Next Article in Journal
Midday Depression and Legacy Effect Disrupt SIF-GPP Coupling in Northern Peatlands During Combined Heat and Drought Stress
Previous Article in Journal
Multiple Vegetation Indicators Reveal Contrasting Post-Drought Recovery Time in the Yangtze River Basin Following the 2022 Extreme Drought
Previous Article in Special Issue
Semantic Segmentation of Remote Sensing Images Based on RS3mamba and Wavelet Transform
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Remote Sensing
Volume 18
Issue 16
10.3390/rs18162825
remotesensing-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Enhancing the Reliability, Performance, and Practical Value of Deep Learning Landslide Mapping via Pixel-Level Uncertainty Analysis

by
Shan Dong
1,2,
Hui Li
3,
Cheng Zhong
1,2,4 and
Junjie Pan
3,*
1
Badong National Observation and Research Station of Geohazards, China University of Geosciences, Wuhan 430074, China
2
Three Gorges Research Center for Geo-Hazard, Ministry of Education, China University of Geosciences, Wuhan 430074, China
3
School of Earth and Planetary Sciences, China University of Geosciences, Wuhan 430074, China
4
Jiangxi Provincial Technology Innovation Center for Territorial Spatial Information Acquisition and Processing, Nanchang 330002, China
*
Author to whom correspondence should be addressed.
Remote Sens. 2026, 18(16), 2825; https://doi.org/10.3390/rs18162825
Submission received: 21 July 2026 / Revised: 13 August 2026 / Accepted: 18 August 2026 / Published: 20 August 2026
(This article belongs to the Special Issue Geohazard Mapping, Monitoring and Prediction with Advanced Remote Sensing Techniques)
Browse Figures
Versions Notes

Abstract

Pixel-level uncertainty assessment is commonly overlooked in current deep learning-based landslide detection, which greatly limits the reliability, performance, and practical value of the results. To fill this gap, this study employs Monte Carlo Dropout to systematically quantify pixel-level uncertainty. Subsequently, it interprets how external factors, such as terrain, vegetation, clouds, and shadows, interfere with model predictions. Taking SegFormer as an example, this study further investigates how weight allocation across different scales influences the uncertainty. Finally, we introduce an uncertainty ranking-based FP rejection strategy coupled with an FN priority capture strategy to improve the efficiency of mapping results inspection, thus improving landslide identification performance. The results indicate that by removing only the top 10% of pixels with the highest uncertainty, the mIoU increases by at least 7%. This study greatly enhanced the reliability, performance, and practical value of remote sensing-based landslide mapping from a new perspective.
Keywords: landslide; remote sensing; uncertainty; deep learning; machine learning landslide; remote sensing; uncertainty; deep learning; machine learning

Share and Cite

MDPI and ACS Style

Dong, S.; Li, H.; Zhong, C.; Pan, J. Enhancing the Reliability, Performance, and Practical Value of Deep Learning Landslide Mapping via Pixel-Level Uncertainty Analysis. Remote Sens. 2026, 18, 2825. https://doi.org/10.3390/rs18162825

AMA Style

Dong S, Li H, Zhong C, Pan J. Enhancing the Reliability, Performance, and Practical Value of Deep Learning Landslide Mapping via Pixel-Level Uncertainty Analysis. Remote Sensing. 2026; 18(16):2825. https://doi.org/10.3390/rs18162825

Chicago/Turabian Style

Dong, Shan, Hui Li, Cheng Zhong, and Junjie Pan. 2026. "Enhancing the Reliability, Performance, and Practical Value of Deep Learning Landslide Mapping via Pixel-Level Uncertainty Analysis" Remote Sensing 18, no. 16: 2825. https://doi.org/10.3390/rs18162825

APA Style

Dong, S., Li, H., Zhong, C., & Pan, J. (2026). Enhancing the Reliability, Performance, and Practical Value of Deep Learning Landslide Mapping via Pixel-Level Uncertainty Analysis. Remote Sensing, 18(16), 2825. https://doi.org/10.3390/rs18162825

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

Article Metrics

Back to TopTop