No abstract

focus to leverage long term sustained funding. The next 10 years will be "make or break" for many ocean systems. The decadal challenge is to develop the governance and cooperative mechanisms to harness emerging information technology to deliver on the goal of generating the information and knowledge required to sustain oceans into the future.

Data from real-time sensor networks along the Great Barrier Reef (GBR) over the 2015-2016 austral summer showed that reef water temperatures exceeded empirical coral bleaching thresholds at a number of sites. Temperatures in the southern GBR were within historically normal limits with temperatures below the empirical bleaching threshold. The central GBR just reached the empirical bleaching threshold while, in the north, Lizard Island recorded four consecutive days above the bleaching threshold. Thursday Island in the far northern GBR experienced 10 days above the bleaching threshold. The in situ data predicted only slight bleaching in the southern GBR, moderate bleaching in the central GBR, widespread bleaching in the north and severe bleaching in the far north, which compares well with the initial survey data. Peak temperatures occurred later in the year in the north (mid-March 2016) than in the south (early February 2015) with temperatures remaining above the long-term mean well into the austral autumn. Comparison against satellite sea surface temperature data highlighted issues of cloud cover with data only being available for 30-40% of days over the summer. While the agreement with the in situ data was good, the satellite data missed fine-scale events and underestimated the event at Thursday Island.

Background Artificial intelligence (AI) and machine learning (ML) are poised to transform infectious disease testing. Uniquely, infectious disease testing is technologically diverse spaces in laboratory medicine, where multiple platforms and approaches may be required to support clinical decision-making. Despite advances in laboratory informatics, the vast array of infectious disease data is constrained by human analytical limitations. Machine learning can exploit multiple data streams, including but not limited to laboratory information and overcome human limitations to provide physicians with predictive and actionable results. As a quickly evolving area of computer science, laboratory professionals should become aware of AI/ML applications for infectious disease testing as more platforms are become commercially available. Content In this review we: (a) define both AI/ML, (b) provide an overview of common ML approaches used in laboratory medicine, (c) describe the current AI/ML landscape as it relates infectious disease testing, and (d) discuss the future evolution AI/ML for infectious disease testing in both laboratory and point-of-care applications. Summary The review provides an important educational overview of AI/ML technique in the context of infectious disease testing. This includes supervised ML approaches, which are frequently used in laboratory medicine applications including infectious diseases, such as COVID-19, sepsis, hepatitis, malaria, meningitis, Lyme disease, and tuberculosis. We also apply the concept of “data fusion” describing the future of laboratory testing where multiple data streams are integrated by AI/ML to provide actionable clinical knowledge.

The southern Great Barrier Reef (GBR), a region that rarely experiences cyclones, was impacted by tropical cyclone (TC) Hamish in March 2009. We documented on-reef physical and habitat conditions before, during and after the cyclone at One Tree Reef (OTR) using data from environmental sensor instrumentation and benthic surveys. Over 5 years of monitoring, ocean mooring data revealed that OTR experienced large swells (4-8 m) of short duration (10-20 min) not associated with a cyclone in the area. These swells may have contributed to the physical disturbance of benthic biota and decline in coral cover recorded prior to and after TC Hamish. During the cyclone, OTR sustained southeasterly gale force winds ([61.2 km h -1 ) for 18.5 h and swells [6 m in height for 4 h. Benthic surveys of exposed sites documented a 20% drop in live coral cover, 30% increase in filamentous algae cover and the presence of dislodged corals and rubble after the storm. Leeward sites were largely unaffected by the cyclone. Benthic cover did not change in the lagoon sites. Significant rubble movement and infill of the lagoon occurred. Two years after the cyclone, algal cover remained high and laminar corals had not recovered. Total coral cover at impacted sites had continued to decline. Environmental conditions and habitat surveys supported Puotinen's (Int J Geogr Inf Sci 21:97-120, 2007) model for cyclone conditions that cause reef destruction. While TC Hamish had a major impact on the reef, change in benthic cover over several years was due to multiple stressors. This on-reef scale integration of physical and biological data provided a rare opportunity to assess impacts of a major storm and other disturbances, showing the importance of considering multiple stressors (short-lived and sustained) in assessing change to reef habitats.