# Prithvi-Complimentary Adaptive Fusion Encoder (CAFE): unlocking full-potential for flood inundation mapping

Source: [Prithvi-Complimentary Adaptive Fusion Encoder (CAFE): unlocking full-potential for flood inundation mapping](<https://www.sota2.com/research/paper/695c970753fdd5c3617437c3>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-09T06:00:01.920Z

Authors: Saurabh Kaushik, Lalit Maurya, Beth Tellman

Published: 2026-01-05T18:07:21.000Z

## Abstract

Geo-Foundation Models (GFMs), have proven effective in diverse downstream applications, including semantic segmentation, classification, and regression tasks. However, in case of flood mapping using Sen1Flood11 dataset as a downstream task, GFMs struggles to outperform the baseline U-Net, highlighting model's limitation in capturing critical local nuances. To address this, we present the Prithvi-Complementary Adaptive Fusion Encoder (CAFE), which integrate Prithvi GFM pretrained encoder with a parallel CNN residual branch enhanced by Convolutional Attention Modules (CAM). Prithvi-CAFE enables fast and efficient fine-tuning through adapters in Prithvi and performs multi-scale, multi-level fusion with CNN features, capturing critical local details while preserving long-range dependencies. We achieve state-of-the-art results on two comprehensive flood mapping datasets: Sen1Flood11 and FloodPlanet. On Sen1Flood11 test data, Prithvi-CAFE (IoU 83.41) outperforms the original Prithvi (IoU 82.50) and other major GFMs (TerraMind 82.90, DOFA 81.54, spectralGPT: 81.02). The improvement is even more pronounced on the hold-out test site, where Prithvi-CAFE achieves an IoU of 81.37 compared to the baseline U-Net (70.57) and original Prithvi (72.42). On FloodPlanet, Prithvi-CAFE also surpasses the baseline U-Net and other GFMs, achieving an IoU of 64.70 compared to U-Net (60.14), Terramind (62.33), DOFA (59.15) and Prithvi 2.0 (61.91). Our proposed simple yet effective Prithvi-CAFE demonstrates strong potential for improving segmentation tasks where multi-channel and multi-modal data provide complementary information and local details are critical. The code is released on \\href{https://github.com/Sk-2103/Prithvi-CAFE}{Prithvi-CAFE Github}

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Flood Inundation Mapping on Sen1Flood11 Bolivia](<https://www.sota2.com/research/sota/flood-inundation-mapping-on-sen1flood11-bolivia.md>): Flood Inundation Mapping; Sen1Flood11 Bolivia; mIoU: 88.87.

- [Flood Segmentation on FloodPlanet (4-fold cross-val)](<https://www.sota2.com/research/sota/flood-segmentation-on-floodplanet-4-fold-cross-val.md>): Flood Segmentation; FloodPlanet (4-fold cross-val); IoU Water: 64.7.

- [Flood Inundation Mapping on Sen1Flood11](<https://www.sota2.com/research/sota/flood-inundation-mapping-on-sen1flood11.md>): Flood Inundation Mapping; Sen1Flood11; mIoU: 90.5.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2601.02315>)

[PDF](<https://arxiv.org/pdf/2601.02315.pdf>)

[Implementation](<https://github.com/Sk-2103/Prithvi-CAFE>)
