UASea: A Data Acquisition Toolbox for Improving Marine Habitat Mapping

Unmanned aerial systems (UAS) are widely used in the acquisition of high-resolution information in the marine environment. Although the potential applications of UAS in marine habitat mapping are constantly increasing, many limitations need to be overcome—most of which are related to the prevalent environmental conditions—to reach efficient UAS surveys. The knowledge of the UAS limitations in marine data acquisition and the examination of the optimal flight conditions led to the development of the UASea toolbox. This study presents the UASea, a data acquisition toolbox that is developed for efficient UAS surveys in the marine environment. The UASea uses weather forecast data (i.e., wind speed, cloud cover, precipitation probability, etc.) and adaptive thresholds in a ruleset that calculates the optimal flight times in a day for the acquisition of reliable marine imagery using UAS in a given day. The toolbox provides hourly positive and negative suggestions, based on optimal or non-optimal survey conditions in a day, calculated according to the ruleset calculations. We acquired UAS images in optimal and non-optimal conditions and estimated their quality using an image quality equation. The image quality estimates are based on the criteria of sunglint presence, sea surface texture, water turbidity, and image naturalness. The overall image quality estimates were highly correlated with the suggestions of the toolbox, with a correlation coefficient of −0.84. The validation showed that 40% of the toolbox suggestions were a positive match to the images with higher quality. Therefore, we propose the optimal flight times to acquire reliable and accurate UAS imagery in the coastal environment through the UASea. The UASea contributes to proper flight planning and efficient UAS surveys by providing valuable information for mapping, monitoring, and management of the marine environment, which can be used globally in research and marine applications.

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

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.

UAS DATA ACQUISITION PROTOCOL FOR MARINE HABITAT MAPPING: AN ACCURACY ASSESSMENT STUDY

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.

Automated Filtering of Multibeam Water-Column Data to Detect Relative Abundance of Giant Kelp (Macrocystis pyrifera)

Modern multibeam echosounders can record backscatter data returned from the water above the seafloor. These water-column data can potentially be used to detect and map aquatic vegetation such as kelp, and thus contribute to improving marine habitat mapping. However, the strong sidelobe interference noise that typically contaminates water-column data is a major obstacle to the detection of targets lying close to the seabed, such as aquatic vegetation. This article presents an algorithm to filter the noise and artefacts due to interference from the sidelobes of the receive array by normalizing the slant-range signal in each ping. To evaluate the potential of the filtered data for the detection of aquatic vegetation, we acquired a comprehensive water-column dataset over a controlled experimental site. The experimental site was a transplanted patch of giant kelp (Macrocystis pyrifera) forest of known biomass and spatial configuration, obtained by harvesting several individuals from a nearby forest, measuring and weighing them, and arranging them manually on an area of seafloor previously bare. The water-column dataset was acquired with a Kongsberg EM 2040 C multibeam echosounder at several frequencies (200, 300, and 400 kHz) and pulse lengths (25, 50, and 100 μs). The data acquisition process was repeated after removing half of the plants, to simulate a thinner forest. The giant kelp plants produced evident echoes in the water-column data at all settings. The slant-range signal normalization filter greatly improved the visual quality of the data, but the filtered data may under-represent the true amount of acoustic energy in the water column. Nonetheless, the overall acoustic backscatter measured after filtering was significantly lower, by 2 to 4 dB on average, for data acquired over the thinned forest compared to the original experiment. We discuss the implications of these results for the potential use of multibeam echosounder water-column data in marine habitat mapping.