Oceanographic Research Articles

Water quality monitoring with an early warning system for enhancing the shrimp aquaculture production

Aquaculture provided 43% of the aquatic animal food consumed by humans in 2007, and it is anticipated to expand even more to meet the increasing future demand. Marine Science Techno Park (MSTP) is one of the Techno Parks in Indonesia and is located in Teluk Awur, Jepara. MSTP has an intensive system of Vannamei shrimp farming activities. The challenge that has been faced annually is the organic matter of the remaining shrimp feed that accumulates in the waters can cause a decrease in pond water quality. Ammonia-N anions derived from the decomposition of feed residues can cause toxins in shrimp culture ponds which can further interfere with shrimp survival. The objective of this study is to design a self-controlled water quality monitoring system that is equipped with an early warning system based on internet of things (IoT) and to implement the design for analyzing the water quality including dissolved oxygen (DO), pH, and temperature in the Vannamei farming pond of MSTP UNDIP through integrating IoT which is equipped with an early warning system. If the water quality reaches a threshold value, the monitoring system will send a sound signal to the buzzer followed by sending an alert notification in real-time conditions automatically to a smartphone.

Preface

The purpose of the three-day 2023 2nd International Conference on Acoustics, Fluid Mechanics and Engineering (AFME 2023), held during November 17th to 19th, 2023 in Nanjing, China, was to create a timely forum for multi-disciplinary discussions related to the recent developments on acoustics, fluid mechanics and engineering.Highly eventful program of the Conference, the list of well-established organizations-participants and devoted engagement of many colleagues throughout all the stages of the Conference preparation instill confidence in practical importance of mutual initiative. As usual, the program of the meeting mainly consisted of plenary speeches, invited speeches, oral presentations and poster presentations, discussing significant problems facing technologies related to areas of acoustics, fluid mechanics and engineering, proposing innovative ideas and approaches to solution of the problems, and considering new possibilities of application and development of cutting-edge technology.In the framework of experimental and theoretical approaches, the Conference gathered 150 delegates from all over the world and addressed a number of highly relevant aspects of acoustics, fluid mechanics and engineering. Covering topics on Acoustic Materials, Hydrodynamic Acoustics, Ultrasonics, Physical Chemical Hydrodynamics, Hydromechanical Hydrodynamics, Engineering Fluid Mechanics, etc., the selected contributions of this special issue provide guidance for future interdisciplinary developments. In this way, the multi-scale aspects of acoustics, fluid mechanics and engineering should be considered.We received various manuscripts of invited papers and other contributions presented at the Conference. All of these papers have gone through a rigorous peer review process and are collected in this volume. We would like to thank all the anonymous colleagues who have acted as referees to assess the suitability of the various articles for publication in Journal of Physics: Conference Series. We are confident that the high quality of both invited and contributed papers contained in this Proceedings will be appreciated by relevant communities.We would like to express our thanks to all the authors for their time and genuine contributions, and to the reviewers for their fruitful comments during the preparation of this volume. We also acknowledge the support provided in various ways by Guangdong University of Technology, Dalian Maritime University, School of Marine Science and Technology, Northwestern Polytechnical University, and University of Toronto.List of Committee Member is available in this pdf.

A Tool to Characterize Learning Objectives in Marine Science Education: Marine Science Learning Objectives Tool (MS-LOT)

Effective marine science teaching starts with well-written, measurable learning objectives that define outcomes for learners, inform instruction, and guide assessment. Yet, there are few resources to help marine science educators write effective learning objectives. To address this need, we created an evidence-based Marine Science Learning Objectives Tool (MS-LOT) to help marine educators evaluate their learning objectives. MS-LOT considers two critical aspects of learning objectives in marine science education: focus and assessment. As a case study, University of Georgia (UGA) Marine Extension and Georgia Sea Grant educators used MS-LOT to analyze their 207 learning objectives for 5th–12th grade educational programs. Findings revealed 1) gaps in content, science practices, and affective outcomes in instruction, 2) a focus on low-cognitive level outcomes, and 3) unmeasurable learning objectives. We respond to issues uncovered from the analysis and detail how MS-LOT will be useful for all marine educators, especially those working with K-12 learners.

Emerging underwater survey technologies: A review and future outlook

Emerging underwater survey technologies are revolutionizing the way we explore and understand the underwater world. This review examines the latest advancements in underwater survey equipment, highlighting their operational benefits and potential areas for future development. Recent developments in underwater survey technologies have led to significant improvements in accuracy, efficiency, and data quality. Advanced sonar systems, such as multibeam and sidescan sonars, provide high-resolution images of the seafloor, allowing for detailed mapping of underwater features. Autonomous underwater vehicles (AUVs) equipped with sophisticated sensors and cameras enable precise data collection in challenging environments, such as deep-sea areas or complex underwater structures. The operational benefits of these technologies are vast. They allow for faster surveying, reduced costs, and improved safety for personnel. Additionally, the high-quality data obtained from these surveys can lead to better decision-making in various industries, including offshore energy, marine research, and underwater archaeology. Looking ahead, the future of underwater survey technologies is promising. There is a growing interest in developing integrated systems that combine multiple sensors and data processing capabilities to provide a more comprehensive view of underwater environments. Artificial intelligence and machine learning algorithms are also being increasingly utilized to analyze large datasets and extract valuable insights. However, several challenges remain, such as the need for better underwater communication systems, improved battery life for autonomous vehicles, and enhanced data processing capabilities. Addressing these challenges will be crucial for the continued advancement of underwater survey technologies. In conclusion, the latest advancements in underwater survey technologies offer exciting opportunities for enhancing our understanding of the underwater world. By leveraging these technologies and addressing key challenges, we can unlock new possibilities for underwater exploration and research.

A Review of Pacific Salmon Hatcheries in British Columbia, Canada, and Interactions With Natural Populations

Pacific salmon Oncorhynchus spp. hatcheries in British Columbia (BC) have been the major activity of the Salmonid Enhancement Program since 1977. However, the present diminished abundance of Pacific salmon and loss of fisheries in BC called for a review of hatchery effectiveness. The Pacific Salmon Foundation conducted a review resulting in 15 reports publicly available on the Pacific Salmon Foundation marine science website. The review includes evaluations of effectiveness of hatchery production, evidence of interactions with natural salmon populations (including rebuilding natural populations with hatchery‐produced salmon), and future opportunities via genomics. Beyond the estimation of juvenile production and contribution to catches and spawning escapements, the ability to assess effectiveness was limited. The assessments of interactions provided a few examples of positive outcomes, but most were negative. The lack of comparative assessments in purely wild populations seriously limits interpretations of hatchery–wild interactions. Future evaluations of the hatchery effectiveness require more quantitative and integrated assessments of hatchery and wild salmon, open data sharing for public review or research, and related studies could benefit from application of new genomic technologies. This paper presents recommendations to address these needs and calls for regularized reviews of the Salmonid Enhancement Program and its net value to sustainability of BC's Pacific salmon.

Assessment of mariculture-derived microplastic pollution in Dapeng Cove, China

Marine microplastic pollution just as ocean acidification and greenhouse effect has attracted much environmental concern and become a hot research subject for marine researchers globally. The abundances, distribution, and characteristics of microplastics in surface seawater and sediments from Dapeng Cove were investigated in this study. The results indicated that the abundance of microplastics was 1333 ± 773 items/m3 in surface seawater and 1381 ± 1021 items/kg in sediments, showing a medium microplastic pollution level compared with other sea areas. Fibers were the prevailing shapes of microplastics in both surface seawater and sediments, representing 65.4% and 52.1% of the total microplastic numbers, respectively. Moreover, small microplastics (<1mm) in surface seawater and sediments accounted for 69.6% and 62.2%, respectively. According to the identification by Fourier Transform Infrared microscope (micro-FTIR), the main composition of microplastics in surface seawater and sediments was polyethylene (PE) or polypropylene (PP). It is necessary to enhance the regulation of current plastic products used in aquaculture, reduce the production and release of microplastics during the mariculture process, and develop alternatives to plastic fishing gear. The results of this study suggested that long-term mariculture development had caused the accumulation of a large amount of microplastics in water and sediments in Dapeng Cove. We constructed the first basic data of microplastics pollution about Dapeng Cove. This study will serve as a reference for further studies of the distribution and migration of microplastics in mariculture zones.

Climate Variability of Air Temperature and Its Warming Trends in the Arabian Gulf

Over a 41-year period (1979–2019), the climate of the Arabian Gulf (Gulf) exhibited notable variability. This variation, influenced by mesoscale and globalscale meteorological and climatic determinants, showed temperature fluctuations, predominantly in the Northern Gulf (N Gulf). The N Gulf recorded an average temperature of 25.9 °C, a noticeable 3 °C higher than the broader Gulf average. This period marked extreme temperature records, with a peak at 53.8 °C in July 2016, paralleling the highest known temperatures in Asia. Data reveals a warming trend (0.1–0.6 °C per decade) in the region, with the N Gulf’s rise surpassing global trends. The years 2014–2019 were notably warmer, impacting overall trends, and 1997 was the transitional year shifting from cooler to warmer climates. The N Gulf’s seasonal dynamics are also transforming, with extended summers and shortened winters. In this study, we employed empirical orthogonal function (EOF) decomposition analysis to examine the interannual to multidecadal fluctuations in air temperature within the Gulf from 1979 to 2019, using hourly air temperature data from the Watch Forcing Dataset (WFDE5) generated from the fifth generation (ERA5) European Centre for Medium-Range Weather Fore-casts (ECMWF). Through this method, we discerned three principal EOF modes, which together accounted for 82% of the air temperature variability in the Gulf, highlighting external influences such as North Atlantic Oscillation (NAO), El Nino-Southern Oscillation (ENSO), and Atlantic Multidecadal Oscillation (AMO). The data for these external influences were sourced from the National Oceanic and Atmospheric Administration (NOAA) Physical Sciences Laboratory. These findings stress the pressing need for detailed climate studies and mitigation strategies for a rapidly warming Gulf region, especially the N Gulf.

Use of Unmanned Surface Vehicles (USVs) in Water Chemistry Studies.

Unmanned surface vehicles (USVs) equipped with integrated sensors are a tool valuable to several monitoring strategies, offering enhanced temporal and spatial coverage over specific timeframes, allowing for targeted examination of sites or events of interest. The elaboration of environmental monitoring programs has relied so far on periodic spot sampling at specific locations, followed by laboratory analysis, aiming at the evaluation of water quality at a catchment scale. For this purpose, automatic telemetric stations for specific parameters have been installed by the Institute of Marine Biological Resources and Inland Waters of Hellenic Centre for Marine Research (IMBRIW-HCMR) within several Greek rivers and lakes, providing continuous and temporal monitoring possibilities. In the present work, USVs were deployed by the Athens Water and Sewerage Company (EYDAP) as a cost-effective tool for the environmental monitoring of surface water bodies of interest, with emphasis on the spatial fluctuations of chlorophyll α, electrical conductivity, dissolved oxygen and pH, observed in Koumoundourou Lake and the rivers Acheloos, Asopos and Kifissos. The effectiveness of an innovative heavy metal (HM) system installed in the USV for the in situ measurements of copper and lead was also evaluated herewith. The results obtained demonstrate the advantages of USVs, setting the base for their application in real-time monitoring of chemical parameters including metals. Simultaneously, the requirements for accuracy and sensitivity improvement of HM sensors were noted, in order to permit full exploitation of USVs' capacities.

We need more oceanography graduates: Phoebe Woodworth‐Jefcoats on increasing opportunities for graduate students

Phoebe Woodworth‐Jefcoats, an oceanographer, collaborated with six other authors to publish a study about their findings on increasing access to oceanography degrees for adult learners. Noting that, “By 2030, the global ocean economy is expected to be twice the size it was in 2010 (OECD, 2016),” the authors write, we will be in critical need of people with “expertise and innovation in the ocean sciences” to “[ensure] this growth is environmentally sustainable.” The article was published in a special issue of Oceanography, focused on “Building Diversity, Equity and Inclusion in the Ocean Sciences.”

Harnessing Deep Learning for Underwater plastic Trash Identification

Abstract—Machine and deep learning (DL) offer significant opportunities for exploring and monitoring oceans and for tackling important problems ranging from litter and oil spill detection to marine biodiversity estimation. Reasonably priced hardware platforms, in the form of autonomous (AUV) and remote operated (ROV) underwater vehicles, are also becoming available, fuelling the growth of data and offering new types of ap- plication areas. This article presents a research vision for DL in the oceans, collating applications and use cases, identifying opportunities, constraints, and open research challenges. We conduct experiments on underwater marine litter detection to demon- strate the benefits DL can bring to underwater envi- ronments. Our results show that integrating DL in underwater explorations can automate and scale-up monitoring, and highlight practical challenges in enabling underwater operations. This project introduces a refined YOLOv8-based algorithm tailored for the en- hanced detection of small-scale underwater debris, to mitigate the prevalent challenges of high miss and false detection rates . The research presents the YOLOv8 algorithm, which optimizes the backbone, neck layer, and C2f module for underwater characteristics and incorporates an effective attention mech- anism. This algorithm improves the accuracy of underwater trash detection while simplifying the computational model. Empirical evidence underscores the superiority of this method over the other conventional network, manifesting in a significant uplift in detection performance. Notably, the proposed method realized a 63% mean average precision (mAP50), a 60% surge in recall (R). Transcending its foundational utility in marine conservation, this methodology harbors potential for subsequent integra- tion into remote sensing ventures. Such an adaptation could substantially enhance the precision of detection models, particularly in the realm of localized surveillance, thereby broad- ening the scope of its applicability and impact.

State of the Art on Fe Precipitation in Porous Media: Hydrogeochemical Processes and Evolving Parameters

The mixing of terrestrial groundwater and seawater creates dynamic reaction zones in intertidal areas, where land-derived Fe(II) is oxidized to Fe(III) and then precipitates as Fe hydroxides at the groundwater–seawater interface. These hydrogeochemical processes contribute to the formation of iron bands at the saltwater wedge (SW) and beneath the upper saline plume (USP). This study provides a comprehensive review of physical and geochemical processes at field scale in coastal areas, explores the impact of mineral precipitation on pore structure at pore scale, and synthesizes reactive transport modeling (RTM) approaches for illustrating continuum-scale soil physio-chemical parameters during the evolution of porous media. Upon this review, knowledge gaps and research needs are identified. Additionally, challenges and opportunities are presented. Therefore, we reach the conclusion that the incorporation of observational data into a comprehensive physico-mathematical model becomes imperative for capturing the pore-scale processes in porous media and their influence on groundwater flow and solute transport at large scales. Additionally, a synergistic approach, integrating pore-scale modeling and non-invasive imaging, is equally essential for providing detailed insights into intricate fluid–pore–solid interactions for future studies, as well as facilitating the development of regional engineering-scale models and physio-chemical coupled models with diverse applications in marine science and engineering.

Detecting changes in seafloor elevation in sandy coastal environments using low-cost opensource tooling

Knowledge of sediment erosion and deposition can be useful for a variety of engineering, marine science, and environmental applications, but collecting detailed time-series measurements of the sediment–water interface can be challenging, particularly in coastal marine environments. We developed economical and open-source sediment level loggers to record sediment–water interface time-series data with accuracy up to 1 cm. The logger is composed of a programmable Circuit-Python (or Arduino) microcontroller and “breakout boards” that attach to a specially designed printed circuit board (PCB) and an array of evenly spaced photoresistors enclosed in a robust waterproof housing. These instruments were paired with temperature sensors in a study off the coast of Charleston, SC in the South Atlantic Bight where heat was used as a tracer to detect the flow of porewater in the permeable coastal sediments. This approach requires accurate knowledge of the depth of temperature sensors relative to the sediment–water interface. In this application, improved knowledge of the elevation of the sediment–water interface elevation data from the sediment level loggers reduced average root mean squared errors in modeling submarine groundwater discharge by as much as 25 %. The sediment level loggers can be easily installed, withstand long deployment times, and provide long-term recording abilities suitable for a range of environments.

Research on model predictive control of autonomous underwater vehicle based on physics informed neural network modeling

In the rapidly evolving field of Autonomous Underwater Vehicles (AUVs), achieving precise control remains a critical endeavor. This study presents a pioneering integration of Model Predictive Control (MPC) with a Physics-Informed Neural Network (PINN), aiming to enhance control system precision and operational efficiency in AUVs. The efficacy of MPC lies in its adept handling of the intricate constraints and inherent nonlinear dynamics intrinsic to AUV systems. Concurrently, the PINN architecture incorporates the fundamental physical laws represented by Partial Differential Equations (PDEs), augmenting the predictive fidelity of the system. Firstly, this research implements the novel PINN-enhanced MPC framework for trajectory tracking and conducts a comparative evaluation against adaptive proportional-integral-derivative (PID) and Gaussian-process-based MPC controllers. This comparative analysis elucidates the advancements in control mechanisms attributable to the PINN integration. Furthermore, this study meticulously assesses the PINN-MPC's proficiency in navigating through static and dynamic obstacles within three-dimensional marine environments, a critical capability for AUV operations. Through extensive and meticulous simulations, the proposed approach demonstrates notable progress in overcoming environmental challenges and executing intricate operational tasks, such as obstacle avoidance, with heightened efficiency and dexterity. This research constitutes a substantial contribution to the theoretical advancement and elucidation of control systems in the AUV domain, bearing profound practical implications. It lays the foundation for the development of increasingly sophisticated, advanced, and reliable AUV missions, signifying a crucial advancement in the realms of underwater exploration and operational technology.

Diatom record the holocene marine facies deposition history in inner bay of Pearl River Estuary, South China

To understand the evolution of river mouth systems under natural and human being forces is a critical task in coastal and marine science studies. We present a new sedimentary record with diatom, grainsize analysis and radiocarbon age dating, recovered from a drilling core in an inner bay of the Pearl River Estuary, South China, in order to describe marine facies depositional history and to examine relative palaeoclimatic and palaeoenvrionmental changes during the Holocene. The occurrence of marine diatoms at ca. 9,000 cal. yr. BP provides marine facies starting point at this core profile in the shoal area, west of the Pearl River Estuary. Three fossil diatom units were distinguished following the early to late Holocene epoch division. The changed diatom bio-facies before and after ca. 8,200 cal. yr. BP, especially in coastal and neritic species relative abundances contrast, offers a diatom floral response to the "8.2 kyr" event. In middle Holocene, enhanced diatom absolute abundances of tropical open-sea water species and increased neritic species number and relative abundances, with more sand fractions, provide evidences of diatom bio-facies response to higher sea-level and strong hydrodynamic clearly. Following the regression, fossil diatom flora experienced a long-term decline after ca. 5,500 cal. yr. BP, until to ca. 1,400 cal. yr. BP. In the past ca. 1,400 years, there has been a clear increase in the absolute abundances and biodiversity of diatoms, along with a greater presence of coarse granularity fractions. This is a strong signal that human activities influenced local environmental change, combined with natural forces.An interesting phenomenon of higher sedimentation rate was observed in three periods as a millennial-scale pulse, at ca. 9,000–8,000 cal. yr. BP, ca. 6,500 - 5,500 cal. yr. BP, and ca. 1,000 - 0 cal. yr. BP. Meanwhile, two periods of lower sedimentation rate over longer time interval occurred during those pulses. Through regional correlation, this study presents a record of deposition after ca. 9,000 cal. yr. BP in Holocene marine facies, provide improved understanding of the west shoal evolution history in Pearl River Estuary, and natural and human being impact on diatom flora and coastal geo-environment in low latitude river mouth systems in Asian Monsoon realm.

Balancing protection and production in ocean conservation

AbstractWith the acceleration of the global biodiversity and climate crises, the need to protect and sustainably manage ocean resources has never been greater. However, the science needed to integrate ocean protection (through marine protected areas and OECMs) and sustainable production in the blue economy (particularly pelagic fisheries) remains underdeveloped and contested. The scientific divide and the knowledge gaps still remaining have created serious real-world challenges for practitioners seeking to reconcile protection and production approaches, and is hindering progress in achieving global conservation targets. Here, we identify the vital science necessary to bring together the “twin pillars” of protection and production, integrating mutually reinforcing meaningful protections at scale, while also driving management of production systems to internationally accepted sustainability standards. The research community must rapidly develop this new horizon of ocean science – particularly in pelagic ecosystems - to aid countries and practitioners in achieving global conservation and sustainable development targets.

Watching the sunrise on our ocean planet in a new era of marine science

Abstract Over the last 30 years, ocean sciences have been undergoing a technological revolution. Changes include the transition of autonomous platforms from being interesting engineering projects to being critical tools for scientists studying a range of processes at sea. My career has benefitted immensely from these technical innovations, allowing me to be at sea (virtually) 365 days a year and operate ocean networks globally. While these technical innovations have opened many research doors, many aspects of oceanography are unchanged. In my experience, working/talking/scheming with scientists is most effective face-to-face. Despite the growing capabilities of robotic platforms, we will still need to go to sea on ships to conduct critical experiments. As the responsibilities of scientists expand with mandated outreach efforts, I strongly urge young scientists to leverage the expertise of Broader Impact professionals, who are increasingly available to our community, in order to maximize the effectiveness and efficiency of our outreach efforts. Given the increasing observations of change occurring in the ocean, our work is ever-more important while still being fun. I am blessed to have had a career as an oceanographer exploring this planet.

Underwater Imagery Enhancement with Multi-Channel Histogram Equalization, Depth-Adaptive Correction, and Deep Reinforcement Learning

Underwater imagery plays a pivotal role in various scientific, industrial, and recreational applications, ranging from marine biology and oceanography to underwater archaeology and resource exploration. However, capturing high-quality images in underwater environments poses unique challenges due to factors such as light attenuation, color distortion, and particulate matter suspended in the water. In recent years, significant advancements have been made in the development of advanced techniques for enhancing underwater imagery aimed at improving perceptual quality, sharpness, and detail preservation. This research explores state-of-the-art enhancement techniques, focusing on multi-channel histogram equalization and depth-adaptive correction in the context of deep reinforcement learning (DRL) and variational autoencoders (VAE). The research presents a comprehensive analysis of the performance of these techniques using numerical metrics such as perceptual quality, sharpness, and detail preservation, derived from experimental evaluations. The findings demonstrate the effectiveness of VAE in enhancing perceptual quality and sharpness, with underwater image dehazing exhibiting commendable results as well. Furthermore, Convolutional Neural Networks (CNN) emerge as a promising approach for detail preservation in underwater images. By advancing the capabilities of underwater image enhancement techniques, this research contributes to the broader goal of unlocking the full potential of underwater exploration and understanding. The findings reveal significant improvements in image quality achieved by these techniques. VAE exhibits the highest perceptual quality scores, averaging around 0.84, with sharpness scores reaching approximately 0.91.

Sea Surface Height Wavenumber Spectrum from Airborne Interferometric Radar Altimeter

The proposed “Guanlan” ocean science satellite, led by China’s Laoshan Laboratory, includes an interferometric radar altimeter (IRA) as a key payload. As an integral part of its development, an airborne IRA experiment was conducted on 6 November 2021, with a flight path of approximately 90 km in the South China Sea. This study investigates the IRA’s ability to observe ocean sea surface height (SSH) across scales ranging from meters to mesoscale. The sea surface height anomaly (SSHA) of the IRA is aligned with the SSHA of the AVISO at scales greater than 30 km, but also demonstrates the ability to capture small-scale SSHA changes in two dimensions. We analyzed wavenumber spectra of SSHA obtained from the airborne IRA, ICESat-2, and SARAL/AltiKa satellite for this region. The results show a good agreement in power spectral density (PSD) levels between ICESat-2, SARAL/AltiKa and IRA at scales larger than 30 km. Within the submesoscale range of 1–10 km, the IRA SSHA spectrum exhibits a distinctly negative slope and the lowest energy level. The minimum PSD level of the IRA fell in the range of 10−4–10−3 m2/cycle/km, at scales around 1 km, which is more than an order of magnitude lower than that of ICESat-2, forming a spectral gap that is in agreement with the theoretical expectation. Furthermore, IRA-derived wave direction and significant wave height matched well with the MFWAM wave data. The results of this study underscore the considerable potential of airborne IRA in capturing SSHA across a range of scales, from oceanic waves to submesoscale.

Developing a hybrid model with multiview learning for acoustic classification of Atlantic herring schools

AbstractAdvances in active acoustic technology have outpaced the ability to process and analyze the data in a timely manner. Currently, scientists rely on manual scrutiny or limited automation to translate acoustic backscatter to biologically meaningful metrics useful for fisheries and ecosystem management. The National Oceanic and Atmospheric Administration Northeast Fisheries Science Center has monitored the Atlantic herring population in the Gulf of Maine and Georges Bank since 1999 due to the stocks' important economic and ecological role for the commercial lobster industry. Manual scrutinization to identify Atlantic herring schools from the water column sonar data is time‐consuming and impractical for large‐scale studies. To automate this process, a hybrid model with multiview learning was proposed for automatic Atlantic herring school detection, which consists of two steps: (1) region‐of‐interest (ROI) detection and (2) ROI classification. The ROI detection step was designed to detect school‐like objects, and the ROI classification step was designed to distinguish Atlantic herring schools from other objects. The co‐training algorithm was employed for multiview learning as well as semi‐supervised learning. Within this framework, single‐view vs. multiview learning and supervised vs. semi‐supervised learning were evaluated and compared. Our results showed that multiview learning can improve the performance of the hybrid model in Atlantic herring school detection, and the utilization of unlabeled data is also helpful when the training set is small. The best‐performed model achieved an F1‐score of 0.804. This new framework provides an efficient and effective tool for automatic Atlantic herring school detection.

Fluorescence patterns and diversity of hydrozoans from Bocas del Toro, Panama

Many metazoans contain molecules capable of fluorescence, the absorption and re-emission of light. Since the anatomical distribution, or patterning, of these molecules is variable across taxa, patterns of fluorescence may serve as a powerful diagnostic tool in taxonomy and ecology. However, species-specific fluorescence patterns among marine invertebrates are poorly understood. Here, we show that hydrozoans have diverse fluorescence patterns, which may result from molecules that are produced intrinsically or obtained from dietary sources. We surveyed hydrozoans including siphonophores, hydromedusae, and hydroids across 5 orders from pelagic and benthic marine environments in Bocas del Toro, Panama. Our findings show that fluorescence patterns are highly prevalent and may vary across hydrozoan species and throughout development. Most of the examined hydrozoan taxa exhibited some form of fluorescence, with variation observed between life stages and body parts. Fluorescence was documented in 88% of hydromedusae (Leptothecata, Anthoathecata, Limnomedusae and Narcomedusae), 50% of hydroid, and 75% of siphonophore taxa that were observed in this study. Our results illustrate how fluorescence patterns may serve as a useful diagnostic tool to explore marine biodiversity, highlighting the need for further documentation of fluorescence patterns across marine diversity and research into the molecules that underlie this phenomenon.