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery](https://mlsanity.com/paper/2207.08051/) (2022)
- [Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning](https://mlsanity.com/paper/2212.14532/) (2022)
- [Foundation Models for Generalist Geospatial Artificial Intelligence](https://mlsanity.com/paper/2310.18660/) (2023)
- [AlphaEarth Foundations: An embedding field model for accurate and efficient global mapping from sparse label data](https://mlsanity.com/paper/2507.22291/) (2025)
- [TerraMind: Large-Scale Generative Multimodality for Earth Observation](https://mlsanity.com/paper/2504.11171/) (2025)
- [TerraTorch: The Geospatial Foundation Models Toolkit](https://mlsanity.com/paper/2503.20563/) (2025)
- [Large-scale Building Damage Assessment using a Novel Hierarchical Transformer Architecture on Satellite Images](https://mlsanity.com/paper/2208.02205/) (2022)
- [Kuro Siwo: 33 billion m2 under the water. A global multi-temporal satellite dataset for rapid flood mapping](https://mlsanity.com/paper/2311.12056/) (2023)
- [Assessment of a new GeoAI foundation model for flood inundation mapping](https://mlsanity.com/paper/2309.14500/) (2023)
- [UrbanSARFloods: Sentinel-1 SLC-Based Benchmark Dataset for Urban and Open-Area Flood Mapping](https://mlsanity.com/paper/2406.04111/) (2024)
- [Flood Segmentation on Sentinel-1 SAR Imagery with Semi-Supervised Learning](https://mlsanity.com/paper/2107.08369/) (2021)
- [Mapping Global Floods with 10 Years of Satellite Radar Data](https://mlsanity.com/paper/2411.01411/) (2024)
- [DamageCAT: A Deep Learning Transformer Framework for Typology-Based Post-Disaster Building Damage Categorization](https://mlsanity.com/paper/2504.11637/) (2025)
- [Attentive Dual Stream Siamese U-net for Flood Detection on Multi-temporal Sentinel-1 Data](https://mlsanity.com/paper/2204.09387/) (2022)
- [ELEV-VISION: Automated Lowest Floor Elevation Estimation from Segmenting Street View Images](https://mlsanity.com/paper/2306.03050/) (2023)
- [FloodGenome: Interpretable Machine Learning for Decoding Features Shaping Property Flood Risk Predisposition in Cities](https://mlsanity.com/paper/2403.10625/) (2024)
- [FloodDamageCast: Building Flood Damage Nowcasting with Machine Learning and Data Augmentation](https://mlsanity.com/paper/2405.14232/) (2024)
- [DAM-Net: Global Flood Detection from SAR Imagery Using Differential Attention Metric-Based Vision Transformers](https://mlsanity.com/paper/2306.00704/) (2023)
- [Flood-DamageSense: Multimodal Mamba with Multitask Learning for Building Flood Damage Assessment using SAR Remote Sensing Imagery](https://mlsanity.com/paper/2506.06667/) (2025)
- [A Parametric Framework for Anticipatory Flashflood Warning: Integrating Landscape Vulnerability with Precipitation Forecasts](https://mlsanity.com/paper/2512.17785/) (2025)
- [Sensor-Adaptive Flood Mapping with Pre-trained Multi-Modal Transformers across SAR and Multispectral Modalities](https://mlsanity.com/paper/2509.23035/) (2025)

## Built on by (most cited first, 1 of 1)

- [Extending Dynamic World Surface Water Mapping to Sentinel-1 with AlphaEarth Embeddings](https://mlsanity.com/paper/2610.06704/) (2026)

## Abstract (arXiv)

Rapid flood mapping is critical for emergency response, yet optical imagery is often unusable during major flooding and single-temporal SAR is ambiguous, since new inundation, permanent water, and other smooth surfaces produce similar backscatter. This study evaluates whether stable land-context priors can improve post-event SAR flood segmentation when a registered, seasonally matched pre-event acquisition is unavailable. Using the CONUS (Continental United States) subset of ImpactMesh-Flood, we compare four backbones spanning distinct pretraining regimes-a from-scratch CNN UNet, an ImageNet-pretrained UNet, the SAR-pretrained TerraMind Vision Transformer, and the optical-satellite-pretrained DINOv3 Vision Transformer-in SAR-only, SAR+DEM, and SAR+AlphaEarth configurations under an identical fusion design, training protocol, and event-stratified split. Models are selected on a validation flood event and evaluated separately on two held-out events, Hurricane Florence and the Louisiana floods, with three-seed reporting for auxiliary configurations. Both auxiliary priors improve over the observed SAR-only baselines across all backbones and test events. AlphaEarth exceeds DEM on the harder Florence event for every backbone and achieves the best Florence IoU, while DEM is competitive on Louisiana and produces the best result there. The seed analysis reveals a trade-off: DEM is more stable across initializations, whereas AlphaEarth offers higher peak performance and higher recall on the harder event. Cross-event differences track flood-class prevalence and similarity to the training distribution, underscoring the need for per-event evaluation. We reframe single-temporal SAR flood segmentation as an alignment between radar observations and stable land-surface priors, where learned and physical context offer complementary pathways to more reliable rapid flood mapping.