Maps that depict the distribution of substrate, habitat or biotope types on the seabed are in increasing demand by marine ecologists and spatial planners, underpinning decision making in relation to marine spatial planning and marine protected area network design. Yet, the science discipline of image-based seabed mapping has not fully matured and rapid progress is needed to improve the reliability and accuracy of maps. To speed up the process we have conducted a literature review of common practices in terrestrial image classification based on remote sensing data, a related discipline, albeit with a larger scientific community and longer history. We identified the following key elements of a mapping workflow: (i) Data pre-processing, (ii) Feature extraction, (iii) Feature selection, (iv) Classification, (v) Post-classification enhancements, and (vi) Evaluation of classification performance. Insights gained from the review served as a baseline against which recent seabed mapping studies were compared. In this way we identified knowledge gaps and propose modifications to the mapping workflow. A main concern in current seabed mapping practice is that a large amount of often correlated predictor features is extracted, creating a multidimensional feature space. To effectively fill this space with an appropriate amount of training samples is likely to be impossible. Hence, it is necessary to reduce the dimensionality of the feature space via data transformation [e.g. principal component analysis (PCA)] or feature selection and remove correlated features. We propose to make dimensionality reduction an integral part of any mapping workflow. We also suggest to adopt recommendations for accuracy assessment originally drawn up for terrestrial land cover mapping. These include the publication of two or more measures of accuracy including overall and class-specific metrics, publication of associated confidence limits and the provision of the error matrix.

The application of a biological traits analysis, in the present study, has allowed benthic habitat sensitivities and their risk of impact to be mapped at a spatial scale appropriate for the assessment of the North Sea ecoregion. This study considered habitat impacts associated with five important marine sectors; bottom fishing, marine aggregate dredging, sediment disposal, renewable energy devices (tidal, waves, and wind) and the oil and gas sectors, both individually and cumulatively. The significance of the “actual” footprint of impact arising from these human activities and their associated pressures (sediment abrasion, sediment removal, smothering, and placement of hard structures) is presented and discussed. Notable differences in sensitivity to activities are seen depending on habitat type. Some of the more substantial changes in benthic habitat function evaluated are potentially associated with the placement of hard structures in shallow mobile sedimentary habitats, which result in a shift in habitat dominated by small, short-living infaunal species, to a habitat dominated by larger, longer-lived, sessile epibenthic suspension feeders. In contrast, the impacts of bottom fishing, dredging and disposal activities are all assessed to be most severe when executed in deep, sedimentary habitats. Such assessments are important in supporting policies (e.g. spatial planning) directed towards ensuring sustainable “blue-growth,” through a better understanding of the potential ecological impacts associated with human activities operating across different habitat types. The aim of this study is to provide a better understanding of the spatial extent of selected human activities and their impacts on seabed habitats using a biological trait-based sensitivity analysis.

Summary: To generate realistic predictions, species distribution models require the accurate coregistration of occurrence data with environmental variables. There is a common assumption that species occurrence data are accurately georeferenced; however, this is often not the case. This study investigates whether locational uncertainty and sample size affect the performance and interpretation of fine‐scale species distribution models. This study evaluated the effects of locational uncertainty across multiple sample sizes by subsampling and spatially degrading occurrence data. Distribution models were constructed for kelp (Ecklonia radiata), across a large study site (680 km²) off the coast of southeastern Australia. Generalized additive models were used to predict distributions based on fine‐resolution (2·5 m cell size) seafloor variables, generated from multibeam echosounder data sets, and occurrence data from underwater towed video. The effects of different levels of locational uncertainty in combination with sample size were evaluated by comparing model performance and predicted distributions. While locational uncertainty was observed to influence some measures of model performance, in general this was small and varied based on the accuracy metric used. However, simulated locational uncertainty caused changes in variable importance and predicted distributions at fine scales, potentially influencing model interpretation. This was most evident with small sample sizes. Results suggested that seemingly high‐performing, fine‐scale models can be generated from data containing locational uncertainty, although interpreting their predictions can be misleading if the predictions are interpreted at scales similar to the spatial errors. This study demonstrated the need to consider predictions across geographic space rather than performance alone. The findings are important for conservation managers as they highlight the inherent variation in predictions between equally performing distribution models, and the subsequent restrictions on ecological interpretations.

Sediment maps developed from categorical data are widely applied to support marine spatial planning across various fields. However, deriving maps independently of sediment classification potentially improves our understanding of environmental gradients and reduces issues of harmonising data across jurisdictional boundaries. As the groundtruth samples are often measured for the fractions of mud, sand and gravel, this data can be utilised more effectively to produce quantitative maps of sediment composition. Using harmonised data products from a range of sources including the European Marine Observation and Data Network (EMODnet), spatial predictions of these three sediment fractions were generated for the north-west European continental shelf using the random forest algorithm. Once modelled these sediment fraction maps were classified using a range of schemes to show the versatility of such an approach, and spatial accuracy maps were generated to support their interpretation. The maps produced in this study are to date the highest resolution quantitative sediment composition maps that have been produced for a study area of this extent and are likely to be of interest for a wide range of applications such as ecological and biophysical studies.

The ocean floor, its species and habitats are under pressure from various human activities. Marine spatial planning and nature conservation aim to address these threats but require sufficiently detailed and accurate maps of the distribution of seabed substrates and habitats. Benthic habitat mapping has markedly evolved as a discipline over the last decade, but important challenges remain. To test the adequacy of current data products and classification approaches, we carried out a comparative study based on a common dataset of multibeam echosounder bathymetry and backscatter data, supplemented with groundtruth observations. The task was to predict the spatial distribution of five substrate classes (coarse sediments, mixed sediments, mud, sand, and rock) in a highly heterogeneous area of the south-western continental shelf of the United Kingdom. Five different supervised classification methods were employed, and their accuracy estimated with a set of samples that were withheld. We found that all methods achieved overall accuracies of around 50%. Errors of commission and omission were acceptable for rocky substrates, but high for all sediment types. We predominantly attribute the low map accuracy regardless of mapping approach to inadequacies of the selected classification system, which is required to fit gradually changing substrate types into a rigid scheme, low discriminatory power of the available predictors, and high spatial complexity of the site relative to the positioning accuracy of the groundtruth equipment. Some of these issues might be alleviated by creating an ensemble map that aggregates the individual outputs into one map showing the modal substrate class and its associated confidence or by adopting a quantitative approach that models the spatial distribution of sediment fractions. We conclude that further incremental improvements to the collection, processing and analysis of remote sensing and sample data are required to improve map accuracy. To assess the progress in benthic habitat mapping we propose the creation of benchmark datasets.