Comparative Assessment of Five Machine Learning Algorithms for Supervised Object-Based Classification of Submerged Seagrass Beds Using High-Resolution UAS Imagery

被引:5
作者
Thomasberger, Aris [1 ]
Nielsen, Mette Moller [1 ]
Flindt, Mogens Rene [2 ]
Pawar, Satish [1 ]
Svane, Niels [2 ]
机构
[1] Tech Univ Denmark, Natl Inst Aquat Resources, Sect Coastal Ecol, DK-2800 Lyngby, Denmark
[2] Univ Southern Denmark, Dept Biol, DK-5230 Odense, Denmark
关键词
object-based image analysis; OBIA; unoccupied aerial systems; UAS; drones; photogrammetry; machine learning; hyperparameter; seagrasses; coastal zone mapping; Limfjorden; LAND-COVER CLASSIFICATION; RANDOM FOREST CLASSIFIER; ECOSYSTEM SERVICES; SAMPLE-SIZE; SEGMENTATION; EELGRASS; CHALLENGES; SYSTEMS;
D O I
10.3390/rs15143600
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Knowledge about the spatial distribution of seagrasses is essential for coastal conservation efforts. Imagery obtained from unoccupied aerial systems (UAS) has the potential to provide such knowledge. Classifier choice and hyperparameter settings are, however, often based on time-consuming trial-and-error procedures. The presented study has therefore investigated the performance of five machine learning algorithms, i.e., Bayes, Decision Trees (DT), Random Trees (RT), k-Nearest Neighbor (kNN), and Support Vector Machine (SVM) when used for the object-based classification of submerged seagrasses from UAS-derived imagery. The influence of hyperparameter tuning and training sample size on the classification accuracy was tested on images obtained from different altitudes during different environmental conditions. The Bayes classifier performed well (94% OA) on images obtained during favorable environmental conditions. The DT and RT classifier performed better on low-altitude images (93% and 94% OA, respectively). The kNN classifier was outperformed on all occasions, while still producing OA between 89% and 95% in five out of eight scenarios. The SVM classifier was most sensitive to hyperparameter tuning with OAs ranging between 18% and 97%; however, it achieved the highest OAs most often. The findings of this study will help to choose the appropriate classifier and optimize related hyperparameter settings.
引用
收藏
页数:22
相关论文
共 78 条
  • [1] Agisoft LLC, 2023, AG AG MET US MAN PRO
  • [2] NS-k-NN: Neutrosophic Set-Based k-Nearest Neighbors Classifier
    Akbulut, Yaman
    Sengur, Abdulkadir
    Guo, Yanhui
    Smarandache, Florentin
    [J]. SYMMETRY-BASEL, 2017, 9 (09):
  • [3] Segmentation optimization and stratified object-based analysis for semi-automated geomorphological mapping
    Anders, Niels S.
    Seijmonsbergen, Arie C.
    Bouten, Willem
    [J]. REMOTE SENSING OF ENVIRONMENT, 2011, 115 (12) : 2976 - 2985
  • [4] Lightweight unmanned aerial vehicles will revolutionize spatial ecology
    Anderson, Karen
    Gaston, Kevin J.
    [J]. FRONTIERS IN ECOLOGY AND THE ENVIRONMENT, 2013, 11 (03) : 138 - 146
  • [5] Baatz M., 1999, P 2 INT S OPERATIONA
  • [6] Assessment of Machine Learning Methods for Seagrass Classification in the Mediterranean
    Bakirman, Tolga
    Gumusay, Mustafa Umit
    [J]. BALTIC JOURNAL OF MODERN COMPUTING, 2020, 8 (02): : 315 - 326
  • [7] High-resolution, low-altitude aerial photography in physical geography: A case study characterizing eelgrass (Zostera marina L.) and blue mussel (Mytilus edulis L.) landscape mosaic structure
    Barrell, Jeffrey
    Grant, Jon
    [J]. PROGRESS IN PHYSICAL GEOGRAPHY-EARTH AND ENVIRONMENT, 2015, 39 (04): : 440 - 459
  • [8] Beck MW, 2001, BIOSCIENCE, V51, P633, DOI 10.1641/0006-3568(2001)051[0633:TICAMO]2.0.CO
  • [9] 2
  • [10] Object based image analysis for remote sensing
    Blaschke, T.
    [J]. ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2010, 65 (01) : 2 - 16