| Peer-Reviewed

Mangrove Information Extraction and Precision Analysis Based on Multi-Feature Combination

Received: 24 July 2023    Accepted: 8 August 2023    Published: 28 August 2023
Views:       Downloads:
Abstract

Extracting information of mangroves at different tide levels from remote sensing images is challenging. In this study, we investigated the use of multiple features for mangrove information extraction, including spectral features, vegetation indices (NDVI, NIMI), and texture features. The accuracy of the extraction was also analyzed. We collected remote sensing images covering mangrove areas at different tide levels and conducted a comprehensive analysis of these images and extracted the desired features. The collected data were then used to train and evaluate classification models for accurate mangrove identification. The results showed that: (1) The integration of NDVI, NIMI, and band features effectively enhanced the classification accuracy of mangroves. These features provided valuable information about the vegetation cover and health of mangroves, enabling better differentiation from other land cover types. (2) The introduction of texture features for classification resulted in a significant decrease in user classification accuracy of mangroves. This suggests that texture features may not be as reliable in distinguishing mangroves from other land cover types, possibly due to the complex and heterogeneous nature of mangrove ecosystems. (3) Feature selection methods played a crucial role in improving the accuracy of mangrove extraction. By selecting an appropriate number of relevant features, these methods helped to avoid data redundancy and reduce the influence of weak features. This was particularly beneficial for the extraction of submerged mangroves, which are often challenging to detect accurately. These findings contribute to the development of improved methods for monitoring and managing mangrove ecosystems, which are vital for their conservation and sustainable management.

Published in American Journal of Remote Sensing (Volume 11, Issue 2)
DOI 10.11648/j.ajrs.20231102.12
Page(s) 36-43
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2024. Published by Science Publishing Group

Keywords

Mangroves, Information Extraction, Sentinel-2 Imagery, Multiple Feature Combination, Random Forest

References
[1] Stijn T, M E H, W K K, et al. Marshes and Mangroves as Nature-Based Coastal Storm Buffers. [J]. Annual review of marine science, 2022, 15.
[2] Kirwan Matthew L, Megonigal J Patrick. Tidal wetland stability in the face of human impacts and sea-level rise. [J]. Nature, 2013, 504 (7478).
[3] Collins Daniel S, Avdis Alexandros, Allison Peter A, Johnson Howard D, Hill Jon, Piggott Matthew D, Hassan Meor H Amir, Damit Abdul Razak. Tidal dynamics and mangrove carbon sequestration during the Oligo-Miocene in the South China Sea. [J]. Nature communications, 2017, 8 (1).
[4] Huang K, Meng X Z, Yang G and Sun W W. 2022. Spatio-temporal probability threshold method of remote sensing for mangroves mapping in China. National Remote Sensing Bulletin, 26 (6): 1083-1095 [DOI: 10.11834/jrs.20220449].
[5] Chen LuZhen, Wang WenQing, Zhang YiHui, Lin GuangHui. Recent progresses in mangrove conservation, restoration and research in China. [J]. Journal of Plant Ecology, 2009, 2 (2).
[6] Wang Gang, Singh Minerva, Wang Jiaqiu, Xiao Ling, Guan Dongsheng. Effects of marine pollution, climate, and tidal range on biomass and sediment organic carbon in Chinese mangrove forests [J]. Catena, 2021, 202.
[7] Liu Kai et al. based on the GEE platform, used its Landsat data set, and used the NDVI index to classify mangroves with decision trees based on expert knowledge (Liu et al., 2019);
[8] Chen B, Xiao X, Li X, et al. A mangrove forest map of China in 2015: Analysis of time series Landsat 7/8 and Sentinel-1A imagery in Google Earth Engine cloud computing platform [J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2017, 131.
[9] Kerrylee Rogers, Leo Lymburner, Rafaela Salum, Brendan P. Brooke, Colin D. Woodroffe. Mapping of mangrove extent and zonation using high and low tide composites of Landsat data [J]. Hydrobiologia, 2017, 803 (1).
[10] Hu Pingbo, Sharifi Alireza, Tahir Muhammad Naveed, Tariq Aqil, Zhang Lili, Mumtaz Faisal, Shah Syed Hassan Iqbal Ahmad. Evaluation of Vegetation Indices and Phenological Metrics Using Time-Series MODIS Data for Monitoring Vegetation Change in Punjab, Pakistan [J]. Water, 2021, 13 (18).
[11] Luo J H, Yang J Z C, Duan H T, Lu L R, Sun Z and Xin Y H. 2022. Research progress of aquatic vegetation remote sensing in shallow lakes. National Remote Sensing Bulletin, 26 (1): 68-76 [DOI: 10.11834/jrs.20221208].
[12] Y, Li Y, Tan J, et al. Information extraction method of mangrove forests based on GF-6 data [J]. Remote Sensing for Natural Resources, 2023, 35 (1); 41-48.
[13] Mingming Jia, Zongming Wang, Chao Wang, Dehua Mao, Yuanzhi Zhang. A New Vegetation Index to Detect Periodically Submerged Mangrove Forest Using Single-Tide Sentinel-2 Imagery [J]. Remote Sensing, 2019, 11 (17).
[14] Cheng L N, Zhong C R, Li X Y, Jia M M, Wang Z M and Mao D H. 2022. Rapid and automatic classification of intertidal wetlands based on intensive time series Sentinel-2 images and Google Earth Engine. National Remote Sensing Bulletin, 26 (2): 348-357 [DOI: 10.11834/jrs.20211311].
[15] Wang Y M, Li S, Dong C Y, et al. Remote sensing information extraction for mangrove forests supported by multi-fea-ture parameters: A case study of Guangdong Province [J]. Remote Sensing for Natural Resources.
[16] Zhu L, Guo Q Z, Wu Z P, et al. 2022. Extraction of saline-alkali land based on multi-scale segmentation and feature optimization [J]. Journal of Earth Environment, 13 (6): 714–723.
[17] Jiang Luyuan, Xiao Pengfeng, Feng Xuezhi, et al. Assessment of Large-scale Land Cover Datasets in Typical Areas of China based on Sub-fractional Error Matrix [J]. Remote Sensing Technology and Application, 2015, 30 (2): 353-363.
Cite This Article
  • APA Style

    Mingli Zhou, Angying Xu, Chengming Yang, Lifeng Liang. (2023). Mangrove Information Extraction and Precision Analysis Based on Multi-Feature Combination. American Journal of Remote Sensing, 11(2), 36-43. https://doi.org/10.11648/j.ajrs.20231102.12

    Copy | Download

    ACS Style

    Mingli Zhou; Angying Xu; Chengming Yang; Lifeng Liang. Mangrove Information Extraction and Precision Analysis Based on Multi-Feature Combination. Am. J. Remote Sens. 2023, 11(2), 36-43. doi: 10.11648/j.ajrs.20231102.12

    Copy | Download

    AMA Style

    Mingli Zhou, Angying Xu, Chengming Yang, Lifeng Liang. Mangrove Information Extraction and Precision Analysis Based on Multi-Feature Combination. Am J Remote Sens. 2023;11(2):36-43. doi: 10.11648/j.ajrs.20231102.12

    Copy | Download

  • @article{10.11648/j.ajrs.20231102.12,
      author = {Mingli Zhou and Angying Xu and Chengming Yang and Lifeng Liang},
      title = {Mangrove Information Extraction and Precision Analysis Based on Multi-Feature Combination},
      journal = {American Journal of Remote Sensing},
      volume = {11},
      number = {2},
      pages = {36-43},
      doi = {10.11648/j.ajrs.20231102.12},
      url = {https://doi.org/10.11648/j.ajrs.20231102.12},
      eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajrs.20231102.12},
      abstract = {Extracting information of mangroves at different tide levels from remote sensing images is challenging. In this study, we investigated the use of multiple features for mangrove information extraction, including spectral features, vegetation indices (NDVI, NIMI), and texture features. The accuracy of the extraction was also analyzed. We collected remote sensing images covering mangrove areas at different tide levels and conducted a comprehensive analysis of these images and extracted the desired features. The collected data were then used to train and evaluate classification models for accurate mangrove identification. The results showed that: (1) The integration of NDVI, NIMI, and band features effectively enhanced the classification accuracy of mangroves. These features provided valuable information about the vegetation cover and health of mangroves, enabling better differentiation from other land cover types. (2) The introduction of texture features for classification resulted in a significant decrease in user classification accuracy of mangroves. This suggests that texture features may not be as reliable in distinguishing mangroves from other land cover types, possibly due to the complex and heterogeneous nature of mangrove ecosystems. (3) Feature selection methods played a crucial role in improving the accuracy of mangrove extraction. By selecting an appropriate number of relevant features, these methods helped to avoid data redundancy and reduce the influence of weak features. This was particularly beneficial for the extraction of submerged mangroves, which are often challenging to detect accurately. These findings contribute to the development of improved methods for monitoring and managing mangrove ecosystems, which are vital for their conservation and sustainable management.},
     year = {2023}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - Mangrove Information Extraction and Precision Analysis Based on Multi-Feature Combination
    AU  - Mingli Zhou
    AU  - Angying Xu
    AU  - Chengming Yang
    AU  - Lifeng Liang
    Y1  - 2023/08/28
    PY  - 2023
    N1  - https://doi.org/10.11648/j.ajrs.20231102.12
    DO  - 10.11648/j.ajrs.20231102.12
    T2  - American Journal of Remote Sensing
    JF  - American Journal of Remote Sensing
    JO  - American Journal of Remote Sensing
    SP  - 36
    EP  - 43
    PB  - Science Publishing Group
    SN  - 2328-580X
    UR  - https://doi.org/10.11648/j.ajrs.20231102.12
    AB  - Extracting information of mangroves at different tide levels from remote sensing images is challenging. In this study, we investigated the use of multiple features for mangrove information extraction, including spectral features, vegetation indices (NDVI, NIMI), and texture features. The accuracy of the extraction was also analyzed. We collected remote sensing images covering mangrove areas at different tide levels and conducted a comprehensive analysis of these images and extracted the desired features. The collected data were then used to train and evaluate classification models for accurate mangrove identification. The results showed that: (1) The integration of NDVI, NIMI, and band features effectively enhanced the classification accuracy of mangroves. These features provided valuable information about the vegetation cover and health of mangroves, enabling better differentiation from other land cover types. (2) The introduction of texture features for classification resulted in a significant decrease in user classification accuracy of mangroves. This suggests that texture features may not be as reliable in distinguishing mangroves from other land cover types, possibly due to the complex and heterogeneous nature of mangrove ecosystems. (3) Feature selection methods played a crucial role in improving the accuracy of mangrove extraction. By selecting an appropriate number of relevant features, these methods helped to avoid data redundancy and reduce the influence of weak features. This was particularly beneficial for the extraction of submerged mangroves, which are often challenging to detect accurately. These findings contribute to the development of improved methods for monitoring and managing mangrove ecosystems, which are vital for their conservation and sustainable management.
    VL  - 11
    IS  - 2
    ER  - 

    Copy | Download

Author Information
  • Department of Geography, Lingnan Normal University, Zhanjiang, China

  • Department of Geography, Lingnan Normal University, Zhanjiang, China

  • Department of Geography, Lingnan Normal University, Zhanjiang, China

  • Department of Geography, Lingnan Normal University, Zhanjiang, China; Guangdong Coastal Economic Belt Development Research Center, Lingnan Normal University, Zhanjiang, China; Mangrove Institute, Lingnan Normal University, Zhanjiang, China

  • Sections