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 667 records · Page 37
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Deep Generative Models that Solve PDEs: Distributed Computing for Training Large Data-Free Models

Recent progress in scientific machine learning (SciML) has opened up the possibility of training novel neural network architectures that solve complex partial differential equations (PDEs). Several (nearly data free) approaches have been recently reported that successfully solve PDEs, with examples including deep feed forward networks, generative networks, and deep encoder-decoder networks. However, practical adoption of these approaches is limited by the difficulty in training these models, especially to make predictions at large output resolutions (≥1024×1024). Here we report on a software framework for data parallel distributed deep learning that resolves the twin challenges of training these large SciML models - training in reasonable time as well as distributing the storage requirements. Our framework provides several out of the box functionality including (a) loss integrity independent of number of processes, (b) synchronized batch normalization, and (c) distributed higher-order optimization methods. We show excellent scalability of this framework on both cloud as well as HPC clusters, and report on the interplay between bandwidth, network topology and bare metal vs cloud. We deploy this approach to train generative models of sizes hitherto not possible, showing that neural PDE solvers can be viably trained for practical applications. We also demonstrate that distributed higher-order optimization methods are 2-3× faster than stochastic gradient-based methods and provide minimal convergence drift with higher batch-size.

PDEs↗
DOE OSTI2024

Deep Learning-Based Weather-Related Power Outage Prediction with Socio-Economic and Power Infrastructure Data

This paper presents a deep learning-based approach for hourly power outage probability prediction within census tracts encompassing a utility company's service territory. Two distinct deep learning models, conditional Multi-Layer Perceptron (MLP) and unconditional MLP, were developed to forecast power outage probabilities, leveraging a rich array of input features gathered from publicly available sources including weather data, weather station locations, power infrastructure maps, socio-economic and demographic statistics, and power outage records. Given a one-hour-ahead weather forecast, the models predict the power outage probability for each census tract, taking into account both the weather prediction and the location's characteristics. The deep learning models employed different loss functions to optimize prediction performance. Our experimental results underscore the significance of socio-economic factors in enhancing the accuracy of power outage predictions at the census tract level.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2019

DeepWelding: a Deep Learning Enhanced Approach to GTAW Using Multi-source Sensing Images

Deep learning has great potential to reshape manufacturing industries. In this paper, we present DeepWelding, a novel framework that applies deep learning techniques to improve gas tungsten arc welding (GTAW) process monitoring and penetration detection using multi-source sensing images. The framework is capable of analyzing multiple types of optical sensing images synchronously and consists of three deep learning enhanced consecutive phases: image preprocessing, image selection, and weld penetration classification. Specifically, we adopted generative adversarial networks (pix2pix) for image denoising and classic convolutional neural networks (AlexNet) for image selection. Both pix2pix and AlexNet delivered satisfactory performance. However, five individual neural networks with heterogeneous architectures demonstrated inconsistent generalization capabilities in the classification phase when holding out multi-source images generated with specific experimental settings. Therefore, two ensemble methods combining multiple neural networks were designed to improve the model performance on unseen data collected from different experimental settings. In conclusion, we also found that the quality of model prediction was heavily influenced by the data stream collection environment. We think these findings are beneficial for the broad intelligent welding community.

42 ENGINEERING↗
DOE OSTI2021

Deep Cellular Recurrent Network for Efficient Analysis of Time-Series Data With Spatial Information

Efficient processing of large-scale time series data is an intricate problem in machine learning. Conventional sensor signal processing pipelines with hand engineered feature extraction often involve huge computational cost with high dimensional data. Deep recurrent neural networks have shown promise in automated feature learning for improved time-series processing. However, generic deep recurrent models grow in scale and depth with increased complexity of the data. This is particularly challenging in presence of high dimensional data with temporal and spatial characteristics. Consequently, this work proposes a novel deep cellular recurrent neural network (DCRNN) architecture to efficiently process complex multi-dimensional time series data with spatial information. Here, the cellular recurrent architecture in the proposed model allows for location-aware synchronous processing of time series data from spatially distributed sensor signal sources. Extensive trainable parameter sharing due to cellularity in the proposed architecture ensures efficiency in the use of recurrent processing units with high-dimensional inputs. This study also investigates the versatility of the proposed DCRNN model for classification of multi-class time series data from different application domains. Consequently, the proposed DCRNN architecture is evaluated using two time-series datasets: a multichannel scalp EEG dataset for seizure detection, and a machine fault detection dataset obtained in-house. The results suggest that the proposed architecture achieves state-of-the-art performance while utilizing substantially less trainable parameters when compared to comparable methods in the literature.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2018

A Study of Complex Deep Learning Networks on High-Performance, Neuromorphic, and Quantum Computers

Current deep learning approaches have been very successful using convolutional neural networks trained on large graphical-processing-unit-based computers. Three limitations of this approach are that (1) they are based on a simple layered network topology, i.e., highly connected layers, without intra-layer connections; (2) the networks are manually configured to achieve optimal results, and (3) the implementation of the network model is expensive in both cost and power. In this paper, we evaluate deep learning models using three different computing architectures to address these problems: quantum computing to train complex topologies, high performance computing to automatically determine network topology, and neuromorphic computing for a low-power hardware implementation. We use the MNIST dataset for our experiment, due to input size limitations of current quantum computers. Our results show the feasibility of using the three architectures in tandem to address the above deep learning limitations. Finally, we show that a quantum computer can find high quality values of intra-layer connection weights in a tractable time as the complexity of the network increases, a high performance computer can find optimal layer-based topologies, and a neuromorphic computer can represent the complex topology and weights derived from the other architectures in low power memristive hardware.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Indications of a Decrease in the Depth of Deep Convective Cores with Increasing Aerosol Concentration during the CACTI Campaign

Abstract An aerosol indirect effect on deep convective cores (DCCs), by which increasing aerosol concentration increases cloud-top height via enhanced latent heating and updraft velocity, has been proposed in many studies. However, the magnitude of this effect remains uncertain due to aerosol measurement limitations, modulation of the effect by meteorological conditions, and difficulties untangling meteorological and aerosol effects on DCCs. The Cloud, Aerosol, and Complex Terrain Interactions (CACTI) campaign in 2018–19 produced concentrated aerosol and cloud observations in a location with frequent DCCs, providing an opportunity to examine the proposed aerosol indirect effect on DCC depth in a rigorous and robust manner. For periods throughout the campaign with well-mixed boundary layers, we analyze relationships that exist between aerosol variables (condensation nuclei concentration > 10 nm, 0.4% cloud condensation nuclei concentration, 55–1000-nm aerosol concentration, and aerosol optical depth) and meteorological variables [level of neutral buoyancy (LNB), convective available potential energy, midlevel relative humidity, and deep-layer vertical wind shear] with the maximum radar-echo-top height and cloud-top temperature (CTT) of DCCs. Meteorological variables such as LNB and deep-layer shear are strongly correlated with DCC depth. LNB is also highly correlated with three of the aerosol variables. After accounting for meteorological correlations, increasing values of the aerosol variables [with the exception of one formulation of aerosol optical depth (AOD)] are generally correlated at a statistically significant level with a warmer CTT of DCCs. Therefore, for the study region and period considered, increasing aerosol concentration is mostly associated with a decrease in DCC depth.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Combining multitask and transfer learning with deep Gaussian processes for autotuning-based performance engineering

We combine deep Gaussian processes (DGPs) with multitask and transfer learning for the performance modeling and optimization of HPC applications. Deep Gaussian processes merge the uncertainty quantification advantage of Gaussian processes (GPs) with the predictive power of deep learning. Multitask and transfer learning allow for improved learning efficiency when several similar tasks are to be learned simultaneously and when previous learned models are sought to help in the learning of new tasks, respectively. A comparison with state-of-the-art autotuners shows the advantage of our approach on two application problems. In this article, we combine DGPs with multitask and transfer learning to allow for both an improved tuning of an application parameters on problems of interest but also the prediction of parameters on any potential problem the application might encounter.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Physical and hydrodynamic properties of deep sea mining-generated, abyssal sediment plumes in the Clarion Clipperton Fracture Zone (eastern-central Pacific)

The anthropogenic impact of polymetallic nodule harvesting in the Clarion-Clipperton Fracture Zone is expected to strongly affect the benthic ecosystem. To predict the long-term, industrial-scale impact of nodule mining on the deep-sea environment and to improve the reliability of the sediment plume model, information about the specific characteristics of deep-sea particles is needed. Discharge simulations of mining-related fine-grained (median diameter ≈ 20 µm) sediment plumes at concentrations of 35–500 mg L –1 (dry weight) showed a propensity for rapid flocculation within 10 to 135 min, resulting in the formation of large aggregates up to 1100 µm in diameter. The results indicated that the discharge of elevated plume concentrations (500 mg L –1 ) under an increased shear rate (G ≥ 2.4 s –1 ) would result in improved efficiency of sediment flocculation. Furthermore, particle transport model results suggested that even under typical deep-sea flow conditions (G ≈ 0.1 s –1 ), rapid deposition of particles could be expected, which would restrict heavy sediment blanketing (several centimeters) to a smaller fall-out area near the source, unless subsequent flow events resuspended the sediments. Planning for in situ tests of these model projections is underway.

42 ENGINEERING↗
DOE OSTI2025

Denoising Seismograms in the Time Domain Using a Deep Learning Model

Deep learning has emerged as a transformative tool for enhancing the extraction of reliable information from seismograms, addressing the increasing demand for precise and efficient seismic data analysis. We introduce an innovative encoder–decoder deep learning model, named WaveDenoiser, designed for noise reduction in the time domain, thereby eliminating the need for spectrogram computations that have been used for existing deep learning tools and significantly improving processing speed. Utilizing the benchmark dataset that is Stanford Earthquake Dataset, we developed three models of varying sizes: base, medium, and large. Notably, the large (referred to as WaveDenoiser) model demonstrated superior performance, achieving a median signal‐to‐noise ratio improvement of 8.8 dB on in‐distribution unseen data (in the same geographic region) and 7.7 dB on out‐distribution unseen data (in a new geographic region), outpacing both the base and medium models. Further evaluation of the WaveDenoiser model revealed a reduction in median arrival‐time errors by 0.02 s for P waves and 0.01 s for S waves when processing waveforms prior to phase picking using PhaseNet on in‐distribution unseen data. When tested on out‐distribution unseen data, the model also effectively reduced the P‐wave median arrival‐time error by 0.02 and 0.01 s in median arrival‐time error for S waves. Importantly, the application of WaveDenoiser resulted in a significant reduction of phase picking outliers by 1.1% to 3.6% for both P and S waves. In addition, we achieved over five times acceleration in processing speed compared with the seisBench implementation of DeepDenoiser. Our findings underscore the potential of WaveDenoiser as a powerful tool for improving seismic data analysis and processing efficiency.

P-waves↗
DOE OSTI2014

Phase 1 Methyl Iodide Deep-Bed Adsorption Tests

Nuclear fission results in the production of fission products (FPs) and activation products including iodine-129, which could evolve into used fuel reprocessing facility off-gas systems, and could require off-gas control to limit air emissions to levels within acceptable emission limits. Research, demonstrations, and some reprocessing plant experience have indicated that diatomic iodine can be captured with efficiencies high enough to meet regulatory requirements. Research on the capture of organic iodides has also been performed, but to a lesser extent [Jubin 2012b]. Several questions remain open regarding the capture of iodine bound in organic compounds. Deep-bed methyl iodide adsorption testing has progressed according to a multi-laboratory methyl iodide adsorption test plan. This report summarizes the first phase of methyl iodide adsorption work performed according to this test plan using the deep-bed iodine adsorption test system at the Idaho National Laboratory (INL), performed during Fiscal Year (FY) 2013 and early FY-2014. Testing has been performed to address questions posed in the test plan, and followed the testing outline in the test plan. Tests established detection limits, developed procedures for sample analysis with minimal analytical interferences, and confirmed earlier results that show that the methyl iodide reacts when in contact with the AgZ sorbent, and not significantly in the gas flow upstream of the sorbent. The reaction(s) enable separation of the iodine from the organic moiety, so that the iodine can chemisorb onto the sorbent. The organic moiety can form other compounds, some of which are organic compounds that are detected and can be tentatively identified using GC-FID and GCMS. Test results also show that other gas constituents (NOx and/or H2O) can affect the methyl iodide reactions. With NOx and H2O present in the gas stream, the majority of uncaptured iodine exiting iodine-laden sorbent beds is in the form of I2 or HI, species that are soluble in NaOH scrubbing solution for iodine analysis. But when NOx and H2O are not present, then the majority of the uncaptured iodine exiting iodine-laden sorbent is in the form of methyl iodide. Methyl iodide adsorption efficiencies have been high enough so that initial DFs exceed 1,000 to 10,000. The methyl iodide mass transfer zone depths are estimated at 4-8 inches, possibly deeper than mass transfer zone depths estimated for I2 adsorption on AgZ. Additional deep-bed testing and analyses are recommended to (a) expand the data base for methyl iodide adsorption under various conditions specified in the methyl iodide test plan, and (b) provide more data for evaluating organic iodide reactions and reaction byproducts for different potential adsorption conditions.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2016

Phased Retrofits in Existing Homes In Florida Phase I: Shallow and Deep Retrofits

The U.S. Department of Energy (DOE) Building America program, in collaboration with Florida Power and Light (FPL), conducted a phased residential energy-efficiency retrofit program. This research sought to establish impacts on annual energy and peak energy reductions from the technologies applied at two levels of retrofit - shallow and deep, with savings levels approaching the Building America program goals of reducing whole-house energy use by 40%. Under the Phased Deep Retrofit (PDR) project, we have installed phased, energy-efficiency retrofits in a sample of 56 existing, all-electric homes. End-use savings and economic evaluation results from the phased measure packages and single measures are summarized in this report. Project results will be of interest to utility program designers, weatherization evaluators, and the housing remodel industry. Shallow retrofits were conducted in all homes from March to June 2013. The measures for this phase were chosen based on ease of installation, targeting lighting (CFLs and LED lamps), domestic hot water (wraps and showerheads), refrigeration (cleaning of coils), pool pump (reduction of operating hours), and the home entertainment center (smart plugs). Deep retrofits were conducted on a subset of ten PDR homes from May 2013 through March 2014. Measures included new air source heat pumps, duct repair, ceiling insulation, heat pump water heaters, variable speed pool pumps and learning thermostats. Major appliances such as refrigerators and dishwashers were replaced where they were old and inefficient.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2020

Geothermal Deep Direct Use for Turbine Inlet Cooling in East Texas

The National Renewable Energy Laboratory (NREL), the Southern Methodist University Geothermal Laboratory (SMU), Eastman Chemical (Longview, TX), and TAS (Houston, TX) evaluated the feasibility of using geothermal heat to improve the performance of a natural-gas power plant in East Texas. The area of interest is the Eastman Chemical plant in Longview, Texas, which is on the northwestern margin of a geologic region known as the Sabine Uplift. The feasibility study focused on determining the potential for accessing a subsurface hot-water geothermal resource within a 10-km radius of the site to provide thermal energy for absorption chillers. Wells within a 20-km radius are included for broader geological comparison to determine the heat flow, temperature-at-depth, field porosity and permeability. The lithologies of most interest are the Lower Cretaceous Trinity Group and Upper Jurassic Cotton Valley Group. The deeper Cotton Valley formations are hotter (averaging 117 to 130°C), yet permeability and porosity are low. The shallower Trinity Group contains more variability in permeability and porosity and lower temperatures averaging about 98 to 117°C. The shallower formations are considered despite the lower temperature because of increased ability to produce larger volumes of water and extract enough heat before reinjection. The complete SMU analysis is available in the National Geothermal Data System (NGDS). Tapping such deep geothermal sources for direct heating (as opposed to power generation) is known as geothermal deep direct use (DDU). Geothermal DDU has potential across a wide swath of the United States but is underutilized due to challenging project economics associated with developing a deep geothermal resource for what are typically small-scale, variable-demand projects. This project examines the feasibility of geothermal energy integration in a natural-gas combined cycle power station in East Texas. The DDU resource is tapped to drive absorption chillers (24/7) for production of chilled water at 5-10°C (41-50°F). This chilled water is stored until needed, which allows for continuous operation with a relatively small-capacity geothermal/absorption chiller system. When conditions are favorable, the chilled water is dispatched to cool the air entering the compressor stage of a gas combustion turbine. This process, known as turbine inlet cooling (TIC), boosts power production during periods of high temperature and high-power demand. Such systems can enhance grid reliability and reduce the cost for peak-demand power. A simulation model of the power plant was developed in IPSEpro software and validated against operational data from the plant. This model allowed the team to estimate the additional power that could be produced by applying TIC under different operating and ambient conditions. Absorption chiller performance was estimated from vendor sources to determine the production rate of chilled water from the geothermal resource. Geothermal drilling and development costs were estimated using NREL's GEOPHIRES 2.0. The expected lower drilling costs in this region led to an estimated cost of geothermal heat of about $4/MMBtu (1.4 cents/kWh t ). The estimated cost for the absorption chillers and TIC hardware were obtained from literature sources and project partners. Hourly data were obtained for weather, natural gas and electricity prices, and plant operating state for 2017, which served as a representative year. NREL estimated the capital cost, operating cost, and additional electricity production and revenue for different combinations of geothermal capacity, chiller capacity, and water storage-tank size. The analysis drove toward smaller geothermal and chiller systems to reduce equipment cost. A relatively low-cost water storage tank accumulated the near-continuous chilled water output for later use when TIC was most valued.

15 GEOTHERMAL ENERGY↗
DOE OSTI2021

Geothermal Heat Recovery Complex: Large-Scale, Deep Direct-Use System in a Low-Temperature Sedimentary Basin (Final Report)

A feasibility study of using deep direct-use (DDU) geothermal energy to heat agricultural research facilities (ARFs) was conducted at the University of Illinois at Urbana-Champaign (U of IL) and its similar application to military facilities in the Illinois Basin (ILB). The geothermal energy system (GES) investigated utilizes low-temperature (30–90°C; 90–190°F) geothermal fluid (i.e., brine) from an extraction well that is part of a deep, two-well (doublet) system that extends to the bottom of the ILB. The geothermal reservoir modeled, the Mt. Simon Sandstone (MSS), is about 1,280 m (4,200 feet) deep and 457 m thick (1,500 feet) beneath the U of IL. The DDU GES surface infrastructure includes heat exchangers connected in-parallel to pipelines carrying the geothermal fluid and fresh cold and hot water. Analysis of the GES indicated that the MSS can provide a baseload of 2 MMBtu/hr to heat the ARFs by extracting 954 m³/d (6,000 barrels/day [bbl/d]) of geothermal fluid that has a temperature of 44–46 °C (111–115 °F). In addition to analyzing the levelized cost of heat (LCOH) and life cycle costs, the environmental effects of the DDU GES were evaluated, including reduced greenhouse gas (GHG) emissions and water consumption. Multiple system designs were evaluated and then ranked based on their maximum heating performance, energy efficiency, and cost recovery. This feasibility study identified the key components of the fully-integrated DDU technology that can be implemented, both technically and economically. The results and information from this study provides end-users and policy makers with guidance for additional research on the specific components of DDU technology such that its widespread use can provide an uninterruptible energy source, increase resilience from extreme weather conditions, reduce U.S. dependency on fossil fuels, and reduce greenhouse gas (GHG) emissions. The site-specific part of this study gives U of IL administrators a realistic and pragmatic assessment of the financial resources necessary to add a DDU GES in the MSS to the campus’ energy portfolio.

15 GEOTHERMAL ENERGY↗
DOE OSTI2022

Nonlocal Kernel Network (NKN): a Stable and Resolution-Independent Deep Neural Network.

Neural operators have recently become popular tools for designing solution maps between function spaces in the form of neural networks. Differently from classical scientific machine learning approaches that learn parameters of a known partial differential equation (PDE) for a single instance of the input parameters at a fixed resolution, neural operators approximate the solution map of a family of PDEs [6, 7]. Despite their success, the uses of neural operators are so far restricted to relatively shallow neural networks and confined to learning hidden governing laws. In this work, we propose a novel nonlocal neural operator, which we refer to as nonlocal kernel network (NKN), that is resolution independent, characterized by deep neural networks, and capable of handling a variety of tasks such as learning governing equations and classifying images. Our NKN stems from the interpretation of the neural network as a discrete nonlocal diffusion reaction equation that, in the limit of infinite layers, is equivalent to a parabolic nonlocal equation, whose stability is analyzed via nonlocal vector calculus. The resemblance with integral forms of neural operators allows NKNs to capture long-range dependencies in the feature space, while the continuous treatment of node-to-node interactions makes NKNs resolution independent. The resemblance with neural ODEs, reinterpreted in a nonlocal sense, and the stable network dynamics between layers allow for generalization of NKN’s optimal parameters from shallow to deep networks. This fact enables the use of shallow-to-deep initialization techniques [8]. Our tests show that NKNs outperform baseline methods in both learning governing equations and image classification tasks and generalize well to different resolutions and depths.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Multi-Level Structural Damage Characterization Using Sparse Acoustic Sensor Networks and Knowledge Transferred Deep Learning

Standard structural health monitoring techniques face well-known difficulties for comprehensive defect diagnosis in real-world structures that have structural, material, or geometric complexity. This motivates the exploration of machine-learning-based structural health monitoring methods in complex structures. However, creating sufficient training data sets with various defects is an ongoing challenge for data-driven machine (deep) learning algorithms. The ability to transfer the knowledge of a trained neural network from one component to another or to other sections of the same component would drastically reduce the required training data set. Also, it would facilitate computationally inexpensive machine learning based inspection systems. In this work, a machine-learning-based multi-level damage characterization is demonstrated with the ability to transfer trained knowledge within the sparse sensor network. A novel network spatial assistance and an adaptive convolution technique are proposed for efficient knowledge transfer within the deep learning algorithm. Proposed structural health monitoring method is experimentally evaluated on an aluminum plate with artificially induced defects. It was observed that the method improves the performance of knowledge transferred damage characterization by 50% during localization and 24% during severity assessment. Further, experiments using time windows with and without multiple edge reflections are studied. Results reveal that multiply scattered waves contain rich and deterministic defect signatures that can be mined using deep learning neural networks, improving the accuracy of both identification and quantification. In the case of a fixed sensor network, using multiply scattered waves shows 100% prediction accuracy at all levels of damage characterization.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Physics-Informed Deep Learning for Reconstruction of Spatial Missing Climate Information in the Antarctic

Understanding the influence of the Antarctic on the global climate is crucial for the prediction of global warming. However, due to very few observation sites, it is difficult to reconstruct the rational spatial pattern by filling in the missing values from the limited site observations. To tackle this challenge, regional spatial gap-filling methods, such as Kriging and inverse distance weighted (IDW), are regularly used in geoscience. Nevertheless, the reconstructing credibility of these methods is undesirable when the spatial structure has massive missing pieces. Inspired by image inpainting, we propose a novel deep learning method that demonstrates a good effect by embedding the physics-aware initialization of deep learning methods for rapid learning and capturing the spatial dependence for the high-fidelity imputation of missing areas. We create the benchmark dataset that artificially masks the Antarctic region with ratios of 30%, 50% and 70%. The reconstructing monthly mean surface temperature using the deep learning image inpainting method RFR (Recurrent Feature Reasoning) exhibits an average of 63% and 71% improvement of accuracy over Kriging and IDW under different missing rates. With regard to wind speed, there are still 36% and 50% improvements. In particular, the achieved improvement is even better for the larger missing ratio, such as under the 70% missing rate, where the accuracy of RFR is 68% and 74% higher than Kriging and IDW for temperature and also 38% and 46% higher for wind speed. In addition, the PI-RFR (Physics-Informed Recurrent Feature Reasoning) method we proposed is initialized using the spatial pattern data simulated by the numerical climate model instead of the unified average. Compared with RFR, PI-RFR has an average accuracy improvement of 10% for temperature and 9% for wind speed. When applied to reconstruct the spatial pattern based on the Antarctic site observations, where the missing rate is over 90%, the proposed method exhibits more spatial characteristics than Kriging and IDW.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

G2PDeep-v2: A Web-Based Deep-Learning Framework for Phenotype Prediction and Biomarker Discovery for All Organisms Using Multi-Omics Data

Multi-omics data offers rich insights into complex traits across organisms, yet integrating and analyzing these datasets for phenotype prediction and marker discovery remains challenging. Researchers need accessible tools that combine deep learning, hyperparameter optimization, visualization, and downstream analysis in a unified web platform. To address this, we developed G2PDeep-v2, a web-based platform powered by deep learning for phenotype prediction and marker discovery from multi-omics data across a wide range of organisms, including humans and plants. The server provides multiple services for researchers to create deep-learning models through an interactive interface and train these models using an automated hyperparameter tuning algorithm on high-performance computing resources. Users can visualize the results of phenotype and markers predictions and perform Gene Set Enrichment Analysis for the significant markers to provide insights into the molecular mechanisms underlying complex diseases, conditions and other biological phenotypes being studied.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2018

Adiabatic Quantum Computation Applied to Deep Learning Networks

Training deep learning networks is a difficult task due to computational complexity, and this is traditionally handled by simplifying network topology to enable parallel computation on graphical processing units (GPUs). However, the emergence of quantum devices allows reconsideration of complex topologies. We illustrate a particular network topology that can be trained to classify MNIST data (an image dataset of handwritten digits) and neutrino detection data using a restricted form of adiabatic quantum computation known as quantum annealing performed by a D-Wave processor. We provide a brief description of the hardware and how it solves Ising models, how we translate our data into the corresponding Ising models, and how we use available expanded topology options to explore potential performance improvements. Although we focus on the application of quantum annealing in this article, the work discussed here is just one of three approaches we explored as part of a larger project that considers alternative means for training deep learning networks. The other approaches involve using a high performance computing (HPC) environment to automatically find network topologies with good performance and using neuromorphic computing to find a low-power solution for training deep learning networks. Our results show that our quantum approach can find good network parameters in a reasonable time despite increased network topology complexity; that HPC can find good parameters for traditional, simplified network topologies; and that neuromorphic computers can use low power memristive hardware to represent complex topologies and parameters derived from other architecture choices.

97 MATHEMATICS AND COMPUTING↗