Ecosystem monitoring is central to effective management, where rapid reporting is essential to provide timely advice. While digital imagery has greatly improved the speed of underwater data collection for monitoring benthic communities, image analysis remains a bottleneck in reporting observations. In recent years, a rapid evolution of artificial intelligence in image recognition has been evident in its broad applications in modern society, offering new opportunities for increasing the capabilities of coral reef monitoring. Here, we evaluated the performance of Deep Learning Convolutional Neural Networks for automated image analysis, using a global coral reef monitoring dataset. The study demonstrates the advantages of automated image analysis for coral reef monitoring in terms of error and repeatability of benthic abundance estimations, as well as cost and benefit. We found unbiased and high agreement between expert and automated observations (97%). Repeated surveys and comparisons against existing monitoring programs also show that automated estimation of benthic composition is equally robust in detecting change and ensuring the continuity of existing monitoring data. Using this automated approach, data analysis and reporting can be accelerated by at least 200x and at a fraction of the cost (1%). Combining commonly used underwater imagery in monitoring with automated image annotation can dramatically improve how we measure and monitor coral reefs worldwide, particularly in terms of allocating limited resources, rapid reporting and data integration within and across management areas.

Coral reefs are among the most diverse and iconic ecosystems on Earth, but a range of anthropogenic pressures are threatening their persistence. Owing to their remoteness, broad spatial coverage and cross-jurisdictional locations, there are no high-resolution remotely sensed maps available at the global scale. Here we present a framework that is capable of mapping coral reef habitats from individual reefs (~200 km 2) to entire barrier reef systems (200 000 km 2) and across vast ocean extents (>6 000 000 km 2). This is the first time this has been demonstrated using a consistent and transparent remote sensing mapping framework. The ten maps that we present achieved good accuracy (78% mean overall accuracy) from multiple input image datasets and training data sources, and our framework was shown to be adaptable to either benthic or geomorphic reef features and across diverse coral reef environments. These new generation high-resolution map data will be useful for supporting ecosystem risk assessments, detecting change in ecosystem dynamics and targeting efforts to monitor local-scale changes in coral cover and reef health.

No abstract

Karimunjawa National Park is one of Indonesia’s oldest established marine parks. Coral reefs across the park are being impacted by fishing, tourism and declining water quality (local stressors), as well as climate change (global pressures). In this study, we apply a multivariate statistical model to detailed benthic ecological datasets collected across Karimunjawa’s coral reefs, to explore drivers of community change at the park level. Eighteen sites were surveyed in 2014 and 2018, before and after the 2016 global mass coral bleaching event. Analyses revealed that average coral cover declined slightly from 29.2 ± 0.12% (Standard Deviation, SD) to 26.3 ± 0.10% SD, with bleaching driving declines in most corals. Management zone was unrelated to coral decline, but shifts from massive morphologies toward more complex foliose and branching corals were apparent across all zones, reflecting a park-wide reduction in damaging fishing practises. A doubling of sponges and associated declines in massive corals could not be related to bleaching, suggesting another driver, likely declining water quality associated with tourism and mariculture. Further investigation of this potentially emerging threat is needed. Monitoring and management of water quality across Karimunjawa may be critical to improving resilience of reef communities to future coral bleaching.

Our ability to completely and repeatedly map natural environments at a global scale have increased significantly over the past decade. These advances are from delivery of a range of on-line global satellite image archives and global-scale processing capabilities, along with improved spatial and temporal resolution satellite imagery. The ability to accurately train and validate these global scale-mapping programs from what we will call “reference data sets” is challenging due to a lack of coordinated financial and personnel resourcing, and standardized methods to collate reference datasets at global spatial extents. Here, we present an expert-driven approach for generating training and validation data on a global scale, with the view to mapping the world’s coral reefs. Global reefs were first stratified into approximate biogeographic regions, then per region reference data sets were compiled that include existing point data or maps at various levels of accuracy. These reference data sets were compiled from new field surveys, literature review of published surveys, and from individually sourced contributions from the coral reef monitoring and management agencies. Reference data were overlaid on high spatial resolution satellite image mosaics (3.7 m × 3.7 m pixels; Planet Dove) for each region. Additionally, thirty to forty satellite image tiles; 20 km × 20 km) were selected for which reference data and/or expert knowledge was available and which covered a representative range of habitats. The satellite image tiles were segmented into interpretable groups of pixels which were manually labeled with a mapping category via expert interpretation. The labeled segments were used to generate points to train the mapping models, and to validate or assess accuracy. The workflow for desktop reference data creation that we present expands and up-scales traditional approaches of expert-driven interpretation for both manual habitat mapping and map training/validation. We apply the reference data creation methods in the context of global coral reef mapping, though our approach is broadly applicable to any environment. Transparent processes for training and validation are critical for usability as big data provide more opportunities for managers and scientists to use global mapping products for science and conservation of vulnerable and rapidly changing ecosystems.