BMCF-Net: A Bi-Temporal Multimodal Cross-Fusion Network for Precise Segmentation of Coastal Aquaculture Areas

Liang, Zunxun; Guo, Jianke; Gao, Qian; Jiang, Yufeng; Zhao, Jianhua; Qin, Yafeng; Wang, Fangxiong; Zhang, Shuai

doi:10.3390/rs18111795

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

BMCF-Net: A Bi-Temporal Multimodal Cross-Fusion Network for Precise Segmentation of Coastal Aquaculture Areas

by

Zunxun Liang

^1,2,†

,

Jianke Guo

^1,2,†

,

Qian Gao

³,

Yufeng Jiang

^1,2,

Jianhua Zhao

⁴,

Yafeng Qin

^1,2

,

Fangxiong Wang

¹

and

Shuai Zhang

^5,*

¹

School of Geography, Liaoning Normal University, Dalian 116029, China

²

Institute of Marine Sustainable Development, Liaoning Normal University, Dalian 116029, China

³

School of Education, Liaoning Normal University, Dalian 116029, China

⁴

National Marine Environmental Monitoring Center, Dalian 116029, China

⁵

School of Geodesy and Geomatics, Wuhan University, Wuhan 430079, China

^*

Author to whom correspondence should be addressed.

^†

These authors contributed equally to this work.

Remote Sens. 2026, 18(11), 1795; https://doi.org/10.3390/rs18111795

Submission received: 14 April 2026 / Revised: 27 May 2026 / Accepted: 28 May 2026 / Published: 1 June 2026

(This article belongs to the Special Issue Vision–Language Multimodal Learning for Remote Sensing and Geospatial Artificial Intelligence)

Download Versions Notes

Abstract

Accurate mapping of offshore aquaculture remains challenging in complex coastal environments due to heterogeneous backgrounds, variable sea states, blurred pond boundaries, adhesion among densely distributed cages, and the weak texture of floating rafts. To address these limitations, this study proposes a bi-temporal multimodal cross-fusion network (BMCF-Net) for fine-scale offshore aquaculture segmentation from Sentinel-1/2 imagery. The framework jointly exploits bi-temporal observations acquired during non-ice and sea-ice periods and integrates them through a bi-temporal fusion module to enhance target–background separability and suppress environmental noise. In addition, a feature correction module and a multi-head feature fusion module are introduced to strengthen cross-modal alignment between SAR structural information and optical spectral–textural cues, thereby improving the separation of dense aquaculture units and the detection of weak-texture targets. Experiments conducted on a multimodal dataset from the Liaoning coastal zone show that BMCF-Net achieves F1-scores of 93.15%, 93.90%, and 89.04% for aquaculture ponds, cages, and floating rafts, respectively, outperforming state-of-the-art segmentation models such as FTransUNet. The proposed model was further applied to produce a high-resolution aquaculture distribution map for Liaoning Province in 2023 and to analyze area dynamics over the past six years. The results demonstrate the potential of BMCF-Net for large-scale offshore aquaculture monitoring and coastal resource management.

Keywords: multimodal remote sensing imagery; coastal aquaculture areas; attention mechanism; semantic segmentation; Sentinel-1; Sentinel-2

Share and Cite

MDPI and ACS Style

Liang, Z.; Guo, J.; Gao, Q.; Jiang, Y.; Zhao, J.; Qin, Y.; Wang, F.; Zhang, S. BMCF-Net: A Bi-Temporal Multimodal Cross-Fusion Network for Precise Segmentation of Coastal Aquaculture Areas. Remote Sens. 2026, 18, 1795. https://doi.org/10.3390/rs18111795

AMA Style

Liang Z, Guo J, Gao Q, Jiang Y, Zhao J, Qin Y, Wang F, Zhang S. BMCF-Net: A Bi-Temporal Multimodal Cross-Fusion Network for Precise Segmentation of Coastal Aquaculture Areas. Remote Sensing. 2026; 18(11):1795. https://doi.org/10.3390/rs18111795

Chicago/Turabian Style

Liang, Zunxun, Jianke Guo, Qian Gao, Yufeng Jiang, Jianhua Zhao, Yafeng Qin, Fangxiong Wang, and Shuai Zhang. 2026. "BMCF-Net: A Bi-Temporal Multimodal Cross-Fusion Network for Precise Segmentation of Coastal Aquaculture Areas" Remote Sensing 18, no. 11: 1795. https://doi.org/10.3390/rs18111795

APA Style

Liang, Z., Guo, J., Gao, Q., Jiang, Y., Zhao, J., Qin, Y., Wang, F., & Zhang, S. (2026). BMCF-Net: A Bi-Temporal Multimodal Cross-Fusion Network for Precise Segmentation of Coastal Aquaculture Areas. Remote Sensing, 18(11), 1795. https://doi.org/10.3390/rs18111795

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

BMCF-Net: A Bi-Temporal Multimodal Cross-Fusion Network for Precise Segmentation of Coastal Aquaculture Areas

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI