Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

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

Binbin Wang¹, Zijie Chen¹, Hailin Zou²

¹School of Computer Science and Engineering, Macau University of Science and Technology, Macau, China.

Scientific Reports

|June 1, 2026

Summary

Related Concept Videos

Applications of GIS: Disaster Management and Emergency Response

Applications of GIS: Disaster Management and Emergency Response

Geographic Information System (GIS) technology is essential for risk identification, action prioritization, and resource optimization in critical situations like flooding and earthquakes. By integrating spatial and demographic data, GIS provides a comprehensive framework for emergency response.GIS integrates data layers, like rainfall intensity, topography, elevation profiles, and river levels, to model high-risk flood zones. These layers assess areas susceptible to flooding based on their...

Design Example: Analyzing Capacity Contours for Flood Risk Assessment

Design Example: Analyzing Capacity Contours for Flood Risk Assessment

Flood risk assessment involves careful planning and analysis to ensure the safety of communities near water retention structures. Capacity contours are a vital tool in this process, as they illustrate the potential spread of water at specific levels in a given area. In the context of building a bund across a small valley, these contours play a critical role in evaluating the safety of nearby residential areas.In this example, the bund is intended to store stormwater in the valley. The engineers...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Isoliquiritigenin, an Extract from Licorice, Attenuates Dexamethasone-Induced Muscle Atrophy via Akt/mTOR Pathway.

Molecular nutrition & food research·2025

Same author

Puerarin combined with <i>Hericium erinaceus</i> insoluble dietary fiber alleviates obesity induced by high-fat diet through regulating the glycerophospholipid metabolism pathway influenced by gut microbiota.

Applied and environmental microbiology·2025

Same author

Associations between neutrophil-lymphocyte ratio and risk of cognitive impairment among Chinese older adults.

BMC geriatrics·2025

Same author

Epidemiological patterns and therapeutic approaches of toad toxin poisoning in a retrospective case study.

Scientific reports·2025

Same author

AI protocol for retrieving protein dynamic structures from two-dimensional infrared spectra.

Proceedings of the National Academy of Sciences of the United States of America·2025

Same author

Integrating Significant SNPs Identified by GWAS for Genomic Prediction of the Number of Ribs and Carcass Length in Suhuai Pigs.

Animals : an open access journal from MDPI·2025

This summary is machine-generated.

FM-Mamba, a new deep learning model, offers accurate real-time flood mapping using synthetic aperture radar images. It achieves high accuracy with significantly reduced parameters and computational cost, outperforming existing methods for disaster response.

Area of Science:

Remote Sensing
Artificial Intelligence
Geospatial Analysis

Background:

Accurate, real-time flood mapping is crucial for effective disaster response.
Current methods face a trade-off between model accuracy and computational efficiency.
Synthetic aperture radar (SAR) imagery is a key data source for flood detection.

Purpose of the Study:

Introduce FM-Mamba, a novel network designed to overcome the accuracy-efficiency bottleneck in SAR-based flood mapping.
Leverage state space models for improved spatial context capture and parameter efficiency.
Provide a solution for operational, real-time flood mapping.

Main Methods:

Developed an encoder using non-causal Mamba blocks for long-range spatial context with linear complexity.

Keywords:

Computer vision Flood mapping Lightweight model SAR imagery State space model Visual segmentation

Related Experiment Videos

Designed a parameter-efficient decoder for precise flood boundary segmentation.

Evaluated the FM-Mamba network on the Sen1Floods11 and S1GFloods benchmarks.

Main Results:

FM-Mamba achieved leading segmentation accuracy, comparable or superior to state-of-the-art methods in F1-score and IoU.
The model utilizes only 3.93 million parameters.
Demonstrated a significantly reduced computational footprint compared to existing approaches.

Conclusions:

FM-Mamba effectively balances high performance and computational efficiency for real-time flood mapping.
The novel architecture breaks the traditional accuracy-efficiency trade-off.
Presents a viable solution for operational disaster management and flood monitoring.