What question did this study set out to answer?

This research aims to improve flood mapping accuracy and efficiency using advanced network modeling techniques.

June 3, 2026Open Access

FM-Mamba: end-to-end non-causal Mamba-based network for efficient flood mapping

Key Points

This research aims to improve flood mapping accuracy and efficiency using advanced network modeling techniques.
Introduced FM-Mamba, an end-to-end network leveraging a non-causal Mamba framework.
Evaluated using Sen1Floods11 and S1GFloods benchmarks.
Designed with a lightweight architecture comprising an encoder and parameter-efficient decoder.
FM-Mamba achieved leading segmentation accuracy outperforming state-of-the-art methods with significant improvements in F1-score and IoU.
Utilized only 3.93 million parameters, resulting in a reduced computational footprint.
Demonstrated superior performance and efficiency balance ideal for real-time applications.

Abstract

Accurate, real-time flood mapping from synthetic aperture radar image is vital for disaster response but is hindered by a persistent trade-off between model accuracy and computational efficiency. This paper introduces FM-Mamba, a novel network that leverages a state space model to break this bottleneck. Its core innovation is an encoder built with non-causal Mamba blocks, which captures essential long-range spatial context with linear complexity, paired with a parameter-efficient decoder designed for precise boundary recovery. Evaluated on the Sen1Floods11 and S1GFloods benchmarks, FM-Mamba achieves leading segmentation accuracy, matching or exceeding state-of-the-art methods in F1-score and IoU. Crucially, it accomplishes this with only 3.93 million parameters and a drastically reduced computational footprint, demonstrating a superior balance of performance and efficiency that is ideal for operational, real-time flood mapping.

Ask AI

Mark Helpful

Bookmark

Relay

View Full Paper