Advances and Challenges in Deep Learning-driven Remote 
Sensing Retrieval for Coral Reefs

Yupeng Zhu; Jun Tang*; Ru Jing; Shuteng Lin

doi:10.70711/aitr.v3i8.8916

Advances and Challenges in Deep Learning-driven Remote Sensing Retrieval for Coral Reefs

Yupeng Zhu, Jun Tang*, Ru Jing, Shuteng Lin

Abstract

Coral reefs are the core of the marine ecosystem, playing a crucial role in maintaining biodiversity and regulating the marine environment. Their health status directly affects global ecological security. Remote sensing imagery, with their advantages of wide coverage, noncontact and periodicity, have become the core means for obtaining information about coral reefs. The retrieval technology serves as the key
to bridging remote sensing data with the actual parameters of coral reefs. Deep learning has broken through the limitations of conventional
inversion methods and significantly improved retrieval accuracy and efficiency with its powerful feature extraction and nonlinear fitting capabilities, thus becoming a research hotspot. This paper expounds this technology comprehensively, outlines its core principles and research status, analyzes the application characteristics of mainstream models, discusses the existing bottlenecks and explores future development trends,
aiming to provide reference for subsequent research.

Keywords

Deep Learning; Remote Sensing Imagery; Coral Reef; Retrieval Technology; Feature Extraction

Full Text:

PDF

Included Database

References

[1] Xiaotao Xi. (2024) Deep Learning Models of Water Depth Retrieval for Multispectral and Hyperspectral Satellites and Their Application [D]. Shanghai Ocean University.

[2] Zhengxian Duan, Xiuling Zuo, Kefu Yu, Fenzhen Su, Shenglin Zang, Binni Qin, Huisheng Wu. (2023) Coral Reef Water Depth Remote

Sensing Optimization Retrieval Methods Based on ICESat-2 and GF-1 under Geomorphic Zoning [J]. Scientia Geographica Sinica, 43

(09), 1640-1648.

[3] Feifei Zhang. (2023) Deep Learning Classification Method for Coral Reef Landform Types Based on Multi-scale Remote Sensing [D].

Inner Mongolia Normal University.

[4] Jikun Wang et al. (2018) Multi-spectral Remote Sensing Water Depth Retrieval in Coral Reef Areas [J]. Remote Sensing Technology and

Application, 33(1), 7.

[5] Wanzhi Wang, Xinqing Zou, Haiyu Li. (2022) Multi-spectral Remote Sensing Water Depth Retrieval in Optical Shallow Water Areas of

Coral Reefs in the South China Sea [J]. Geological Journal of China Universities, 28(5), 758-767.

[6] Kai Zeng. (2022) In-situ Spectral Recognition and Retrieval of Bottom Sediment Information of the Coral Reef Waters in the South

China Sea [D]. University of Chinese Academy of Sciences.

DOI: http://dx.doi.org/10.70711/aitr.v3i8.8916

Refbacks

There are currently no refbacks.