High-Resolution Seagrass Species Mapping and Propeller Scars Detection in Tanjung Benoa, Bali through UAV Imagery

Abstract

As a part of the marine ecosystem, seagrass plays a significant role in the coastal environment. However, due to increased threats from natural causes and anthropogenic pressures, seagrass decline will likely begin in many areas of the world. Therefore, several studies have been carried out to observe seagrass distribution to help resolve the issue. Remote sensing is often used due to its ability to achieve high accuracy when distinguishing seagrass dis - tribution. Still, this method lacks in species classification because not all satellites and similar aerial vehicles have fine spatial resolution to distinguish distinct species of seagrass. In this study, we aim to address the issue by utiliz - ing unmanned aerial vehicles (UAV), which are known for providing finer resolution and better imagery. Samuh Beach at Tanjung Benoa, Bali, Indonesia, was chosen as the study site location because it experiences high levels of marine tourism and anthropogenic activities. From the UAV flight mission, the images obtained were processed. The result’s accuracy was also tested with an error matrix. The species found in this study are Enhalus acoroides , Halodule pinifolia , Thalassia hemprichii , Cymodocea rotundata , and Syringodium isoetifolium , with 65% overall accuracy of the species classification map. This result indicates that UAVs can be a strong option for similar studies in the future. In addition to that, this study was able to observe the scars on the seagrass beds left by boat propeller activities from marine tourism. However, further research is needed to gain a better understanding of these objects.