TRB-Net: Terrain-Residual and Boundary-Assisted Multimodal Martian Landslide Segmentation on a Local MMLSv2 Split

Li, Yu; He, Jinxin; Wang, Yongzhi; Zhan, Ye; Yang, Yongbin; Zhang, Hanya

doi:10.3390/rs18152638

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

Open AccessArticle

TRB-Net: Terrain-Residual and Boundary-Assisted Multimodal Martian Landslide Segmentation on a Local MMLSv2 Split

by

Yu Li

¹,

Jinxin He

^1,*,

Yongzhi Wang

²

,

Ye Zhan

³,

Yongbin Yang

¹ and

Hanya Zhang

¹

College of Earth Sciences, Jilin University, Changchun 130061, China

²

College of Geoexploration Science and Technology, Jilin University, Changchun 130012, China

³

Aviation Operations Service College, Aviation University Air Force, Changchun 130021, China

^*

Author to whom correspondence should be addressed.

Remote Sens. 2026, 18(15), 2638; https://doi.org/10.3390/rs18152638

Submission received: 29 May 2026 / Revised: 15 July 2026 / Accepted: 16 July 2026 / Published: 6 August 2026

(This article belongs to the Section Remote Sensing Image Processing)

Download Versions Notes

Abstract

Martian landslide segmentation is challenging because annotated samples are limited and landslide deposits can have weak boundaries, heterogeneous textures, and visual similarity to crater rims and canyon walls. This study evaluates a terrain-residual and boundary-assisted network (TRB-Net) on the locally available MMLSv2 train/validation/test split. TRB-Net combines RGB texture with digital elevation model (DEM), slope, thermal inertia, and grayscale information through terrain-residual fusion, an atrous spatial pyramid pooling decoder, and auxiliary boundary supervision. The compact evaluation checkpoint, using a validation-selected threshold of 0.55, achieves an mIoU of 0.8060, foreground IoU of 0.7502, F1-score of 0.8573, precision of 0.8473, and recall of 0.8676 with 5.255 million parameters. In same-split comparisons, DeepLabV3+ obtains the highest overlap scores, while TRB-Net provides competitive segmentation and an explicit architecture for tracing how terrain and boundary cues enter the prediction. These results apply only to the local MMLSv2 split; geographically isolated and large-area Martian mapping performance were not evaluated.

Keywords: Martian landslide; semantic segmentation; multimodal remote sensing; terrain-guided fusion; boundary supervision; MMLSv2

Share and Cite

MDPI and ACS Style

Li, Y.; He, J.; Wang, Y.; Zhan, Y.; Yang, Y.; Zhang, H. TRB-Net: Terrain-Residual and Boundary-Assisted Multimodal Martian Landslide Segmentation on a Local MMLSv2 Split. Remote Sens. 2026, 18, 2638. https://doi.org/10.3390/rs18152638

AMA Style

Li Y, He J, Wang Y, Zhan Y, Yang Y, Zhang H. TRB-Net: Terrain-Residual and Boundary-Assisted Multimodal Martian Landslide Segmentation on a Local MMLSv2 Split. Remote Sensing. 2026; 18(15):2638. https://doi.org/10.3390/rs18152638

Chicago/Turabian Style

Li, Yu, Jinxin He, Yongzhi Wang, Ye Zhan, Yongbin Yang, and Hanya Zhang. 2026. "TRB-Net: Terrain-Residual and Boundary-Assisted Multimodal Martian Landslide Segmentation on a Local MMLSv2 Split" Remote Sensing 18, no. 15: 2638. https://doi.org/10.3390/rs18152638

APA Style

Li, Y., He, J., Wang, Y., Zhan, Y., Yang, Y., & Zhang, H. (2026). TRB-Net: Terrain-Residual and Boundary-Assisted Multimodal Martian Landslide Segmentation on a Local MMLSv2 Split. Remote Sensing, 18(15), 2638. https://doi.org/10.3390/rs18152638

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

Article Menu

TRB-Net: Terrain-Residual and Boundary-Assisted Multimodal Martian Landslide Segmentation on a Local MMLSv2 Split

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI