The distribution of Posidonia oceanica seagrass meadows is mapped by a combination of remote sensing techniques, Geographical Information Systems (GIS), and sonar data. A fundamental, but challenging, part of this methodology is the remote sensing image classification. This article presents a review of different image classification techniques to optimize the final maps, in order to take efficient actions to conserve seagrass meadows.
Seagrass monitoring and mapping
The degradation of P. oceanica seagrass meadows is a major concern, since these marine ecosystems play a fundamental role in the health and productivity of many Mediterranean marine habitats. Seagrass monitoring and mapping are fundamental tools for measuring the status and trends of meadows and their environmental condition (Topouzelis et al., 2018). The Greek Non-Governmental Organisation Archipelagos Institute of Marine Conservation, operating from the islands of Samos and Lipsi, is committed to collecting spatial data around the Greek coast to generate more accurate habitat distribution maps of P. oceanica in order to monitor and protect these highly valuable ecosystems. Archipelagos conducts marine research with multiple research vessels, including the 22-meter long Aegean Explorer (Figure 1). This vessel is equipped with an array of scientific instruments, including single- and multibeam sonar, structure scanner, biomass scanner as well as an underwater camera capable of reaching depths of 300 meters.
Mapping seagrass distribution
The distribution of P. oceanica is mapped by means of remote sensing techniques, GIS, and sonar measurements in the field. The input for the remote sensing methodology is Sentinel-2A satellite imagery. The satellite image is pre-processed to deal with necessary corrections of the interferences that determine the light in the atmosphere and water before deriving any quantitative information on the aquatic habitats that focus on seagrass (Traganos and Reinartz, 2018). The main steps here are atmospheric correction, sun glint removal, and water column correction.
During the field operations ground truth data about the seagrass meadows collected. A DownScan sonar is installed on a research vessel and on the back of the kayak to obtain information about the seafloor (Figure 2 and 3). The sonar transducer emits ultra-sound waves to the seafloor from which bottom morphology is derived. When P. oceanica is present it occurs on the sonar output as a fuzziness above the seafloor as shown in Figure 4. Waypoints are set for P. oceanica (P) or no P. oceanica (NP), which are used as training data during the image classification process and accuracy data during the accuracy assessment.
Free weekly newsletter
Fill out your e-mail address to receive our newsletter!
By entering your email address you agree to receive our newsletter and agree with our privacy policy.
You may unsubscribe at any time.
Classifying seagrass presence or absence
After correcting the satellite image, the pixels are classified to indicate P. oceanica presence or absence. Essential in most aquatic remote sensing studies is the process of identifying distinctive cover or substrate types in the study area on a satellite image into sensible classes, which is defined as remote sensing image classification. In this methodology supervised image classification is applied, in which the classification is performed with ground truth data.
Four supervised image classifiers are reviewed: Maximum Likelihood Classifier (MLC), Radial Support Vector Machine (SVM), Linear SVM and Random Forest (RF). Each of these techniques is built on its own mathematical function. The choice for a technique can be based on different criteria, such as image resolution, spatial scale and the ground truth data set. The techniques are reviewed on their accuracy percentage and Kappa Index. These parameters are derived by means of the accuracy waypoints and a Confusion Matrix (Cohen, 1960).
Comparing image classifiers
The four image classification techniques are performed for six different islands in the Southeast Aegean Sea, at three different spatial scales and with different waypoint densities to optimally explore the function and performance of the techniques. Figure 5 indicates the seagrass distribution around the island of Lipsi modelled by the four classifiers. Due to the limitations of satellite imagery the distribution is modelled till a bathymetry of 20 meters. The maps show significant differences in seagrass distribution modelled by the four techniques.
RF and Radial SVM resulted in the most accurate maps (respectively 88% and 72%) for this study, even when the waypoint density is reduced. It can be noticed between these two that the seagrass pixels classified by RF are more randomly distributed than with Radial SVM, which clearly shows the function of these two techniques. MLC seems to overestimate the P. oceanica coverage since more than 50% of the NP points are modelled as P pixels. Linear SVM makes an extreme underestimation as 98% of the P points are modelled as NP pixels.
Concluding remarks
The modelling of P. oceanica coverage around islands in the Southeast Aegean Sea resulted in high accurate outputs modelled by RF and Radial SVM. The review has shown that each image classification technique consists of its own function and therefore delivers distinguishing outputs. The choice for a classification technique depends on different criteria, including spatial scale, image resolution and the ground truth data set.
Simultaneously, the choice for a classification technique also strongly depends on the purpose and use of the final maps. For example, Archipelagos is committed to conserve the seagrass by using the maps to the government, local communities, ports and fishermen to achieve legislation, protection and awareness. A classifier that slightly overestimates is more likely to be selected in this case, than one that strongly underestimates. These classification purposes and applications should be kept in mind when investigating the techniques and the motives to select one. Because of these motivations further contributions and efforts are required to investigate the assessment and applications of remote sensing image classification techniques.
Acknowledgements
I would like to thank Thodoris Tsimpidis and Anastasia Miliou (Directors of Archipelagos Institute of Marine Conservation) for the opportunities and resources they provided me both on- and offshore during my research internship. Due to their love for the ocean and the commitment for marine research, they are a source of inspiration.
About the author
Inge van den Meiracker is a MSc graduate student in Geographical Information Management and Applications (GIMA). During her six months research internship at Archipelagos she was committed to use GIS and remote sensing as a solution for effective marine conservation strategies.
More about Archipelagos: http://archipela
More about modelling seagrass: http://archipelago.g
More about my internship: http://archipelago
