The complex ocean dynamics in the Northwest Pacific high-seas fishing grounds shape phytoplankton communities, which serve as the foundation for commercially pelagic species. This study investigates how mesoscale eddies modulate phytoplankton groups’ structures by analyzing the spatiotemporal evolution of eight phytoplankton functional types (PFTs) from 2014 to 2023. Utilizing high-resolution AI-driven model data (AIGD-PFT) and a normalized radial distance grid (0–2 R), we quantified PFTs concentrations within cyclonic (CE) and anticyclonic (AE) eddies, validated by Biogeochemical Argo (BGC-Argo) and in situ measurements. Results reveal that diatoms and dinoflagellates dominate the region, accounting for 88.7% of phytoplankton with distinct seasonal peaks in spring and autumn, respectively. CE significantly enhance diatom and dinoflagellate concentration, particularly within the 0.4 R–1.2 R dynamic ring, while AE favor the aggregation of picophytoplankton, such as Prochlorococcus, in mid-to-low latitudes. Correlation analysis indicates that diatom abundance is strongly linked to dissolved oxygen and negatively correlated with sea surface height. We conclude that mesoscale eddies drive the spatial remodeling of phytoplankton communities by altering local physical and nutrient conditions. These findings provide a critical ecological context for assessing the habitat distribution and sustainable management of North Pacific fisheries across different trophic levels.

The Eastern Equatorial Pacific hosts complex current systems that generate widespread mesoscale eddies, profoundly shaping primary productivity and marine ecosystems. Using the Angular Momentum Eddy Detection and Tracking Algorithm (AMEDA), this study analyzed spatiotemporal patterns of mesoscale eddies from 2016 to 2021 and their correlation with Dosidicus gigas distribution during March–August each year. A total of 929 anticyclonic eddies (AEs) and 1,047 cyclonic eddies (CEs) were identified. AEs concentrated near the equator, overlapping with the Equatorial Undercurrent and Equatorial Countercurrent, whereas CEs were mainly distributed within 3°–5°S and 3°–5°N, corresponding to the southern and northern equatorial surface currents. Significant differences in D. gigas distribution were observed inside and outside the two eddy types, with abundance markedly higher in AEs than in CEs. The population favored the northeastern eddy core (0–R) of AEs and the northern and southwestern margins (R) of CEs, with peak abundance concentrated at the one-radius (R) edge for both types. Suitable environmental ranges for D. gigas were 25–26°C (SST), 0.1–0.2 m (SSH), 34–36 (SSS), and 0.25–0.30 mg/m3 (CHLA). Dense D. gigas regions within AEs featured low temperature, low salinity, high CHLA, and high SSH, while those within CEs exhibited low SST, low salinity, low CHLA, and high SSH. This study suggests that relatively low temperatures within both eddy types provide suitable thermal habitats for equatorial D. gigas to avoid high surface temperatures, and high SSH in the northern regions of both eddy types enhances mixing efficiency through accelerated currents and upwelling, thereby promoting nutrient aggregation and prey supply. These findings reveal regulatory mechanisms of eddy type, structure, and environmental patterns on D. gigas habitat, offering mesoscale dynamic indicators for fisheries resource prediction in this region.

The Chub mackerel (Scomber japonicus) is a key commercial species in the light purse seine fishery in the Northwest Pacific Ocean. Its distribution is highly sensitive to environmental change, yet the regulatory mechanisms of mesoscale eddies on its aggregation remain poorly understood. To further understand the regulatory mechanisms, this study employed a dataset of mesoscale eddies in the Northwest Pacific Ocean (2014–2021) from AVISO (Archiving, Validation, and Interpolation of Satellite Oceanographic Data), combined with fishery data of Chub mackerel and multi-source environmental data (including chlorophyll-a, temperature and dissolved oxygen at different water layers, sea surface salinity, current velocity, and mixed layer depth). By integrating the Gradient Forest (GF) approach, a Generalized Additive Model (GAM), and a Habitat Suitability Index (HSI) model, we quantitatively analyzed the ecological mechanisms of mesoscale eddies on the distribution of Chub mackerel. A total of 800982 mesoscale eddies were identified in the study area, and cyclonic eddies (CEs) accounted for 52.3

Global oceans have warmed markedly and will continue to do so. Superimposed on this trend are abrupt, persistent decadal regime shifts between warm and cold phases that alter ocean-atmosphere dynamics and reshape ecosystem composition and function. Despite recognition of the increasing risk of irreversible climate tipping points, the past and future evolution of these decadal warm-cold shifts remains unclear. Here, combining observations and simulations, we show a widespread 130-140% increase in the frequency and amplitude of sea surface temperature regime shifts across global Large Marine Ecosystems over the past 150 years, with asymmetries stronger in the Northern Hemisphere. Climate models attribute these trends to anthropogenic warming, which suppresses cold-regime transitions and reinforces warm regimes. Without mitigation, these shifts are projected to rise 130-180% by the late-21st century relative to recent levels, whereas only the lowest-emission scenario could constrain their intensification-except in the Arctic oceans. Further analyses reveal close links between intensified temperature regime shifts and abrupt ecological and fishery changes, showing 21-46% synchrony that is rising, potentially amplifying decadal ecosystem instability and socio economic challenges. From a marine perspective, these findings underscore the urgency of achieving the Paris Agreement's target and the Arctic's marked vulnerability.

In order to explore distribution changes of jumbo flying squid Dosidicus gigas under different emission scenarios in the future, this study established a maximum entropy model to examine the suitable habitats of Dosidicus gigas in different sea areas in the Eastern Pacific in summer, based on seven crucial environmental factors and fishery data. The results showed that the area under the receiver operating characteristic curve (AUC) of the maximum entropy model in each sea area was greater than 0.8, and the actual fishing locations coincided with the suitable habitat range fitted by the model. By comparing the contribution rates of each environment factors, it was found that the impact on the habitat of the D.gigas have regional differences. SSH had the greatest influence on the habitat across all three regions. The optimal habitats of D.gigas under the medium emission scenario (SSP370) and high emission scenario (SSP585) showed the potential optimal habitats of D.gigas in the equatorial and offshore waters of Peru were declining year by year, while that in the coastal waters of Chile showed an increasing trend. The gravity center of the optimum habitat of D.gigas in the equatorial waters moved westward, the gravity center of the optimum habitat in the waters off Peru and off Chile moved to the southwest. Under more severe emission scenarios, these changes in future habitat suitability were even more intense. This pole-ward and westward redistribution in the future could restructure regional squid fisheries and should be explicitly considered in trans-boundary management plans.

Aim: Small pelagic species constitute a critical component of fishery resources in the northwest Pacific Ocean. Understanding the interactions among interspecific relationships, environmental niches, and resource abundance is essential for developing science-based fisheries management. This study aims to investigate the differential habitat responses of small pelagic species in the Northwest Pacific to environmental factors, specifically evaluating the ecological interpretation of interspecific relationships through joint species distribution modelling. Location: The northwest Pacific Ocean. Taxon: Japanese sardine; Chub mackerel; neon flying squid. Methods: This study examined three economically important small pelagic species from the northwest Pacific Ocean: Japanese sardine (Sardinops melanostictus), chub mackerel (Scomber japonicus) and neon flying squid (Ommastrephes bartramii). Using a joint species distribution model (JSDM) and ecological niche theory, we integrated multiple environmental variables to analyse interspecific associations and patterns of synchronous habitat variation among these species. Results: The JSDM accurately predicted suitable habitats for all three species, revealing spatial synchrony in habitat suitability. Notably, a positive interspecific (0.9) association is observed between S. melanostictus and S. japonicus, while both exhibit negative associations (-0.84 and -0.95) with O. bartramii. The breadth of suitable ecological niches for key environmental factors and their corresponding response curves offers ecological insights into these interspecific interactions, confirming the dynamic variations in suitable habitat ranges for these species. Main Conclusions: The interspecific relationships reflected similar species responses to environmental factors and highlighted their occupation of overlapping ecological niches. This consistency in environmental responses may drive synchronised habitat shifts, potentially affecting fluctuations in small pelagic species abundance.

Marine ecosystems exhibit high spatiotemporal heterogeneity, making it crucial to understand the mechanisms sustaining biological hotspots. Ocean fronts shape local biogeochemical processes and have long been recognized as biological hotspots aggregating organisms from phytoplankton to top predators and attracting fisheries (hotspot effects). However, fronts also exhibit pronounced environmental differences between their two sides (barrier effects), and how species and fishery distributions respond to these effects remains poorly understood. By integrating satellite-based front detection with commercial catch records, fishery-independent surveys, and global fishing datasets, we show that fishery distributions across diverse regions and major commercial stocks worldwide respond strongly to barrier effects, exhibiting 15-70% differences in distribution between the frontal warm and cold zones, driven by species-specific local thermal preferences. In contrast, responses to hotspot effects are generally sporadic with only 5-20% differences between frontal and non-frontal zones, and they emerge only when aggregations on one side of fronts offset avoidance on the other. This offset has led earlier studies to conservatively underestimate front-induced fishery variations by 55-75%. Our findings complement the traditional front-induced hotspot paradigm by clarifying the importance of barrier effects and underscore the need to reassess the role of ocean fronts in marine ecosystems.

Coastal land reclamation is widely implemented to support coastal development, yet its effects on microbial indicators in coupled surface water-groundwater systems remain poorly understood. This study examined the spatiotemporal variability of four microbial indicators and their environmental associations using 46 months of monthly monitoring (April 2016-January 2020) in eastern Guanghai Bay, China. Total bacterial counts, fecal coliforms, Escherichia coli, and total coliforms were analyzed using multivariate statistical methods. Surface water exhibited elevated levels of fecal indicators, with consistently higher pollution levels in the Xiaoma River than in the Dama River and clear seasonal variation associated with climatic and hydrological conditions. Groundwater showed pronounced spatial heterogeneity: Wells 1 and 2 exhibited relatively elevated microbial contamination, whereas Well 3 maintained persistently low microbial levels under high-salinity and high-alkalinity conditions. These patterns suggest that reclamation may be associated with groundwater microbial distribution through changes in groundwater transport pathways and hydrochemical conditions, while anthropogenic pressures also played an important role in shaping contamination patterns. These findings offer practical insights for groundwater protection and sustainable management in reclaimed coastal environments.

Argentine shortfin squid (Illex argentinus) is an important fishery species in the southwest Atlantic Ocean. Its abundance is influenced by the marine environment, exhibiting significant spatial clustering, and it is assumed that there is a spatially stationary relationship between I. argentinus and its environment. However, a growing body of research suggests spatial nonstationarity. To investigate the potential spatial nonstationarity between the distribution of I. argentinus and the complex marine environment in the Patagonian Shelf waters, we developed a multiscale geographically weighted regression (MGWR) model. Based on local regression, this model analyzed the relationships between various environmental factors and the catch per unit effort (CPUE) of I. argentinus. The model results revealed significant spatial heterogeneity between I. argentinus CPUE and key environmental factors, including sea surface height (SSH), water temperature at 50 m depth (T50m), chlorophyll-a concentration (Chl-a), and sea surface salinity (SSS). The local regression coefficients of these environmental factors exhibited significant spatial variation, with effects particularly pronounced on the continental slope and in adjacent waters, where both positive and negative influences were observed. Furthermore, compared to the generalized additive model (GAM), the MGWR model provided a better explanation for the local impacts of environmental factors on I. argentinus. This provides evidence that the complex marine dynamic processes in the Patagonian Shelf waters have shaped a spatially heterogeneous marine environment, thereby influencing the distribution and feeding migration of I. argentinus, resulting in spatial nonstationarity between the species and its environment.

Catch per unit effort (CPUE) is a key indicator of fish stock abundance. However, CPUE estimates derived from fishery logbooks are highly susceptible to noise and missing entries, leading to systematic bias in abundance estimation. To address this issue, we developed a comprehensive knowledge-guided machine learning (KGML) framework that incorporates both data preprocessing and model refinement, designed to enhance the accuracy and ecological consistency of spatial CPUE predictions. We applied this framework to neon flying squid (Ommastrephes bartramii) data collected in the Northwest Pacific during 2002–2019, using ocean environmental variables, including sea surface temperature, salinity, height, and chlorophyll-a, as factors for modeling and prediction. Guided by fishery expertise, we first constructed a refined dataset by removing implausible outliers and likely false-zero records. Initial experimental results confirmed that knowledge-guided data cleaning substantially improved model performance. However, subsequent Shapley additive explanations (SHAP) feature contribution analysis revealed spatial information dominated the feature importance rankings to an unreasonable degree, suggesting the model primarily memorized locations. To mitigate this effect, we further introduced a cost-aware loss function in model refinement, assigning a greater weight to the loss incurred by non-zero CPUE samples. The final SHAP analysis validated this refinement strategy, confirming a successful shift in the model's predictive focus from spatial memorization towards environmental drivers. In conclusion, this two-stage KGML approach not only maximized predictive accuracy and robustness but also significantly strengthened species distribution models by ensuring theoretical consistency in feature contributions. This provides a practical and robust framework for improving ecological indicators and supporting ecosystem-based fishery management, particularly in data-limited contexts.

Gadiformes is one of the major taxa in the subarctic seas of the northeast Pacific Ocean, a region with significant high-latitude fishery production. However, little is known about Gadiformes species within these waters. Distribution and abundance fluctuations of Gadiformes are closely linked to shifts in the marine environment, and play a crucial role in maintaining ecosystem structural stability of high-latitude regions. This study examined the community composition and spatiotemporal distribution of Gadiformes in four major subarctic regions within the northeast Pacific (Aleutian Islands, Bering Sea shelf, eastern Bering Sea, and Gulf of Alaska) using bottom trawl survey data from the Alaska Fisheries Science Center (AFSC). Gadiformes diversity was assessed using ecological approaches such as diversity indices and cluster analysis, and the relationship between catch-per-unit-effort (CPUE) of the three dominant species and depth, sea surface temperature, and bottom temperature was examined using a generalized additive model (GAM). A comparative analysis was carried out for the cold years (2010/2011) and warm years (2015/2016) to investigate the influence of bottom water temperature on the dominant species. The results indicated that 13 species of Gadiformes from 4 families and 9 genera were present in these subarctic regions, with the dominant species being Gadus chalcogrammus, G. macrocephalus and Albatrossia pectoralis. Additionally, the distribution and abundance of these dominant species showed clear spatial patchiness, with G. chalcogrammus and G. macrocephalus mainly occurring on the eastern Bering Sea shelf, whereas A. pectoralis was primarily distributed in deeper waters. In addition, A. pectoralis exhibited totally higher abundance than the other two species. The GAM results indicated that bottom water temperature was the most influential variable, followed by depth and spatial location, with nonlinear relationships observed between CPUE and environmental factors. Comparing cold and warm years, the abnormal warming of seawater during the warm years expanded the suitable habitat area for G. chalcogrammus and G. macrocephalus, with increasing abundance, whereas habitat distribution and abundance of A. pectoralis exhibited almost no change. This study provides further understanding of Gadiformes distribution and species response to environmental change in the subarctic seas of the northeast Pacific.

Abstract Mesoscale oceanic fronts are critical hotspots for marine productivity and fisheries, yet the fine‐scale mechanisms linking frontal dynamics to the specific distribution of catches remain poorly understood. This study investigates this link by analyzing a high‐resolution, decade‐long (2009–2021) fishery dataset for neon flying squid ( Ommastrephes bartramii ) in the Northwest Pacific's dynamic Kuroshio‐Oyashio Extension region, particularly within the Oyashio frontal zone. Using a frontal coordinate system and a null model based on simulated fishing operations, we identify a systematic asymmetric catch distribution, with catches 1.6‐fold higher on the warm side of fronts and an optimal fishing offset of approximately 10 km into warmer waters. We propose that the observed pattern reflects three complementary components: thermal habitat, prey‐related productivity, and a geometric amplification associated with frontal inclination. Neon flying squid forage and are captured at night within the upper water column, with approximately 50 m used as a representative nocturnal depth. Because the front is displaced warmward with depth, an aggregation located near or slightly warmward of the 50 m front is represented farther toward the warm side when the catch is recorded at the surface position of the fishing vessel and referenced to the surface SST front. Our findings offer a depth‐dependent perspective grounded in the subsurface structure of oceanic fronts, helping to clarify how predator behavior and subsurface oceanography interact to shape surface catch patterns and informing fisheries applications and ecosystem‐based management in dynamic frontal systems.

The jumbo flying squid Dosidicus gigas is widely distributed throughout the Eastern Pacific Ocean, where it plays a critical role in the marine ecosystem. This squid has high economic value and is an important fishing target for global cephalopod fisheries. At present, D. gigas is strictly regulated through the South Pacific Regional Fisheries Management Organization. As a short-lived squid species, climate variability in combination with certain oceanographic conditions substantially affects its life history, abundance, and habitat distribution. Here, we present a literature review of the fishery status and main life history processes of D. gigas and a summary of its ecological responses to multi-scale climatic and environmental changes. In this review, D. gigas fisheries are examined, with a specific focus on China. Life history of D. gigas including population structure, age growth, migration, reproduction, and feeding are summarized and their relationship with climate clarified. The impacts of climate variability on the spatial and temporal distributions of D. gigas habitats are also reviewed, highlighting the critical impact of climatic and environmental changes on the life history and distribution of D. gigas, which greatly challenges fisheries management. Our findings suggest that adaptive management measures for D. gigas fisheries should be proposed to mitigate and adapt to the effects of climate change. The following steps are suggested: (1) strengthening the monitoring of anomalous climatic events and the assessment of their impacts; (2) strengthening international cooperation to establish a monitoring system for D. gigas abundance in the Eastern Pacific and develop long-term forecasting techniques; (3) developing an assessment model for D. gigas that integrates climatic factors and examines different potential management strategies; (4) increasing awareness and guidance on the impacts of climate change and establishing climate adaptive fisheries management measures.

Mesoscale eddies exert profound influences on marine environments, thereby regulating habitat quality and the distribution of marine organisms. The waters off Chile are a region of intense mesoscale eddy activity and represent a major habitat for the jumbo flying squid (Dosidicus gigas), a short-lived and economically important species. However, the effects of mesoscale eddies on the habitat of D. gigas in this region remain poorly understood. In this study, we integrated autumn (March-May) fisheries data of D. gigas from 2015 to 2021 with environmental variables, including sea surface temperature (SST), chlorophyll-a concentration (Chl-a), and sea surface dissolved oxygen concentration (DO), to develop and validate habitat suitability index (HSI) models with different weighting schemes. Using the optimal HSI model in combination with mesoscale eddy data, we compared the impacts of cyclonic and anticyclonic eddies on D. gigas abundance and habitat suitability. The results revealed that the optimal HSI model effectively predicted the potential habitats of D. gigas, with weights for SIDO, SISST, and SIChl-a of 0.1, 0.1, and 0.8, respectively. Compared with anticyclonic eddies, cyclonic eddies provided broader areas of suitable habitats, characterized by suitable Chl-a and DO levels, and supported higher D. gigas abundances. Furthermore, the habitat suitability of D. gigas within mesoscale eddies exhibited interannual variability and was significantly correlated with the radius, velocity, and amplitude of the eddies. This study highlighted the critical role of mesoscale eddies in shaping the habitat suitability of D. gigas and provided valuable insights for the management and conservation of cephalopod resources.

Marine heatwaves (MHW) events intensified by global warming, threaten Argentine shortfin squid (Illex argentinus), a key species in the Patagonian Shelf. To assess these potential impacts, the spatiotemporal characteristics of MHWs were analyzed using sea surface temperature data from 2013 to 2019, and the effects of these MHWs on the abundance and distribution of I. argentinus were evaluated using a Generalized Additive Model (GAM) and a habitat suitability index (HSI) model. The results indicated that: (1) MHW events exhibited high frequency and intensity in the northern coastal waters of the Patagonian Shelf (near 40°S), characterized by significant temperature anomalies; (2) The GAM analysis revealed a significant negative correlation (p < 0.05) between catch per unit effort (CPUE) and the mean, maximum, and cumulative intensity of MHWs; (3) During MHW events, environmental conditions underwent substantial changes, leading to a sharp decline in the HSI and a shift in the distributional center of I. argentinus. These findings suggest that MHWs may regulate the habitat suitability of I. argentinus through environmental alterations, thereby driving changes in its abundance and distribution. This study confirms the negative impact of MHWs on cephalopod fishery resources and underscores the necessity of establishing climate-adaptive fisheries management strategies to mitigate the challenges posed by MHWs.

The purpleback flying squid (Sthenoteuthis oualaniensis) is widely distributed in the Arabian Sea and highly sensitive to environmental changes. Mesoscale eddies largely occur in the Arabian Sea, playing a significant role in regional biogeochemical processes. However, the impact of eddies on squid abundance is not well studied. Therefore, mesoscale eddies impacts on abundance and spatial distribution of S. oualaniensis were investigated in this study. The results indicated that the monthly catch-per-unit-effort (CPUE) of S. oualaniensis correlated with the variation in the number of eddies, and CPUE within cyclonic eddies (CE) was higher than that within anticyclonic eddies (AE). Sea surface temperature (SST), chlorophyll-a concentration (Chl-a), and dissolved oxygen at 150 m (DO150m) strongly affected the abundance of S. oualaniensis, showing distinct spatial distributions within CEs and AEs. These three key environmental factors were used to construct a habitat suitability index (HSI) model to evaluate the habitat distribution characteristics of S. oualaniensis within CEs and AEs, and results demonstrated CEs were more suitable. Within CEs, suitable SST and relatively lower DO150m aid in the growth and predator avoidance of S. oualaniensis. Overall, the eddies in the Arabian Sea regulate the abundance and distribution of S. oualaniensis, with CEs providing a more suitable habitat.

Upwelling is often associated with high productivity, biodiversity, and fishery resource abundance. This study employed a generalized additive model (GAM) to analyze the effects of Ekman pumping and transport on the abundance and distribution of jumbo flying squid (Dosidicus gigas) using wind field data and Chinese commercial fishing catch data off Peru from 2012 to 2020. The results indicate that the spatial distribution of Ekman pumping and transport exhibited significant monthly variation and exerted a considerable impact on the abundance and distribution of D. gigas. Ekman pumping fluctuated between 4.98 × 10−9 to 6.84 × 10−7 m/s, with the strongest upwelling effects observed from February to March and October to December. Ekman transport varied from 0.89 to 2.56 m3/s and peaked in August. The GAM results indicate that the catch per unit effort (CPUE) of D. gigas was significantly affected by Ekman pumping, while the latitudinal gravity centers (LATG) of D. gigas were significantly influenced by Ekman transport and chlorophyll-a concentration (Chl-a). Both hydrodynamic processes had a significant influence on Chl-a. Ekman pumping contributed greatly to upwelling formation, significantly increasing Chl-a concentration in the northern region, while strong Ekman transport pushed high-Chl-a coastal waters offshore in the central and southern regions when Ekman pumping was weaker, resulting in increasing offshore Chl-a concentrations. Furthermore, Chl-a concentration was significantly positively correlated with Ekman pumping after a two-month lag. An El Niño weakened the intensity of Ekman pumping, leading to notable declines in Chl-a concentration and D. gigas CPUE. These findings demonstrate that Ekman pumping and transport significantly influence the distribution of Chl-a, to which D. gigas is sensitive, influencing the abundance and distribution of this species off the coast of Peru.

Mesoscale eddies, particularly cyclonic eddies (CEs), are known to influence the abundance and distribution of purpleback flying squid (Sthenoteuthis oualaniensis) resources in the northwest Indian Ocean. Sthenoteuthis oualaniensis is a short-lived species and is sensitive to environmental changes. The evolution of CEs is accompanied by structural and energetic transformations, exerting varying impacts on the local marine environment. However, the response of S. oualaniensis to these evolving CEs remains unclear. Therefore, this study analyzed the changes in basic eddy characteristics during CEs evolution and the environmental changes (sea surface temperature, chlorophyll-a concentration, and dissolved oxygen concentration at 150 m depth) driven by CEs. Combined with a habitat suitability index (HSI) model, the distribution of S. oualaniensis during the different life stages of CEs was analyzed. The results showed that the CEs experienced three stages: the early stage, the mature stage and the aged stage. At different stages, the parameters of CEs exhibited distinct distribution patterns. As the eddy evolved, the gravity center of S. oualaniensis abundance in latitude and longitude exhibited a movement trajectory similar to the eddy center. The environmental changes driven by this evolution process influenced the distribution of S. oualaniensis, and the maximum suitable habitat area was generated during the CEs mature stage. These results show that the evolution of CEs significantly affects the habitat distribution of S. oualaniensis in the northwest Indian Ocean.

Exploring the impacts of climate variability on the marine fishery ecosystems in the Southwest Atlantic Ocean is conducive to establishing an ecosystem-based approach for the protection and rational utilization of fishery resources. In this study, long-term fisheries data, 23 environmental data from the entire Southwest Atlantic, and 25 global climate data have been used to explore the regime shift of the fishery ecosystem and the response of fishery resources to climate change from 1950 to 2018. The results indicated that changes in the Southwest Atlantic fishery ecosystem exhibited a significant nonstationary trend, and there were three noteworthy regime shifts in 1976/1977, the late 1980s, and the late 20th century. The temperature, sea surface height, water runoff, and cloudiness were the environmental variables with the greatest impact on fishery resources within the Southwest Atlantic Fishery Ecosystem, while zonal wind speed and air temperature yielded a more significant impact on low latitude areas. In terms of climate indices, fishery resources have the most obvious response to the Global Mean Land-Ocean Temperature Index and Antarctic Sea Ice Extent, and the Atlantic Multidecadal Oscillation had an intense impact on low latitude areas concurrently. The study highlights the climate-related nonstationary changes in the Southwest Atlantic fishery ecosystem.

With the advent of the big data era in ocean remote sensing and fisheries, there is a growing demand for finer temporal scales to predict spatial distribution of the jumbo flying squid (Dosidicus gigas). This can help reduce fuel costs and provide higher quality and faster decision-making. Therefore, this study employed a deep neural network (DNN) model, using sea surface temperature, sea surface height, sea surface salinity, and photosynthetically active radiation as input factors, with catch per unit effort as the output factor. We construct five cases with temporal scales of 3, 6, 10, 15, and 30 days using data spanning 10 years (2012–2021). Additionally, the performance of DNN was compared with those of traditional methods such as generalized additive model (GAM), extreme gradient boosting (XGBoost), and artificial neural network (ANN). The results demonstrated that the DNN model had the best performance. As the temporal scale decreased, the mean squared error and the mean absolute error increased, whereas the area under the precision−recall curve decreased, indicating a decline in model performance. The interpretability analysis indicated that spatial and temporal factors significantly contributed to the model, with longitude exhibiting the highest contribution. To improve the accuracy of finer temporal scales, future research should focus on reducing noise in the data and address the presence-only nature of fishery data, particularly by cleaning the unsampled portions.