Benthic Mapping of Coral Reef Areas at Varied Water Depths Using Integrated Active and Passive Remote Sensing Data and Novel Visual Transformer Models

被引:1
作者
Zhou, Yan [1 ,2 ]
Mao, Zhihua [1 ,2 ]
Mao, Zexi [3 ]
Zhang, Xianliang [2 ]
Zhang, Longwei [1 ,2 ]
Huang, Haiqing [2 ]
机构
[1] Zhejiang Univ, Ocean Coll, Hangzhou 310058, Peoples R China
[2] Minist Nat Resources, Inst Oceanog 2, State Key Lab Satellite Ocean Environm Dynam, Hangzhou 310012, Peoples R China
[3] Univ Maine, Sch Marine Sci, Orono, ME 04469 USA
来源
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING | 2024年 / 62卷
基金
中国国家自然科学基金;
关键词
Marine vegetation; Remote sensing; Transformers; Bathymetry; Accuracy; Sea surface; Oceans; coral reef; PlanetScope; remote sensing; visual transformer; OPTICAL-PROPERTIES; CLASSIFICATION;
D O I
10.1109/TGRS.2024.3468380
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
In recent years, various coral reef retrieval methods have experienced considerable progress due to a variety of observational instruments and innovative parameter calculation techniques. However, these labor-intensive methods are deficient in handling high-precision remote sensing mapping of coral reef benthic environments, facing challenges, including enhancing the robustness of scaled coral reef retrieval against varying water depths and complex water column conditions. To overcome these limitations, we propose a novel method for coral reef benthic mapping. Our method primarily consists of two central components: water depth extraction and coral reef information acquisition. Accurate bathymetry is critical for coral reef remote sensing inversion. To obtain more precise water depth, we propose the Bathymetry Transformer model. Our Bathymetry Transformer model aggregates vast amounts of active and passive remote sensing data, generates accurate bathymetry (with a 0.375-m RMSE, ranging from 0- to 12-m water depth) that eliminates the need for in situ examinations, and maintains a harmonious balance between greater bathymetry precision and finer spatial resolution. Based on this, water column corrections are then applied, and the results derived from various active and passive remote sensing processes, along with their respective band calculation outcomes, are fed into the proposed coral reef Transformer (CR Transformer) model to generate high-accuracy coral reef benthic mapping results. Copious experimental outcomes affirm that our CR Transformer surpasses current state-of-the-art (SOTA) methods in computational efficiency and results accuracy. Impressively, the CR Transformer achieves a notable mean intersection over union (mIoU) of 91.25% and an accuracy of 95.71% on the validation dataset.
引用
收藏
页数:15
相关论文
共 56 条
[1]   Impacts of overfishing and sedimentation on the feeding behavior and ecological function of herbivorous fishes in coral reefs [J].
Akita, Yuichi ;
Kurihara, Takeo ;
Uehara, Masato ;
Shiwa, Toshiyuki ;
Iwai, Kenji .
MARINE ECOLOGY PROGRESS SERIES, 2022, 686 :141-157
[2]   Impact of water characteristics on the discrimination of benthic cover in and around coral reefs from imaging spectrometer data [J].
Bel, Tom W. ;
Okin, Gregory S. ;
Cavanaugh, Kyle C. ;
Hochberg, Eric J. .
REMOTE SENSING OF ENVIRONMENT, 2020, 239
[3]   Mapping the distribution of coral reefs and associated sublittoral habitats in Pacific Panama: a comparison of optical satellite sensors and classification methodologies [J].
Benfield, S. L. ;
Guzman, H. M. ;
Mair, J. M. ;
Young, J. A. T. .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2007, 28 (22) :5047-5070
[4]   GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond [J].
Cao, Yue ;
Xu, Jiarui ;
Lin, Stephen ;
Wei, Fangyun ;
Hu, Han .
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW), 2019, :1971-1980
[5]   Masked-attention Mask Transformer for Universal Image Segmentation [J].
Cheng, Bowen ;
Misra, Ishan ;
Schwing, Alexander G. ;
Kirillov, Alexander ;
Girdhar, Rohit .
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, :1280-1289
[6]   Fluid lensing and machine learning for centimeter-resolution airborne assessment of coral reefs in American Samoa [J].
Chirayath, Ved ;
Instrella, Ron .
REMOTE SENSING OF ENVIRONMENT, 2019, 235
[7]   Polarization effects on oceanographic lidar [J].
Churnside, James H. .
OPTICS EXPRESS, 2008, 16 (02) :1196-1207
[8]   Global declines in coral reef calcium carbonate production under ocean acidification and warming [J].
Cornwall, Christopher E. ;
Comeau, Steeve ;
Kornder, Niklas A. ;
Perry, Chris T. ;
Hooidonk, Ruben van ;
DeCarlo, Thomas M. ;
Pratchett, Morgan S. ;
Anderson, Kristen D. ;
Browne, Nicola ;
Carpenter, Robert ;
Diaz-Pulido, Guillermo ;
D'Olivo, Juan P. ;
Doo, Steve S. ;
Figueiredo, Joana ;
Fortunato, Sofia A. V. ;
Kennedy, Emma ;
Lantz, Coulson A. ;
McCulloch, Malcolm T. ;
Gonzalez-Rivero, Manuel ;
Schoepf, Verena ;
Smithers, Scott G. ;
Lowe, Ryan J. .
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2021, 118 (21)
[9]  
Dosovitskiy A, 2021, Arxiv, DOI arXiv:2010.11929
[10]   The economic value of coral reefs: Climate change impacts and spatial targeting of restoration measures [J].
Fezzi, Carlo ;
Ford, Derek J. ;
Oleson, Kirsten L. L. .
ECOLOGICAL ECONOMICS, 2023, 203