Assessment of Sentinel‐2A multispectral image for benthic habitat composition mapping

Wicaksono, Pramaditya; Fauzan, Muhammad Afif; Asta, Septian Galih Widhi

doi:10.1049/iet-ipr.2018.6044

Cited by 6 publications

(4 citation statements)

References 28 publications

(40 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In comparison to these studies, the accuracy of the maps in this study was found to be similar to those that produced benthic habitat maps with 8 to 9 benthic habitat classes. It is worth noting that the accuracy of the resulting map decreases as the number of classified benthic habitat classes increases (Andréfouët et al 2003;Mastu et al 2018;Siregar et al 2020;Wicaksono et al 2020).…”

Section: Discussionmentioning

confidence: 99%

Spatial distribution of benthic habitats in Kapota Atoll (Wakatobi National Park, Indonesia) using remote sensing imagery

HAMUNA,

PUJIYATI,

GAOL

et al. 2023

Biodiversitas

View full text Add to dashboard Cite

Abstract. Hamuna B, Pujiyati S, Gaol JL, Hestirianoto T. 2023. Spatial distribution of benthic habitats in Kapota Atoll (Wakatobi National Park, Indonesia) using remote sensing imagery. Biodiversitas 24: 3700-3707. This study aims to classify and map benthic habitats in Kapota Atoll, Wakatobi National Park, using Sentinel-2A satellite imagery, that has undergone both atmospheric and geometric corrections. Sentinel-2A satellite imagery was processed using pixel-based classification method. This study used two machine learning algorithms: support vector machine (SVM) and random forest (RF). This study used nine classified benthic habitat classes, namely five homogeneous benthic classes (sand, live coral, dead coral, rubble, and dense seagrass) and four mixed benthic classes (mixed rubble and sand, mixed sand and rare seagrass, mixed medium seagrass and sand, and a mixture of rubble, dead coral, and seagrass). The RF algorithm produced benthic habitat maps with a higher overall accuracy than the SVM algorithm, which was 65.31% and 63.51%, respectively. These accuracy values have met the standards of accuracy for mapping benthic habitats that apply in Indonesia. The SVM algorithm classification results showed that the benthic habitat of the mixed class of medium seagrass and sand was more dominant than other benthic habitat classes. In contrast, the RF algorithm showed the class dense seagrass was more dominant. The selection of the appropriate algorithm for processing satellite imagery was found to be a significant factor in producing an accurate benthic habitat map.

show abstract

Section: Discussionmentioning

confidence: 99%

Spatial distribution of benthic habitats in Kapota Atoll (Wakatobi National Park, Indonesia) using remote sensing imagery

HAMUNA,

PUJIYATI,

GAOL

et al. 2023

Biodiversitas

View full text Add to dashboard Cite

show abstract

“…A range of secondary features may also be calculated from spectral remote sensing data acquired using airor satellite-borne optical sensors. Many of these -including band ratios (e.g., Roelfsema et al, 2013;McIntyre et al, 2018) and various vegetation indices (e.g., Bajjouk et al, 2020;Forsey et al, 2020;Wicaksono et al, 2020) -utilize differences between wavelengths of different spectral bands of multi-or hyper-spectral sensors. Waveform variables calculated from LiDAR also offer potential for increased discrimination of bottom type, for example, by calculating features based on waveform geometry (e.g., Tulldahl & Wikström, 2012), hue saturation intensity (HSI; e.g., Zavalas et al, 2014) or statistics and vegetation indices comparable to those of spectral data (e.g., Collin et al, 2008;Collin et al, 2012).…”

Section: Derived Predictor Datamentioning

confidence: 99%

“…Some use of previous maps or compiled datasets as ground truth also occurs where they are deemed high quality (e.g., Immordino et al, 2019). Occasionally, high resolution remotely sensed optical datasets such as those acquired via airborne hyperspectral sensors or drones are used to ground truth lower resolution optical sensors that may cover a broader extent, such as satellite data (e.g., Wicaksono et al, 2020;Poursanidis et al, 2021).…”

Section: Ground Validationmentioning

confidence: 99%

Benthic habitat mapping: A review of three decades of mapping biological patterns on the seafloor

Misiuk,

Brown

2023

Preprint

View full text Add to dashboard Cite

What is benthic habitat mapping, how is it accomplished, and how has that changed over time? We query the published literature to answer these questions and synthesize the results quantitatively to provide a comprehensive review of the field over the past three decades. Categories of benthic habitat maps are differentiated unambiguously by the response variable (i.e., the subject being mapped) rather than the approaches used to produce the map. Additional terminology in the literature is clarified and defined based on provenance, statistical criteria, and common usage. Mapping approaches, models, data sets, technologies, and a range of other attributes are reviewed based on their application, and we document changes to the ways that these components have been integrated to map benthic habitats over time. We found that the use of acoustic remote sensing has been surpassed by optical methods for obtaining benthic environmental data. Although a wide variety of approaches are employed to ground truth habitat maps, underwater imagery has become the most common validation tool – surpassing physical sampling. The use of empirical machine learning models to process these data has increased dramatically over the past 10 years, and has superseded expert manual interpretation. We discuss how map products derived from these data and approaches are used to address ecological questions in the emerging field of seascape ecology, and how remote sensing technologies and field survey logistics pose different challenges to this research field across benthic ecosystems from intertidal and shallow sublittoral regions to the deep ocean. Outstanding challenges are identified and discussed in context with the trajectory of the field.

show abstract

“…The ability of S2 for benthic classification and quantification has mostly been investigated in clear ocean waters 16 , 18 – 22 Recently, there has been increasing interest to use the sensor also in optically complex, temperate water bodies. For example, S2 imagery was used for the vegetation presence and absence prediction in optically complex waters of the Atlantic Canada 23 .…”

Section: Introductionmentioning

confidence: 99%

On the possibility to map submerged aquatic vegetation cover with Sentinel-2 in low-transparency waters

Vahtmäe,

Toming,

Argus

et al. 2023

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

.Modifications in submerged aquatic vegetation (SAV) spatial and temporal abundance patterns indicate changes in marine environmental conditions or physical disturbances and need to be monitored. Vegetation percent cover (%cover) is recognized as one of the key parameters in SAV monitoring. Coastal waters of the Baltic Sea are often turbid and contain high amount of colored dissolved organic matter. These factors significantly reduce the water depth, where benthic parameters can be detected by remote sensing. Field campaigns were carried out in a low-transparency Pärnu Bay area to assess to what extent multispectral Sentinel-2 (S2) satellite can be used for SAV %cover mapping in such waters. An average depth restriction for S2 benthic vegetation detection remained near 1.5 to 2.0 m. Empirical and physics-based methods were applied to S2 imagery to compare their performance for SAV %cover retrieval. Both methods identified similar %cover patterns. Model validation results showed that R2 of the best-performing models remained between 0.56 and 0.66 and root-mean-square error between 22.11 and 28.06. As physics-based inversion models do not require extensive set of training data for model calibration, those can be used for retrospective time series analysis across multitemporal images.

show abstract

Assessment of Sentinel‐2A multispectral image for benthic habitat composition mapping

Cited by 6 publications

References 28 publications

Spatial distribution of benthic habitats in Kapota Atoll (Wakatobi National Park, Indonesia) using remote sensing imagery

Spatial distribution of benthic habitats in Kapota Atoll (Wakatobi National Park, Indonesia) using remote sensing imagery

Benthic habitat mapping: A review of three decades of mapping biological patterns on the seafloor

On the possibility to map submerged aquatic vegetation cover with Sentinel-2 in low-transparency waters

Contact Info

Product

Resources

About