Semi-Automated Semantic Segmentation of Arctic Shorelines Using Very High-Resolution Airborne Imagery, Spectral Indices and Weakly Supervised Machine Learning Approaches

Aryal, Bibek; Escarzaga, Stephen M.; Vargas Zesati, Sergio A.; Velez-Reyes, Miguel; Fuentes, Olac; Tweedie, Craig

doi:10.3390/rs13224572

Open AccessTechnical Note

Semi-Automated Semantic Segmentation of Arctic Shorelines Using Very High-Resolution Airborne Imagery, Spectral Indices and Weakly Supervised Machine Learning Approaches

by

Bibek Aryal

^1,*,†

,

Stephen M. Escarzaga

^2,†,

Sergio A. Vargas Zesati

^2,†

,

Miguel Velez-Reyes

³

,

Olac Fuentes

⁴ and

Craig Tweedie

²

¹

Computational Science Program, The University of Texas at El Paso, 500 W University Ave., El Paso, TX 79968, USA

²

Environmental Science and Engineering Program, The University of Texas at El Paso, 500 W University Ave., El Paso, TX 79968, USA

³

College of Engineering, Electrical & Computer Engineering, The University of Texas at El Paso, 500 W University Ave., El Paso, TX 79968, USA

⁴

Department of Computer Science, The University of Texas at El Paso, 500 W University Ave., El Paso, TX 79968, USA

^*

Author to whom correspondence should be addressed.

^†

These authors contributed equally to this work.

Remote Sens. 2021, 13(22), 4572; https://doi.org/10.3390/rs13224572

Submission received: 29 September 2021 / Revised: 9 November 2021 / Accepted: 9 November 2021 / Published: 14 November 2021

(This article belongs to the Special Issue Computer Vision and Deep Learning for Remote Sensing Applications)

Download

Browse Figures

Versions Notes

Abstract

Precise coastal shoreline mapping is essential for monitoring changes in erosion rates, surface hydrology, and ecosystem structure and function. Monitoring water bodies in the Arctic National Wildlife Refuge (ANWR) is of high importance, especially considering the potential for oil and natural gas exploration in the region. In this work, we propose a modified variant of the Deep Neural Network based U-Net Architecture for the automated mapping of 4 Band Orthorectified NOAA Airborne Imagery using sparsely labeled training data and compare it to the performance of traditional Machine Learning (ML) based approaches—namely, random forest, xgboost—and spectral water indices—Normalized Difference Water Index (NDWI), and Normalized Difference Surface Water Index (NDSWI)—to support shoreline mapping of Arctic coastlines. We conclude that it is possible to modify the U-Net model to accept sparse labels as input and the results are comparable to other ML methods (an Intersection-over-Union (IoU) of 94.86% using U-Net vs. an IoU of 95.05% using the best performing method).

Keywords: land water segmentation; remote sensing; deep learning; sparse labels

Share and Cite

MDPI and ACS Style

Aryal, B.; Escarzaga, S.M.; Vargas Zesati, S.A.; Velez-Reyes, M.; Fuentes, O.; Tweedie, C. Semi-Automated Semantic Segmentation of Arctic Shorelines Using Very High-Resolution Airborne Imagery, Spectral Indices and Weakly Supervised Machine Learning Approaches. Remote Sens. 2021, 13, 4572. https://doi.org/10.3390/rs13224572

AMA Style

Aryal B, Escarzaga SM, Vargas Zesati SA, Velez-Reyes M, Fuentes O, Tweedie C. Semi-Automated Semantic Segmentation of Arctic Shorelines Using Very High-Resolution Airborne Imagery, Spectral Indices and Weakly Supervised Machine Learning Approaches. Remote Sensing. 2021; 13(22):4572. https://doi.org/10.3390/rs13224572

Chicago/Turabian Style

Aryal, Bibek, Stephen M. Escarzaga, Sergio A. Vargas Zesati, Miguel Velez-Reyes, Olac Fuentes, and Craig Tweedie. 2021. "Semi-Automated Semantic Segmentation of Arctic Shorelines Using Very High-Resolution Airborne Imagery, Spectral Indices and Weakly Supervised Machine Learning Approaches" Remote Sensing 13, no. 22: 4572. https://doi.org/10.3390/rs13224572

APA Style

Aryal, B., Escarzaga, S. M., Vargas Zesati, S. A., Velez-Reyes, M., Fuentes, O., & Tweedie, C. (2021). Semi-Automated Semantic Segmentation of Arctic Shorelines Using Very High-Resolution Airborne Imagery, Spectral Indices and Weakly Supervised Machine Learning Approaches. Remote Sensing, 13(22), 4572. https://doi.org/10.3390/rs13224572

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

Article Menu

Semi-Automated Semantic Segmentation of Arctic Shorelines Using Very High-Resolution Airborne Imagery, Spectral Indices and Weakly Supervised Machine Learning Approaches

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI