Multiple Marine Research Articles

Integrating AI and climate change scenarios for multi-risk assessment in the coastal municipalities of the Veneto region.

Global climate is experiencing exceptional warming, leading to a rise in extreme events worldwide. Coastal regions are particularly vulnerable to climate change (CC), due to dense populations, interconnected economies, and fragile ecosystems. These areas face escalating risks as CC intensifies the severity and frequency of extreme weather phenomena, like heavy precipitation, sea-level rise (SLR), storm surges. Integrated approaches are crucial to assess the combined impacts of atmospheric and marine hazards at the land-sea interface. Machine Learning (ML) offer innovative solutions to analyse multi-risk events, leveraging large and heterogeneous datasets and modelling complex, non-linear interactions. This study introduces a two-tier ML approach to estimate risks associated with extreme weather events for the Veneto coastal municipalities under current and future scenarios. The model, tested and validated with present-day data, showed satisfactory performance (error margin ∼20%). The model was applied to mid-term (until 2045) and long-term (until 2100) periods under different CC scenarios, represented by various Representative Concentration Pathways (RCP). Mid-term analysis reveals an increasing risk trend, driven by SLR under RCP8.5, underscoring the significance of considering non-linear interactions between multiple marine and atmospheric hazards. Long-term analysis highlights how future risks depend mainly on precipitation and SLR across the analysed CC scenarios (RCP2.6/4.5/8.5). Results indicate a gradual increase in the expected annual risk trend, with RCP8.5 scenario showing the most severe outcomes. By 2100, the risks under RCP8.5 are projected to be ten times higher than those observed during the historical period, highlighting the importance of developing effective strategies to address these challenges.

A collision avoidance decision-making method for multiple marine autonomous surface ships based on P3DL-PPO algorithm

A collision avoidance decision-making method for multiple marine autonomous surface ships based on P3DL-PPO algorithm

Depositional Environment Conditions and Organic Matter Enrichment Mechanism of the First Member of Upper Cretaceous Qingshankou Formation in the Heiyupao Depression, Northern Songliao Basin

The first member of the Qingshankou Formation (Qing Member 1) is rich in oil and gas resources and represents the first lacustrine transgression period, during which the lake basin area reached its maximum. This study utilizes major and trace element analyses, along with pyrolysis, to investigate the sedimentary environment and mechanisms of organic matter enrichment in the hydrocarbon source rocks of the Heiyupao Depression Qing Member 1. The results indicate that the hydrocarbon source rocks in this area exhibit good to excellent organic richness, mainly comprising Type I and Type II1 organic matter, and are at a high stage of maturity. Furthermore, the paleoclimate conditions during the Qing Member 1 period in the study area were characterized by a warm and humid climate, with an open lake basin and freshwater to brackish water conditions. The water was low in oxygen, suboxic to anoxic, and had relatively high primary productivity. Multiple marine transgressions occurred during the Qing Member 1, transporting substantial nutrients into the lake, which promoted algal blooms in the water. The correlation analysis of TOC content in the Qing Member 1 shale and various indicators shows that the enrichment of organic matter in the study area is primarily influenced by paleoproductivity and paleosalinity, while paleoclimate, paleoredox conditions, and paleowater are not the main controlling factors for organic matter enrichment in the area. Organic matter only accumulates under relatively high salinity and paleoproductivity conditions. Event-driven marine transgressions also play an essential role in enhancing paleoproductivity. Therefore, the organic matter enrichment model in the study area is more aligned with a productivity-driven model. Finally, a comprehensive organic matter enrichment model of hydrocarbon source rocks in the Qing Member 1 of the Heiyupao Depression is proposed.

Vibrio alginolyticus is the pathogen of "Baotou" disease causing serious damage to Gracilariopsis lemaneiformis cultivation in China.

In recent years, a disease called "Baotou" has been causing large-scale yield reductions of Gracilariopsis lemaneiformis in China. Interestingly, Vibrio alginolyticus, which once reported to be a probiotic or pathogen for multiple marine organisms, was strongly proved to be the pathogen causing "Baotou" disease in this study. Analysis of 16S rRNA gene profiling revealed that V. alginolyticus was the most abundant and dominant bacterium on the algal thalli suffering from "Baotou" disease, whereas its presence was scarcely detected on healthy thalli. Scanning electron microscope (SEM) analysis revealed that a large number of V. alginolyticus cells were found to be attached to the algal thalli with "Baotou" disease and the rotten thalli acquired by the lab infection treatment. V. alginolyticus could cause the rotten symptoms which were consistent with those of "Baotou" disease. According to Koch's postulates, V. alginolyticus was identified as the pathogen causing "Baotou" disease.IMPORTANCEA highly contagious disease known as "Baotou" disease has persistently triggered significant yield reductions in G. lemaneiformis throughout China. The pathogen of "Baotou" disease was isolated and identified as V. alginolyticus in this study. Interestingly, V. alginolyticus was once reported to be a probiotic to Saccharina japonica, and pathogen to Haliotis diversicolor, Paleopneustes cristatus, Ruditapes decussatus, and Litopenaeus vannamei. The study indicates that V. alginolyticus play a significant role in the competition or co-existence between G. lemaneiformis, S. japonica, abalone, sea urchin, bivalve, and shrimp.

A deep learning model for detecting and classifying multiple marine mammal species from passive acoustic data

Underwater passive acoustics is used worldwide for multi-year monitoring of marine mammals. Yet, the large amount of audio recordings raises the need to automate the detection of acoustic events. For instance, the increasing number of Offshore Wind Farms (OWF) raises key environmental and societal issues relating to their impacts on wildlife. In this context, monitoring marine mammals along with information on their acoustic environment throughout the OWF life cycle is crucial. The objective of this study is to evaluate the ability of a single deep learning model to precisely detect and localize, in time and in frequency, the marine mammal sounds over a wide frequency range and classify them by species and sound types.A broadband hydrophone, deployed at the Fécamp OWF (Normandy, France), recorded the underwater soundscape including sounds from marine mammals occurring in the area. To visualize these sounds, 15-s spectrograms were computed. From these images, dolphin (D) and porpoise (P) sounds were manually annotated, including different types of sounds: Click-Trains (DCT, PCT), Buzzes (DB, PB) and Whistles (DW). The spectrograms were then split into five-fold cross-validation datasets, each containing one half of manual annotations and one half of only background noise. A Faster R-CNN model was trained to precisely detect and classify the marine mammal sounds in the spectrograms.Three model output configurations were used: (1) overall detection of marine mammals (presence vs. absence), (2) detection and classification of species (two classes: dolphin, porpoise) and (3) sound types (five classes: DCT, DB, DW, PCT, PB). For the simplest configuration (1) 15.4 % of the spectrogram dataset had detections while missing only 6.6 % of annotated spectrograms. For the more precise configurations, (2) and (3), the mean Average Precision (mAP) achieved were 92.3 % (2) and 84.3 % (3), and the macro average Area under the curve (AUC) 95.7 % (2) and 94.9 % (3).This model will help to speed up the annotation processes, by reducing the spectrogram quantity to be manually analyzed and having time-frequency boxes already drawn. Several model parameters can be adjusted to trade off missed detections and false positives which need to be carefully considered and adapted to the problem. For instance, these adjustments would be particularly relevant depending on the human resources available to manually check the model detections and the criticality of missing marine mammal sounds. These models are promising, ranging from the simple detection of marine mammal presence to precise ecological inferences over the long term.

Bounded Containment Maneuvering Protocols for Marine Surface Vehicles With Quantized Communications and Tracking Errors Constrained Guidance: Theory and Experiment.

A new type of containment maneuvering protocols for multiple marine surface vehicles (MSVs) is developed to follow a parameterized path in this work, where the tracking errors are constrained within finite time and the information needed to be transmitted is quantized during coordination. To achieve containment maneuvering of multiple MSVs, a two-objective coordinated control framework is proposed. For the geometric objective, by developing tan-type barrier Lyapunov functions (BLFs) and extended Lyapunov condition-based finite-time guidance laws, the performance of the parameterized line-of-sight guidance framework, including convergence speed and tracking error constraints, is improved. For the dynamic objective, based on quantized control strategy and smooth saturation functions, novel bounded containment maneuvering protocols are proposed to dramatically alleviate the burden of communications among MSVs and ensure more faster dynamic behavior on tracking the path updating speed. Both theoretical analysis and experimental tests with comparative studies illustrate the validity of the proposed containment maneuvering strategy.

Control of simulated ocean ecosystem indicators by biogeochemical observations

To protect marine ecosystems threatened by climate change and anthropic stressors, it is essential to operationally monitor ocean health indicators. These are metrics synthetizing multiple marine processes relevant to the users of operational services. Here we assess if selected ocean indicators simulated by operational models can be controlled (here meaning constrained effectively) by biogeochemical observations, by using a newly proposed methodological framework. The method consists in firstly screening the sensitivities of the indicators with respect to the initial conditions of the observable variables. These initial conditions are perturbed stochastically in Monte Carlo simulations of one-dimensional configurations of a multi-model ensemble. Then, the models are applied in three-dimensional ensemble assimilation experiments, where the reduction of the ensemble variance corroborates the controllability of the indicators by the observations. The method is applied for ten relevant ecosystem indicators (ranging from inorganic chemicals to plankton production), seven observation types (representing data from satellite and underwater platforms), and an ensemble of five biogeochemical models of different complexity, employed operationally by the European Copernicus Marine Service. We demonstrate that all the indicators are controlled by one or more types of observations. In particular, the indicators of phytoplankton phenology are controlled and improved by the merged observations from the surface ocean colour and chlorophyll profiles. Similar observations also control and reduce the uncertainty of the plankton community structure and production. However, the uncertainty of the trophic efficiency and POC increases when assimilating chlorophyll-a data, though observations were not available to assess whether that was due to a worsen model skill. We recommend that the assessment of controllability proposed here becomes a standard practice in designing operational monitoring, reanalysis and forecast systems, to ultimately provide the users of operational services with more precise estimates of ocean ecosystem indicators.

Under-ice ambient noise and its masking effect on marine mammals in the Arctic

Climate change is changing the pattern of sea ice in the Arctic, which increases underwater ambient sound levels during the ice-covered season. The Arctic is home to multiple marine mammal species, even during the winter, which rely on the underwater acoustic environment for acoustic communication. Thus, climate change may be impacting the ability of these animals to communicate. Under-ice ambient noise is primarily generated by wind acting on the ice surface, rapid temperature changes, and impulsive transient signals resulting from ice cracking and ridging. To characterize under-ice ambient noise, acoustic data were collected from several locations in the western Canadian Arctic in this study. To determine the relationship between the received noise level, and wind speed and ice concentration, correlation analysis was used. For the detection and analysis of broadband transient events in the acoustic data, a spectrogram image processing approach was used. The spectral characteristics of transient events were generated using measurements and a random pulse train model. Furthermore, the wind and ice generated noise components were combined to predict the total ambient noise field in an ice-covered ocean using a wavenumber integral model. Finally, the model together with measurements was used to assess how ice-generated noise can cause communication masking in marine mammals such as ringed seals and bearded seals.

Decoupled terrestrial temperature and hydroclimate during the Plio-Pleistocene in the East Asian monsoonal region

The independent reconstructions of temperature and hydroclimate records are crucial to understanding past changes in Earth's climate. However, the temperature and hydroclimate history of East Asia during the late Cenozoic remains largely unknown. Here, we reconstructed terrestrial temperature and hydroclimate patterns in the East Asian monsoonal regions using GDGTs (glycerol dialkyl glycerol tetraethers) in a sediment core from North China spanning 5.5 million years (Ma). Our data show a decoupled terrestrial temperature and hydroclimate evolution over the past 5.5 Ma. The methylation index of branched GDGTs (brGDGTs), i.e. MBT'5ME-inferred temperature, significantly decreases at ∼2.6 Ma and likely reflects a response to Northern Hemisphere glaciation (NHG), in agreement with multiple marine temperature records. The MBT'5ME temperature record shows a decline of approximately 6.5 °C at around 2.6 Ma, which is larger than the decline recorded in marine sequences. Interestingly, this temperature decline occurs much later than the large GDGT-inferred (i.e., Ri/b and GDGT-0/Cren) increase in rainfall at ∼4.0 Ma, which aligns with the strengthening of Pacific zonal and meridional sea surface temperature (SST) gradients as well as the increased marine-land temperature gradients. Our study thus suggests differing mechanisms driving temperature and hydroclimate evolution in East Asia during the Plio-Pleistocene.

Connecting the dots: Applying multispecies connectivity in marine park network planning

Marine ecosystems are highly dynamic, and their connectivity is affected by a complex range of biological, spatial, and oceanographic factors. Incorporating connectivity as a factor in the planning and management of marine protected areas (MPAs) is important yet challenging. Here, we implemented a novel integrative framework that uses intraspecific genetic and genomic data for multiple marine species to characterise connectivity across a recently established South Australian MPA network. We generated connectivity networks, estimated cross-species concordance of connectivity patterns, and tested the impact of key spatial and oceanographic factors on each species. Connectivity patterns varied markedly among species, but were most correlated among those with similar dispersal strategies. Ordination analyses revealed significant associations with both waterway distances and oceanographic advection models. Notably, waterway distances provided better predictive power in all-species combined analyses. We extended the practical relevance of our findings by employing spatial prioritisation with Marxan, using node values derived from both genetic and geographic connectivity networks. This allowed the identification of several priority areas for conservation, and substantiated the initial decision to employ spatial distance as a proxy for biological connectivity for the design of the South Australian marine park network. Our study establishes a baseline for connectivity monitoring in South Australian MPAs, and provides guidelines for adapting this framework to protected networks elsewhere in the world.

Corrosion evolution and quantitative corrosion monitoring of Q355 steel for offshore wind turbines in multiple marine corrosion zones

Offshore wind turbines operating in harsh marine environments are at risk of corrosion. Thickness loss and perforation caused by corrosion can lead to component failure or structure collapse. An environmental test setup was constructed to simulate various marine corrosion zones. Several experimental studies were conducted on Q355 steel, commonly used in offshore wind turbines. The mass loss and electrochemical properties of the steel specimens were analyzed, including electrochemical impedance spectra and polarization curves. The results indicate that corrosion remains stable in the immersion and tidal zones, whereas corrosion in the splash zone is the most severe, with a corrosion rate as high as 0.70 mm/a. A significant macroscopic corrosion cell effect was observed on the vertical steel strip, accelerating corrosion in the splash zone and at the low tide line. The corrosion product compositions and corrosion morphology of each corrosion zone were characterized and analyzed. Furthermore, a corrosion monitoring sensor based on electromechanical impedance was proposed. A prediction model for the mass loss rate of vertical steel strips was developed based on the conductance peak frequency. This study elucidates the corrosion evolution of wind turbine structural steel and proposes a comprehensive steel corrosion monitoring solution.

Diet variation and trophic impact of weakfish, Cynoscion regalis, within multiple marine habitats of the eastern United States.

Weakfish (Cynoscion regalis) is not federally managed but feeds on species of management and ecological interest. We examined the trophic ecology of weakfish in Chesapeake Bay and the coastal and offshore waters of the eastern United States. For these areas, we determined the dominant prey of weakfish; identified how much diet variation was explained by the factors: season, size class, and year; and quantified prey biomass removed by weakfish from 2007 to 2019. In general, diet composition was mostly dominated by Engraulidae, Osteichthyes (bony fishes), and Mysidacea, and significantly varied by season and size class in Chesapeake Bay and coastal waters, although this was less dramatic in Chesapeake Bay. The total amount of variance explained by the three factors was 23.1% (Chesapeake Bay) and 14.7% (coastal waters), with year not being a significant factor in explaining weakfish diet variation for these areas. Weakfish total prey biomass removal occurred primarily in coastal waters in the fall and small size class (annual mean: approximately 41,038 t; maximum: approximately 63,793 t). Highly opportunistic feeders, weakfish cannibalism also played an essential part of their diet. These results have implications for fisheries and ecosystem management of weakfish when considering ecological interactions in regulatory approaches, such as recruitment and cannibalism, competition with federally managed fishes, and the natural mortality of their prey.

Corals that survive repeated thermal stress show signs of selection and acclimatization.

Climate change is transforming coral reefs by increasing the frequency and intensity of marine heatwaves, often leading to coral bleaching and mortality. Coral communities have demonstrated modest increases in thermal tolerance following repeated exposure to moderate heat stress, but it is unclear whether these shifts represent acclimatization of individual colonies or mortality of thermally susceptible individuals. For corals that survive repeated bleaching events, it is important to understand how past bleaching responses impact future growth potential. Here, we track the bleaching responses of 1,832 corals in leeward Maui through multiple marine heatwaves and document patterns of coral growth and survivorship over a seven-year period. While we find limited evidence of acclimatization at population scales, we document reduced bleaching over time in specific individuals that is indicative of acclimatization, primarily in the stress-tolerant taxa Porites lobata. For corals that survived both bleaching events, we find no relationship between bleaching response and coral growth in three of four taxa studied. This decoupling suggests that coral survivorship is a better indicator of future growth than is a coral's bleaching history. Based on these results, we recommend restoration practitioners in Hawai'i focus on colonies of Porites and Montipora with a proven track-record of growth and survivorship, rather than devote resources toward identifying and cultivating bleaching-resistant phenotypes in the lab. Survivorship followed a latitudinal thermal stress gradient, but because this gradient was small, it is likely that local environmental factors also drove differences in coral performance between sites. Efforts to reduce human impacts at low performing sites would likely improve coral survivorship in the future.

Including Marine-Related Items in the ISSP Environment Module is Important for a More Holistic Measure of Public Environmental Perceptions

In this study, we examine public perceptions of the importance of addressing marine ecosystem problems by including an item (which we treated as a dependent variable) in the Environment IV module of the International Social Survey Programme (ISSP) in New Zealand. Overall importance perception was high (mean rating of 4.44 on a 5-point scale). However, our hypotheses that ratings on ISSP items, which implicitly represent marine stressors (e.g., air pollution, nuclear waste), would be consistently associated with high-importance ratings for addressing marine ecosystem problems were not supported. This observation suggests that perceptions of marine issues are not necessarily underpinned by an understanding of multiple marine stressors. Including compulsory marine-related items in the ISSP could provide a clearer understanding of public perceptions of marine ecosystems and assist in informing public education and communication. This inclusion would offer a valuable global perspective, given that the ISSP is implemented in Western and non-Western countries. The ISSP offers questions on multiple environmental domains, including attitudinal, behavioral, and political and unique demographic questions that would enable in-depth country-comparative analyses of marine-related perceptions not possible in existing international environmental perception surveys.

Heterogeneous marine response during the Toarcian Oceanic Anoxic Event (TOAE): The potential role of storminess

The Toarcian Oceanic Anoxic Event (TOAE; ∼183 Ma) represents an important hyperthermal and deoxygenation event in the Early Jurassic. However, TOAE marine records are spatially heterogeneous with regard to nutrient levels, primary productivity, redox conditions and organic enrichment. This non-uniform response to global hyperwarming is not readily accounted for by local variations in paleogeography, climate, or water depth. Largely overlooked to date is the intensified storm activity that characterized the TOAE, and the role that this may have played in controlling marine responses to that event. A review of TOAE studies from multiple marine environments suggests that storm intensity covaried with paleoceanographic conditions, such as nutrient availability, primary productivity, redox conditions, and organic-rich sedimentation. At mid-paleolatitude sites, relatively weak storm activity during the TOAE induced short-term watermass oxygenation, and marine settings were mainly characterized by enhanced anoxia (even euxinia), water-column stratification, increased primary productivity (fueled by terrestrial runoff and P regeneration in euxinic settings), and organic-rich sedimentation. At low-paleolatitude sites, TOAE storm activity was relatively strong, and contributed to marine environments characterized by oxic to suboxic conditions, reduced water-column stratification, decreased primary productivity (possibly due to limited P regeneration and upwelling), low sedimentary organic content, and locally high oolite abundance. TOAE marine sites at all paleolatitudes exhibit: i) sea-level rise and enhanced continental weathering fluxes linked to an intensified hydrological cycle; ii) reduced dinoflagellate and increased cyanobacterial activity; and iii) low δ15N values (mainly −1‰ to +3‰) linked to enhanced diazotrophic nitrogen fixation. The spatial heterogeneity of the response of TOAE marine systems is difficult to reconcile with scenarios linking increased terrestrial flux to marine eutrophication, primary productivity increase and organic-rich sedimentation. Consequently, we hypothesize that the intensity of storm activity influenced TOAE marine systems, and that this factor can, at least partially, account for heterogeneous patterns of environmental changes at middle versus low paleolatitudes and open versus restricted marine settings. Importantly, increased storm activity can induce pycnocline deepening via vertical water-column mixing, thereby promoting: i) enhanced aerobic degradation of organic matter (low sediment organic matter content) due to a reduced oxygen-minimum zone; ii) less nutrient upwelling from deep waters into the photic zone (nutrient-depleted upper ocean), and iii) blooms of nitrogen-fixing cyanobacteria (low δ15N) and calcification (ooid formation). Thus, the interaction between storminess and pycnocline depth is a potentially important factor affecting marine environmental changes during TOAE. These findings have implications for modern oceans now experiencing climatic warming and intensified tropical storm activity.

Experimental study of a semi-submersible floating wind turbine with aquaculture cages under combined wind and irregular waves

The coordinated and integrated development of multiple marine industries is conducive to achieving efficient utilization of the ocean. Here, a novel semi-submersible floating wind power platform integrated with aquaculture cages is proposed. Then, model tests of the innovative floating wind-aquaculture platform (FWAP) with scaling ratio of 1/40 are carried out. Four sea conditions (below rated, rated, cut out and 50-year sea states) and three incident angles of combined wind and waves (0 deg, 90 deg and 180 deg) are considered in the tests. Correspondingly, three typical motion responses of the FWAP, the acceleration response of the wind turbine and the representative mooring line tension are analyzed. The experimental results show that one obvious response peak is mainly found in the response amplitude operator (RAO) curves for the in-plane motion of the new FWAP, including surge, sway and yaw. While for out-of-plane motions including heave, roll and pitch, the RAO curves show two distinct response peaks. Notably, as the environmental conditions progress from below rated to rated, cut out, and finally to 50-year extreme sea state, the motion response of the FWAP becomes increasingly pronounced. Furthermore, the acceleration of the wind turbine under rated and cut out conditions is significantly large, which can be attributed to the effect of rotor rotation. While the maximum mooring line tension in the FWAP is observed at the 50-year sea state, the maximum average tension occurs at the rated condition. The response power spectra of the new FWAP reveal the presence of multiple frequency components. Additionally, the nets can act as an excited or damping effect on the motion of the FWAP, the acceleration of the wind turbine and the mooring line system, depending on the variation of the sea conditions or the incident angle. This study can provide reference for the design improvement and engineering application of such new FWAP.

A probabilistic time geographic approach to quantifying seabird‐vessel interactions

AbstractAccounting for uncertainty is essential for precautionary approaches to managing seabird bycatch in commercial fisheries. However, there is no existing mechanism to explicitly quantify the uncertainty of seabird‐vessel interactions (i.e. co‐occurrence in space and time). Here we develop a time geographic method to measure the probability of individual birds encountering (co‐occurring within 30 km) and attending (within 5 km) individual fishing vessels. The approach involves creating voxel‐based probabilistic space–time prisms (PSTPs) to model the movements of individual birds and vessels, with trajectory data from bird‐borne GPS devices and vessel Automatic Identification Systems (AIS). We intersected these PSTPs to quantify the probability of interaction between bird‐vessel pairs over time and space. We demonstrate the approach with a case study of interactions of Endangered Toroa (Antipodean Albatross; Diomedea antipodensis antipodensis) with pelagic longline vessels in part of the South Pacific high seas. We found 15 vessels within 150 km and 3 h of two birds, yet interaction occurred with only two of those vessels. We visualised the probability of encounter and attendance over time and space and determined that interactions lasted several hours each (up to 6.2–14.1 h attendance, 20.8–26.1 h encounter for one bird‐vessel pair). Our time geographic approach adds to existing tools to quantify seabird bycatch risk by providing an explicit measure of uncertainty of seabird‐vessel interactions. We provide a flexible methodological pathway and R scripts, the application of which would allow managers to estimate interaction probability for multiple marine species and fisheries, including those with lower‐resolution positional datasets.

Intensive Radiosonde Observations of Environmental Conditions on the Development of a Mesoscale Convective System in the Baiu Frontal Zone

AbstractMesoscale convective systems (MCSs) that occur in the Baiu frontal zone (BFZ) can cause devastating flash floods during early summer in Japan; however, the environmental conditions necessary for their development require further investigation. High‐frequency atmospheric soundings, conducted using multiple marine vessels in the East China Sea on 19 June 2022, captured the detailed environmental conditions pertaining to the development of an MCS within the BFZ. The MCS, which developed rapidly without any remarkable preceding synoptic or mesoscale disturbance in the mid‐ or upper troposphere, caused intense precipitation exceeding 80 mm/hr. The MCS persisted for approximately 6 hr, and it intensified when the influx of nearly saturated air near the sea surface toward a weak surface front overlapped with the influx of free‐tropospheric moist air. The influx of nearly saturated air near the sea surface ensured conditional instability within the lower troposphere. The influx of moist air in the free troposphere contributed to the near‐saturation conditions above the boundary layer, a feature inherent to the BFZ, and played an important role in minimizing the reduction in the buoyancy of air parcels. The results of this study indicate that a better forecast of the horizontal distribution of free tropospheric moist air is beneficial for limiting the potential area of genesis of MCS in the BFZ, and a more comprehensive understanding of the vertical variations in moisture transport contributes to an improved forecast skill for MCS in the BFZ.

Development of machine learning-based shelf-life prediction models for multiple marine fish species and construction of a real-time prediction platform

At least 10 million tons of seafood products are spoiled or damaged during transportation or storage every year worldwide. Monitoring the freshness of seafood in real time has become especially important. In this study, four machine learning algorithms were used for the first time to develop a multi-objective model that can simultaneously predict the shelf-life of five marine fish species at multiple storage temperatures using 14 features such as species, temperature, total viable count, K-value, total volatile basic‑nitrogen, sensory and E-nose-GC-Ms/Ms. as inputs. Among them, the radial basis function model performed the best, and the absolute errors of all test samples were <0.5. With the optimal model as the base layer, a real-time prediction platform was developed to meet the needs of practical applications. This study successfully realized multi-objective real-time prediction with accurate prediction results, providing scientific basis and technical support for food safety and quality.

A spatiotemporal attention-augmented ConvLSTM model for ocean remote sensing reflectance prediction

Remote sensing reflectance (Rrs) is an essential parameter in ocean color remote sensing and a fundamental input for the estimation of ocean color elements. Predicting Rrs has the potential to enable simultaneous prediction of multiple marine environmental parameters, facilitating multi-perspective analysis of marine environmental changes. This paper proposes a spatiotemporal attention-augmented ConvLSTM-based model for ocean Rrs prediction. The developed model can predict Rrs for up to seven days by simultaneously learning spatiotemporal features from time series Rrs and auxiliary environmental variables. According to the experiments, the proposed model achieves optimal performances on Rrs predictions at 443, 488, and 555 nm, with Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE) for the first four prediction days less than 5.6*10-4 sr-1 and 8.6 %, respectively, which are better than the performance of the convolutional neural network (CNN), the LSTM, CNN-LSTM, and the ConvLSTM. The spatial and temporal variations of Rrs are also compared to evaluate the effectiveness of the model, presenting a consistent spatiotemporal pattern between predicted and observed Rrs. We also found that integrating sea surface temperature (SST), photosynthetically available radiation (PAR), and aerosol optical thickness at 869 nm (AOT869) into the model can improve the prediction accuracy in various degrees. This work suggests the proposed deep learning model can predict Rrs for 7 days with a convincing performance, providing critical data and technical support for ocean-related applications, such as algae bloom monitoring.