Engineering Papers⌕ Search

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.

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

At least 1,585 records · Page 88
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Toward Complete Merger Identification at Cosmic Noon with Deep Learning

As we enter the era of large imaging surveys such as Roman, Rubin, and Euclid, a deeper understanding of potential biases and selection effects in optical astronomical catalogs created with the use of ML-based methods is paramount. This work focuses on a deeper understanding of the performance and limitations of deep learning-based classifiers as tools for galaxy merger identification. We train a ConvNeXT-Pico model on mock HST CANDELS images from the IllustrisTNG50 simulation. Our focus is on a more challenging classification of galaxy mergers and non-mergers at higher redshifts 1 < z < 1.5, including minor mergers and lower mass galaxies down to the stellar mass of 108M⊙. We demonstrate, for the first time, that a deep learning model, such as the one developed in this work, can successfully identify even minor and low mass mergers even at these redshifts. Our model achieves overall accuracy, purity, and completeness of over 73%. We show that some galaxy mergers can only be identified from certain observation angles, leading to a potential upper limit in overall accuracy. Using Grad-CAMs and UMAPs, we more deeply examine the performance and observe a visible gradient in the latent space with stellar mass and specific star formation rate, but no visible gradient with merger mass ratio or merger stage.

Schechter, Aimee L. [U. Colorado, Boulder]↗
DOE OSTI2025

UNCERTAINTY-AWARE DEEP LEARNING FRAMEWORK FOR FORECASTING COASTAL WATER LEVEL IN VIRGINIA BEACH

Coastal areas like Virginia Beach, USA, are increasingly vulnerable to flooding. To mitigate the impact of flooding, it is crucial for the City of Virginia Beach to have reliable 72-hour-ahead (3 days) forecasts of water levels at key gauge locations. To support this effort, several sensors have been installed throughout the city to monitor water levels and other environmental parameters such as wind speed, precipitation, and atmospheric pressure. Leveraging sensor data from one of these locations, we developed an uncertainty-aware deep learning model to forecast water levels. We employed deep quantile regression (DQR) to quantify variability in the predictions and examined the performance of three different model architectures. In addition to exclusively including historical data, we investigated the improvement wind forecasts provide to the accuracy of 72-hour-ahead water level predictions. The results show a twelvefold improvement in the flood forecast for a real flooding event.

Hasan, Mahmud [Thomas Jefferson National Accelerat↗
DOE OSTI2019

Deep vadose zone respiration contributions to CO2 fluxes from a semi-arid floodplain, Vadose Zone Journal: Dataset

This data package provides lists of parameter values presented in the paper “Deep vadose zone respiration contributions to CO2 fluxes from a semi-arid floodplain” by Tokunaga et al., Vadose Zone J. 2016. Each table or figure from that paper that contains numerical information is represented as a sheet within the Excel file. Table 1 lists depth profile values for particle-size, bulk density, and parameters for correlating moisture contents with matric potentials. Table 2 lists soil respiration fluxes reported in other studies of semi-arid environments. Figure 3. Presents representative relations between moisture contents with matric potentials. Figure 4 presents depth profiles on different dates at site TT03 for hydraulic head, matric head, pore space volumetric air fraction, temperature, and the effective CO2 diffusion coefficient. Figure 5a presents the time-dependence of relative water table elevation (relative to the deepest measured depth during the study), daily CO2 flux rates at the soil surface, and soil temperature at a depth of 0.20 m. Figure 5b presents continuous measurements of CO2 flux and soil temperature. Figure 6 presents depth profiles on different dates of CO2 concentrations in the gas phase at the 5 monitoring stations. Figure 7 presents CO2 surface fluxes calculated by the gradient method, comparisons between calculated and measured rates at the soil surface, CO2 fluxes at 2m depth, and the ratio of deep (2 m) to surface CO2 fluxes.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Automatically parallelizing batch inference on deep neural networks using Fiats and Fortran 2023 `do concurrent`

This paper introduces novel programming strategies that leverage features of the Fortran 2023 standard of the International Standards Organization (ISO) to automatically parallelize computations on deep neural networks. The paper focuses on the interplay of object-oriented, parallel, and functional programming paradigms in the Fiats deep learning library. We demonstrate how several infrequently used language features play a role in enabling efficient, parallel execution. Specifically, the ability to explicitly declare that a procedure is pure facilitates inference in the context of the language’s loop-parallelism construct `do concurrent`. Also, explicitly prohibiting the overriding of a parent type’s type-bound procedures eliminates the need for dynamic dispatch in performance-critical code. Finally, this paper uses batch inference calculations on a neural network surrogate for atmospheric aerosol dynamics to demonstrate that LLVM Flang compiler’s automatic parallelization of `do concurrent` achieves roughly the same performance and scalability as achieved by OpenMP compiler directives. We also demonstrate that double-precision inference costs 37–72% longer runtime than default-real precision with most values in the range 57-60%.

Rouson, Damian↗
DOE OSTI2017

Deep Water Impact Ensemble Data Set

Asteroids of various sizes, speeds, and compositions are zipping around the solar system with potential future Earth engagements. Most of the earth is covered in ocean and impacts would likely occur in deep ocean water. The IEEE SciVis Contest 2018 is dedicated to the visualization and analysis of simulations designed to study asteroid impacts in deep ocean water.

"asteroid impact" meteor "in situ" visualization↗
DOE OSTI2022

Encoding Diel Hysteresis and the Birch Effect in Dryland Soil Respiration Models through Knowledge-Guided Deep Learning

Soil respiration in dryland ecosystems is challenging to model due to its complex interactions with environmental drivers. Knowledge-guided deep learning provides a much more effective means of accurately representing these complex interactions than traditional Q10-based models. Mutual information analysis revealed that future soil temperature shares more information with soil respiration than past soil temperature, consistent with their clockwise diel hysteresis. We explicitly encoded diel hysteresis, soil drying, and soil rewetting effects on soil respiration dynamics in a newly designed Long Short Term Memory (LSTM) model. The model takes both past and future environmental drivers as inputs to predict soil respiration. The new LSTM model substantially outperformed three Q10-based models and the Community Land Model when reproducing the observed soil respiration dynamics in a semi-arid ecosystem. The new LSTM model clearly demonstrated its superiority for temporally extrapolating soil respiration dynamics, such that the resulting correlation with observational data is up to 0.7 while the correlations of the Q10-based models and the Community Land Model (CLM) are less than 0.4. Our results underscore the high potential for knowledge-guided deep learning to replace Q10-based soil respiration modules in Earth system models.

Jiang, Peishi↗
DOE OSTI2025

End-to-end deep learning pipeline for real-time Bragg peak segmentation: from training to large-scale deployment

X-ray crystallography reconstruction, which transforms discrete X-ray diffraction patterns into three-dimensional molecular structures, relies critically on accurate Bragg peak finding for structure determination. As X-ray free electron laser (XFEL) facilities advance toward MHz data rates (1 million images per second), traditional peak finding algorithms that require manual parameter tuning or exhaustive grid searches across multiple experiments become increasingly impractical. While deep learning approaches offer promising solutions, their deployment in high-throughput environments presents significant challenges in automated dataset labeling, model scalability, edge deployment efficiency, and distributed inference capabilities. We present an end-to-end deep learning pipeline with three key components: (1) a data engine that combines traditional algorithms with our peak matching algorithm to generate high-quality training data at scale, (2) a modular architecture that scales from a few million to hundreds of million parameters, enabling us to train large expert-level models offline while deploying smaller, distilled models at the edge, and (3) a decoupled producer-consumer architecture that separates specialized data source layer from model inference, enabling flexible deployment across diverse computing environments. Using this integrated approach, our pipeline achieves accuracy comparable to traditional methods tuned by human experts while eliminating the need for experiment-specific parameter tuning. Although current throughput requires optimization for MHz facilities, our system's scalable architecture and demonstrated model compression capabilities provide a foundation for future high-throughput XFEL deployments.

Wang, Cong↗
DOE OSTI2021

Cosmic Ray Background Removal With Deep Neural Networks in SBND

In liquid argon time projection chambers exposed to neutrino beams and running on or near surface levels, cosmic muons, and other cosmic particles are incident on the detectors while a single neutrino-induced event is being recorded. In practice, this means that data from surface liquid argon time projection chambers will be dominated by cosmic particles, both as a source of event triggers and as the majority of the particle count in true neutrino-triggered events. In this work, we demonstrate a novel application of deep learning techniques to remove these background particles by applying deep learning on full detector images from the SBND detector, the near detector in the Fermilab Short-Baseline Neutrino Program. We use this technique to identify, on a pixel-by-pixel level, whether recorded activity originated from cosmic particles or neutrino interactions.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2020

Deep Minima in the Triply Differential Cross Section for Ionization of Atomic Hydrogen by Electron and Positron Impact

We investigate ionization of atomic hydrogen by electron- and positron-impact. We apply the Coulomb–Born (CB1) approximation, various modified CB1 approximations, the three body distorted wave (3DW) approximation, and the time-dependent close-coupling (TDCC) method to electron-impact ionization of hydrogen. For electron-impact ionization of hydrogen for an incident energy of approximately 76.45 eV, we obtain a deep minimum in the CB1 triply differential cross section (TDCS). However, the TDCC for 74.45 eV and the 3DW for 74.46 eV gave a dip in the TDCS. For positron-hydrogen ionization (breakup) we apply the CB1 approximation and a modified CB1 approximation. We obtain a deep minimum in the TDCS and a zero in the CB1 transition matrix element for an incident energy of 100 eV with a gun angle of 56.13 °. Corresponding to a zero in the CB1 transition matrix element, there is a vortex in the velocity field associated with this element. For both electron- and positron-impact ionization of hydrogen the velocity field rotates in the same direction, which is anticlockwise. All calculations are performed for a doubly symmetric geometry; the electron-impact ionization is in-plane and the positron-impact ionization is out-of-plane.

74 ATOMIC AND MOLECULAR PHYSICS↗
DOE OSTI2016

Effect of Deep Drying and Torrefaction Temperature on Proximate, Ultimate Composition, and Heating Value of 2-mm Lodgepole Pine (Pinus contorta) Grind

Deep drying and torrefaction is a thermal pretreatment method, where biomass is heated in the temperature range of 150–300°C in an inert or reduced environment. The process parameters like temperature and residence time has a significant impact on proximate, ultimate, and energy properties of the biomass. In the present study, torrrefaction experiments were conducted on 2 mm lodgepole pine grind using a thermogravimetric analyzer. Both deep drying and torrefaction temperature (160–270°C) and time (15–120 min) were selected. Torrefied samples were analyzed for proximate, ultimate and energy properties. Results indicated that moisture content decreased with increases in torrefaction temperature and time, where at 270°C and 120 min, the moisture content was found to be 1.15% (w.b.). Volatile content in the biomass decreased from about 80% to about 45%, and ash content increased from 0.77 to about 1.91% at 270°C and 120 min. The hydrogen, oxygen and sulfur content decreased to 3%, 28.24%, and 0.01 whereas carbon content and higher heating value increased to 68.86% and 23.67 MJ/kg at 270°C and 120 min. H/C and O/C ratio calculated at 270°C and 120 min residence time were about 0.56 and 0.47. This study indicated that higher torrefaction temperatures >230°C and residence time >15 min influenced the proximate, ultimate, and energy properties.

09 BIOMASS FUELS↗
DOE OSTI2019

Impact of Misclassification Rates on Compression Efficiency of Red Blood Cell Images of Malaria Infection Using Deep Learning

Malaria is a severe public health problem worldwide, with some developing countries being most affected. Reliable remote diagnosis of malaria infection will benefit from efficient compression of high-resolution microscopic images. This paper addresses a lossless compression of malaria-infected red blood cell images using deep learning. Specifically, we investigate a practical approach where images are first classified before being compressed using stacked autoencoders. We provide probabilistic analysis on the impact of misclassification rates on compression performance in terms of the information-theoretic measure of entropy. We then use malaria infection image datasets to evaluate the relations between misclassification rates and actually obtainable compressed bit rates using Golomb–Rice codes. Simulation results show that the joint pattern classification/compression method provides more efficient compression than several mainstream lossless compression techniques, such as JPEG2000, JPEG-LS, CALIC, and WebP, by exploiting common features extracted by deep learning on large datasets. This study provides new insight into the interplay between classification accuracy and compression bitrates. The proposed compression method can find useful telemedicine applications where efficient storage and rapid transfer of large image datasets is desirable.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2019

Post-Closure Performance Assessment for Deep Borehole Disposal of Cs/Sr Capsules

Post-closure performance assessment (PA) calculations suggest that deep borehole disposal of cesium (Cs)/strontium (Sr) capsules, a U.S. Department of Energy (DOE) waste form (WF), is safe, resulting in no releases to the biosphere over 10,000,000 years when the waste is placed in a 3–5 km deep waste disposal zone. The same is true when a hypothetical breach of a stuck waste package (WP) is assumed to occur at much shallower depths penetrated by through-going fractures. Cs and Sr retardation in the host rock is a key control over movement. Calculated borehole performance would be even stronger if credit was taken for the presence of the WP.

58 GEOSCIENCES↗
DOE OSTI2020

Closure Learning for Nonlinear Model Reduction Using Deep Residual Neural Network

Developing accurate, efficient, and robust closure models is essential in the construction of reduced order models (ROMs) for realistic nonlinear systems, which generally require drastic ROM mode truncations. We propose a deep residual neural network (ResNet) closure learning framework for ROMs of nonlinear systems. The novel ResNet-ROM framework consists of two steps: (i) In the first step, we use ROM projection to filter the given nonlinear system and construct a spatially filtered ROM. This filtered ROM is low-dimensional, but is not closed. (ii) In the second step, we use ResNet to close the filtered ROM, i.e., to model the interaction between the resolved and unresolved ROM modes. We emphasize that in the new ResNet-ROM framework, data is used only to complement classical physical modeling (i.e., only in the closure modeling component), not to completely replace it. We also note that the new ResNet-ROM is built on general ideas of spatial filtering and deep learning and is independent of (restrictive) phenomenological arguments, e.g., of eddy viscosity type. The numerical experiments for the 1D Burgers equation show that the ResNet-ROM is significantly more accurate than the standard projection ROM. The new ResNet-ROM is also more accurate and significantly more efficient than other modern ROM closure models.

Xie, Xuping↗
DOE OSTI2021

Hardware-Based Emulator with Deep Learning Model for Building Energy Control and Prediction Based on Occupancy Sensors’ Data

Heating, ventilation, and air conditioning (HVAC) is the largest source of residential energy consumption. Occupancy sensors’ data can be used for HVAC control since it indicates the number of people in the building. HVAC and sensors form a typical cyber-physical system (CPS). In this paper, we aim to build a hardware-based emulation platform to study the occupancy data’s features, which can be further extracted by using machine learning models. In particular, we propose two hardware-based emulators to investigate the use of wired/wireless communication interfaces for occupancy sensor-based building CPS control, and the use of deep learning to predict the building energy consumption with the sensor data. We hypothesize is that the building energy consumption may be predicted by using the occupancy data collected by the sensors, and question what type of prediction model should be used to accurately predict the energy load. Another hypothesis is that an in-lab hardware/software platform could be built to emulate the occupancy sensing process. The machine learning algorithms can then be used to analyze the energy load based on the sensing data. To test the emulator, the occupancy data from the sensors is used to predict energy consumption. The synchronization scheme between sensors and the HVAC server will be discussed. We have built two hardware/software emulation platforms to investigate the sensor/HVAC integration strategies, and used an enhanced deep learning model—which has sequence-to-sequence long short-term memory (Seq2Seq LSTM)—with an attention model to predict the building energy consumption with the preservation of the intrinsic patterns. Because the long-range temporal dependencies are captured, the Seq2Seq models may provide a higher accuracy by using LSTM architectures with encoder and decoder. Meanwhile, LSTMs can capture the temporal and spatial patterns of time series data. The attention model can highlight the most relevant input information in the energy prediction by allocating the attention weights. The communication overhead between the sensors and the HVAC control server can also be alleviated via the attention mechanism, which can automatically ignore the irrelevant information and amplify the relevant information during CNN training. Our experiments and performance analysis show that, compared with the traditional LSTM neural network, the performance of the proposed method has a 30% higher prediction accuracy.

Ye, Zhijing↗
DOE OSTI2022

Integrating Deep Learning and Hydrodynamic Modeling to Improve the Great Lakes Forecast

The Laurentian Great Lakes, one of the world’s largest surface freshwater systems, pose a modeling challenge in seasonal forecast and climate projection. While physics-based hydrodynamic modeling is a fundamental approach, improving the forecast accuracy remains critical. In recent years, machine learning (ML) has quickly emerged in geoscience applications, but its application to the Great Lakes hydrodynamic prediction is still in its early stages. This work is the first one to explore a deep learning approach to predicting spatiotemporal distributions of the lake surface temperature (LST) in the Great Lakes. Our study shows that the Long Short-Term Memory (LSTM) neural network, trained with the limited data from hypothetical monitoring networks, can provide consistent and robust performance. The LSTM prediction captured the LST spatiotemporal variabilities across the five Great Lakes well, suggesting an effective and efficient way for monitoring network design in assisting the ML-based forecast. Furthermore, we employed an explainable artificial intelligence (XAI) technique named SHapley Additive exPlanations (SHAP) to uncover how the features impact the LSTM prediction. Our XAI analysis shows air temperature is the most influential feature for predicting LST in the trained LSTM. The relatively large bias in the LSTM prediction during the spring and fall was associated with substantial heterogeneity of air temperature during the two seasons. In contrast, the physics-based hydrodynamic model performed better in spring and fall yet exhibited relatively large biases during the summer stratification period. Finally, we developed a statistical integration of the hydrodynamic modeling and deep learning results based on the Best Linear Unbiased Estimator (BLUE). The integration further enhanced prediction accuracy, suggesting its potential for next-generation Great Lakes forecast systems.

Xue, Pengfei (ORCID:000000025702421X)↗
DOE OSTI2023

Simple Statistical Models for Predicting Overpressure Due to CO2 and Low-Salinity Waste-Fluid Injection into Deep Saline Formations

Deep saline aquifers have been used for waste-fluid disposal for decades and are the proposed targets for large-scale CO2 storage to mitigate CO2 concentration in the atmosphere. Due to relatively limited experience with CO2 injection in deep saline formations and given that the injection targets for CO2 sometimes are the same as waste-fluid disposal formations, it could be beneficial to model and compare both practices and learn from the waste-fluid disposal industry. In this paper, we model CO2 injection in the Patterson Field, which has been proposed as a site for storage of 50 Mt of industrial CO2 over 25 years. We propose general models that quickly screen the reservoir properties and calculate pressure changes near and far from the injection wellbore, accounting for variable reservoir properties. The reservoir properties we investigated were rock compressibility, injection rate, vertical-to-horizontal permeability ratio, average reservoir permeability and porosity, reservoir temperature and pressure, and the injectant total dissolved solids (TDS) in cases of waste-fluid injection. We used experimental design to select and perform simulation runs, performed a sensitivity analysis to identify the important variables on pressure build-up, and then fit a regression model to the simulation runs to obtain simple proxy models for changes in average reservoir pressure and bottomhole pressure. The CO2 injection created more pressure compared to saline waste-fluids, when similar mass was injected. However, we found a more significant pressure buildup at the caprock-reservoir interface and lower pressure buildup at the bottom of the reservoir when injecting CO2 compared with waste-fluid injection.

Ansari, Esmail↗
DOE OSTI2026

Deep Learning and Photogrammetric Reconstruction for Automated Crack Detection and Dimensional Measurement in Mining Operations

Surface crack detection and dimensional measurement at active mining sites present significant safety and operational challenges. Manual inspection methods are labor-intensive, spatially incomplete, and expose personnel to hazardous environments, while existing automated approaches have been developed primarily for concrete civil infrastructure and have not been validated on the complex, variable surfaces characteristic of mining environments. This dissertation presents an automated pipeline that integrates deep learning semantic segmentation with Structure-from-Motion photogrammetry to detect surface cracks and measure their aperture, length, and vertical displacement from standard RGB imagery acquired during routine Uncrewed Aerial Vehicle (UAV) survey operations, without requiring additional sensor hardware or manual measurement. The pipeline combines a U-Net architecture with an EfficientNet-B0 encoder, pretrained on the SDNET2018 concrete crack dataset and fine-tuned on a mining-specific dataset spanning laboratory concrete specimens, coal refuse impoundment embankments, and post-blast limestone quarry benches. Photogrammetric reconstruction is performed using COLMAP Structure-from-Motion and Multi-View Stereo, with crack segmentation masks projected into the reconstructed point cloud to enable three-dimensional vertical displacement measurement through local plane fitting and bimodal surface detection. The pipeline was validated across 36 controlled laboratory specimens at three imaging distances and four vertical displacement levels, achieving aperture measurement RMSE of 0.047 cm and R² of 0.954, and vertical displacement RMSE of 0.140 cm and R² of 0.966, against independent caliper measurements. Field application at a coal refuse impoundment in southwestern Pennsylvania detected 71 crack components across the embankment crest, with a dominant longitudinal crack exhibiting aperture values reaching 28 cm and a 95th percentile vertical displacement of 35.53 cm, consistent in magnitude and spatial distribution with simultaneously acquired LiDAR-derived estimates. Application across four post-blast limestone quarry bench datasets in California successfully characterized blast-induced fracture networks at ground sampling distances ranging from 0.59 to 1.23 cm/pixel, with detected crack geometries physically consistent with observable surface conditions at each site. The results demonstrate that deep learning-based crack detection and photogrammetric measurement can be integrated into routine UAV inspection workflows at mining sites, providing repeatable, scalable, and quantitative crack characterization across surface types, crack scales, and displacement magnitudes not previously addressed in the literature. The pipeline requires no dedicated surveying equipment beyond the UAV platforms already deployed at mine sites for survey and monitoring purposes, supporting practical adoption within existing operational workflows.

Crack detection, Dimensional Measurement↗