SEARCH · Engineering Papers

Results for “Deep”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 55 records · Page 3

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Large-scale deep learning for metastasis detection in pathology reports

Objectives No existing algorithm can reliably identify metastasis from pathology reports across multiple cancer types and the entire US population. In this study, we develop a deep learning model that automatically detects patients with metastatic cancer by using pathology reports from many laboratories and of multiple cancer types. Materials and Methods We use 60 471 unstructured pathology reports from 4 Surveillance, Epidemiology, and End Results (SEER) registries. The reports were coded into 1 of 3 labels: metastasis negative, metastases positive, or metastasis undetermined. We utilize a task-specific deep neural network trained from scratch and compare its performance with a widely used large language model (LLM). Results Our deep learning architecture trained on task-specific data outperforms a general-purpose LLM, with a recall of 0.894 compared to 0.824. We quantified model uncertainty and used it to defer reports for human review. We found that retaining 72.9% of reports increased recall from 0.894 to 0.969. Discussion A smaller deep learning architecture trained on task-specific data outperforms a general LLM. Equally critical to model performance is the incorporation of uncertainty quantification, achieved here through an abstention mechanism. Conclusions This study’s finding demonstrate the feasibility of developing algorithms to automatically identify metastatic cancer cases from unstructured pathology reports.

machine learning↗

DOE OSTI2024

Impacts of floating-point non-associativity on reproducibility for HPC and deep learning applications

Run to run variability in parallel programs caused by floating-point non-associativity has been known to significantly affect reproducibility in iterative algorithms, due to accumulating errors. Non-reproducibility can critically affect the efficiency and effectiveness of correctness testing for stochastic programs. Recently, the sensitivity of deep learning training and inference pipelines to floating-point non-associativity has been found to sometimes be extreme. It can prevent certification for commercial applications, accurate assessment of robustness and sensitivity, and bug detection. New approaches in scientific computing applications have coupled deep learning models with high-performance computing, leading to an aggravation of debugging and testing challenges. Here we perform an investigation of the statistical properties of floating-point non-associativity within modern parallel programming models, and analyze performance and productivity impacts of replacing atomic operations with deterministic alternatives on GPUs. We examine the recently-added deterministic options in PyTorch within the context of GPU deployment for deep learning, uncovering and quantifying the impacts of input parameters triggering run to run variability and reporting on the reliability and completeness of the documentation. Finally, we evaluate the strategy of exploiting automatic determinism that could be provided by deterministic hardware, using the Groq LPUTM accelerator for inference portions of the deep learning pipeline. We demonstrate the benefits that a hardware-based strategy can provide within reproducibility and correctness efforts.

Shanmugavelu, Sanjif↗

DOE OSTI2024

A Deep Multimodal Representation Learning Framework for Accurate Molecular Properties Prediction

Drug discovery is a complex and challenging process, requiring the optimization of candidate compounds to identify those with the potential to become safe and effective drugs. Predicting molecular properties is an indispensable step in the drug discovery pipeline. Traditionally, this process is costly and time-intensive, involving multiple rounds of experiments and clinical trials, rendering it impractical for every candidate compound. Deep learning techniques have emerged as a promising approach to drug discovery to reduce the cost and time required to identify novel drugs. However, prevalent research in deep learning models focused on predicting molecular properties has primarily fixated on single-modal models, which utilize a single modality of data, neglecting the potential benefits of combining different data modalities. To overcome this limitation, we introduce MRL-Mol: a deep \textbf{M}ultimodal \textbf{R}epresentation \textbf{L}earning framework for accurate \textbf{Mol}ecular properties prediction. MRL-Mol harnesses three data modalities: sequence, graph, and image, augmenting the depth of comprehension. Leveraging a large-scale unlabeled dataset~($\sim$1M unique molecules), we pretrain MRL-Mol to extract inter- and intra-modal information. Our study demonstrates the superior performance of MRL-Mol in predicting molecular properties across six benchmark datasets, including both classification and regression tasks. Notably, MRL-Mol outperforms other state-of-the-art molecular properties prediction models. These findings suggest that by combining information from multiple data modalities, MRL-Mol can comprehend molecules better than single-modal deep learning models and identify molecular properties with better accuracy.

Yang, Yuxin↗

DOE OSTI2025

Development and Evaluation of a General Drag Model for Gas-Solid Flows via Deep Learning

This project presents the development and evaluation of a general drag model for gas–solid multiphase flows using deep learning techniques. A comprehensive database of more than 4,000 experimental and numerical data points for spherical and non spherical particles was compiled, incorporating geometric features such as sphericity, aspect ratio, and orientation. Several predictive approaches—including traditional em pirical correlations, machine learning, and deep neural networks—were benchmarked, with the proposed Drag Coefficient Correlation-aided Deep Neural Network (DCC DNN) demonstrating superior accuracy. To account for particle–particle interactions, additional drag data were generated using CFD-based simulations of packed and flu idized beds, leading to the development of a retrained model capable of incorporat ing volume fraction effects. Integration of the trained model with the MFiX CFD solver was achieved using FTorch, enabling drag predictions during discrete element method (DEM) simulations. Validation against experimental data for single particles and fluidized beds confirmed the model’s improved predictive ability, particularly for non-spherical geometries. While the model performed strongly under fluidized con ditions, limitations remained in unfluidized regimes, suggesting a need for expanded datasets. Overall, this study demonstrates the feasibility of combining deep learning with physics-informed CFD to improve drag modeling for gas–solid flows, with promis ing implications for scaling multiphase simulations in industrial applications.

42 ENGINEERING↗

DOE OSTI2025

Collaborative Proposal: Improving understanding of the internal structure and dynamics of deep convection using ARM observations and large eddy simulations

Recent observational and large eddy simulation (LES) modeling studies have nearly unanimously supported the view of deep cumulus convection being composed of a series of quasi-spherical bubbles of buoyant air, known as moist thermals. Despite the prevalence of moist thermals in deep convection, a comprehensive theory for the dynamics of these structures is lacking. Most current conceptual models for cumulus convection are based on canonical scaling theories for dry thermals or plumes; however, there is considerable evidence that the behavior of moist thermals differs markedly from these theories. Furthermore, the theoretical basis for most cumulus parameterizations originates from the plume conceptual model, and therefore these parameterizations are inconsistent with the real structure of moist convection. Motivated by the aforementioned knowledge gaps, this “end-to-end” research effort use theory, observations, numerical simulations, and direct improvements to the Zhang-McFarlane (ZM) convection scheme in the global climate Community Atmosphere Model (CAM) to address the following research questions: What key environmental parameters determine whether or not shallow convection will transition into deep convection, in the context of thermal-like updrafts? What factors regulate the size of thermals within cumulus updrafts? How does vertical wind shear influence thermal behavior, and as a consequence, vertical velocity and mass flux profiles and the shallow-to-deep convective transition? What are the critical processes that determine updraft vertical velocities and their connection to the vertical mass flux profile for thermal-like updrafts? Idealized LES modeling will be used in conjunction with theoretical models for the core properties of thermal-like updrafts to better understand key processes that regulate thermal ascent rates and entrainment properties. Thermal-tracking procedures will be used to characterize the behavior of thermals within the LES, and recently developed direct measures of entrainment and detrainment will be used to quantify entrainment/detrainment rates. Building from these results, we will analyze the structure of moist thermals from hemispheric range-height indicator scans taken during the Atmospheric Radiation Measurement Cloud, Aerosol, and Complex Terrain Interactions (CACTI) field campaign, and from “real case” LES of CACTI events. This combined modeling and observational analysis will provide essential validation for the existing body of research on moist thermal dynamics, which is based primarily on modeling studies. With the insight gained from the aforementioned activities, we will modify the Zhang-McFarlane convection scheme to improve its representation of updraft vertical velocity and entrainment rate profiles. These process-level changes will be tested in the Community Atmosphere Model to assess the impact on global climate simulations.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2024

Integrating multi-modal remote sensing, deep learning, and attention mechanisms for yield prediction in plant breeding experiments

In both plant breeding and crop management, interpretability plays a crucial role in instilling trust in AI-driven approaches and enabling the provision of actionable insights. The primary objective of this research is to explore and evaluate the potential contributions of deep learning network architectures that employ stacked LSTM for end-of-season maize grain yield prediction. A secondary aim is to expand the capabilities of these networks by adapting them to better accommodate and leverage the multi-modality properties of remote sensing data. In this study, a multi-modal deep learning architecture that assimilates inputs from heterogeneous data streams, including high-resolution hyperspectral imagery, LiDAR point clouds, and environmental data, is proposed to forecast maize crop yields. The architecture includes attention mechanisms that assign varying levels of importance to different modalities and temporal features that, reflect the dynamics of plant growth and environmental interactions. The interpretability of the attention weights is investigated in multi-modal networks that seek to both improve predictions and attribute crop yield outcomes to genetic and environmental variables. This approach also contributes to increased interpretability of the model's predictions. The temporal attention weight distributions highlighted relevant factors and critical growth stages that contribute to the predictions. The results of this study affirm that the attention weights are consistent with recognized biological growth stages, thereby substantiating the network's capability to learn biologically interpretable features. Accuracies of the model's predictions of yield ranged from 0.82-0.93 R 2 ref in this genetics-focused study, further highlighting the potential of attention-based models. Further, this research facilitates understanding of how multi-modality remote sensing aligns with the physiological stages of maize. The proposed architecture shows promise in improving predictions and offering interpretable insights into the factors affecting maize crop yields, while demonstrating the impact of data collection by different modalities through the growing season. By identifying relevant factors and critical growth stages, the model's attention weights provide valuable information that can be used in both plant breeding and crop management. The consistency of attention weights with biological growth stages reinforces the potential of deep learning networks in agricultural applications, particularly in leveraging remote sensing data for yield prediction. To the best of our knowledge, this is the first study that investigates the use of hyperspectral and LiDAR UAV time series data for explaining/interpreting plant growth stages within deep learning networks and forecasting plot-level maize grain yield using late fusion modalities with attention mechanisms.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2024

A Cohesive Deep Drilling Field Strategy for LSST Cosmology

The Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST) will image billions of astronomical objects in the wide–fast–deep primary survey and in a set of minisurveys including intensive observations of a group of deep drilling fields (DDFs). The DDFs are a critical piece of three key aspects of the LSST Dark Energy Science Collaboration (DESC) cosmological measurements: they provide a required calibration for photometric redshifts (photo- z ) and weak gravitational lensing (WL) measurements and they directly contribute to cosmological constraints from the most distant Type Ia supernovae (SNe Ia). We present a set of cohesive DDF strategies fulfilling science requirements relevant to DESC and following the guidelines of the Survey Cadence Optimization Committee. We propose a method to estimate the observing strategy parameters and we perform simulations of the corresponding surveys. We define a set of metrics for each science case to assess the performance of the proposed observing strategies. We show that the most promising results are achieved with deep rolling surveys characterized by two sets of fields: ultradeep fields ( z ≲ 1.1) observed at a high cadence with a large number of visits over a limited number of seasons, and deep fields ( z ≲ 0.7), observed with a cadence of ~3 nights for 10 yr. These encouraging results should be confirmed with realistic simulations using the LSST scheduler. A DDF budget of ~8.5% is required to design observing strategies satisfying all the cosmological requirements. A lower DDF budget leads to surveys that either do not fulfill the photo- z /WL requirements or are not optimal for SN Ia cosmology.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2026

Legacy Survey of Space and Time Data Preview 2: deep_coadd_input_summary dataset type

We present Rubin Data Preview 2 (DP2), the second data preview from the NDF-DOE Vera C. Rubin Observatory. Data Preview 2 (DP2) comprises coadds, detection catalogs, and ancillary data products; and when fully released will also include single-epoch images and difference images. DP2 is derived from observations acquired by the LSST Science Camera (LSSTCam) on the Simonyi Survey Telescope at the Summit Facility on Cerro Pachón, Chile, primarily during the on-sky commissioning campaign between 2025-04-16 and 2025-09-21, supplemented by observations taken between 2025-10-25 and 2026-01-06 that overlap the commissioning footprint. The DP2 footprint comprises the Science Validation wide-area survey, five Deep Drilling Fields, and a number of targeted small-field regions, including Trifid and Lagoon, Prawn, M49, and New Horizons, all observed as part of the Rubin First Look campaign. Each field was imaged in up to six broad photometric bands, ugrizy, and coadded to produce deep imaging covering an estimated 3,000 deg2. The addition of single-visit-only areas expands the total DP2 footprint to an estimated 15,000 deg2, with coverage in at least one filter. The median per-visit PSF FWHM across the wide-area survey ranges from 1.17 arcsec in the z band to 1.26 arcsec in g and r bands. The deepest field, reaches estimated coadded 5σ depths of u=26 mag, g=26.8 mag, r=26.3 mag, i=26.1 mag, z=25.3 mag, y=23.9 mag. Based on a roughly five-month primary observing baseline and covering only part of the eventual LSST footprint, DP2's area, depth, and multiband coverage nonetheless support a broad range of early science investigations ahead of LSST Data Release This dataset is a subset of the full data release consisting of the deep_coadd_input_summary dataset type. These are summary of the visit images that contribute to each deep coadd patch. This release contains 1 dataset of this type.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2024

Impurity gas detection for SNF canisters using probabilistic deep learning and acoustic sensing *

Abstract Monitoring impurity gases in spent nuclear fuel (SNF) canisters is a novel structural health monitoring approach for SNF in dry storage. The SNF canisters are sealed containers that do not facilitate visual access to the inside. Acoustic sensing can be deployed by taking advantage of the pathways unobstructed by internal hardware. Although the ultrasonic time-of-flight measurement can provide valuable information, it is limited in its ability to discern the concentration of only one impurity gas. As such, deep learning algorithms, particularly convolutional neural networks (CNNs), offer a promising solution. In this study, CNN-based probabilistic deep learning models were implemented to detect and quantify multiple impurity gases in helium. An experimental platform was established to simulate canister conditions, and ultrasonic test data were collected. The presence of argon and air in helium at concentrations ranging from 0% to 1.2% at increments of 0.05% was considered. The multi-layer perceptron, decision tree, and logistic regression classifiers achieved high accuracies when distinguishing pure helium from helium with impurities. CNN with dropout layers and CNN using maximum likelihood estimation showed a similar performance, indicating their ability to capture uncertainties. The ensemble CNN model exhibited improved predictions and the ability to balance individual gas concentration by integrating 1D- and 2D-CNN models. These findings contribute probabilistic deep learning solutions for impurity gas detection and analysis within SNF canisters, thus ensuring safe storage and management of SNFs.

47 OTHER INSTRUMENTATION↗

DOE OSTI2026

Unlocking plant-microbial interactions in deep Mollisols in the Midwestern US: Linking depth gradients in roots, microbial activity, and soil carbon in agroecosystems

Deep-rooted plants may build soil carbon (C) stocks, but most research has focused on shallow soils, leaving gaps in our understanding of how shifts in the balance between decomposition and C inputs drive soil C accumulation with depth. Thus, our objectives were to: (1) link depth gradients in root biomass with microbial activity and soil C stocks down to 1 m, and (2) examine the potential of simple C inputs to prime soil C across depths. To this end, we dug 5 quantitative soil pits in Argiudolls under mature perennial miscanthus plots in the SoyFACE Farm (Champaign-Urbana, IL). We added 13 C labeled glucose to our soils to determine the fate of simple C inputs with depth. We found that fine root biomass, total soil C, mineral-associated organic C (MAOC), particulate organic C (POC), and microbial activity (as measured by potential enzyme activity) declined with depth. POC declined more rapidly than MAOC, resulting in an increase in the ratio of MAOC-to-POC. Root biomass, enzyme activity (either acid phosphatase or n-acetyl-glucosaminadase) activity, and microbial respiration explained 74% and 38% of the variability in soil total C and MAOC, respectively, while POC was dependent on root biomass and microbial respiration (47%). Although the incorporation of simple 13 C inputs into MAOC was similar across depths, these inputs led to greater net MAOC losses in shallow soils than in deeper soils between 50 and 100 cm. The divergent impact of simple C inputs across depths may suggest that MAOC in shallow soils is more susceptible to priming losses, while C inputs into deep soils may instead be more persistent. Collectively, our results suggest that depth gradients in soil C stocks represents a balance between inputs, decomposition, and microbial necromass production and that increases in root C inputs by deep-rooted plants may have the potential to build stable MAOC.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2024

Deep-learning based artificial intelligence tool for melt pools and defect segmentation

Accelerating fabrication of additively manufactured components with precise microstructures is important for quality and qualification of built parts, as well as for a fundamental understanding of process improvement. Accomplishing this requires fast and robust characterization of melt pool geometries and structural defects in images. This paper proposes a pragmatic approach based on implementation of deep learning models and self-consistent workflow that enable systematic segmentation of defects and melt pools in optical images. Deep learning is based on an image-to-image translation–conditional generative adversarial neural network architecture. An artificial intelligence (AI) tool based on this deep learning model enables fast and incrementally more accurate predictions of the prevalent geometric features, including melt pool boundaries and printing-induced structural defects. We present statistical analysis of geometric features that is enabled by the AI tool, showing strong spatial correlation of defects and the melt pool boundaries. The correlations of widths and heights of melt pools with dataset processing parameters show the highest sensitivity to thermal influences resulting from laser passes in adjacent and subsequent layer passes. The presented models and tools are demonstrated on the aluminum alloy and datasets produced with different sets of processing parameters. However, they have universal quality and could easily be adapted to different material compositions. The method can be easily generalized to microstructural characterizations other than optical microscopy.

additive manufacturing↗

DOE OSTI2026

Deep learning for time series forecasting: a survey of recent advances

Time series forecasting plays a critical role in numerous real-world applications, such as finance, healthcare, transportation, and scientific computing. In recent years, deep learning has become a powerful tool for modeling complex temporal patterns and improving forecasting accuracy. This survey provides an overview of recent deep learning approaches for time series forecasting, involving various architectures including RNNs, CNNs, GNNs, transformers, large language models, MLP-based models, and diffusion models. We first identify key challenges in the field, such as temporal dependency, efficiency, and cross-variable dependency, which drive the development of forecasting techniques. Then, the general advantages and limitations of each architecture are discussed to contextualize their adaptation in time series forecasting. Furthermore, we highlight promising design trends like multi-scale modeling, decomposition, and frequency-domain techniques, which are shaping the future of the field. This paper serves as a compact reference for researchers and practitioners seeking to understand the current landscape and future trajectory of deep learning in time series forecasting.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2026

Inverse design of hypoeutectoid pearlite steel microstructures using a deep learning and genetic algorithm optimization framework

Goal-oriented microstructure design in metallic materials is a challenging task due to complex structure-property relationships. Traditional experimental and computational approaches are time-intensive and economically inefficient, limiting their applicability for large-scale design space exploration. Here, in this work, we propose an end-to-end framework that integrates deep learning models with genetic optimization to design microstructures with targeted mechanical properties. Deep learning models enable accurate forward design, while their integration with genetic optimization enables efficient inverse design within a few hours, compared to days or weeks using conventional finite element simulations. The framework combines experimental characterization and finite element modeling to analyze the influence of microstructural features on the mechanical behavior of hypoeutectoid steels. Data from both experiments and simulations are used to train the deep learning models. To demonstrate its effectiveness, we apply the framework to 0.63% carbon steel with proeutectoid ferrite and pearlite phases, commonly used in industrial applications. In this study, 2D microstructures were used for modeling, selected primarily for computational efficiency and to establish proof of concept. The framework successfully optimizes microstructures for targeted yield strength, ultimate strength, and stress concentration factors while significantly reducing computational time. Beyond hypoeutectoid steels, this scalable framework can be extended to other material systems and integrated with additive manufacturing, offering an efficient approach for accelerating microstructure design for specific engineering applications.

ConvLSTM↗

DOE OSTI2025

Comprehensive assessment of deep reinforcement learning approaches for economic dispatch in nuclear-driven microgrids

As the electrical grid integrates more variable renewable energy sources such as wind and solar, the demand for distributed and flexible systems to address this increased variability becomes critical. Nuclear-driven microgrids provide a promising solution by offering stable generation to complement intermittent renewables, ensuring grid reliability and operating efficiency. This paper proposes a recurrent deep reinforcement learning framework for optimal economic dispatch in a nuclear-powered microgrid integrating renewable energy sources, small modular reactors, battery storage systems, and balance-of-plant dynamics. A three-agent control architecture is developed, where demand and renewable energy agents act as forecasters, and a reinforcement learning-based dispatch agent performs real-time energy allocation. A nonlinear programming formulation is first used to generate an optimal baseline for benchmarking. The proposed dispatch controller, based on Proximal Policy Optimization enhanced with Long Short-Term Memory networks, exploits temporal correlations in system dynamics by taking advantage of the time series used as inputs to improve policy robustness under uncertainty. Comparative analysis against established deep reinforcement learning methods, including Proximal Policy Optimization with a feedforward architecture, Soft Actor-Critic, and Twin Delayed Deep Deterministic Policy Gradient, demonstrates superior performance. Numerical results indicate that the proposed controller achieves a 0.39% cost reduction relative to the nonlinear programming benchmark and outperforms other learning-based methods by generating additional revenue of up to 0.35%. All reinforcement learning controllers compute dispatch actions in less than 0.3 s, resulting in a computational speedup of more than three orders of magnitude over the nonlinear programming baseline. The findings of this paper highlight their applicability for real-time operation and control in nuclear-integrated microgrids under volatile operating conditions.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2026

Deep learning–based digital twins for heat pumps

Heat pumps are effective cooling and heating appliances to save energy in buildings. However, traditional heat pump models are challenging to integrate with building demands in a co-simulation environment because of the nonlinear thermodynamics of refrigerants. Developing digital twin representatives for heat pumps capable of faster calculations with good accuracy is desirable. This study aimed to establish a generic deep learning–based digital twin for heat pumps with a large amount of high-fidelity data. Two refrigerants for two different heat pumps were considered: an air source heat pump with refrigerant R-410A, an air source heat pump with refrigerant CO 2 , a water source heat pump with refrigerant R-410A, and a water source heat pump with refrigerant CO 2 . Furthermore, results showed that the deep learning (long short-term memory) models effectively represented these four heat pumps as a digital twin: (a) accuracy for training and testing showed smaller than 0.02 for heating electricity and heating demands, and (b) the digital twins showed good consistency with original data for heating electricity and heating demands (root mean square errors of less than 0.12 W and 0.19 W, respectively). Therefore, deep learning–based heat pump models can be used in the co-simulation of building mechanical systems.

Air source heat pump↗

DOE OSTI2025

Reproducibility of Radiokrypton in Deep Desert Aquifers: Insights from a Decade of Research

Great technical advances have been achieved since the first atom-trap trace analysis (ATTA) -based radiokrypton application in Egypt, where 1 Myr old groundwater was discovered. Beyond advances in ATTA measurement capabilities, including reduction in sample size, analysis duration, and analytical uncertainty, major progress has been achieved over the past two decades in the sample collection and preparation techniques. These advances paved the expansion of ATTA-based noble gas applications to many other aquifers worldwide, illuminating the nature and flow pattern of deep groundwater systems. While the potential of this new analytical technique for old groundwater dating is well recognized, another important aspect yet to be examined is the reproducibility of radiokrypton in aquifers over time, i.e., how representative is a discrete groundwater sample, collected at a specific time and location, for the natural groundwater system? The likelihood of a negative answer is increased by flow-field disturbance in aquifers following massive groundwater abstraction. Here, in this work, we present repeated 81 Kr sampling and measurements in twenty-one sites over Israel, mostly of deep (up to 1 km) wells tapping confined aquifers in the arid to hyperarid Negev desert. The results demonstrate that radiokrypton measurements are indeed reproducible, even in cases where samples were collected as long as nine years apart and from highly productive (∼1 Mm 3 /yr order) pumping wells. Furthermore, many of the repeated measurements in this study (17 out of the 21 sites) were conducted with different ATTA Instruments in two different laboratories using slightly different sampling, preparation, and analysis techniques, yet with an overall good agreement. The consistency in the ATTA-based 81 Kr-dating results over time highlights the robustness of this state-of-the-art technique as a tool to unravel groundwater flow patterns and encourages further applications to many other yet-to-be-explored deep aquifers.

atom-trap trace analysis↗

DOE OSTI2026

Aragonite saturation horizon variability along North Pacific seamounts and implications for deep-sea coral reefs

The 2014 discovery of living deep-sea coral reefs along the Northwest Hawaiian Islands (NWHI) and lower Emperor Seamount Chain (ESC), despite the North Pacific’s shallow aragonite saturation horizon (ASH) and high CaCO3 dissolution rates, underscores the need to understand the local seawater chemistry that allows these reefs to persist. We investigated seawater carbonate chemistry using discrete samples along the NWHI and ESC from two cruises ~1 year apart (08/26/21 – 09/26/21, 09/09/22 – 10/24/22). Across the two cruises, ASH depth difference ranged from 15 to 77 m. Since the Pacific ASH shoals by 1–2 m yr?¹, this long-term trend cannot explain the magnitude of ASH change observed between cruises. Temperature-salinity plots similarly indicate no major shifts in intermediate water masses that could account for these changes. Instead, ASH depth variability was primarily governed by localized biogeochemical processes, namely changes in intermediate water respiration and CaCO3 dissolution. Indicators for dissolution (TA*) and respiration (AOU) suggest changes in ASH depth were driven by changes in dissolution at the northern- and southern-most sites, whereas respiration exerted stronger control at central sites. Combining 2021 and 2022 data with data from 2014 – 2019 (excluding 2018) revealed high interannual ASH variability, by as much as >200 m at one site. Deep-sea coral reefs across the NWHI and ESC currently reside close to the ASH depth and likely experience seasonal and interannual shifts between under- and supersaturation. As ocean acidification progresses however, persistent exposure to undersaturated seawater could further threaten these critical deep-sea ecosystems.

coral reefs↗

DOE OSTI2024

Inferring effective electrostatic interaction of charge-stabilized colloids from scattering using deep learning

In this article, an innovative strategy is presented that incorporates deep auto-encoder networks into a least-squares fitting framework to address the potential inversion problem in small-angle scattering. To evaluate the performance of the proposed approach, a detailed case study focusing on charged colloidal suspensions was carried out. The results clearly indicate that a deep learning solution offers a reliable and quantitative method for studying molecular interactions. The approach surpasses existing deterministic approaches with respect to both numerical accuracy and computational efficiency. Overall, this work demonstrates the potential of deep learning techniques in tackling complex problems in soft-matter structures and beyond.

36 MATERIALS SCIENCE↗