Application of Deep Learning for Classification of Intertidal Eelgrass from Drone-Acquired Imagery

被引:7
作者
Tallam, Krti [1 ]
Nguyen, Nam [2 ]
Ventura, Jonathan [2 ]
Fricker, Andrew [3 ]
Calhoun, Sadie [3 ]
O'Leary, Jennifer [4 ]
Fitzgibbons, Maurica [5 ]
Robbins, Ian [6 ]
Walter, Ryan K. K. [6 ]
机构
[1] Stanford Univ, Biol Dept, Stanford, CA 94305 USA
[2] Calif Polytech State Univ San Luis Obispo, Comp Sci & Software Engn Dept, San Luis Obispo, CA 93407 USA
[3] Calif Polytech State Univ San Luis Obispo, Social Sci Dept, San Luis Obispo, CA 93407 USA
[4] Wildlife Conservat Soc, Mombasa 9947080100, Kenya
[5] Calif Polytech State Univ San Luis Obispo, Dept Food & Environm Sci, San Luis Obispo, CA 93407 USA
[6] Calif Polytech State Univ San Luis Obispo, Phys Dept, San Luis Obispo, CA 93407 USA
关键词
shallow estuarine habitat; eelgrass; drones; machine learning; coastal dynamics; climate; Morro Bay; DYNAMICS; SHALLOW; COAST; UAV; PHOTOGRAMMETRY; RESILIENCE; RECOVERY; SYSTEMS; CARBON; PATCH;
D O I
10.3390/rs15092321
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Shallow estuarine habitats are globally undergoing rapid changes due to climate change and anthropogenic influences, resulting in spatiotemporal shifts in distribution and habitat extent. Yet, scientists and managers do not always have rapidly available data to track habitat changes in real-time. In this study, we apply a novel and a state-of-the-art image segmentation machine learning technique (DeepLab) to two years of high-resolution drone-based imagery of a marine flowering plant species (eelgrass, a temperate seagrass). We apply the model to eelgrass (Zostera marina) meadows in the Morro Bay estuary, California, an estuary that has undergone large eelgrass declines and the subsequent recovery of seagrass meadows in the last decade. The model accurately classified eelgrass across a range of conditions and sizes from meadow-scale to small-scale patches that are less than a meter in size. The model recall, precision, and F1 scores were 0.954, 0.723, and 0.809, respectively, when using human-annotated training data and random assessment points. All our accuracy values were comparable to or demonstrated greater accuracy than other models for similar seagrass systems. This study demonstrates the potential for advanced image segmentation machine learning methods to accurately support the active monitoring and analysis of seagrass dynamics from drone-based images, a framework likely applicable to similar marine ecosystems globally, and one that can provide quantitative and accurate data for long-term management strategies that seek to protect these vital ecosystems.
引用
收藏
页数:13
相关论文
共 89 条
  • [1] Ainis AF, 2019, SOC ECO ISL COAST AR, P135
  • [2] Anderson R.O., 2020, High Resolution Remote Sensing of Eelgrass (Zostera marina) in South Slough
  • [3] Mapping and Quantification of the Dwarf Eelgrass Zostera noltei Using a Random Forest Algorithm on a SPOT 7 Satellite Image
    Benmokhtar, Salma
    Robin, Marc
    Maanan, Mohamed
    Bazairi, Hocein
    [J]. ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION, 2021, 10 (05)
  • [4] Drone Image Segmentation Using Machine and Deep Learning for Mapping Raised Bog Vegetation Communities
    Bhatnagar, Saheba
    Gill, Laurence
    Ghosh, Bidisha
    [J]. REMOTE SENSING, 2020, 12 (16)
  • [5] Supervised Classification of Benthic Reflectance in Shallow Subtropical Waters Using a Generalized Pixel-Based Classifier across a Time Series
    Blakey, Tara
    Melesse, Assefa
    Hall, Margaret O.
    [J]. REMOTE SENSING, 2015, 7 (05): : 5098 - 5116
  • [6] The ups and downs of a canopy-forming seaweed over a span of more than one century
    Blanfune, Aurelie
    Boudouresque, Charles Francois
    Verlaque, Marc
    Thibaut, Thierry
    [J]. SCIENTIFIC REPORTS, 2019, 9 (1)
  • [7] Estuarine ecosystem function response to flood and drought in a shallow, semiarid estuary: Nitrogen cycling and ecosystem metabolism
    Bruesewitz, Denise A.
    Gardner, Wayne S.
    Mooney, Rae F.
    Pollard, Lindsey
    Buskey, Edward J.
    [J]. LIMNOLOGY AND OCEANOGRAPHY, 2013, 58 (06) : 2293 - 2309
  • [8] Adopting deep learning methods for airborne RGB fluvial scene classification
    Carbonneau, Patrice E.
    Dugdale, Stephen J.
    Breckon, Toby P.
    Dietrich, James T.
    Fonstad, Mark A.
    Miyamoto, Hitoshi
    Woodget, Amy S.
    [J]. REMOTE SENSING OF ENVIRONMENT, 2020, 251
  • [9] Study of wave runup using numerical models and low-altitude aerial photogrammetry: A tool for coastal management
    Casella, Elisa
    Rovere, Alessio
    Pedroncini, Andrea
    Mucerino, Luigi
    Casella, Marco
    Cusati, Luis Alberto
    Vacchi, Matteo
    Ferrari, Marco
    Firpo, Marco
    [J]. ESTUARINE COASTAL AND SHELF SCIENCE, 2014, 149 : 160 - 167
  • [10] Lipton ZC, 2014, Arxiv, DOI arXiv:1402.1892