Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “quantile regression”

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 55 records · Page 3

Hypertension and hematologic parameters in a community near a uranium processing facility

Background: Environmental uranium exposure originating as a byproduct of uranium processing can impact human health. The Fernald Feed Materials Production Center functioned as a uranium processing facility from 1951 to 1989, and potential health effects among residents living near this plant were investigated via the Fernald Medical Monitoring Program (FMMP). Methods: Data from 8216 adult FMMP participants were used to test the hypothesis that elevated uranium exposure was associated with indicators of hypertension or changes in hematologic parameters at entry into the program. A cumulative uranium exposure estimate, developed by FMMP investigators, was used to classify exposure. Systolic and diastolic blood pressure and physician diagnoses were used to assess hypertension; and red blood cells, platelets, and white blood cell differential counts were used to characterize hematology. The relationship between uranium exposure and hypertension or hematologic parameters was evaluated using generalized linear models and quantile regression for continuous outcomes, and logistic regression or ordinal logistic regression for categorical outcomes, after adjustment for potential confounding factors. Results: Of 8216 adult FMMP participants 4187 (51%) had low cumulative uranium exposure, 1273 (15%) had moderate exposure, and 2756 (34%) were in the high (>0.50 Sievert) cumulative lifetime uranium exposure category. Participants with elevated uranium exposure had decreased white blood cell and lymphocyte counts and increased eosinophil counts. Female participants with higher uranium exposures had elevated systolic blood pressure compared to women with lower exposures. However, no exposure-related changes were observed in diastolic blood pressure or hypertension diagnoses among female or male participants. Conclusions: Results from this investigation suggest that residents in the vicinity of the Fernald plant with elevated exposure to uranium primarily via inhalation exhibited decreases in white blood cell counts, and small, though statistically significant, gender-specific alterations in systolic blood pressure at entry into the FMMP.

63 RADIATION, THERMAL, AND OTHER ENVIRON. POLLUTAN↗

What factors affect the prices of low-priced U.S. solar PV systems?

The price of solar PV systems has declined rapidly, yet there are some much lower-priced systems than others. This study explores the factors that determine prices in these low-priced (LP) systems. Using a data set of 42,611 residential-scale PV systems installed in the U.S. in 2013, we use quantile regressions to estimate the importance of factors affecting the installed prices for LP systems (those at the 10th percentile) in comparison to median-priced systems. We find that the value of solar to consumers-a variable that accounts for subsidies, electric rates, and PV generation levels-is associated with lower prices for LP systems but higher prices for median priced systems. Conversely, systems installed in new home construction are associated with lower prices at the median but higher prices for LP. Other variables have larger price-reducing effects on LP than on median priced systems: systems installed in Arizona and Florida, as well as commercial and thin film systems. In contrast, the following have a smaller effect on prices for LP systems than median priced systems: tracking systems, self-installations, systems installed in Massachusetts, the system size, and installer experience. Furthermore, these results highlight the complex factors at play that lead to LP systems and shed light into how such LP systems can come about.

14 SOLAR ENERGY↗

Constructing probabilistic scenarios for wide-area solar power generation

Optimizing thermal generation commitments and dispatch in the presence of high penetrations of renewable resources such as solar energy requires a characterization of their stochastic properties. In this study, we describe novel methods designed to create day-ahead, wide-area probabilistic solar power scenarios based only on historical forecasts and associated observations of solar power production. Each scenario represents a possible trajectory for solar power in next-day operations with an associated probability computed by algorithms that use historical forecast errors. Scenarios are created by segmentation of historic data, fitting non-parametric error distributions using epi-splines, and then computing specific quantiles from these distributions. Additionally, we address the challenge of establishing an upper bound on solar power output. Our specific application driver is for use in stochastic variants of core power systems operations optimization problems, e.g., unit commitment and economic dispatch. These problems require as input a range of possible future realizations of renewables production. However, the utility of such probabilistic scenarios extends to other contexts, e.g., operator and trader situational awareness. Finally, we compare the performance of our approach to a recently proposed method based on quantile regression, and demonstrate that our method performs comparably to this approach in terms of two widely used methods for assessing the quality of probabilistic scenarios: the Energy score and the Variogram score.

14 SOLAR ENERGY↗

Economic consequences of aviation system disruptions: A reduced-form computable general equilibrium analysis

The state of the art approach to economic consequence analysis (ECA) is computable general equilibrium (CGE) modeling. However, such models contain thousands of equations and cannot readily be incorporated into computerized systems used by policy analysts to yield estimates of economic impacts of various types of transportation system failures due to natural hazards, human related attacks or technological accidents. This paper presents a reduced-form approach to simplify the analytical content of CGE models to make them more transparent and enhance their utilization potential. The reduced-form CGE analysis is conducted by first running simulations one hundred times, varying key parameters, such as magnitude of the initial shock, duration, location, remediation, and resilience, according to a Latin Hypercube sampling procedure. Statistical analysis is then applied to the “synthetic data” results in the form of both ordinary least squares and quantile regression. The analysis yields linear equations that are incorporated into a computerized system and utilized along with Monte Carlo simulation methods for propagating uncertainties in economic consequences. Although our demonstration and discussion focuses on aviation system disruptions caused by terrorist attacks, the approach can be applied to a broad range of threat scenarios.

Aviation System Disruptions↗

Spatial Predictions and Associated Uncertainty of Annual Soil Respiration at the Global Scale

Abstract Soil respiration (Rs), the soil‐to‐atmosphere CO 2 flux produced by microbes and plant roots, is a critical but uncertain component of the global carbon cycle. Our current understanding of the variability and dynamics is limited by the coarse spatial resolution of existing estimates. We predicted annual Rs and associated uncertainty across the world at 1‐km resolution using a quantile regression forest algorithm trained with observations from the global Soil Respiration Database spanning from 1961 to 2011. This model yielded a global annual Rs estimate of 87.9 Pg C/year with an associated global uncertainty of 18.6 (mean absolute error) and 40.4 (root mean square error) Pg C/year. The estimated annual heterotrophic respiration (Rh), derived from empirical relationships with Rs, was 49.7 Pg C/year over the same period. Predicted Rs rates and associated uncertainty varied widely across vegetation types, with the greatest predicted rates of Rs in evergreen broadleaf forests (accounting for 20.9% of global Rs). The greatest prediction uncertainties were in northern latitudes and arid to semiarid ecosystems, suggesting that these areas should be targeted in future measurement campaigns. This study provides predictions of Rs (and associated prediction uncertainty) at unprecedentedly high spatial resolution across the globe that could help constrain local‐to‐global process‐based models. Furthermore, it provides insights into the large variability of Rs and Rh across vegetation classes and identifies regions and vegetation types with poor model performance that should be prioritized for future data collection.

Warner, D. L.↗

Uncertainty quantification of the virial black hole mass with conformal prediction

Precise measurements of the black hole mass are essential to gain insight on the black hole and host galaxy co-evolution. A direct measure of the black hole mass is often restricted to nearest galaxies and instead, an indirect method using the single-epoch virial black hole mass estimation is used for objects at high redshifts. However, this method is subjected to biases and uncertainties as it is reliant on the scaling relation from a small sample of local active galactic nuclei. In this study, we propose the application of conformalized quantile regression (CQR) to quantify the uncertainties of the black hole predictions in a machine learning setting. We compare CQR with various prediction interval techniques and demonstrated that CQR can provide a more useful prediction interval indicator. In contrast to baseline approaches for prediction interval estimation, we show that the CQR method provides prediction intervals that adjust to the black hole mass and its related properties. That is it yields a tighter constraint on the prediction interval (hence more certain) for a larger black hole mass, and accordingly, bright and broad spectral line width source. Using a combination of neural network model and CQR framework, the recovered virial black hole mass predictions and uncertainties are comparable to those measured from the Sloan Digital Sky Survey. The code is publicly available.

79 ASTRONOMY AND ASTROPHYSICS↗

Deep Learning and Likelihood Approaches for Viral Phylogeography Converge on the Same Answers Whether the Inference Model Is Right or Wrong

Abstract Analysis of phylogenetic trees has become an essential tool in epidemiology. Likelihood-based methods fit models to phylogenies to draw inferences about the phylodynamics and history of viral transmission. However, these methods are often computationally expensive, which limits the complexity and realism of phylodynamic models and makes them ill-suited for informing policy decisions in real-time during rapidly developing outbreaks. Likelihood-free methods using deep learning are pushing the boundaries of inference beyond these constraints. In this paper, we extend, compare, and contrast a recently developed deep learning method for likelihood-free inference from trees. We trained multiple deep neural networks using phylogenies from simulated outbreaks that spread among 5 locations and found they achieve close to the same levels of accuracy as Bayesian inference under the true simulation model. We compared robustness to model misspecification of a trained neural network to that of a Bayesian method. We found that both models had comparable performance, converging on similar biases. We also implemented a method of uncertainty quantification called conformalized quantile regression that we demonstrate has similar patterns of sensitivity to model misspecification as Bayesian highest posterior density (HPD) and greatly overlap with HPDs, but have lower precision (more conservative). Finally, we trained and tested a neural network against phylogeographic data from a recent study of the SARS-Cov-2 pandemic in Europe and obtained similar estimates of region-specific epidemiological parameters and the location of the common ancestor in Europe. Along with being as accurate and robust as likelihood-based methods, our trained neural networks are on average over 3 orders of magnitude faster after training. Our results support the notion that neural networks can be trained with simulated data to accurately mimic the good and bad statistical properties of the likelihood functions of generative phylogenetic models.

Evolutionary Biology↗

Probabilistic Short-Term Wind Forecasting Based on Pinball Loss Optimization

Probabilistic wind power forecasts that quantify the uncertainty in wind output have the potential to aid in the economic grid integration of wind power at large penetration levels. In this paper, a novel probabilistic wind forecasting approach based on pinball loss optimization is proposed, in conjunction with a multi-model machine learning based ensemble deterministic forecasting framework. By assuming the point-forecasted value as the mean at each point, one unknown parameter (i.e., standard deviation) of a predictive distribution at each forecasting point is determined by minimizing the pinball loss. A surrogate model is developed to represent the unknown distribution parameter as a function of deterministic forecasts. This surrogate model can be used together with deterministic forecasts to predict the unknown distribution parameter and thereby generate probabilistic forecasts. Numerical results of case studies show that the proposed method has improved the pinball loss by up to 35% compared to a baseline quantile regression forecasting model.

17 WIND ENERGY↗

Bi-Level Adaptive Storage Expansion Strategy for Microgrids Using Deep Reinforcement Learning

Battery energy storage (BES) is a versatile resource for the secure and economic operation of microgrids (MGs). Prevailing stochastic optimization-based approaches for BES expansion planning for MGs are computationally complicated. This work proposes a data-driven bi-level multi-period BES expansion planning framework to determine the siting, sizing, and timing of BES installations. The proposed planning framework unifies deep reinforcement learning (DRL) and linear programming, thereby decoupling the determinations for the integer and continuous decision variables in two time scales, respectively. In the upper level, a rainbow DRL agent with quantile regression is trained to provide dynamic planning policies to accommodate stochastic renewable energy resources (RESs), load, and battery price changes efficiently. Further, the lower level computes the optimal operation of MGs with frequency constraints to hedge the islanding contingency. The two levels communicate with one another by exchanging storage configuration and operating expenses in order to accomplish the shared goal of minimizing investment and operation costs. Comparative case studies on an MG are carried out to demonstrate the superiority of the proposed DRL-based solution to the mixed-integer linear programming counterpart on efficiency, scalability, and adaptability.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Spatial biases of information influence global estimates of soil respiration: how can we improve global predictions?

Soil respiration (Rs), the efflux of CO2 from soils to the atmosphere, is a major component of the terrestrial carbon cycle, but is poorly constrained from regional to global scales. The global soil respiration database (SRDB) is a compilation of in-situ Rs observations from around the globe that has been consistently updated with new measurements over the past decade. It is unclear whether the addition of data to new versions of the SRDB has produced better-constrained global Rs estimates. We compared two versions of the SRDB (v3.0 n=5173 and v5.0 n=10366) to determine how additional data influenced the global sum and uncertainty of Rs as predicted by a quantile regression forest model. A model parameterized using SRDBv3 yielded a global Rs sum of 88.6 Pg C yr-1, and associated uncertainty of 29.9 (mean absolute error) and 57.9 (standard deviation) Pg C yr-1, whereas parameterization using SRDBv5 yielded 96.5 Pg C yr-1 and associated uncertainty of 30.2 (mean average error) and 73.4 (standard deviation) Pg C yr-1. Empirically estimated global heterotrophic respiration (Rh) from v3 and v5 were 49.9-50.2 (mean 50.1) and 53.3-53.5 (mean 53.4) Pg C yr-1, respectively. Interestingly, SRDBv5’s inclusion of new data from underrepresented regions (e.g., Asia, Africa, South America) thus resulted in overall higher model uncertainty. The SRDBv5 is still biased towards northern latitudes and temperate zones, so we tested that an optimized global distribution of Rs measurements resulted in a global sum of 96.4 ± 21.4 Pg C yr-1 and lower model uncertainty. These results support current global estimates of Rs but highlight spatial inconsistencies that influence model parameterization and interpretation that should be addressed to improve regional- to global-scale predictions.

Stell, Emma↗

Methane fluxes in tidal marshes of the conterminous United States

Abstract Methane (CH 4 ) is a potent greenhouse gas (GHG) with atmospheric concentrations that have nearly tripled since pre‐industrial times. Wetlands account for a large share of global CH 4 emissions, yet the magnitude and factors controlling CH 4 fluxes in tidal wetlands remain uncertain. We synthesized CH 4 flux data from 100 chamber and 9 eddy covariance (EC) sites across tidal marshes in the conterminous United States to assess controlling factors and improve predictions of CH 4 emissions. This effort included creating an open‐source database of chamber‐based GHG fluxes ( https://doi.org/10.25573/serc.14227085 ). Annual fluxes across chamber and EC sites averaged 26 ± 53 g CH 4 m −2 year −1 , with a median of 3.9 g CH 4 m −2 year −1 , and only 25% of sites exceeding 18 g CH 4 m −2 year −1 . The highest fluxes were observed at fresh‐oligohaline sites with daily maximum temperature normals (MATmax) above 25.6°C. These were followed by frequently inundated low and mid‐fresh‐oligohaline marshes with MATmax ≤25.6°C, and mesohaline sites with MATmax >19°C. Quantile regressions of paired chamber CH 4 flux and porewater biogeochemistry revealed that the 90th percentile of fluxes fell below 5 ± 3 nmol m −2 s −1 at sulfate concentrations >4.7 ± 0.6 mM, porewater salinity >21 ± 2 psu, or surface water salinity >15 ± 3 psu. Across sites, salinity was the dominant predictor of annual CH 4 fluxes, while within sites, temperature, gross primary productivity (GPP), and tidal height controlled variability at diel and seasonal scales. At the diel scale, GPP preceded temperature in importance for predicting CH 4 flux changes, while the opposite was observed at the seasonal scale. Water levels influenced the timing and pathway of diel CH 4 fluxes, with pulsed releases of stored CH 4 at low to rising tide. This study provides data and methods to improve tidal marsh CH 4 emission estimates, support blue carbon assessments, and refine national and global GHG inventories.

54 ENVIRONMENTAL SCIENCES↗

Comparison of Current-Use Pesticide and Other Toxicant Urinary Metabolite Levels among Pregnant Women in the CHAMACOS Cohort and NHANES

We measured 34 metabolites of current-use pesticides and other precursor compounds in urine samples collected twice during pregnancy from 538 women living in the Salinas Valley of California, a highly agricultural area (1999–2001). Precursors of these metabolites included fungicides, carbamate, organochlorine, organophosphorus (OP), and pyrethroid insecticides, and triazine and chloroacetanilide herbicides. We also measured ethylenethiourea, a metabolite of the ethylene-bisdithiocarbamate fungicides. Repeat measurements of the compounds presented here have not been reported in pregnant women previously. To understand the impact of the women’s regional environment on these findings, we compared metabolite concentrations from the CHAMACOS (Center for the Health Assessment of Mothers and Children of Salinas) cohort with U.S. national reference data for 342 pregnant women sampled by the National Health and Nutrition Examination Survey (1999–2002).The eight metabolites detected in > 50% of samples [2,4-dichlorophenol (2,4-DCP); 2,5- dichlorophenol (2,5-DCP); 1- and 2-naphthol; ortho-phenylphenol (ORTH); para-nitrophenol (PNP); 2,4,6-trichlorophenol (2,4,6-TCP); and 3,4,6-trichloro-2-pyridinol (TCPy)] may be related to home or agricultural pesticide use in the Salinas Valley, household products, and other sources of chlorinated phenols. More than 78% of women in this study had detectable levels of at least one of the OP pesticide-specific metabolites that we measured, and > 30% had two or more. The 95th percentile values of six of the most commonly detected (> 50%) compounds were significantly higher among the CHAMACOS women after controlling for age, race, socioeconomic status, and smoking [(2,4-DCP; 2,5-DCP; ORTH; PNP; 2,4,6-TCP; and TCPy); quantile regression p < 0.05]. Findings suggest that the CHAMACOS cohort has an additional burden of precursor pesticide exposure compared with the national sample, possibly from living and/or working in an agricultural area.

54 ENVIRONMENTAL SCIENCES↗

Evidence That Obesity Risk Factor Potencies Are Weight Dependent, a Phenomenon That May Explain Accelerated Weight Gain in Western Societies

Background: We have shown that individuals at the highest percentiles of the body mass index (BMI) distribution (i.e., most overweight) experience greater increases in body weight from sedentary lifestyle than those from the lowest percentiles. The purpose of the current analyses was to assess whether recent, accelerated increases in obesity could potentially be due to increased vulnerability to obesity risk factors as the population has become more overweight. Methodology/Principal Findings: Quantile regression was used to compare BMI population percentiles to obesity risk factors (lower education, diets characterized by high-meat/low-fruit content, parental adiposity) in two independent samples of men (N1 = 3,513, N2 = 11,365) and women (N1 = 15,809, N2 = 10,159). The samples were subsets of the National Walkers’ (Study 1) and Runners’ (Study 2) Health Studies whose physical activities fell short of nationally recommended activity levels. The data were adjusted for age, race, and any residual effects of physical activity. The regression slopes for BMI vs. education, diet, and family history became progressively stronger from the lowest (e.g., 5th, 6th…) to the highest (e.g., …, 94th, 95th) BMI percentiles. Compared to the 10th BMI percentile, their effects on the 90th BMI percentile were: 1) 2.7- to 8.6-fold greater in women and 2.0- to 2.4-fold greater in men for education; 2) 3.6- to 4.8-fold greater in women and 1.7- to 2.7-fold greater in men for diet; and 3) 2.0- to 2.6-fold greater in women and 1.7-fold greater in men for family history. Conclusions/Significance: Thus we propose risk factors that produce little weight gain in lean individuals may become more potent with increasing adiposity. This leads us to hypothesize that an individual’s obesity is itself a major component of their obesogenic environment, and that, the cycle of weight gain and increased sensitivity to obesity risk factors may partly explain recent increases in obesity in western societies.

59 BASIC BIOLOGICAL SCIENCES↗

Development and testing of improved statistical wind power forecasting methods.

Wind power forecasting (WPF) provides important inputs to power system operators and electricity market participants. It is therefore not surprising that WPF has attracted increasing interest within the electric power industry. In this report, we document our research on improving statistical WPF algorithms for point, uncertainty, and ramp forecasting. Below, we provide a brief introduction to the research presented in the following chapters. For a detailed overview of the state-of-the-art in wind power forecasting, we refer to [1]. Our related work on the application of WPF in operational decisions is documented in [2]. Point forecasts of wind power are highly dependent on the training criteria used in the statistical algorithms that are used to convert weather forecasts and observational data to a power forecast. In Chapter 2, we explore the application of information theoretic learning (ITL) as opposed to the classical minimum square error (MSE) criterion for point forecasting. In contrast to the MSE criterion, ITL criteria do not assume a Gaussian distribution of the forecasting errors. We investigate to what extent ITL criteria yield better results. In addition, we analyze time-adaptive training algorithms and how they enable WPF algorithms to cope with non-stationary data and, thus, to adapt to new situations without requiring additional offline training of the model. We test the new point forecasting algorithms on two wind farms located in the U.S. Midwest. Although there have been advancements in deterministic WPF, a single-valued forecast cannot provide information on the dispersion of observations around the predicted value. We argue that it is essential to generate, together with (or as an alternative to) point forecasts, a representation of the wind power uncertainty. Wind power uncertainty representation can take the form of probabilistic forecasts (e.g., probability density function, quantiles), risk indices (e.g., prediction risk index) or scenarios (with spatial and/or temporal dependence). Statistical approaches to uncertainty forecasting basically consist of estimating the uncertainty based on observed forecasting errors. Quantile regression (QR) is currently a commonly used approach in uncertainty forecasting. In Chapter 3, we propose new statistical approaches to the uncertainty estimation problem by employing kernel density forecast (KDF) methods. We use two estimators in both offline and time-adaptive modes, namely, the Nadaraya-Watson (NW) and Quantilecopula (QC) estimators. We conduct detailed tests of the new approaches using QR as a benchmark. One of the major issues in wind power generation are sudden and large changes of wind power output over a short period of time, namely ramping events. In Chapter 4, we perform a comparative study of existing definitions and methodologies for ramp forecasting. We also introduce a new probabilistic method for ramp event detection. The method starts with a stochastic algorithm that generates wind power scenarios, which are passed through a high-pass filter for ramp detection and estimation of the likelihood of ramp events to happen. The report is organized as follows: Chapter 2 presents the results of the application of ITL training criteria to deterministic WPF; Chapter 3 reports the study on probabilistic WPF, including new contributions to wind power uncertainty forecasting; Chapter 4 presents a new method to predict and visualize ramp events, comparing it with state-of-the-art methodologies; Chapter 5 briefly summarizes the main findings and contributions of this report.

17 WIND ENERGY↗

What Factors Affect the Prices of Low-Priced U.S. Solar PV Systems?

The price of solar PV systems has declined rapidly, yet there are some much lower-priced systems than others. This study explores the factors leading some systems to be so much lower priced than others. Using a data set of 42,611 residential-scale PV systems installed in the U.S. in 2013, we use quantile regressions to estimate the importance of factors affecting the installed prices for low-priced (LP) systems (those at the 10th percentile) in comparison to median-priced systems. We find that the value of solar to consumers–a variable that accounts for subsidies, electric rates, and PV generation levels–is associated with lower prices for LP systems but higher prices for median priced systems. Conversely, systems installed in new home construction are associated with lower prices at the median but higher prices for LP. Other variables have larger cost-reducing effects on LP than on median priced systems: systems installed in Arizona and Florida, as well as commercial and thin film systems. In contrast, the following have a smaller effect on prices for LP systems than median priced systems: tracking systems, self-installations, systems installed in Massachusetts, the system size, and installer experience. These results highlight the complex factors at play that lead to LP systems and shed light into how such LP systems can come about.

14 SOLAR ENERGY↗

Advancing Multiscale Simulation of Plasma-Surface Interfaces

We report the development of an atomistic-informed, surface-state-dependent predictive model for particle exchange in a carbon-tungsten plasma-surface interface. The predictive model uses machine learning (ML) techniques to learn the energy and angular distributions for particle exchange and rate functions for surface state evolution from molecular dynamics simulations of cumulative bombardment of tungsten by energetic carbon ions. Each predictive component is sensitive to the energy and trajectory of incident plasma species and the surface state. The surface state is represented by a set of surface state descriptors, which were derived from the atomistic surface state for each independent carbon bombardment event. These descriptors are representative of the composition and degree of amorphization of the outermost angstrom of surface material and were chosen to optimize predictive performance for particle exchange at the interface. The distributions for particle exchange (reflection/sputtering) are demonstrated to vary with each surface state descriptor, motivating the development of surface-state-dependent particle exchange models for plasma simulations. The performance of various ML methods was compared, including polynomial quantile regression, artificial neural networks, k-nearest neighbors, and random forest algorithms, with polynomial regression performing the best for interpolation and extrapolation of learned relationships. In addition to the particle exchange model, a neutral network was developed and used to identify data sufficiency throughout surface descriptor space, which will enable real-time feedback during future data production to ensure data is produced where it is most needed, and we provide commentary on improvements to the data production workflow for future endeavors.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Examples of Mission-driven Data Science from Jefferson Lab and ACES

This presentation details mission-driven data science initiatives at Jefferson Lab and the Joint Institute for Advanced Computing on Environmental Studies (ACES). JLab, a U.S. Department of Energy Office of Science national laboratory, operates the Continuous Electron Beam Accelerator Facility (CEBAF), and is the lead institute for the new High Performance Data Facility (HPDF) Hub. The Joint Institute for ACES brings together interdisciplinary teams in health informatics, climate modeling, computer science, and physics to address environmental challenges, including flood modeling. The Hampton Roads region, particularly Norfolk and Virginia Beach, faces increasing flood risks, motivating the need for rapid, reliable, and risk-aware decision support. ACES’s flooding work has a focus on uncertainty quantification (UQ) and machine learning (ML) for coastal flood management. The work is motivated by the increasing vulnerability of communities such as Norfolk and Virginia Beach, Virginia, to frequent coastal flooding events, and the need for rapid, reliable decision support. The research develops computationally efficient ML surrogate models to forecast water levels and flooding risk. A central theme is the quantification and calibration of predictive uncertainty, especially for out-of-distribution (OOD) scenarios, using techniques such as Monte Carlo Dropout, Deep Ensembles, Gaussian Processes, and Deep Quantile Regression (DQR). The study demonstrates that distance-aware UQ is critical for reliable scientific AI, particularly in high-dimensional, safety-critical, and real-time applications.

McSpadden, Diana [Thomas Jefferson National Accele↗

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

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

Hasan, Mahmud [Thomas Jefferson National Accelerat↗