Volume 28, Issue 7 pp. 2379-2396
RESEARCH ARTICLE

A Two-Step Approach to Extracting Sandy Beaches Through Integrating Spatial Semantic Information From Open-Source Geospatial Datasets

Zhe Wang

Zhe Wang

State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China

Search for more papers by this author
Zhixiang Fang

Corresponding Author

Zhixiang Fang

State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China

Correspondence:

Zhixiang Fang ([email protected])

Search for more papers by this author
Jiayi Chang

Jiayi Chang

College of Urban and Environmental Sciences, Central China Normal University, Wuhan, China

Search for more papers by this author
Zhongyuan Wang

Zhongyuan Wang

School of Geomatics Science and Technology, Nanjing Tech University, Nanjing, China

Search for more papers by this author
Weiming Shen

Weiming Shen

State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China

Search for more papers by this author
First published: 05 September 2024

Funding: The work was supported by the National key Research and Development Plan (Grant 2022YFC3105101).

ABSTRACT

Sandy beaches, widespread in coastal areas, provide valuable economic and ecological benefits. However, a substantial proportion of sandy beaches are undergoing erosion caused by marine disasters and human interventions. Advanced sandy beach extraction (SBE) approaches are indispensable to sandy beach observation and protection. This study proposes a novel two-step SBE approach using remote sensing images and digital elevation models. First, sea–land segmentation is performed as a preparatory work. We model sea–land segmentation as an optimization problem and develop an improved NSGA-II, SCS-NSGA-II, to solve it, considering both topographical and spectral costs. Second, a region growing algorithm is applied to generate the final sandy beach extents. The assessment results verify that (1) our approach effectively reduces the false-positive rate, thereby resulting in more accurate SBE results compared with existing approaches. (2) SCS-NSGA-II ensures the diversity of individuals in spatial patterns and exhibits superior performance compared with NSGA-II in this task.

Conflicts of Interest

The authors declare no conflicts of interest.

Data Availability Statement

The data that support the findings of this study are available on request from the corresponding author. The data are not publicly available due to privacy or ethical restrictions.

The full text of this article hosted at iucr.org is unavailable due to technical difficulties.