Predicting heterogeneous and non-linear processes remains a fundamental challenge in Earth sciences. Here, we present an artificial intelligence (AI)-guided framework that iteratively combines predictive modeling with targeted field sampling to rapidly improve environmental predictions. We demonstrate our workflow by predicting oxygen consumption, a key process of stream metabolism, across the contiguous United States (CONUS). Our approach consisted of 18 iterative loops of measurements and models, combining distributed participatory field sampling, lab analysis, automated machine learning (ML) predictions, and error and distinctiveness analyses to autonomously guide the next sampling at optimal site locations. Through our approach, we increased the predictive power of sediment oxygen consumption across CONUS by over fifteenfold between the first and last iteration. Relative to our last sampling iteration, our first sampling missed sites with high rates and underestimated median oxygen consumption rates by 68%. In addition to identifying areas of high oxygen consumption rates, iterations enabled refinement of laboratory and data handling methods, and engagement with a broad community of field researchers. We conclude that AI-guided iterative loops between targeted sampling and predictive modeling are a powerful and efficient approach for improving predictions of heterogeneous environmental processes. ### Competing Interest Statement The authors have declared no competing interest. Office of Biological and Environmental Research, https://ror.org/0114b2m14, This research was supported by the U.S. Department of Energy (DOE), Office of Biological and Environmental Research (BER), Environmental System Science (ESS) Program as part of the River Corridor Science Focus Area (SFA) at the Pacific Northwest National Laboratory (PNNL). PNNL is operated by Battelle Memorial Institute for the DOE under Contract No. DE-AC05-76RL01830.

AbstractRiver sediment microbial respiration is a key indicator of ecosystem functioning and the biogeochemical fluxes across this critical zone link surface and subsurface waters. As such, there is tremendous interest in measuring and mapping these respiration rates. Respiration observations are expensive and labor intensive; there is limited data available to the community. An open science, collaborative initiative is collecting samples for respiration rate analysis and multi‐scale metadata; this evolving data set is being used for making machine learning (ML) predictions at unsampled sites to help inform continued community engagement. However, it is a challenge to find an optimum configuration for ML models to work with this feature‐rich (i.e., 100+ possible input variables) data set. Here, we present results from a two‐tiered approach to managing the analysis of this complex data set: (a) a stacked ensemble of models that automatically optimizes hyperparameters and manages the training of many models and (b) feature permutation importance to detect the most important features in the models. The major elements of this workflow are modular, portable, open, and cloud‐based thus making this implementation a potential template for other applications. The models developed here predict that sediment organic matter chemistry is one of the most important features for predicting sediment respiration rate. Other larger‐scale, important features fall into the categories of climatic, ecological, geological, and fluvial settings. Leveraging these larger‐scale features to generate data‐driven estimates of river sediment respiration rates reveals spatially consistent but heterogeneous patterns across the river network of the Columbia River Basin.

Cold-water corals (CWCs) thrive in areas with complex and rough topography favoring the development of highly diverse benthic communities. Several biotic and abiotic factors including organic matter supply, temperature, bottom roughness and currents are important drivers of ecosystem structure and functioning in deep-sea environments at different spatial and temporal scales. Little is known, however, how basin-scale changes in the ocean climate affect these drivers at local scales. Here, we use high-resolution implementations of the hydrodynamic model ROMS-AGRIF for estimating characteristic spatial and temporal scales of local hydrodynamics in response to variations of basin-scale currents imposed by distinct changes of the Atlantic Meridional Overturning Circulation (AMOC) in the past century. We focus on two CWC communities on the SE Rockall Bank slope and at Condor Seamount. We considered two contrasting AMOC states that were identified from the 1958-2009 hindcast of the 1/20 degrees resolution VIKING20 North Atlantic basin-scale ocean circulation model and used as boundary conditions for the high-resolution local area models. At SE Rockall Bank, variability of near-bottom currents in both regions was largely dominated by tidal dynamics, but strongly modified by AMOC induced basin-scale variations of water mass properties and bottom currents. During strong AMOC years, waters in the main CWC depth corridor (600-1200 m) were cooler and less saline but were dominated by stronger bottom currents when compared with conditions during weak AMOC years. At Condor Seamount, bottom currents were largely unaffected by AMOC related changes close to the summit at water depths < 400 m. Kinetic energy dissipation rates derived from the 3D near -bottom velocity field appeared to positively relate with the in-situ CWC distribution. Kinetic energy dissipation is therefore proposed as a mechanistic descriptor of CWC presence as it provides a more mechanistic view of hydrodynamics driving organic matter supply to filter and suspension-feeding communities.

Ecosystem connectivity is an essential consideration for marine spatial planning of competing interests in the deep sea. Immobile, adult communities are connected through freely floating larvae, depending on new recruits for their health and to adapt to external pressures. We hypothesize that the vertical swimming ability of deep-sea larvae, before they permanently settle at the bottom, is one way larvae can control dispersal. We test this hypothesis with more than 3× 10^8 simulated particles with a range of active swimming behaviours embedded within the currents of a high-resolution ocean model. Despite much stronger horizontal ocean currents, vertical swimming of simulated larvae can have an order of magnitude impact on dispersal. These strong relationships between larval dispersal, pathways, and active swimming demonstrate that lack of data on larval behaviour traits is a serious impediment to modelling deep-sea ecosystem connectivity; this uncertainty greatly limits our ability to develop ecologically coherent marine protected area networks.

The northern North Atlantic Ocean and its adjacent shelf seas, are influenced by several large-scale physical processes which can be described by various climate indices. Although the signal of these indices on the upper ocean has been investigated, the potential effects on vulnerable benthic ecosystems remains unknown. In this study, we examine the relationship between pertinent climate indices and bottom conditions across the northern North Atlantic region for the first time. Changes are assessed using a composite approach over a 50 year period. We use an objectively-analyzed observational dataset to investigate changes in bottom salinity and potential temperature, and output from a high-resolution ocean model to examine changes in bottom kinetic energy. Statistically significant, and spatially coherent, changes in bottom potential temperature and salinity are seen for the North Atlantic Oscillation (NAO), Atlantic Meridional Overturning Circulation (AMOC), Atlantic Multi-decadal Oscillation (AMO), and Subpolar Gyre (SPG); with statistically significant changes in bottom kinetic energy seen in the subpolar boundary currents for the NAO and AMOC. As the climate indices have multi-annual timescales, changes in bottom conditions may persist for several years exposing sessile benthic ecosystems to sustained changes. Variations in baseline conditions will also alter the likelihood of extreme events such as marine heatwaves, and will modify any longer-term trends. A thorough understanding of natural variability and its effect on benthic conditions is thus essential for the evaluation of future scenarios and management frameworks.

Microplastics are widely dispersed through the marine environment. Few studies have assessed the long-term or historic prevalence of microplastics, yet acquiring such data can inform their distribution, transport and the environmental risks posed. To quantify the distribution and polymer types temporally, sediment cores were collected from >2000 m water depth in the Rockall Trough, North Atlantic Ocean. As hypothesized, a significant negative trend was observed in the frequency of microplastics with increasing sediment age, however there was an increase in polymer diversity. Microplastics were pervasive throughout the sediment analysed (10 cm depth), yet lead-210 (210Pb) activities were confined to the upper 4 cm, indicating this layer to be ~150 years old and thus the presence of microplastics far exceed the production of modern plastic. A number of mechanisms, including sediment reworking, could redistribute microplastics vertically. Additionally, microplastics abundance was significantly correlated with sediment porosity, suggesting interstitial transport via pore waters.

To provide an observational basis for the Intergovernmental Panel on Climate Change projections of a slowing Atlantic meridional overturning circulation (MOC) in the 21st century, the Overturning in the Subpolar North Atlantic Program (OSNAP) observing system was launched in the summer of 2014. The first 21-month record reveals a highly variable overturning circulation responsible for the majority of the heat and freshwater transport across the OSNAP line. In a departure from the prevailing view that changes in deep water formation in the Labrador Sea dominate MOC variability, these results suggest that the conversion of warm, salty, shallow Atlantic waters into colder, fresher, deep waters that move southward in the Irminger and Iceland basins is largely responsible for overturning and its variability in the subpolar basin.

The data set includes all necessary data for set up, initial and boundary conditions of high-resolution local area model implementations using the ROMS-AGRIF model in two case study areas, Rockall Bank and Condor Seamount, conducted as part of the EU ATLAS project. The data include all computational grids, initialization fields (temperature, salinity) and boundary conditions (temperature salinity, currents, sea surface height) for each case study area.

Although evidence suggests the ubiquity of microplastics in the marine environment, our knowledge of its occurrence within remote habitats, such as the deep sea, is scarce. Furthermore, long term investigations of microplastic abundances are even more limited. Here we present a long-term study of the ingestion of microplastics by two deep-sea benthic invertebrates (Ophiomusium lymani and Hymenaster pellucidus) sampled over four decades. Specimens were collected between the years 1976–2015 from a repeat monitoring site >2000 m deep in the Rockall Trough, North East Atlantic. Microplastics were identified at a relatively consistent level throughout and therefore may have been present at this locality prior to 1976. Considering the mass production of plastics began in the 1940s - 50s our data suggest the relatively rapid occurrence of microplastics within the deep sea. Of the individuals examined (n = 153), 45% had ingested microplastics, of which fibres were most prevalent (95%). A total of eight different polymer types were isolated; polyamide and polyester were found in the highest concentrations and in the majority of years, while low-density polystyrene was only identified in 2015. This study provides an assessment of the historic occurrence of microplastics on the deep seafloor and presents a detailed quantification and characterisation of microplastics ingested by benthic species. Furthermore these data advance our knowledge on the long-term fate of microplastic in marine systems.

Seawater rare earth element (REE) concentrations are increasingly applied to reconstruct water mass histories by exploiting relative changes in the distinctive normalised patterns. However, the mechanisms by which water masses gain their patterns are yet to be fully explained. To examine this, we collected water samples along the Extended Ellett Line (EEL), an oceanographic transect between Iceland and Scotland, and measured dissolved REE by offline automated chromatography (SeaFAST) and ICP-MS. The proximity to two continental boundaries, the incipient spring bloom coincident with the timing of the cruise, and the importance of deep water circulation in this climatically sensitive gateway region make it an ideal location to investigate sources of REE to seawater and the effects of vertical cycling and lateral advection on their distribution. The deep waters have REE concentrations closest to typical North Atlantic seawater and are dominated by lateral advection. Comparison to published seawater REE concentrations of the same water masses in other locations provides a first measure of the temporal and spatial stability of the seawater REE signal. We demonstrate the REE pattern is replicated for Iceland-Scotland Overflow Water (ISOW) in the Iceland Basin from adjacent stations sampled 16 years previously. A recently published Labrador Sea Water (LSW) dissolved REE signal is reproduced in the Rockall Trough but shows greater light and mid REE alteration in the Iceland Basin, possibly due to the dominant effect of ISOW and/or continental inputs. An obvious concentration gradient from seafloor sediments to the overlying water column in the Rockall Trough, but not the Iceland Basin, highlights release of light and mid REE from resuspended sediments and pore waters, possibly a seasonal effect associated with the timing of the spring bloom in each basin. The EEL dissolved oxygen minimum at the permanent pycnocline corresponds to positive heavy REE enrichment, indicating maximum rates of organic matter remineralisation and associated REE release. We tentatively suggest a bacterial role to account for the observed heavy REE deviations. This study highlights the need for fully constrained REE sources and sinks, including the temporary nature of some sources, to achieve a balanced budget of seawater REE.

Seawater rare earth element (REE) concentrations are increasingly applied to reconstruct water mass histories by exploiting relative changes in the distinctive normalised patterns. However, the mechanisms by which water masses gain their REE patterns are yet to be fully explained. To examine this, we collected water samples along the Extended Ellett Line (EEL), an oceanographic transect between Iceland and Scotland, and measured dissolved REE by offline automated chromatography (SeaFAST) and ICP-MS. The proximity to two continental boundaries, the incipient spring bloom coincident with the timing of the cruise, and the importance of deep water circulation in this climatically sensitive gateway region make it an ideal location to investigate sources of REE to seawater and the effects of vertical cycling and lateral advection on their distribution. The deep waters have REE concentrations closest to typical North Atlantic seawater and are dominated by lateral advection. Comparison to published seawater REE concentrations of the same water masses in other locations provides a first measure of the temporal and spatial stability of the seawater REE signature. We demonstrate the REE pattern is replicated for Iceland-Scotland Overflow Water (ISOW) in the Iceland Basin from adjacent stations sampled 16 years previously. A recently published Labrador Sea Water dissolved REE signature is reproduced in the Rockall Trough but shows greater light and mid REE alteration in the Iceland Basin, possibly due to the dominant effect of ISOW and/or continental inputs. An obvious concentration gradient from seafloor sediments to the overlying water column in the Rockall Trough, but not the Iceland Basin, highlights release of light and mid REE from resuspended sediments and pore waters, possibly a seasonal effect associated with the timing of the spring bloom in each basin. This study highlights the need for fully constrained REE sources and sinks, including the temporary nature of some sources, to achieve a balanced budget of seawater REE. In this contribution, I discuss some of the potential mechanisms and their implications for the longevity of the seawater REE signature.

We present the first 2 years of UK-OSNAP glider missions on the Rockall Plateau in the North Atlantic subpolar gyre. From July 2014 to August 2016, 20 gliders sections were realized along 58◦N, between 22◦W and 15◦W. Depth-averaged currents estimated from gliders show very strong values (up to 45cm.s-1) associated with mesoscale variability, due particularly to eddies and subpolar mode water formation.

The variability of the Atlantic Meridional Overturning Circulation (AMOC) may play a role in sea surface temperature predictions on seasonal to decadal time scales. Therefore, AMOC seasonal cycles are a potential baseline for interpreting predictions. Here, we present estimates for the seasonal cycle of transports of volume, temperature, and freshwater associated with the upper limb of the AMOC in the eastern subpolar North Atlantic on the Extended Ellett Line hydrographic section between Scotland and Iceland. Due to weather, ship-based observations are primarily in summer. Recent glider observations during other seasons present an opportunity to investigate the seasonal variability in the upper layer of the AMOC. First, we document a new method to quality control and merge ship, float, and glider hydrographic observations. This method accounts for the different spatial sampling rates of the three platforms. The merged observations are used to compute seasonal cycles of volume, temperature, and freshwater transports in the Rockall Trough. These estimates are similar to the seasonal cycles in two eddy-resolving ocean models. Volume transport appears to be the primary factor modulating other Rockall Trough transports. Finally, we show that the weakest transports occur in summer, consistent with seasonal changes in the regional-scale wind stress curl. Although the seasonal cycle is weak compared to other variability in this region, the amplitude of the seasonal cycle in the Rockall Trough, roughly 0.5 to 1 Sv about a mean of 3.4 Sv, may account for up to 7 to 14% of the heat flux between Scotland and Greenland.

Lagrangian analysis is a powerful way to analyse the output of ocean circulation models and other ocean velocity data such as from altimetry. In the Lagrangian approach, large sets of virtual particles are integrated within the three-dimensional, time-evolving velocity fields. Over several decades, a variety of tools and methods for this purpose have emerged. Here, we review the state of the art in the field of Lagrangian analysis of ocean velocity data, starting from a fundamental kinematic framework and with a focus on large-scale open ocean applications. Beyond the use of explicit velocity fields, we consider the influence of unresolved physics and dynamics on particle trajectories. We comprehensively list and discuss the tools currently available for tracking virtual particles. We then showcase some of the innovative applications of trajectory data, and conclude with some open questions and an outlook. The overall goal of this review paper is to reconcile some of the different techniques and methods in Lagrangian ocean analysis, while recognising the rich diversity of codes that have and continue to emerge, and the challenges of the coming age of petascale computing.

AbstractThe Atlantic Meridional Overturning Circulation (AMOC) is a key component of the global climate system through its transport of heat and freshwater. The subpolar North Atlantic (SPNA) is a region where the AMOC is actively developed and shaped though mixing and water mass transformation and where large amounts of heat are released to the atmosphere. Two hydrographic transbasin sections in the summers of 2014 and 2016 provide highly spatially resolved views of the SPNA velocity and property fields on a line from Canada to Greenland to Scotland. Estimates of the AMOC, isopycnal (gyre‐scale) transport, and heat and freshwater transport are derived from the observations. The overturning circulation, the maximum in northward transport integrated from the surface to seafloor and computed in density space, has a high range, with 20.6 ± 4.7 Sv in June–July 2014 and 10.6 ± 4.3 Sv in May–August 2016. In contrast, the isopycnal (gyre‐scale) circulation was lowest in summer 2014: 41.3 ± 8.2 Sv compared to 58.6 ± 7.4 Sv in 2016. The heat transport (0.39 ± 0.08 PW in summer 2014, positive is northward) was highest for the section with the highest AMOC, and the freshwater transport was largest in summer 2016 when the isopycnal circulation was high (−0.25 ± 0.08 Sv). Up to 65% of the heat and freshwater transport was carried by the isopycnal circulation, with isopycnal property transport highest in the western Labrador Sea and the eastern basins (Iceland Basin to Scotland).