Explore the vast range of titles available.

Advances in artificial intelligence and machine learning have revolutionised data analysis, including in the field of marine and fisheries sciences. However, many fisheries agencies manage sensitive or proprietary data that cannot be shared externally, which can limit the adoption of externally hosted artificial intelligence platforms. In this study, we develop and evaluate two residual network-based automatic image annotation models to process fishery specific habitat data to support ecosystem-based fisheries management in the Exmouth Gulf Prawn Managed Fishery in Western Australia. Using an extensive dataset of 13,128 manually annotated benthic habitat images, we train a grid-based annotation model and an image-level object detection model. Both models demonstrated high overall accuracy, with the grid-based model achieving 90.8% and the image-level model 92.9%. Patch-wise accuracy of the image-level model was 74.2%, highlighting its ability to classify broader spatial context without requiring point-based labelling. Precision and recall values for both models often exceeded 70% for dominant habitat classes such as unconsolidated substrate, macroalgae, and seagrass. The development of these models supports the potential for cost-effective, robust, and scalable in-house habitat classification for fishery or ecoregion specific habitat data to support timely decision-making. Further, the grid-based model uniquely integrates spatial precision with compatibility to existing manual data workflows, enabling seamless adoption within many existing fisheries monitoring programs. Despite limitations, such as a class imbalanced dataset, both models present a scalable, data secure solution for fisheries management agencies. This study establishes a foundation for integrating artificial intelligence driven image analysis of proprietary fisheries data, to further support responsive, standardised and data-informed decision making.

Globally, coral bleaching has been responsible for a significant decline in both coral cover and diversity over the past two decades. During the summer of 2010-11, anomalous large-scale ocean warming induced unprecedented levels of coral bleaching accompanied by substantial storminess across more than 12° of latitude and 1200 kilometers of coastline in Western Australia (WA). Extreme La-Niña conditions caused extensive warming of waters and drove considerable storminess and cyclonic activity across WA from October 2010 to May 2011. Satellite-derived sea surface temperature measurements recorded anomalies of up to 5°C above long-term averages. Benthic surveys quantified the extent of bleaching at 10 locations across four regions from tropical to temperate waters. Bleaching was recorded in all locations across regions and ranged between 17% (±5.5) in the temperate Perth region, to 95% (±3.5) in the Exmouth Gulf of the tropical Ningaloo region. Coincident with high levels of bleaching, three cyclones passed in close proximity to study locations around the time of peak temperatures. Follow-up surveys revealed spatial heterogeneity in coral cover change with four of ten locations recording significant loss of coral cover. Relative decreases ranged between 22%-83.9% of total coral cover, with the greatest losses in the Exmouth Gulf. The anomalous thermal stress of 2010-11 induced mass bleaching of corals along central and southern WA coral reefs. Significant coral bleaching was observed at multiple locations across the tropical-temperate divide spanning more than 1200 km of coastline. Resultant spatially patchy loss of coral cover under widespread and high levels of bleaching and cyclonic activity, suggests a degree of resilience for WA coral communities. However, the spatial extent of bleaching casts some doubt over hypotheses suggesting that future impacts to coral reefs under forecast warming regimes may in part be mitigated by southern thermal refugia.

Coral reefs face increasing pressures particularly when on the edge of their distributions. The Houtman Abrolhos Islands (Abrolhos) are the southernmost coral reef system in the Indian Ocean, and one of the highest latitude reefs in the world. These reefs have a unique mix of tropical and temperate marine fauna and flora and support 184 species of coral, dominated by Acropora species. A significant La Niña event during 2011 produced anomalous conditions of increased temperature along the whole Western Australian coastline, producing the first-recorded widespread bleaching of corals at the Abrolhos. We examined long term trends in the marine climate at the Abrolhos using historical sea surface temperature data (HadISST data set) from 1900-2011. In addition in situ water temperature data for the Abrolhos (from data loggers installed in 2008, across four island groups) were used to determine temperature exposure profiles. Coupled with the results of coral cover surveys conducted annually since 2007; we calculated bleaching thresholds for monitoring sites across the four Abrolhos groups. In situ temperature data revealed maximum daily water temperatures reached 29.54°C in March 2011 which is 4.2°C above mean maximum daily temperatures (2008-2010). The level of bleaching varied across sites with an average of ∼12% of corals bleached. Mortality was high, with a mean ∼50% following the 2011 bleaching event. Prior to 2011, summer temperatures reached a mean (across all monitoring sites) of 25.1°C for 2.5 days. However, in 2011 temperatures reached a mean of 28.1°C for 3.3 days. Longer term trends (1900-2011) showed mean annual sea surface temperatures increase by 0.01°C per annum. Long-term temperature data along with short-term peaks in 2011, outline the potential for corals to be exposed to more frequent bleaching risk with consequences for this high latitude coral reef system at the edge of its distribution.

The western rock lobster, Panulirus cygnus, is endemic to Western Australia and supports substantial commercial and recreational fisheries. Due to and its wide distribution and the commercial and recreational importance of the species a key component of managing western rock lobster is understanding the ecological processes and interactions that may influence lobster abundance and distribution. Using terrain analyses and distribution models of substrate and benthic biota, we assess the physical drivers that influence the distribution of lobsters at a key fishery site. Using data collected from hydroacoustic and towed video surveys, 20 variables (including geophysical, substrate and biota variables) were developed to predict the distributions of substrate type (three classes of reef, rhodoliths and sand) and dominant biota (kelp, sessile invertebrates and macroalgae) within a 40 km(2) area about 30 km off the west Australian coast. Lobster presence/absence data were collected within this area using georeferenced pots. These datasets were used to develop a classification tree model for predicting the distribution of the western rock lobster. Interestingly, kelp and reef were not selected as predictors. Instead, the model selected geophysical and geomorphic scalar variables, which emphasise a mix of terrain within limited distances. The model of lobster presence had an adjusted D(2) of 64 and an 80% correct classification. Species distribution models indicate that juxtaposition in fine scale terrain is most important to the western rock lobster. While key features like kelp and reef may be important to lobster distribution at a broad scale, it is the fine scale features in terrain that are likely to define its ecological niche. Determining the most appropriate landscape configuration and scale will be essential to refining niche habitats and will aid in selecting appropriate sites for protecting critical lobster habitats.

A spatially explicit understanding of marine benthic habitats is essential for sustainable marine resource management. While advances in remote sensing, acoustic methodologies, geostatistical modelling, and predictive species distribution models have improved our ability to map underwater habitats, selecting the most appropriate approach, particularly in turbid or remote regions, remains challenging. This study was conducted in the protected nursery area of the Exmouth Gulf Prawn Managed Fishery in Western Australia and compared four commonly used “off-the-shelf” mapping techniques. These included satellite remote sensing, acoustic sounding, predictive modelling, and geostatistical interpolation, with each technique evaluated using comprehensive ground-truthing and output confidence matrices. Geostatistical kriging emerged as the most robust method, delivering the highest predictive accuracy, quantifiable confidence, and spatially explicit seasonal habitat maps. These maps delineated submerged aquatic vegetation, including seagrass and macroalgae, at broad spatial scales and captured seasonal shifts in habitat distribution and density. Our findings enhance knowledge of benthic habitats in Exmouth Gulf and underscore that effective marine habitat mapping, particularly in dynamic and turbid environments, cannot rely on remote methods alone. Spatially balanced field data collection at ecologically relevant temporal scales is essential to support sustainable marine resource management.

Natural fluctuations in the abundance and length of targeted fish are often disrupted by acute environmental changes and anthropogenic impacts, particularly fishing pressure. Long-term assessments of targeted fish populations inside and outside areas closed to fishing are often necessary to elucidate these effects, yet few of these studies extend over long time periods. We assessed trends in the abundance and length of six targeted fish species in areas open and closed to fishing on seven occasions spanning a 9-year period (2005–2010 and 2013) at the Houtman Abrolhos Islands, Western Australia. Shallow (8–12 m) and deep (22–26 m) coral-dominated reef sites were sampled across four geographically separated island groups using baited remote underwater stereo-video (stereo-BRUV). Between 2005 and 2010, populations of Lethrinus miniatus, Lethrinus nebulosus, Plectropomus leopardus , and Chrysophrys auratus became increasingly dominated by larger individuals, potentially indicative of an ageing population. Between 2010 and 2013, however, there was a significant increase in the proportion of smaller L. miniatus , L. nebulosus , and P. leopardus in both open and closed areas, reflecting increased recruitment perhaps due to changing environmental conditions associated with a marine heat wave anomaly. This recruitment pulse was not observed for the other species in this study ( Chr. auratus , Choerodon rubescens , and Glaucosoma hebraicum ). Lethrinus miniatus, L. nebulosus, Chr. auratus , and P. leopardus were larger in closed areas relative to open areas; however, they were not more abundant. These complex responses to protection also varied across sampling years for certain species (e.g., P. leopardus ). Monitoring changes over the long-term in areas open and closed to fishing provides a sound basis for separating environmental variability from that associated with fishing mortality, which is crucial for optimising fisheries management.

Monitoring changes in coral cover and composition through space and time can provide insights to reef health and assist the focus of management and conservation efforts. We used a meta-analytical approach to assess coral cover data across latitudes 10-35°S along the west Australian coast, including 25 years of data from the Ningaloo region. Current estimates of coral cover ranged between 3 and 44% in coral habitats. Coral communities in the northern regions were dominated by corals from the families Acroporidae and Poritidae, which became less common at higher latitudes. At Ningaloo Reef coral cover has remained relatively stable through time (∼28%), although north-eastern and southern areas have experienced significant declines in overall cover. These declines are likely related to periodic disturbances such as cyclones and thermal anomalies, which were particularly noticeable around 1998/1999 and 2010/2011. Linear mixed effects models (LME) suggest latitude explains 10% of the deviance in coral cover through time at Ningaloo. Acroporidae has decreased in abundance relative to other common families at Ningaloo in the south, which might be related to persistence of more thermally and mechanically tolerant families. We identify regions where quantitative time-series data on coral cover and composition are lacking, particularly in north-western Australia. Standardising routine monitoring methods used by management and research agencies at these, and other locations, would allow a more robust assessment of coral condition and a better basis for conservation of coral reefs.

Coral reefs face increasing pressures particularly when on the edge of their distributions. The Houtman Abrolhos Islands (Abrolhos) are the southernmost coral reef system in the Indian Ocean, and one of the highest latitude reefs in the world. These reefs have a unique mix of tropical and temperate marine fauna and flora and support 184 species of coral, dominated by Acropora species. A significant La Niña event during 2011 produced anomalous conditions of increased temperature along the whole Western Australian coastline, producing the first-recorded widespread bleaching of corals at the Abrolhos. We examined long term trends in the marine climate at the Abrolhos using historical sea surface temperature data (HadISST data set) from 1900-2011. In addition in situ water temperature data for the Abrolhos (from data loggers installed in 2008, across four island groups) were used to determine temperature exposure profiles. Coupled with the results of coral cover surveys conducted annually since 2007; we calculated bleaching thresholds for monitoring sites across the four Abrolhos groups. In situ temperature data revealed maximum daily water temperatures reached 29.54°C in March 2011 which is 4.2°C above mean maximum daily temperatures (2008-2010). The level of bleaching varied across sites with an average of ~12% of corals bleached. Mortality was high, with a mean ~50% following the 2011 bleaching event. Prior to 2011, summer temperatures reached a mean (across all monitoring sites) of 25.1°C for 2.5 days. However, in 2011 temperatures reached a mean of 28.1°C for 3.3 days. Longer term trends (1900-2011) showed mean annual sea surface temperatures increase by 0.01°C per annum. Long-term temperature data along with short-term peaks in 2011, outline the potential for corals to be exposed to more frequent bleaching risk with consequences for this high latitude coral reef system at the edge of its distribution.