Semiautomated Mapping of Benthic Habitats and Seagrass Species Using a Convolutional Neural Network Framework in Shallow Water Environments

Mapping seagrasses on the basis of Sentinel-2 images under tidal change

Tidal variations make the water bodies in satellite remote sensing images on different shooting dates have different inundation ranges and depths. Although the underwater substrates do not change, the spectral properties differ due to attenuation effects. These differences have an impact on the results when multi-temporal remote sensing images are used to analyze seagrasses. This paper proposes a remote sensing mapping method for seagrasses taking the tidal influence, using the seagrasses growth area in Xincun Bay, Hainan Province, China as a case study. a) The seagrasses growth area was determined from remote sensing images. The seagrasses were divided into two types: the seagrasses exposed to water surface or tidal flats (non-submerged seagrasses) and the seagrasses submerged in water (submerged seagrasses). b) The spectral features of seagrasses in Sentienl-2 image were analyzed. We found that the spectral characteristics of non-submerged seagrasses were similar to terrestrial vegetation and these seagrasses could be extracted by using NDVI. The submerged seagrasses spectral was different, forming a reflection peak at the first vegetation red edge band (i.e.705 nm) in Sentinel-2 images. This reflection peak was used to design the Submerged Seagrasses Identification Index (SSII) for extracting underwater seagrass. c) The extraction results of non-submerged seagrasses and submerged seagrasses were merged to map the seagrasses in the study area. The experimental results show that the mapping method proposed in this study can fully consider the influence of tidal changes in remote sensing images on seagrasses identification. The SSII constructed based on Sentinel-2 images extracted submerged seagrasses effectively. This study will provide references to remote sensing mapping of seagrasses and integrated ecological management in coastal zones.

Machine-Learning for Mapping and Monitoring Shallow Coral Reef Habitats

Mapping and monitoring coral reef benthic composition using remotely sensed imagery provides a large-scale inference of spatial and temporal dynamics. These maps have become essential components in marine science and management, with their utility being dependent upon accuracy, scale, and repeatability. One of the primary factors that affects the utility of a coral reef benthic composition map is the choice of the machine-learning algorithm used to classify the coral reef benthic classes. Current machine-learning algorithms used to map coral reef benthic composition and detect changes over time achieve moderate to high overall accuracies yet have not demonstrated spatio-temporal generalisation. The inability to generalise limits their scalability to only those reefs where in situ reference data samples are present. This limitation is becoming more pronounced given the rapid increase in the availability of high temporal (daily) and high spatial resolution (<5 m) multispectral satellite imagery. Therefore, there is presently a need to identify algorithms capable of spatio-temporal generalisation in order to increase the scalability of coral reef benthic composition mapping and change detection. This review focuses on the most commonly used machine-learning algorithms applied to map coral reef benthic composition and detect benthic changes over time using multispectral satellite imagery. The review then introduces convolutional neural networks that have recently demonstrated an ability to spatially and temporally generalise in relation to coral reef benthic mapping; and recurrent neural networks that have demonstrated spatio-temporal generalisation in the field of land cover change detection. A clear conclusion of this review is that existing convolutional neural network and recurrent neural network frameworks hold the most potential in relation to increasing the spatio-temporal scalability of coral reef benthic composition mapping and change detection due to their ability to spatially and temporally generalise.

Regional High-Resolution Benthic Habitat Data from Planet Dove Imagery for Conservation Decision-Making and Marine Planning

High-resolution benthic habitat data fill an important knowledge gap for many areas of the world and are essential for strategic marine conservation planning and implementing effective resource management. Many countries lack the resources and capacity to create these products, which has hindered the development of accurate ecological baselines for assessing protection needs for coastal and marine habitats and monitoring change to guide adaptive management actions. The PlanetScope (PS) Dove Classic SmallSat constellation delivers high-resolution imagery (4 m) and near-daily global coverage that facilitates the compilation of a cloud-free and optimal water column image composite of the Caribbean’s nearshore environment. These data were used to develop a first-of-its-kind regional thirteen-class benthic habitat map to 30 m water depth using an object-based image analysis (OBIA) approach. A total of 203,676 km2 of shallow benthic habitat across the Insular Caribbean was mapped, representing 5% coral reef, 43% seagrass, 15% hardbottom, and 37% other habitats. Results from a combined major class accuracy assessment yielded an overall accuracy of 80% with a standard error of less than 1% yielding a confidence interval of 78–82%. Of the total area mapped, 15% of these habitats (31,311.7 km2) are within a marine protected or managed area. This information provides a baseline of ecological data for developing and executing more strategic conservation actions, including implementing more effective marine spatial plans, prioritizing and improving marine protected area design, monitoring condition and change for post-storm damage assessments, and providing more accurate habitat data for ecosystem service models.