Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “variability prediction”

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 1,117 records · Page 62
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Systematically tracking the hourly progression of large wildfires using GOES satellite observations

Abstract. In the western United States, prolonged drought, a warming climate, and historical fuel buildup have contributed to larger and more intense wildfires as well as to longer fire seasons. As these costly wildfires become more common, new tools and methods are essential for improving our understanding of the evolution of fires and how extreme weather conditions, including heat waves, windstorms, droughts, and varying levels of active-fire suppression, influence fire spread. Here, we develop the Geostationary Operational Environmental Satellites (GOES)-Observed Fire Event Representation (GOFER) algorithm to derive the hourly fire progression of large wildfires and create a product of hourly fire perimeters, active-fire lines, and fire spread rates. Using GOES-East and GOES-West geostationary satellite detections of active fires, we test the GOFER algorithm on 28 large wildfires in California from 2019 to 2021. The GOFER algorithm includes parameter optimizations for defining the burned-to-unburned boundary and correcting for the parallax effect from elevated terrain. We evaluate GOFER perimeters using 12 h data from the Visible Infrared Imaging Radiometer Suite (VIIRS)-derived Fire Event Data Suite (FEDS) and final fire perimeters from the California's Fire and Resource Assessment Program (FRAP). Although the GOES imagery used to derive GOFER has a coarser resolution (2 km at the Equator), the final fire perimeters from GOFER correspond reasonably well to those obtained from FRAP, with a mean Intersection-over-Union (IoU) of 0.77, in comparison to 0.83 between FEDS and FRAP; the IoU indicates the area of overlap over the area of the union relative to the reference perimeters, in which 0 is no agreement and 1 is perfect agreement. GOFER fills a key temporal gap present in other fire tracking products that rely on low-Earth-orbit imagery, where perimeters are available at intervals of 12 h or longer or at ad hoc intervals from aircraft overflights. This is particularly relevant when a fire spreads rapidly, such as at maximum hourly spread rates of over 5 km h−1. Our GOFER algorithm for deriving the hourly fire progression using GOES can be applied to large wildfires across North and South America and reveals considerable variability in the rates of fire spread on diurnal timescales. The resulting GOFER product has a broad set of potential applications, including the development of predictive models for fire spread and the improvement of atmospheric transport models for surface smoke estimates. The resulting GOFER product has a broad set of potential applications, including the development of predictive models for fire spread and the improvement of atmospheric transport models for surface smoke estimates (https://doi.org/10.5281/zenodo.8327264, Liu et al., 2023).

Geology↗
DOE OSTI2020

Studies of Single-Transverse Kinematic Variables for Neutrino Interactions on Argon

It is now well-known that a variety of theoretically-challenging nuclear effects play an important role in determining neutrino-nucleus interaction cross sections. Deficiencies in existing models of these effects represent a leading source of systematic uncertainty for neutrino oscillation experiments. In recent neutrino cross section measurements published by the T2K and MINERvA experiments, the study of kinematic observables called Single-Transverse (Kinematic) Variables (STVs) in the plane transverse to the neutrino beam have been demonstrated to provide a powerful tool on nuclear modeling uncertainties. In the near future, the SBN and DUNE experiments will both leverage the novel Liquid Argon Time Projection Chamber technology to pursue high-precision measurements of neutrino oscillations. As the interpretation of the results from these measurements will require a detailed understanding of neutrino-argon scattering cross sections and given the scarcity of available neutri no-argon data, a measurement of Single-Transverse Kinematic Variables distributions in neutrino-argon scattering is of high interest for the neutrino physics community. This thesis presents the first detailed comparison of model predictions for distributions of these observables obtained using four standard neutrino event simulation tools (GENIE, NuWro, GiBUU and NEUT). Results are shown for simulations of muon neutrinos from the Fermilab Booster Neutrino Beam interacting in the MicroBooNE LArTPC. Opportunities for discrimination between nuclear models with respect to future measurements is highlighted. Furthermore, first calculations of STVs from experimental argon data are shown. Data corresponding to 4.449x10^19 POT of exposure were collected using the MicroBooNE LArTPC in the Fermilab Booster Neutrino Beam.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2022

m-CUBES An efficient and portable implementation of multi-dimensional integration for gpus

The task of multi-dimensional numerical integration is frequently encountered in physics and other scientific fields, e.g., in modeling the effects of systematic uncertainties in physical systems and in Bayesian parameter estimation. Multi-dimensional integration is often time-prohibitive on CPUs. Efficient implementation on many-core architectures is challenging as the workload across the integration space cannot be predicted a priori. We propose m-Cubes, a novel implementation of the well-known Vegas algorithm for execution on GPUs. Vegas transforms integration variables followed by calculation of a Monte Carlo integral estimate using adaptive partitioning of the resulting space. m-Cubes improves performance on GPUs by maintaining relatively uniform workload across the processors. As a result, our optimized Cuda implementation for Nvidia GPUs outperforms parallelization approaches proposed in past literature. We further demonstrate the efficiency of m-Cubes by evaluating a six-dimensional integral from a cosmology application, achieving significant speedup and greater precision than the CUBA library's CPU implementation of VEGAS. We also evaluate m-Cubes on a standard integrand test suite. m-Cubes outperforms the serial implementations of the Cuba and GSL libraries by orders of magnitude speedup while maintaining comparable accuracy. Our approach yields a speedup of at least 10 when compared against publicly available Monte Carlo based GPU implementations. In summary, m-Cubes can solve integrals that are prohibitively expensive using standard libraries and custom implementations. A modern C++ interface header-only implementation makes m-Cubes portable, allowing its utilization in complicated pipelines with easy to define stateful integrals. Compatibility with non-Nvidia GPUs is achieved with our initial implementation of m-Cubes using the Kokkos framework.

Sakiotis, Ioannis↗
DOE OSTI2024

Soil Carbon and Nitrogen Stocks Across Hillslopes Underlain by Continuous Permafrost in the Northern Arctic Foothills, Alaska, United States

Constraining the variability of soil organic carbon (SOC) and total nitrogen (TN) stocks across hillslopes in Low Arctic permafrost-affected landscapes remains a significant challenge for improving global estimates of permafrost SOC stocks. We investigated SOC and TN stocks across hillslopes at two sites in the Arctic Foothills of Alaska, United States (Happy Valley and Sagwon Hills). Average SOC and TN stocks for the 0–1-m depth interval were high (52.0 ± 15.1 kg C m −2 and 2.74 ± 0.82 kg N m −2 ) and linearly related ( R 2 = 0.74, p < 0.0001). Unlike soils of other permafrost and nonpermafrost landscapes, variability was greatest within rather than between hillslope positions. Furthermore, SOC and TN stocks in the surface 1 m did not exhibit strong patterns by hillslope position and were only weakly associated with major geomorphic parameters that typically predict SOC and TN stocks well in other landscapes. Although sampling at upper hillslope positions was largely limited to depths of less than 1.5 m due to the presence of coarse fragments in reworked glacial till, deeper observations at lower hillslope positions (footslopes, toeslopes, and basins) revealed significantly larger SOC stocks (92.0 ± 18.0 kg C m −2 at 2 m; 117.1 ± 10.4 kg C m −2 at 3 m). The unique small-scale variability in ice content, cryoturbation, patterned ground, and organic layer thickness on these broad, Low Arctic sites contributes to the relatively homogeneous distribution of SOC and TN stocks across hillslope positions in the top 1 m, but a future focus on deeper sampling may reveal greater differences in SOC and TN stocks.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

An interlaboratory comparison of mid-infrared spectra acquisition: Instruments and procedures matter

Diffuse reflectance spectroscopy has been extensively employed to deliver timely and cost-effective predictions of a number of soil properties. However, although several soil spectral laboratories have been established worldwide, the distinct characteristics of instruments and operations still hamper further integration and interoperability across mid-infrared (MIR) soil spectral libraries. In this study, we conducted a large-scale ring trial experiment to understand the lab-to-lab variability of multiple MIR instruments. By developing a systematic evaluation of different mathematical treatments with modeling algorithms, including regular preprocessing and spectral standardization, we quantified and evaluated instruments' dissimilarity and how this impacts internal and shared model performance. We found that all instruments delivered good predictions when calibrated internally using the same instruments' characteristics and standard operating procedures by solely relying on regular spectral preprocessing that accounts for light scattering and multiplicative/additive effects, e.g., using standard normal variate (SNV). When performing model transfer from a large public library (the USDA NSSCKSSL MIR library) to secondary instruments, good performance was also achieved by regular preprocessing (e. g., SNV) if both instruments shared the same manufacturer. However, significant differences between the KSSL MIR library and contrasting ring trial instruments responses were evident and confirmed by a semi-unsupervised spectral clustering. For heavily contrasting setups, spectral standardization was necessary before transferring prediction models. Non-linear model types like Cubist and memory-based learning delivered more precise estimates because they seemed to be less sensitive to spectral variations than global partial least square regression. In summary, the results from this study can assist new laboratories in building spectroscopy capacity utilizing existing MIR spectral libraries and support the recent global efforts to make soil spectroscopy universally accessible with centralized or shared operating procedures.

58 GEOSCIENCES↗
DOE OSTI2022

Machine learning predictions for local electronic properties of disordered correlated electron systems

We present a scalable machine learning (ML) model to predict local electronic properties such as on-site electron number and double occupation for disordered correlated electron systems. Our approach is based on the locality principle, or the nearsightedness nature, of many-electron systems, which means local electronic properties depend mainly on the immediate environment. A ML model is developed to encode this complex dependence of local quantities on the neighborhood. We demonstrate our approach using the square-lattice Anderson-Hubbard model, which is a paradigmatic system for studying the interplay between Mott transition and Anderson localization. We develop a lattice descriptor based on the group-theoretical method to represent the on-site random potentials within a finite region. The resultant feature variables are used as input to a multilayer fully connected neural network, which is trained from data sets of variational Monte Carlo (VMC) simulations on small systems. We show that the ML predictions agree reasonably well with the VMC data. Our work underscores the promising potential of ML methods for multiscale modeling of correlated electron systems.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Using AI to predict calibration constants for the central drift chamber in GlueX at Jefferson Lab

The AI for Experimental Controls project team at Jefferson Lab has developed an AI system to control and calibrate a large drift chamber system in near-real time. The AI system will monitor environmental and experimental variables to recommend voltage settings that maintain consistent dE/dx gain and optimal resolution throughout the experiment. At present, calibrations are performed after data have been recorded and require a considerable amount of time and attention from experts. The calibrations currently require multiple iterations and depend on accurate tracking information. Our approach uses environmental data, such as atmospheric pressure and gas temperature, and beam conditions, such as the flux of incident particles, as inputs to a Gaussian Process Regression (GPR) model. For the data taken during the GlueX 2020 run period, the GPR is able to predict the existing gain correction factors to within 3.5%. This talk will briefly describe the development, testing, and future plans for this system at Jefferson Lab.

Jeske, Torri↗
DOE OSTI2022

Bayesian State-Space Modeling Framework for Understanding and Predicting Golden Eagle Movements Using Telemetry Data

Predicting raptor movements through a wind power plant under given atmospheric and topographical conditions is a crucial first step in the overall goal of quantifying the risk of turbine-related collisions and mortalities. Extracting behavioral traits of golden eagles (Aquila chrysaetos) from telemetry data requires the fusion of noisy and sparse movement data (location, heading, velocity) with a stochastic mathematical representation of the eagles' decision-making processes. In this study, we framed this problem in a Bayesian state-space framework where both observations and decision-making are assumed to be stochastic processes connected through hidden states (mode of flight, intent), and the unknown model parameters are assumed to be random variables that are calibrated using the available telemetry data. This framework allowed for rigorous consideration of underlying uncertainties while allowing for both data and prior biological knowledge to contribute to a probabilistic and predictive agent-based movement model. We implemented and applied the Bayesian framework to understand movement behavior of 23 GPS-tagged golden eagles travelling in the western US for years 2019 and 2020. Our preliminary findings show that the Bayesian state-space framework provides a robust inverse modeling apparatus to decode eagle behavioral characteristics from telemetry data. This study was primarily aimed at verifying and validating the framework with selected golden eagle tracks (both long- and short-ranged), with future research aimed at extending the framework to include multi-mode flight, consideration of atmospheric data and uplift mechanisms, eagle-to-eagle interaction, and eagle-to-turbine interaction.

Bayesian modeling↗
DOE OSTI2025

Comparing Outdoor to Indoor Performance for Bifacial Modules Affected by Polarization-Type Potential-Induced Degradation

Bifacial photovoltaic (PV) modules have the advantage of using light reflected off of the ground to contribute to power production. Predicting the energy gain is challenging and requires complex models to do so accurately. Often, module degradation over time is neglected in models for the sake of simplicity or is underestimated. Comparing outdoor and indoor current–voltage (I–V) performance for bifacial modules is more challenging than for monofacial modules, as there are additional variables to consider such as rear albedo non-uniformity, cell mismatch, and their effects on temperature. This challenge is compounded when heterogeneous degradation modes occur, such as polarization-type potential-induced degradation (PID-p). To examine the effects of PID-p on I–V predictions using an empirical data-driven approach, 16 bifacial PERC modules are installed outdoors on racks with different albedo conditions. A subset is exposed to high-voltage biases of −1500 V or +1500 V. Outdoor data are traced at irradiance ranges of 150–250 W/m 2 , 500–600 W/m 2 , and 900–1000 W/m 2 . These curves are corrected using control module temperature, wire resistivity, and module resistance measured indoors. We examine several methods to transform indoor I–V curves to accurately, and more simply than existing methods, approximate outdoor performance for bifacial modules without and with varying levels of PID-p degradation. This way, bifacial performance modeling can be more accessible and informed by fielded, degraded modules. Distributions of percent errors between indoor and outdoor performance parameters and Mean Absolute Percent Errors (MAPEs) are used to assess method quality. Results including low-irradiance data (150–250 W/m 2 ) are discussed but are filtered for quantifying method quality as these data introduce substantial errors. The method with the most optimal tradeoff between low MAPE and analysis simplicity involves measuring the front side of a module indoors at an irradiance equal to plane-of-array irradiance plus the product of module bifaciality and albedo irradiance. This method gives MAPE values of 1–6.5% for non-degraded and 1.6–5.9% for PID-p degraded module performance.

14 SOLAR ENERGY↗
DOE OSTI2023

Physics-informed neural network with transfer learning (TL-PINN) based on domain similarity measure for prediction of nuclear reactor transients

Nuclear reactor safety and efficiency can be enhanced through the development of accurate and fast methods for prediction of reactor transient (RT) states. Physics informed neural networks (PINNs) leverage deep learning methods to provide an alternative approach to RT modeling. Applications of PINNs in monitoring of RTs for operator support requires near real-time model performance. However, as with all machine learning models, development of a PINN involves time-consuming model training. Here, we show that a transfer learning (TL-PINN) approach achieves significant performance gain, as measured by reduction of the number of iterations for model training. Using point kinetic equations (PKEs) model with six neutron precursor groups, constructed with experimental parameters of the Purdue University Reactor One (PUR-1) research reactor, we generated different RTs with experimentally relevant range of variables. The RTs were characterized using Hausdorff and Fréchet distance. We have demonstrated that pre-training TL-PINN on one RT results in up to two orders of magnitude acceleration in prediction of a different RT. The mean error for conventional PINN and TL-PINN models prediction of neutron densities is smaller than 1%. We have developed a correlation between TL-PINN performance acceleration and similarity measure of RTs, which can be used as a guide for application of TL-PINNs.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2026

Changing-look Active Galactic Nuclei Powered by Disk Tearing

Changing-look active galactic nuclei (CLAGN) feature order-of-magnitude variability in both the continuum and broad line luminosities on months-to-years-long timescales, and are currently unexplained. Simulations have demonstrated that rotating black holes (BHs) sometimes tear apart tilted accretion disks. These tearing events violently restructure the disk on timescales much shorter than a viscous timescale, hinting at a connection to CLAGN. Here, we show that disk tearing can power changing-look events. We report synthetic observations of an extremely high-resolution, three-dimensional, general-relativistic magnetohydrodynamic simulation of a geometrically thin, tilted accretion disk around a rapidly rotating, 10 8 M ⊙ BH. We perform ray-tracing calculations that follow the thermal disk emission to both a line-of-sight camera and to a distribution of cameras in a prescribed torus-like broad-line region (BLR). The continuum photoionizes the BLR, and we calculate the resulting spectrum. Both the continuum and line luminosities undergo order-of-magnitude swings on months-to-years-long timescales. We find shorter, week-long variability driven by the geometric precession of the inner disk and an intraday quasiperiodic oscillation driven by radial breathing of the inner disk. When the torn disk precesses, it causes asymmetric illumination of the BLR, driving time-evolving red-to-blue asymmetries of the broad emission lines that may be a smoking gun for disk tearing. We also make predictions for future photometric observations from ULTRASAT and Vera Rubin Observatory, given a Shakura–Sunyaev–like effective temperature profile, both of which may play an important role in detecting future changing-look events. Future work should consider nonthermal emission, especially from the time-variable corona.

accretion↗
DOE OSTI2023

Predicting Deposition Rate and Closing the Loop on Aerosol Jet Printing with In‐Line Light Scattering Measurements

Aerosol jet printing is a compelling noncontact, digital manufacturing technology for flexible, hybrid, and conformal electronics, but batch‐to‐batch variability and process drift inhibit systematic study and translation to production environments. Emerging measurement techniques for the aerosol volume fraction, a key parameter governing deposition rate, have shown promise for real‐time response, including a recent demonstration of human‐in‐the‐loop control. By integrating improved light scattering measurements with custom software, a robust environment for real‐time monitoring is established and fully automated closed‐loop control over the deposition rate during printing is enabled. The physical basis for scattering measurements as a feedback source is examined and the quantitative insight this provides for ink development and fundamental process studies is highlighted. Three candidate process variables for closed‐loop control, namely the atomizer voltage, carrier gas flow rate, and print speed, are then evaluated. The atomizer voltage demonstrates the best extended duration validity because it addresses atomization variability directly, but carrier gas flow rate and print speed provide faster and more deterministic responses. This methodology is then demonstrated for electrical properties using a silver nanoparticle ink, maintaining 98% of printed patterns within 10% of the mean resistance value over 3 h of printing.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Probing light quark Yukawa couplings through angularity distributions in Higgs boson decay

We propose to utilize angularity distributions in Higgs boson decay to probe light quark Yukawa couplings at e + e - colliders. Angularities $τ$ a are a class of 2-jet event shapes with variable and tunable sensitivity to the distribution of radiation in hadronic jets in the final state. Using soft-collinear effective theory (SCET), we present a prediction of angularity distributions from Higgs decaying to quark and gluon states at e + e - colliders to NNLL + $\mathcal{O}$(α s ) accuracy. Due to the different color structures in quark and gluon jets, the angularity distributions from H → $q\overline{q}$ and H → gg show different behaviors and can be used to constrain the light quark Yukawa couplings. We show that the upper limit of light quark Yukawa couplings could be probed to the level of ~ 15% of the bottom quark Yukawa coupling in the Standard Model in a conservative analysis window far away from nonperturbative effects and other uncertainties; the limit can be pushed to ≲ 7 – 9% with better control of the nonperturbative effects especially on gluon angularity distributions and/or with multiple angularities.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

A Modeling framework for flocculated cohesive sediment transport in the current bottom boundary layer

Cohesive sediment transport, where its settling velocity is controlled by the flocculation process, is a crucial component in determining biochemical cycles, fate of pollutants, and morphodynamics in many aquatic ecosystems. In this study, a modeling framework is presented to investigate how flocculation influences cohesive sediment transport in the current bottom boundary layer in dilute conditions, consistent with the calibration range of the flocculation model. From a local analysis of floc dynamics in homogenous turbulence, we identify that the floc size distribution is mainly controlled by floc cohesion and yield strength. The uncertainty in fractal dimension plays a minor role for the floc size but it influences the resulting floc density and settling velocity. The transport analysis in the current boundary layer shows that the flocculation process alters the vertical distribution of the settling velocity and hence the sediment concentration with a strong dependence on cohesion, floc yield strength, and floc structure. When the flocs are more susceptible to breaking, a well-mixed concentration profile is obtained. In contrast, for flocs with higher cohesion or yield strength, higher concentration with a sharp gradient is observed close to the bed. Overall, the settling velocity exhibits a low vertical variability within 20 % of the depth-averaged value except near the bed. Further, this suggests that using a depth-averaged settling velocity yields acceptable predictions of the sediment concentration profiles, especially for flocs with lower cohesion.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Bayesian analysis for estimating statistical parameter distributions of elasto-viscoplastic material models

High temperature design methods rely on constitutive models for inelastic deformation and failure typically calibrated against the mean of experimental data without considering the associated scatter. Variability may arise from the experimental data acquisition process, from heat-to-heat material property variations, or both and need to be accurately captured to predict parameter bounds leading to efficient component design. Applying the Bayesian Markov Chain Monte Carlo (MCMC) method to produce statistical models capturing the underlying uncertainty in the experimental data is an area of ongoing research interest. This work varies aspects of the Bayesian MCMC method and explores their effect on the posterior parameter distributions for a uniaxial elasto-viscoplastic damage model using synthetically generated reference data. From our analysis with the uniaxial inelastic model we determine that an informed prior distribution including different types of test conditions results in more accurate posterior parameter distributions. The parameter posterior distributions, however, do not improve when increasing the number of similar experimental data. Additionally, changing the amount of scatter in the data affects the quality of the posterior distributions, especially for the less sensitive model parameters. Moreover, we perform a sensitivity study of the model parameters against the likelihood function prior to the Bayesian analysis. The results of the sensitivity analysis help to determine the reliability of the posterior distributions and reduce the dimensionality of the problem by fixing the insensitive parameters. The comprehensive study described in this work demonstrates how to efficiently apply the Bayesian MCMC methodology to capture parameter uncertainties in high temperature inelastic material models. Quantifying these uncertainties in inelastic models will improve high temperature engineering design practices and lead to safer, more effective component designs.

42 ENGINEERING↗
DOE OSTI2025

Contributions of vegetation heterogeneity within tower footprint to CO 2 flux estimations through graph neural network modeling

Net ecosystem exchange of CO 2 (Fc) measured directly by eddy covariance towers is based on various assumptions, including large, flat and homogenous land cover type. In reality, often a tower site is not large enough for flux measurements, and landscapes consist of patches of different land cover types within the flux footprint. In addition, some portions of fluxes are contributed by different cover types when a footprint exceeds the size of the target ecosystem. The contributions of non-dominant patches to Fc are often ignored. Here, in this study, we propose a novel integrated modeling framework that combines random forest (RF) and XGBoost with a residual correction module based on a deep graph convolutional network (DeeperGCN) to simulate Fc for seven flux measurement sites in southwest Michigan. High-resolution remote sensing vegetation indices, soil properties, meteorological variables, and footprint-weighted spatial features were used as model inputs at three spatial resolutions (10 m, 20 m, 30 m), and their importance in predicting Fc with DeeperGCN was assessed. We found that residual correction using DeeperGCN significantly improved prediction accuracy, with the R 2 increasing from 0.9098 to 0.9479 for RF and from 0.9235 to 0.9433 for XGBoost. At site level, the maximum improvement in R 2 reached 0.1617. Paired t-tests confirmed that these improvements were statistically significant (p < 0.05). Among all predictors, leaf area index and incoming shortwave radiation emerged as the dominant drivers of spatial residual variation, followed by precipitation, relative humidity, and selected vegetation indices. The 20 m resolution yielded the best balance between model performance and computational efficiency. In conclusion, our modeling framework effectively captures both spatial heterogeneity and nonlinear interactions, offering a robust solution for spatially explicit flux modeling in structurally diverse ecosystems beyond the study sites.

footprint model↗
DOE OSTI2023

The inclusion of uncertainty in circularity transition modeling: A case study on wind turbine blade end-of-life management

The transition to a more circular economy (CE) is complex and hard to predict, including in sustainable energy technologies. Many sources of uncertainty make it challenging to model CE scenarios and their potential benefits. As an example, the high variability in costs and revenues of different recycling options makes future wind turbine blade recycling highly uncertain. To better understand this challenge, the circular economy, life cycle assessment and visualization (CELAVI) framework - a discrete event simulation and life cycle assessment framework - is modified to incorporate uncertainty analysis capabilities. Moreover, a 3-step procedure that covers different aspects of uncertainty in CE studies and includes a Monte-Carlo analysis is proposed. The procedure is tested in a case study on wind turbine blade recycling using CELAVI. Results highlight that grinding and landfilling costs are the most influential parameters for wind power circularity. The model's output coefficients of variation (when input parameter uncertainties are propagated) are between 92% and 384% depending on the indicator. The approach developed in this study may help researchers and decision-makers who study circularity prioritize their data collection effort. Finally, our method contributes to a mounting yet critical body of research: the measurement of uncertainty in circularity transitions.

17 WIND ENERGY↗
DOE OSTI2020

Enhancing Streamflow Forecast and Extracting Insights Using Long-Short Term Memory Networks With Data Integration at Continental Scales

Recent observations with varied schedules and types (moving average, snapshot, or regularly spaced) can help to improve streamflow forecasts, but it is challenging to integrate them effectively. Based on a long short-term memory (LSTM) streamflow model, we tested multiple versions of a flexible procedure we call data integration (DI) to leverage recent discharge measurements to improve forecasts. DI accepts lagged inputs either directly or through a convolutional neural network unit. DI ubiquitously elevated streamflow forecast performance to unseen levels, reaching a record continental-scale median Nash-Sutcliffe Efficiency coefficient value of 0.86. Integrating moving-average discharge, discharge from the last few days, or even average discharge from the previous calendar month could all improve daily forecasts. Directly using lagged observations as inputs was comparable in performance to using the convolutional neural network unit. Importantly, we obtained valuable insights regarding hydrologic processes impacting LSTM and DI performance. Before applying DI, the base LSTM model worked well in mountainous or snow-dominated regions, but less well in regions with low discharge volumes (due to either low precipitation or high precipitation-energy synchronicity) and large interannual storage variability. DI was most beneficial in regions with high flow autocorrelation: it greatly reduced baseflow bias in groundwater-dominated western basins and also improved peak prediction for basins with dynamical surface water storage, such as the Prairie Potholes or Great Lakes regions. However, even DI cannot elevate performance in high-aridity basins with 1-day flash peaks. Despite this limitation, there is much promise for a deep-learning-based forecast paradigm due to its performance, automation, efficiency, and flexibility.

54 ENVIRONMENTAL SCIENCES↗