SEARCH · Engineering Papers

Results for “deep generative models”

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 955 records · Page 53

All sources NASA NTRS DOE OSTI

DOE OSTI2024

Sub-millisecond keyhole pore detection in laser powder bed fusion using sound and light sensors and machine learning

Laser powder bed fusion is a mainstream additive manufacturing technology widely used to manufacture complex parts in prominent sectors, including aerospace, biomedical, and automotive industries. However, during the printing process, the presence of an unstable vapor depression can lead to a type of defect called keyhole porosity, which is detrimental to the part quality. In this study, we developed an effective approach to locally detect the generation of keyhole pores during the printing process by leveraging machine learning and a suite of optical and acoustic sensors. Simultaneous synchrotron x-ray imaging allows the direct visualization of pore generation events inside the sample, offering high-fidelity ground truth. A neural network model adopting SqueezeNet architecture using single-sensor data was developed to evaluate the fidelity of each sensor for capturing keyhole pore generation events. Our comparative study shows that the near infrared images gave the highest prediction accuracy, followed by 100 kHz and 20 kHz microphones, and the photodiode sensitive to processing laser wavelength had the lowest accuracy. Using a single sensor, over 90% prediction accuracy can be achieved with a temporal resolution as short as 0.1 ms. A data fusion scheme was also developed with features extracted using SqueezeNet neural network architecture and classification using different machine learning algorithms. Our work demonstrates the correlation between the characteristic optical and acoustic emissions and the keyhole oscillation behavior, and thereby provides strong physics support for the machine learning approach.

36 MATERIALS SCIENCE↗

DOE OSTI2024

Universal Fourier Attack for Time Series

A wide variety of adversarial attacks have been proposed and explored using image and audio data. These attacks are notoriously easy to generate digitally when the attacker can directly manipulate the input to a model, but are much more difficult to implement in the real world. In this paper we present a universal, time invariant attack for general time series data such that the attack has a frequency spectrum primarily composed of the frequencies present in the original data. The universality of the attack makes it fast and easy to implement as no computation is required to add it to an input, while time invariance is useful for real world deployment. Additionally, the frequency constraint ensures the attack can withstand filtering defenses. We demonstrate the effectiveness of the attack on two different classification tasks through both digital and real world experiments, and show that the attack is robust against common transform-and-compare defense pipelines.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2021

Predicting bulge to total luminosity ratio of galaxies using deep learning

ABSTRACT We present a deep learning model to predict the r-band bulge-to-total luminosity ratio (B/T) of nearby galaxies using their multiband JPEG images alone. Our Convolutional Neural Network (CNN) based regression model is trained on a large sample of galaxies with reliable decomposition into the bulge and disc components. The existing approaches to estimate the B/T ratio use galaxy light-profile modelling to find the best fit. This method is computationally expensive, prohibitively so for large samples of galaxies, and requires a significant amount of human intervention. Machine learning models have the potential to overcome these shortcomings. In our CNN model, for a test set of 20 000 galaxies, 85.7 per cent of the predicted B/T values have absolute error (AE) less than 0.1. We see further improvement to 87.5 per cent if, while testing, we only consider brighter galaxies (with r-band apparent magnitude <17) with no bright neighbours. Our model estimates the B/T ratio for the 20 000 test galaxies in less than a minute. This is a significant improvement in inference time from the conventional fitting pipelines, which manage around 2–3 estimates per minute. Thus, the proposed machine learning approach could potentially save a tremendous amount of time, effort, and computational resources while predicting B/T reliably, particularly in the era of next-generation sky surveys such as the Legacy Survey of Space and Time (LSST) and the Euclid sky survey which will produce extremely large samples of galaxies.

Grover, Harsh (ORCID:0000000321338142)↗

DOE OSTI2025

SigTime: Learning and Visually Explaining Time Series Signatures

Understanding and distinguishing temporal patterns in time series data is essential for scientific discovery and decision-making. For example, in biomedical research, uncovering meaningful patterns in physiological signals can improve diagnosis, risk assessment, and patient outcomes. However, existing methods for time series pattern discovery face major challenges, including high computational complexity, limited interpretability, and difficulty in capturing meaningful temporal structures. Here, to address these gaps, we introduce a novel learning framework that jointly trains two Transformer models using complementary time series representations: shapelet-based representations to capture localized temporal structures and traditional feature engineering to encode statistical properties. The learned shapelets serve as interpretable signatures that differentiate time series across classification labels. Additionally, we develop a visual analytics system—SigTime—with coordinated views to facilitate exploration of time series signatures from multiple perspectives, aiding in useful insights generation. We quantitatively evaluate our learning framework on eight publicly available datasets and one proprietary clinical dataset. Additionally, we demonstrate the effectiveness of our system through two usage scenarios along with the domain experts: one involving public ECG data and the other focused on preterm labor analysis.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

The NuMI Flux Prediction at ICARUS

The Deep Underground Neutrino Experiment (DUNE) is a next-generation long-baseline neutrino oscillation experiment seeking to probe fundamental symmetries within the structure of the Pontecorvo-Maki-Nakagawa-Sakata (PMNS) mixing matrix, and perform precision measurements its parameters including the neutrino mass ordering via the sign of $\Delta m^2_{31}$, and the charge-parity violating phase, $\delta_{CP}$. To make these measurements with high precision, DUNE will require external $\nu$-Ar scattering cross section data as a crucial input to the oscillation fit. Imaging Cosmic And Rare Underground Signals (ICARUS) is a 476 t liquid argon neutrino detector located at Fermi National Accelerator Laboratory (FNAL) where it is serving as the far detector for the Short-Baseline Neutrino (SBN) program along the Booster Neutrino Beam (BNB) axis. ICARUS additionally lies 795 m downstream and 100.1 mrad off-axis of the Neutrinos at the Main Injector (NuMI) neutrino beam. From this position, ICARUS is exposed to a large flux of NuMI (anti-)electron and (anti-)muon neutrinos, and poses a unique opportunity to provide high-statistics measurements of quasi-elastic and single pion-production cross sections for four neutrino flavors ($\nu_{\mu}$, $\nu_{e}$, $\bar{\nu}_{\mu}$, $\bar{\nu}_{e}$). This dissertation is centered around accurately characterizing the models and estimating their precision for use in making these measurements. This includes identifying major sources of uncertainty in the models such that they can be properly propagated to the cross section measurements. Specifically, this work focused on the model of the NuMI beamline and its impact on the neutrino fluxes, but also delved into the detector response model and its impact on reconstructed observables in the detector. Significant efforts were made to improve the characterization to enhance precision and thus reduce the level of propagated uncertainty. In particular, the NuMI flux was determined to be composed of 57% $\nu_{\mu}$, 38% $\bar{\nu}_{\mu}$, 3% $\nu_{e}$, and 2% $\bar{\nu}_{e}$ while the horns are operating in the positive-particle focusing configuration. The total uncertainty on the $\nu_{\mu} + \bar{\nu}_{\mu}$ ($\nu_{e} + \bar{\nu}_{e}$) flux while operating in the forward horn operating mode was determined to be 10.84% (9.04%). Compared to the on-axis flux, mesons that eventually decay to neutrinos more frequently reinteract within the NuMI structure, resulting in elevated uncertainty as these processes are not well-constrained by existing hadron interaction cross section measurements. Covariance matrices were calculated to propagate the flux uncertainty characterization to NuMI analyses.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2024

Measurement of the 1-jettiness event shape observable in deep-inelastic electron-proton scattering at HERA

The H1 Collaboration reports the first measurement of the 1-jettiness event shape observable $τ^b_1$ in neutral-current deep-inelastic electron-proton scattering (DIS). The observable $τ^b_1$ is equivalent to a thrust observable defined in the Breit frame. The data sample was collected at the HERA ep collider in the years 2003–2007 with center-of-mass energy of $\sqrt{s}$ = 319 GeV, corresponding to an integrated luminosity of 351.1 pb -1 . Triple differential cross sections are provided as a function of $τ^b_1$, event virtuality $Q^2$, and inelasticity y, in the kinematic region $Q^2$ > 150 GeV 2 . Single differential cross section are provided as a function of $τ^b_1$ in a limited kinematic range. Double differential cross sections are measured, in contrast, integrated over $τ^b_1$ and represent the inclusive neutral-current DIS cross section measured as a function of $Q^2$ and y. The data are compared to a variety of predictions and include classical and modern Monte Carlo event generators, predictions in fixed-order perturbative QCD where calculations up to $\mathcal{O}$($α^3_s$) are available for $τ^b_1$ or inclusive DIS, and resummed predictions at next-to-leading logarithmic accuracy matched to fixed order predictions at $\mathcal{O}$($α^2_s$). These comparisons reveal sensitivity of the 1-jettiness observable to QCD parton shower and resummation effects, as well as the modeling of hadronization and fragmentation. Within their range of validity, the fixed-order predictions provide a good description of the data. Monte Carlo event generators are predictive over the full measured range and hence their underlying models and parameters can be constrained by comparing to the presented data.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2024

Bottom-up design of actinide materials from molecular clusters: Demonstration of a general-purpose simulation capability leveraging machine-learned atomic potentials

Actinide thin-film coatings such as uranium dioxide (UO 2 ) play an important role in nuclear reactors and other mission-relevant applications, but realization of their potential requires a deep fundamental understanding of the chemical vapor deposition (CVD) processes used for their growth. The slow experimental progress can be attributed, in part, to the standard safety guidelines associated with handling uranium byproducts, which are often corrosive, toxic, and radioactive. Accurate simulation techniques, when used in concert with experiment, can improve laboratory safety, material durability, and deliverable timeframes. However, state-of-the-art computational methods are either insufficiently accurate or intractably expensive. To remedy this situation, in this project we suggested a machine-learning (ML) accelerated workflow for simulating molecular clustering toward deposition. As a benchmark test case, we considered molecular clustering in steam and assessed independent components of our workflow by comparing with measured thermodynamic properties of water. After analyzing each component individually and finding no fundamental barrier to realization of the workflow, we attempted to integrate the ML component, a Sandia-developed tool called FitSNAP. As this was the first application of FitSNAP to atoms and molecules in the gas phase at Sandia, the method required more fitting data than was originally anticipated. Systematic improvements were made by including in the fit data diatomic potentials, molecular single-bond-breaking curves, and symmetry-constrained intermolecular potentials. We concluded that our strategy provides a feasible pathway toward modeling CVD and related processes, but that extensive training data must be generated before it can be of practical use.

36 MATERIALS SCIENCE↗

DOE OSTI2025

Effective field theory factorization for diffraction

We derive a factorization formula for coherent and incoherent ep diffraction using the soft collinear effective theory, utilizing multiple power expansion parameters to handle different kinematic regions. This goes beyond the known hard-collinear diffractive factorization to address the small-x Regge dynamics and Pomeron exchange from first principles. The effective field theory analysis also uncovers and factorizes an important irreducible incoherent background generated by color-nonsinglet exchange, dubbed “quasi-diffraction”, for which we calculate the associated Sudakov suppression. For unpolarized scattering we show that there are four diffractive structure functions at leading power, and point out the importance of studying ${F}_{3,4}^D$ through asymmetries, in addition to ${F}_{2,L}^D$. For the quasi-diffractive background, we make model independent predictions for ratios of the corresponding structure functions in a perturbative kinematic region. Our analysis also makes predictions for six leading-power spin-dependent structure functions. Finally, we provide connections to diffractive parton distributions, and assess the Ingelman-Schlein model. Our work lays a path for further QCD-based studies of diffraction.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2024

Reinforcement learning pulses for transmon qubit entangling gates

The utility of a quantum computer is highly dependent on the ability to reliably perform accurate quantum logic operations. For finding optimal control solutions, it is of particular interest to explore model-free approaches, since their quality is not constrained by the limited accuracy of theoretical models for the quantum processor—in contrast to many established gate implementation strategies. In this work, we utilize a continuous control reinforcement learning algorithm to design entangling two-qubit gates for superconducting qubits; specifically, our agent constructs cross-resonance and CNOT gates without any prior information about the physical system. Using a simulated environment of fixed-frequency fixed-coupling transmon qubits, we demonstrate the capability to generate novel pulse sequences that outperform the standard cross-resonance gates in both fidelity and gate duration, while maintaining a comparable susceptibility to stochastic unitary noise. We further showcase an augmentation in training and input information that allows our agent to adapt its pulse design abilities to drifting hardware characteristics, importantly, with little to no additional optimization. Our results exhibit clearly the advantages of unbiased adaptive-feedback learning-based optimization methods for transmon gate design.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DOE OSTI2023

Materials characterization: Can artificial intelligence be used to address reproducibility challenges?

Material characterization techniques are widely used to characterize the physical and chemical properties of materials at the nanoscale and, thus, play central roles in material scientific discoveries. However, the large and complex datasets generated by these techniques often require significant human effort to interpret and extract meaningful physicochemical insights. Artificial intelligence (AI) techniques such as machine learning (ML) have the potential to improve the efficiency and accuracy of surface analysis by automating data analysis and interpretation. In this perspective paper, we review the current role of AI in surface analysis and discuss its future potential to accelerate discoveries in surface science, materials science, and interface science. We highlight several applications where AI has already been used to analyze surface analysis data, including the identification of crystal structures from XRD data, analysis of XPS spectra for surface composition, and the interpretation of TEM and SEM images for particle morphology and size. We also discuss the challenges and opportunities associated with the integration of AI into surface analysis workflows. These include the need for large and diverse datasets for training ML models, the importance of feature selection and representation, and the potential for ML to enable new insights and discoveries by identifying patterns and relationships in complex datasets. Most importantly, AI analyzed data must not just find the best mathematical description of the data, but it must find the most physical and chemically meaningful results. In addition, the need for reproducibility in scientific research has become increasingly important in recent years. The advancement of AI, including both conventional and the increasing popular deep learning, is showing promise in addressing those challenges by enabling the execution and verification of scientific progress. By training models on large experimental datasets and providing automated analysis and data interpretation, AI can help to ensure that scientific results are reproducible and reliable. Although integration of knowledge and AI models must be considered for the transparency and interpretability of models, the incorporation of AI into the data collection and processing workflow will significantly enhance the efficiency and accuracy of various surface analysis techniques and deepen our understanding at an accelerated pace.

Materials Science↗

DOE OSTI2025

In situ Detection of Plasma Induced Surface Interaction based on Deep Learning based Visual Diagnostics (Technical Report)

It is characteristic for many plasma devices to undergo plasma-material interaction leading to surface erosion. These processes, often not easily detectable, lead to changes in device performance and lifespan. State-of-the-art lifetime tests and wear experiments require over 1000s hours. A self-consistent model for accurately predicting the erosion's effects is not available. In situ detection of these processes is not a trivial task since the surface variations at the early stages have a micron scale. Such limitations not only restrict testing and prediction capabilities but also slow the development of new thrusters and limit mission duration. To address these challenges, an in-situ diagnostic for real-time erosion assessment has been developed, aiming to expedite lifetime testing and broaden experimental campaigns. Several works were dedicated to real-time and in situ monitoring of material erosion during plasma exposure using laser holography, microscopy, and with telemicroscopes. However, the applicability of these approaches is limited due to complexity, cost and less flexibility as they often require placing diagnostic equipment inside the vacuum chamber. In collaboration with Princeton Collaborative Research Facility (PCRF), Princeton Plasma Physics Laboratory (PPPL), a new diagnostic approach is developed, where geometry modifications to the ceramic channel walls were introduced that would result in accelerated channel erosion. We employed Long-distance microscope (LDM) imagery, combined with Deep-Learning based Shape from focus or depth from focus (DFF or SFF) approach, that provides an accessible and cost-effective solution. LDM employs focus variation techniques to continuously capture multiple images of the target object at distinct focal planes. DFF, an optical focus variation method, generates a 3D topographical surface depth map from a sequence of variably focused images. Combined with the developed diagnostic, this approach offers a controllable means to study erosion under accelerated conditions. In this work, we develop Neural Network-based DFF algorithm applicable for LDM data to quantitatively evaluate plasma induced surface modification from LDM data. Next, we develop Deep Learning-based super-resolution depth map image reconstruction technique to increase the resolution of depth maps obtained from DFF algorithm to improve the accuracy of erosion measurements. Thirdly, we develop several image processing techniques to remove noise and improve the quality of depth map image. Here we report the results of initial tests for this approach. An experimental setup designed and built in PPPL was employed that consists of a 3-cm gridded ion source that produces a neutralized argon beam with energies up to 600 eV. A hexagonal boron nitride (h-BN) ceramic target, designed based on computational predictions, was used. Tests were conducted to reconstruct the complex geometry of the target under the lighting conditions of the operated ion source.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2020

Optimizing Cornell’s future geothermal district heating performance through systems engineering and simulation

Cornell University’s intention to lower its carbon footprint has motivated this engineering evaluation of using low-temperature geothermal energy to supply heat to the campus district energy system. Optimal selection and operation of heat pumps can significantly improve system performance. To support this analysis, we model the quantitative relationships between heat pump configurations and source flow, supply and distribution temperatures, facility heating design options, output heat generation, and carbon abatement outcomes. A systems approach is used for analysis, troubleshooting, and improvement of the model. The result of this effort is a dynamic tool that appropriately responds to hourly thermal demand and communicates energy response for techno-economic analysis. Simulations indicate that a single well-pair in the local Basement Contact Zone reservoir can satisfy almost 68% of annual thermal demand at nearly 20 MWth average capacity while remaining financially competitive compared to conventional heating with levelized cost of heating (LCOH) as low as $4.55/MMBTU ($15.53/MWh th ). A direct-use scheme with heat pump augmentation provided more carbon abatement and 50 to 150% more annual heat supply than one without augmentation. Exploration of three and four well-pair scenarios prove the capability to achieve 50 MW th baseload heating capacity with competitive LCOH and significant carbon reductions.

15 GEOTHERMAL ENERGY↗

DOE OSTI2024

Mechanical and Thermal Forcing for Upslope Flows and Cumulus Convection over the Sierras de Córdoba

Abstract The upslope flow processes affecting the vertical extent of orographic cumulus convection are examined using observations from the Cloud, Aerosol, and Complex Terrain Interactions (CACTI) field campaign. Specifically, clear air returns from the U.S. Department of Energy (DOE) second-generation C-band scanning Atmospheric Radiation Measurement (ARM) precipitation radar (CSAPR2) are used to characterize the structure and variability of the ridge-normal (i.e., up/downslope) flow components, which transport mass to the crest of Argentina’s Sierras de Córdoba and contribute to convective initiation. Data are compiled for the entire CACTI period (October–April), including days with clear skies, shallow cumuli, cumulus congestus, and deep convection. To examine shared variability among >70 000 radar scans, we use (i) a principal component analysis (PCA) to isolate modes of variability in the upslope flow and (ii) composite analysis based on convective outcomes, determined from GOES-16 satellite observations. These data are contextualized with observed surface sensible heat fluxes, thermodynamic profiles, and synoptic-scale analysis. Results indicate distinct thermally and mechanically forced upslope flow modes, modulated by diurnal heating and synoptic-scale variations, respectively. In some instances, there is a superposition of thermal and mechanical forcing, yielding either deeper or shallower upslope flow. The composite analyses based on satellite data show that successively deeper convective outcomes are associated with successively deeper upslope flow layers that more readily transport mass to the ridge crest in conjunction with lower lifting condensation levels, facilitating convective initiation. These results help to isolate the forcing mechanisms for orographic convection and thus provide a foundation for parameterizing orographic convective processes in coarse resolution models.

Meteorology & Atmospheric Sciences↗

DOE OSTI2021

Interpretation of hydrothermal conditions, production-injection induced effects, and evidence for enhanced geothermal system-type heat exchange in response to >30 years of production at Roosevelt Hot Springs, Utah, USA

The Roosevelt Hot Springs hydrothermal system is located at the base of the Mineral Mountains in southwestern Utah on the eastern side of the Basin and Range. Hydrothermal activity is related to relatively recent bimodal magmatism, and the system is hosted in coarsely crystalline rock made of Oligocene–Miocene granitoids and Precambrian gneiss. The hydrothermal plume covers ~5 km 2 , with a maximum temperature of 268 °C at ~750 m depth, and a vertically extensive fault-fracture mesh east of the Opal Mound fault controls the upflow of hydrothermal fluids. Power generation (currently 38 MWe gross) began in 1984, and up through 2016, four wells were used for fluid production, and three wells were used for edge-field injection. Chemical analyses of produced fluids show that modern reservoir fluid compositions are similar to but more concentrated than those at the start of production, having near-neutral pH, total dissolved solids of 7000–10,000 mg/kg, and ionic ratios of Cl/HCO 3 ~50–100, Cl/SO4 ~50–100, and Na/K ~4–5. Chemical geothermometers indicate equilibration temperatures that mainly range between 240° and 300 °C. Early production induced a steep drop in pressure (~3.0–3.5 MPa), which was accompanied by a 250–300 m lowering of piezometric levels in wells and development of a shallow steam zone across the system. Hydrothermal fluid compositions evolved continuously in response to production-related steam-loss and injection breakthrough, which is reflected by gradual increases in chloride of up to 35% and stable isotope ratios of up to ~2‰δ 18 O and ~10‰δD. Simple mixing model calculations suggest that there has been a significant amount, ~10–20 MW th , of sustained multi-decadal heat mining and enhanced geothermal system (EGS)–type heat transfer by the injectate as it returns to the production zone. Overall, the two factors that have sustained long-term power production (currently 38 MWe gross) are the increased upflow of deep chloride water and, to a lesser extent, the mining of heat at <1 km depth.

58 GEOSCIENCES↗

DOE OSTI2021

Deep Learning Approaches to Surrogates for Solving the Diffusion Equation for Mechanistic Real-World Simulations

In many mechanistic medical, biological, physical, and engineered spatiotemporal dynamic models the numerical solution of partial differential equations (PDEs), especially for diffusion, fluid flow and mechanical relaxation, can make simulations impractically slow. Biological models of tissues and organs often require the simultaneous calculation of the spatial variation of concentration of dozens of diffusing chemical species. One clinical example where rapid calculation of a diffusing field is of use is the estimation of oxygen gradients in the retina, based on imaging of the retinal vasculature, to guide surgical interventions in diabetic retinopathy. Furthermore, the ability to predict blood perfusion and oxygenation may one day guide clinical interventions in diverse settings, i.e., from stent placement in treating heart disease to BOLD fMRI interpretation in evaluating cognitive function (Xie et al., 2019; Lee et al., 2020). Since the quasi-steady-state solutions required for fast-diffusing chemical species like oxygen are particularly computationally costly, we consider the use of a neural network to provide an approximate solution to the steady-state diffusion equation. Machine learning surrogates, neural networks trained to provide approximate solutions to such complicated numerical problems, can often provide speed-ups of several orders of magnitude compared to direct calculation. Surrogates of PDEs could enable use of larger and more detailed models than are possible with direct calculation and can make including such simulations in real-time or near-real time workflows practical. Creating a surrogate requires running the direct calculation tens of thousands of times to generate training data and then training the neural network, both of which are computationally expensive. Often the practical applications of such models require thousands to millions of replica simulations, for example for parameter identification and uncertainty quantification, each of which gains speed from surrogate use and rapidly recovers the up-front costs of surrogate generation. We use a Convolutional Neural Network to approximate the stationary solution to the diffusion equation in the case of two equal-diameter, circular, constant-value sources located at random positions in a two-dimensional square domain with absorbing boundary conditions. Such a configuration caricatures the chemical concentration field of a fast-diffusing species like oxygen in a tissue with two parallel blood vessels in a cross section perpendicular to the two blood vessels. To improve convergence during training, we apply a training approach that uses roll-back to reject stochastic changes to the network that increase the loss function. The trained neural network approximation is about 1000 times faster than the direct calculation for individual replicas. Because different applications will have different criteria for acceptable approximation accuracy, we discuss a variety of loss functions and accuracy estimators that can help select the best network for a particular application. We briefly discuss some of the issues we encountered with overfitting, mismapping of the field values and the geometrical conditions that lead to large absolute and relative errors in the approximate solution.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2024

The Physics behind Precipitation Onset Bias in CMIP6 Models: The Pseudo-Entrainment Diagnostic and Trade-Offs between Lapse Rate and Humidity

Conditional instability and the buoyancy of plumes drive moist convection but have a variety of representations in model convective schemes. Vertical thermodynamic structure information from Atmospheric Radiation Measurement (ARM) sites and reanalysis (ERA5), satellite-derived precipitation (TRMM3b42), and diagnostics relevant for plume buoyancy are used to assess climate models. Previous work has shown that CMIP6 models represent moist convective processes more accurately than their CMIP5 counterparts. However, certain biases in convective onset remain pervasive among generations of CMIP modeling efforts. Here we diagnose these biases in a cohort of nine CMIP6 models with sub-daily output, assessing conditional instability in profiles of equivalent potential temperature θ e and saturation equivalent potential temperature θ es in comparison to a plume model with different mixing assumptions. Most models capture qualitative aspects of the θ es vertical structure, including a substantial decrease with height in the lower free troposphere associated with the entrainment of subsaturated air. We define a “pseudo-entrainment” diagnostic that combines subsaturation and a θ es measure of conditional instability similar to what entrainment would produce under the small-buoyancy approximation. This captures the trade-off between larger θ es lapse rates (entrainment of dry air) and small subsaturation (permits positive buoyancy despite high entrainment). This pseudo-entrainment diagnostic is also a reasonable indicator of the critical value of integrated buoyancy for precipitation onset. Models with poor θ e /θ es structure (those using variants of the Tiedtke Scheme) or low entrainment runs of CAM5, and models with low subsaturation, such as NASA-GISS, lie outside the observational range in this diagnostic.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2022

Capsule network-based semantic segmentation model for thermal anomaly identification on building envelopes

Thermography technology is widely used to inspect thermal anomalies in building façade systems. Computer vision-based techniques provide opportunities to autonomously detect such heat anomalies to significantly improve the efficiency of decision-making for building envelope retrofitting and maintenance. Here, in this work, we propose a novel Capsule Network-based deep learning model – CapsLab – that detects and identifies thermal anomalies by semantic segmentation. CapsLab is built based on our proposed prediction-tuning capsule (PT-Capsule) layer. Different from a traditional capsule layer, which consists of part-whole transformation and capsule-routing process, the proposed layer is composed of a prediction and tuning process, which helps decreasing the number of model parameters significantly. While the applicability of traditional Capsule Networks (CapsNets) has been limited to simpler tasks and smaller datasets due to their scalability issue, we can leverage the lightweight of the proposed PT-Capsule layer, and apply it to the semantic segmentation task. In this work, we also employ our previously presented performance metric, referred to as the Anomaly Identification Metric (AIM) (Kakillioglua et al. 2021), to evaluate the segmentation outputs. Traditional performance metrics do not accurately reflect the true performance of the segmentation models in thermal anomaly identification due to the high subjectivity in the annotation process and higher overlap ratio sensitivity of the standard metrics. AIM, on the other hand, is robust to these drawbacks. Experimental results show, both qualitatively and quantitatively, that our proposed segmentation method can effectively segment the thermal anomalies. Specifically, our model provides 9.38% and 13.53% improvements over the baseline model – DeepLabV3+ – based on traditional mIoU score and the AIM score, respectively, while requiring less model parameters and less computation at the same time. In addition, the scores that the AIM metric generates better align with the scores provided by building performance experts.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2022

Distributed Real-time Plume Monitoring for Deep Sea Mineral Extraction

In the emerging industry of deep-sea mining for minerals and deposits (e.g. polymetallic nodules for nickel, cobalt, copper, and manganese), more data is required to understand the effects of sediment plume generation and predict the distribution of disturbed sediment. There are two main sources of plume generation, the first being at the active mining site where the “collector” directly removes the top layer of the sea floor. The other is the “midwater plume” consisting of unwanted sediment that was collected during extraction that is pumped back into the aphotic zone. The vast majority of plume generation is caused by the collector, causing detrimental and long-lasting impacts on seafloor ecosystems due to the lack of wave activity or strong currents at the sea floor. Therefore, it is crucial to invest in the infrastructure to support the study and constant monitoring over a large area of the sea floor where plume generation is present. Due to the limited number of usable channels and power requirements, current subsea wireless communications technologies are not well suited to instrumenting the large areas of the sea floor needed to monitor plume migration. The scope of this effort is to transition experimental demonstrations of high-bandwidth, full-duplex scalable underwater laser communications to the seafloor in an open ocean environment. Specifically tackling challenges associated with the dynamic nature of the subsea world, including but not limited to, deployment logistics, sustainability, and range. The goal is to enable the internet of underwater things for deep sea industries by broadening the capabilities of subsea communications. By using high-precision laser transmitters, many of the challenges current subsea optical systems face can be circumvented, such as power consumption, interference, and bandwidth limitations. This approach lends itself to wireless interlinking multi-node networks, in series or parallel, facilitating the implementation of a wide array of sensor types. This interlinking allows all the data gathered from the network to be processed through a single hardline uplink to the surface, lowering the complexity required for near real-time data processing. Additionally, the laser control systems produce metadata that can be used to help characterize the water column between the nodes. Combining data from various sensors such as turbidity, temperature, current velocity with metadata such as beam attenuation and deflection can produce a high-resolution model of sea floor conditions around an active mining zone. The resulting near real-time model can be used to optimize location and flow rate of the mining operation to minimize and quantify the environmental impact.

Mons, Ishan↗