scholarly journals NeMO-Net – Gamifying 3D Labeling of Multi-Modal Reference Datasets to Support Automated Marine Habitat Mapping

2021 ◽  
Vol 8 ◽  
Author(s):  
Jarrett van den Bergh ◽  
Ved Chirayath ◽  
Alan Li ◽  
Juan L. Torres-Pérez ◽  
Michal Segal-Rozenhaimer

NASA NeMO-Net, The Neural Multimodal Observation and Training Network for global coral reef assessment, is a convolutional neural network (CNN) that generates benthic habitat maps of coral reefs and other shallow marine ecosystems. To segment and classify imagery accurately, CNNs require curated training datasets of considerable volume and accuracy. Here, we present a citizen science approach to create these training datasets through a novel 3D classification game for mobile and desktop devices. Leveraging citizen science, the NeMO-Net video game generates high-resolution 3D benthic habitat labels at the subcentimeter to meter scales. The video game trains users to accurately identify benthic categories and semantically segment 3D scenes captured using NASA airborne fluid lensing, the first remote sensing technology capable of mitigating ocean wave distortions, as well as in situ 3D photogrammetry and 2D satellite remote sensing. An active learning framework is used in the game to allow users to rate and edit other user classifications, dynamically improving segmentation accuracy. Refined and aggregated data labels from the game are used to train NeMO-Net’s supercomputer-based CNN to autonomously map shallow marine systems and augment satellite habitat mapping accuracy in these regions. We share the NeMO-Net game approach to user training and retention, outline the 3D labeling technique developed to accurately label complex coral reef imagery, and present preliminary results from over 70,000 user classifications. To overcome the inherent variability of citizen science, we analyze criteria and metrics for evaluating and filtering user data. Finally, we examine how future citizen science and machine learning approaches might benefit from label training in 3D space using an active learning framework. Within 7 months of launch, NeMO-Net has reached over 300 million people globally and directly engaged communities in coral reef mapping and conservation through ongoing scientific field campaigns, uninhibited by geography, language, or physical ability. As more user data are fed into NeMO-Net’s CNN, it will produce the first shallow-marine habitat mapping products trained on 3D subcm-scale label data and merged with m-scale satellite data that could be applied globally when data sets are available.

2021 ◽  
Vol 22 (11) ◽  
Author(s):  
Anggita Kartikasari ◽  
TODHI PRISTIANTO ◽  
RIZKI HANINTYO ◽  
EGHBERT ELVAN AMPOU ◽  
TEJA ARIEF WIBAWA ◽  
...  

Abstract. Kartikasari A, Pristianto T, Hanintyo R, Ampou EE, Wibawa TA, Borneo BB. 2021. Representative benthic habitat mapping on Lovina coral reefs in Northern Bali, Indonesia. Biodiversitas 22: 4766-4774. Satellite optical imagery datasets integrated with in situ measurements are widely used to derive the spatial distribution of various benthic habitats in coral reef ecosystems. In this study, an approach to estimate spatial coverage of those habitats based on observation derived from Sentinel-2 optical imagery and a field survey, is presented. This study focused on the Lovina coral reef ecosystem of Northern Bali, Indonesia to support deployment of artificial reefs within the Indonesian Coral Reef Garden (ICRG) programme. Three specific locations were explored: Temukus, Tukad Mungga, and Baktiseraga waters. Spatial benthic habitat coverages of these three waters was estimated based on supervised classification techniques using 10m bands of Sentinel-2 imagery and the medium scale approach (MSA) transect method of in situ measurement.The study indicates that total coverage of benthic habitat is 61.34 ha, 25.17 ha, and 27.88 ha for Temukus, Tukad Mungga, and Baktiseraga waters, respectively. The dominant benthic habitat of those three waters consists of sand, seagrass, coral, rubble, reef slope and intertidal zone. The coral reef coverage is 29.48 ha (48%) for Temukus covered by genus Acropora, Isopora, Porites, Montipora, Pocillopora. The coverage for Tukad Mungga is 8.69 ha (35%) covered by genus Acropora, Montipora, Favia, Psammocora, Porites, and the coverage for Baktiseraga is 11.37 ha (41%) covered by genus Montipora sp, Goniastrea, Pavona, Platygyra, Pocillopora, Porites, Acropora, Leptoseris, Acropora, Pocillopora, Fungia. The results are expected to be suitable as supporting data in restoring coral reef ecosystems in the northern part of Bali, especially in Buleleng District.


Author(s):  
Renato Guimarães de Oliveira ◽  
José Maria Landim Dominguez ◽  
Ivan Cardoso Lemos ◽  
Carla Maria Menegola da Silva

2018 ◽  
Author(s):  
Muhammad Afif Fauzan

Maps of nearshore marine habitat are vital for coastal management and conservation. While traditional field mapping techniques are still commonly used, airborne and satellite remote sensing have proven to be efficient alternatives for creating benthic habitat maps. This paper evaluates the capability of new satellite data, Sentinel-2 MSI, to map nearshore benthic habitat of Derawan Island. Available aerial photographs were used as reference data. The results show that Sentinel-2 MSI data can be used to map benthic habitat with accuracy up to 75%.


Author(s):  
M. Doukari ◽  
K. Topouzelis

Abstract. Marine habitat mapping is essential for updating existing information, preserving, and protecting the marine environment. Unmanned Aerial Systems (UAS) are an important tool for monitoring and mapping coastal and marine environment because of their ability to provide very high-resolution aerial imagery.Environmental conditions have a critical role in marine mapping using UAS. This is due to the limitations of UAS surveys in coastal areas, i.e. the environmental conditions prevailing in the area. The limitations of weather and oceanographic conditions affecting the quality of marine data led to the creation of a UAS protocol for the acquisition of reliable marine information. The produced UAS Data Acquisition Protocol consists of three main categories: (i) Morphology of the study area, (ii) Environmental conditions, (iii) Flight parameters. These categories include the parameters that must be considered for marine habitat mapping.The aim of the present study is the accuracy assessment of the UAS protocol for marine habitat mapping through experimental flights. For the accuracy assessment of the UAS protocol, flights on different dates and environmental conditions were conducted, over a study area. The flight altitude was the same for all the missions, so the results were comparable. The high-resolution orthophoto maps derived from each date of the experiment were classified. The classification maps show several differences in the shape and size of the marine habitats which are directly dependent on the conditions that the habitats were mapped. A change detection comparison was conducted in pairs to examine the exact changes between the classified maps.The results emphasize the importance of the environmental conditions prevailing in an area during the mapping of marine habitats. The present study proves that the optimal flight conditions that are proposed of the UAS Data Acquisition protocol, respond to the real-world conditions and are important to be considered for an accurate and reliable mapping of the marine environment.


2018 ◽  
Vol 168 ◽  
pp. 39-47 ◽  
Author(s):  
Karen Boswarva ◽  
Alyssa Butters ◽  
Clive J. Fox ◽  
John A. Howe ◽  
Bhavani Narayanaswamy

2018 ◽  
Vol 76 (1) ◽  
pp. 10-22 ◽  
Author(s):  
James Asa Strong ◽  
Annika Clements ◽  
Helen Lillis ◽  
Ibon Galparsoro ◽  
Tim Bildstein ◽  
...  

Abstract The production of marine habitat maps typically relies on the use of habitat classification schemes (HCSs). The choice of which HCS to use for a mapping study is often related to familiarity, established practice, and national desires. Despite a superficial similarity, HCSs differ greatly across six key properties, namely, purpose, environmental and ecological scope, spatial scale, thematic resolution, structure, and compatibility with mapping techniques. These properties impart specific strengths and weaknesses for each HCS, which are subsequently transferred to the habitat maps applying these schemes. This review has examined seven HCSs (that are commonly used and widely adopted for national and international mapping programmes), over the six properties, to understand their influence on marine habitat mapping. In addition, variation in how mappers interpret and apply HCSs introduces additional uncertainties and biases into the final maps. Recommendations are provided for improving HCSs for marine habitat mapping as well as for enhancing the working practices of mappers using habitat classification. It is hoped that implementation of these recommendations will lead to greater certainty and usage within mapping studies and more consistency between studies and adjoining maps.


Sign in / Sign up

Export Citation Format

Share Document