Shallow-Water Benthic Habitat Mapping Using Drone with Object Based Image Analyses

Abstract

Spatial information on benthic habitats in Wangiwangi island waters, Wakatobi District, Indonesia was very limited in recent years. However, this area is one of the marine tourism destinations and one of the Indonesia’s triangle coral reef regions with a very complex coral reef ecosystem. The drone technology that has rapidly developed in this decade, can be used to map benthic habitats in this area. This study aimed to map shallow-water benthic habitats using drone technology in the region of Wangiwangi island waters, Wakatobi District, Indonesia. The field data were collected using a 50 × 50 cm squared transect of 434 observation points in March–April 2017. The DJI Phantom 3 Pro drone with a spatial resolution of 5.2 × 5.2 cm was used to acquire aerial photographs. Image classifications were processed using object-based image analysis (OBIA) method with contextual editing classification at level 1 (reef level) with 200 segmentation scale and several segmentation scales at level 2 (benthic habitat). For level 2 classification, we found that the best algorithm to map benthic habitat was the support vector machine (SVM) algorithm with a segmentation scale of 50. Based on field observations, we produced 12 and 9 benthic habitat classes. Using the OBIA method with a segmentation value of 50 and the SVM algorithm, we obtained the overall accuracy of 77.4% and 81.1% for 12 and 9 object classes, respectively. This result improved overall accuracy up to 17% in mapping benthic habitats using Sentinel-2 satellite data within the similar region, similar classes, and similar method of classification analyses.

Object based classification of benthic habitat using Sentinel 2 imagery by applying with support vector machine and random forest algorithms in shallow waters of Kepulauan Seribu, Indonesia

“…Wahidin et al (2015), using Landsat 8 OLI images with support vector machine (SVM), random tree (RT), bayyesian, k-nearest neighbor (KNN) and decision tree (DT) shows that the algorithm SVM has a better ability than other algorithms with an overall accuracy rate of 73% with seven classes. Nababan et al (2021), using drone imagery and applying the SVM algorithm, resulted in an overall accuracy of 77.4 % in 12 classes and 81.1% in 9 classes. The Z test is used to determine whether two or more image classifications differ significantly or not (Congalton and Green 2009).…”

Microdrones in field-based structural geology: a photogrammetry and fracture quantification case study from the North Mountain Basalt, Nova Scotia, Canada

“…The decrease in cost, development of more advanced technologies, such as higher resolution and more lightweight cameras, plus availability of consumer-level drones (i.e. UAVs, uncrewed aerial vehicles) has driven their widespread adoption as a research and teaching tool across the geosciences (Jordan 2015, Behrman et al 2019, Dering et al 2019, Samsu et al 2019, Cirillo 2020 and other disciplines such as ecology (Charton et al 2021, Nababan et al 2021, archeology (Hendrickx et al 2011), and forensic science (Stanković et al 2021). The ability for geoscience researchers and educators to integrate aerially obtained data into their analyses is proving highly valuable both in the field for locating suitable study areas, and also post-fieldwork with numerous use cases reported (Ryberg et al 2015).…”

Caracterización y clasificación del fondo en el arrecife rocoso La Sorpresa (Baja California Sur, México) implementando métodos de interpolación espacial.

“…Generalmente se utilizan imágenes de satélite de alta resolución espacial y espectral en costas someras para obtener clasificación de unidades mediante procesamiento digital de estas imágenes (Silvero et al 2021). También se ha empleado imágenes obtenidas a partir de vehículos aéreos y submarinos no tripulados (drones) para la observación indirecta de hábitats bentónicos (Tait et al, 2021;Nababan et al, 2021) Del Pino-Machado et al…”