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 523 records · Page 29
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

AI-Batt (Autonomous Identification of Battery Life Models) [SWR 21-36]

Autonomous Identification of Battery Life Models (AI-Batt) AI-Batt is a MATLAB code base for developing lifetime models for batteries from accelerated aging data. The code base provides many functions for processing, visualizing, and modeling battery aging data, making the data processing, exploration, and modeling workflow substantially faster. These tools are tailored for working with battery aging data sets, which usually consist of many separate time-series for each cell, with many test conditions and possible replicates at each condition, which makes it difficult to simply process or visualize the data set. Complex modeling tasks, such as cross-validation, sensitivity analysis, and uncertainty quantification have been implemented to enable thorough statistical investigation of model predictions. Additionally, several machine-learning algorithms are implemented to autonomously identify suitable models via symbolic regression. Data processing functions automatically cast data from the struct data type, which is commonly used to store experimental data, but is not an acceptable input for most algorithms, to the table data type, which can be easily used as input to any optimization algorithm. Also, the data can be separated into time-invariant and time-variant data tables, which is helpful for exploring the data set as well as developing separate models for time-variant and time-invariant aging mechanisms. For example, in aging tests with constant temperature, temperature is a time-invariant experimental condition. Visualization tools enable plotting of data, model fits, and model simulations possible with single-line function calls, empowering data exploration of complex data sets with both time-varying and time-invariant trends. Plots can be automatically generated for the whole data set, or separated by data group (groups of test replicates) or individual data series. Data points or data series can be automatically colored by the value of a variable with a variety of color maps, and model predictions can also be colored by the value of a fit statistic. Comparisons between data sets and the predictions/simulations of different models on the same data set can be easily plotted as well. Distributions of parameter values from bootstrap resampling can be plotted to visualize the reliability of parameter estimation, or determine any correlations between parameters. Modeling tools handle the complex task of creating and parsing symbolic equations for modeling battery lifetime. Equations are parsed to grab relevant data variables, parameter values, or specified sub-models for input into optimization, evaluation, or simulation functions. Models can be optimized locally (one set of parameters for each data series), bi-level (some parameters shared across the data set), or globally (single set of parameters for all data). Functions implementing symbolic regression algorithms help users to discover effective model equations, even in poorly sampled, high-dimensional data.

Smith, Kandler↗
DOE OSTI2021

Assessing dynamic vegetation model parameter uncertainty across Alaskan arctic tundra plant communities

Abstract As the Arctic region moves into uncharted territory under a warming climate, it is important to refine the terrestrial biosphere models (TBMs) that help us understand and predict change. One fundamental uncertainty in TBMs relates to model parameters, configuration variables internal to the model whose value can be estimated from data. We incorporate a version of the Terrestrial Ecosystem Model (TEM) developed for arctic ecosystems into the Predictive Ecosystem Analyzer (PEcAn) framework. PEcAn treats model parameters as probability distributions, estimates parameters based on a synthesis of available field data, and then quantifies both model sensitivity and uncertainty to a given parameter or suite of parameters. We examined how variation in 21 parameters in the equation for gross primary production influenced model sensitivity and uncertainty in terms of two carbon fluxes (net primary productivity and heterotrophic respiration) and two carbon (C) pools (vegetation C and soil C). We set up different parameterizations of TEM across a range of tundra types (tussock tundra, heath tundra, wet sedge tundra, and shrub tundra) in northern Alaska, along a latitudinal transect extending from the coastal plain near Utqiaġvik to the southern foothills of the Brooks Range, to the Seward Peninsula. TEM was most sensitive to parameters related to the temperature regulation of photosynthesis. Model uncertainty was mostly due to parameters related to leaf area, temperature regulation of photosynthesis, and the stomatal responses to ambient light conditions. Our analysis also showed that sensitivity and uncertainty to a given parameter varied spatially. At some sites, model sensitivity and uncertainty tended to be connected to a wider range of parameters, underlining the importance of assessing tundra community processes across environmental gradients or geographic locations. Generally, across sites, the flux of net primary productivity (NPP) and pool of vegetation C had about equal uncertainty, while heterotrophic respiration had higher uncertainty than the pool of soil C. Our study illustrates the complexity inherent in evaluating parameter uncertainty across highly heterogeneous arctic tundra plant communities. It also provides a framework for iteratively testing how newly collected field data related to key parameters may result in more effective forecasting of Arctic change.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

Reconstruction of Six-Dimensional Phase Space

A phase space is a mathematical representation of all possible physical states of a system. Particle beams at Fermilab exist within a six-dimensional (6D) phase space defined by three positional components, (x, y, z) and three momentum components, (px, py, pz). To reconstruct this space implies taking measurement data from detectors and mapping out particle behavior using computational methods. The beam detectors, however, are only able to detect spatial distribution among the events of the beam, therefore being limited to positional data. Also, due to the vast number of events in a particle beam, it is extremely difficult to analyze and differentiate every single one’s behavior. However, with Machine Learning (ML), which can distinguish between patterns and map out particle behavior more efficiently. We first used the particle beam software, G4beamline, to simulate a 10,000-event muon beam, adjusting parameters such as initial momentum magnitude (p¬0) and virtual detector position. Using ten virtual detectors, we analyzed p0 values such that minimum 9,990 events were analyzed by every detector. We then input the data from these beam simulations to a C++ program, that randomly selects 100 events, and creates a 2D histogram based on spatial distribution, detector position, and event intensity. This process is repeated 100 times to create 100 histograms per p0 value. These images were then input to a modified ResNet18 Convolutional Neural Network (CNN) for training, and to predict p0 from some unseen set of histograms. The model was accurate when trained on momentum increments of 5 MeV/c and provided with denser training samples around highly variable test values. These results displayed machine learning being able to accurately predict p0 from being trained on different particle behaviors.

Shirlee, Jermain [Fermilab]↗
DOE OSTI2021

Linking habitat suitability with a longleaf pine-hardwood model: Building a species-predictive fire-land management framework

Active management of fire-dependent ecosystems for specific species leads to complex tradeoffs, which affect conservation outcomes to other species. Therefore a multi-species evaluation of management actions is required. Habitat Suitability Models (HSMs) can help in predicting the likelihood of species occurrence using corresponding environmental variables and empirical relationships that link occurrence with specific environmental conditions. Incorporating multiple species into HSMs and relating them to habitat dynamics is crucial for ecosystems that require active management with prescribed fire. To address this issue, we developed multi-species HSM driven within an existing population model of the longleaf pine-hardwood ecosystem to assess the suitability of an ecosystem given different fire management strategies and environmental conditions. The population model used in this study provides spatial and temporal changes of longleaf pine-hardwood habitat structure in response to fire. These habitat values are used by the HSM to calculate habitat suitability for three threatened and endangered faunal species of this ecosystem, which all thrive with frequent fire, but have unique habitat requirements. Transient habitat conditions are traced to predict longleaf pine ecosystem trajectories under various management strategies, thereby evaluating current land management actions, such as thinning or prescribed fire frequencies. We tested a suite of environmental conditions to emphasize the sensitivity of the species to different fire management actions. The results of our modeling suggest that maximum suitable habitat for all three species can be achieved with fire frequency occurring at approximately once every three years. The modeling results support current management actions and provide a new habitat assessment tool that incorporates ecological factors for multiple species, thus providing for habitat optimization.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

On the Use of Satellite Nightlights for Power Outages Prediction

Hurricanes are a dominant disaster in the Caribbean, always causing serious power outages throughout the islands. Hurricane Maria was a prime example, causing unimaginable destruction of the power infrastructure of Puerto Rico (PR). Consequently, one month after the hurricane landfall, approximately 80% of the population was still without power. After an event of such massive destruction, the electric power restoration process progresses very slowly. This timeline can be improved using power outage (PO) forecast models that help identify the vulnerable places before the hurricane landfall. Generally, these models are trained with historical power outages records, associated data on weather conditions, and additional information about the natural and built environments. However, PO records are often difficult to acquire, and, in many instances, the power utility companies may not record them. This study utilizes a satellite-based Visible Infrared Imaging Radiometer Suite (VIIRS) night light data product as a surrogate for the power delivery to predict hurricane-induced PO in areas having limited to nonexistent historical data records. The processed satellite data is then used along with geographic variables, and simulated weather data to formulate machine learning-based algorithms to predict PO for future hurricane events. These models are applied and validated in the context of the PR catastrophic storm, Hurricane Maria.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Modeling neutral defects in III-V ternary alloys with a special quasirandom structure: Analysis of As- and III-site point defects in InGaAs

While first-principles density functional theory modeling has become a vital tool to investigate defect properties in semiconductors, the lack of crystalline periodicity in pseudobinary random composition alloys, such as In 1−𝑥 ⁢Ga 𝑥 ⁢As, complicates such analyses. We present a simulation strategy to systematically take into account the variability in the local defect environment in order to predict statistical properties of neutral intrinsic defects in In 1−𝑥⁢ Ga 𝑥 ⁢As. We use a comprehensive sampling from a modest-sized 64-atom special quasirandom structure (SQS) to define a statistically representative set of defects, and use a 512-atom hypercell, a 2 × 2 × 2 supercell of SQS supercells, to achieve cell-size convergence. We articulate an equivalent site principle and describe how it constrains atomic chemical reference energies in computation of defect formation energies in pseudobinary alloys. A simple protocol for estimating reference energies for the Ga and In atoms sharing the III site succeeds in obtaining the equivalence of defects at Ga-sites and In sites in the SQS supercell, (<30 meV differences in average formation energies). For III-site defects, such as the As antisite As III , the statistical variability in formation energies is modest, ≈ 0.1–0.2 eV. The variability in formation energy at As-site defects, such as the As vacancy 𝑣 As , can be much larger, >1 eV. The As antisite is shown to be a low-energy defect and the most likely to be present in as-grown materials, just as in GaAs. All other defects are higher-energy defects unlikely to be important in native material, but potentially important in radiation-damaged material. With a strong variability in defect energies, especially on the As-site, explicit consideration of statistical variability due to compositional randomness will be imperative for meaningful and quantitative comparisons to experiment.

Density functional theory↗
DOE OSTI2020

Sensor Recommendations for Long Term Monitoring of the F-Area Seepage Basins

In mid-2018, a new paradigm for long-term monitoring was developed after of decade of applied research projects funded by the Department of Energy’s office of Environmental Management Technology Development program. The program at SRNL was focused on transitioning complex environmental waste sites from active to passive remediations strategies. A key result of these studies was that the use of enhanced attenuation approaches at radiologically contaminated sites will result in the creation of secondary source areas in the subsurface that will require monitoring for decades. Alternative monitoring approaches are being developed and tested at the Savannah River Site’s F-Area Hazardous Waste Management Facility, the new paradigm provides innovative solutions that will significantly lower costs of monitoring through the coupling of data collection, machine learning and deterministic groundwater modeling. The foundation of this approach is a well-optimized network of sensors for measuring hydrogeochemical master variables that control, and therefore act as indicators of groundwater contaminant transport. By monitoring changes in the controlling master variables over time arising from geological and environmental shifts, predictive modelling can assist with identifying new strategies for ensuring regulatory requirements are met if trends toward conditions for potential remobilization of attenuated contaminants are detected. In this report, we evaluated commercially available single parameter sensor platforms (e.g., temperature/depth) and configurable multi-parameter sensor platforms (e.g., pH, oxidation-reduction potential, temperature, depth, dissolved oxygen, and conductivity). Each was scored using an optimization function based on how well the system supports the proposed long-term monitoring paradigm, in general, and the site-specific conditions at F-Area, in particular. Several viable sensor systems were identified. Of these, a combined platform including the In-Situ Aqua TROLL 500 multi-parameter sensor platform and the In-Situ temperature/depth sensor had the highest rating and was identified as the most suitable candidate for installation and monitoring of the master variables and potentiometric surface that control groundwater contaminant plumes emanating from the F-Area Seepage Basins. The discussion of recommended potential deployment locations builds upon recommendations made by Denham et al (2019).

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2026

Predicting Li-Ion Battery Capacity Fade Using Early-Life Data and a Hybrid Data-Driven Gaussian Process-Bayesian Regression Approach

Accurately predicting Li-ion battery capacity trajectories using early-life data can dramatically improve battery-life understandings and be used to rapidly evaluate design/cost/performance trade-offs when developing new battery materials. Accurate early-life predictions enable researchers to quickly iterate over cell designs and material precursor properties without consistently cycling cells to failure. To this end, we present a toolbox that uses a combined Gaussian Process and Bayesian regression approach that capitalizes on signals other than just capacity (e.g., dQ/dV, voltage drops) to rapidly predict capacity-fade trajectories. The prediction tool uses Bayesian regression to fit functional forms, e.g., power law, sigmoids, etc., to predict capacity-fade dynamics. By fitting functional forms, the capacity fade can be interrogated at any point in the future, allowing for early cell-failure prediction. Additionally, Bayesian regression allows for accurate uncertainty estimates that account for cell-to-cell variability (aleatoric uncertainty) and the lack of observation data (epistemic uncertainty). By only using early cycle data to predict the capacity fade trajectory, uncertainty bounds at end-of-life can be extremely large. The large uncertainty bounds are further exacerbated because there is no systematic way to define the prior distribution of the functional forms' parameters. We improve our the predicted trajectory confidence interval of our predicted trajectory using two methods. First, we shows that a small amount of held-out cycling data is sufficientuse some train cells, that have been cycled to failure to derive information regarding the appropriate prior distributions for the functional forms' parameters of the functional form, effectively leading to data-driven priors.. We propose constructing the data-driven priors by first running a Bayesian regression starting with uninformed priors to generate intermediate cell-specific posterior parameter distributions. These posterior distributions are combined using a Ggaussian mixture model for each parameter to create the data-driven priors. These mixture models serve as the data-driven prior distributions for the parameters for. Second, we derive multiple features, e.g., C_dchg 0.5 DoD 0.5, log (|mean(dQ/dV_(w_3-w_0 ) (V)|), etc., from the train cellsheld-out cycling data, identify which the features are that best predicting capacity at early/mid-life cycles, and then create Ggaussian process regression models that are used for predicting capacity at early/mid-life cycles for the test cells (see blue dots with error bars in Fig 1b). Finally, these predicted data-points are used in addition to the actual early cycle data capacity fade to construct the Bayesian regression trajectory for the test cell s. Notably. We note that these two methods are complementary and can be combined with each other. We evaluate the performance of our proposed method on an testing open-source dataset from Iowa State University and Iowa Lakes Community College (ISU-ILCC). This dataset comprises of 251 nickel-manganese-cobalt/graphite Lithium-ion cells that are cycled under 63 different conditions. We compute the mean average percentage error (MAPE) and negative log predictive density (NLPD) to quantify the efficacy of our method. Our initial findings suggest that, when only few observations are available, for test cells, when using only Bayesian regression with uninformed priors, a power law functional provides the most accurate predictions. with very few data points. However, asHowever, a the number of data points increases, a twin sigmoidal function becomes more accurate as the number of observations further increases. We also find that using as little as 10% of the data set towards generating data-driven priors can lead to significant improvement in prediction accuracy when using early cycle data. Lastly, we found that augmenting early-cycle data with Gaussian process-predicted capacity data for Bayesian regression greatly improves the prediction accuracy. We will present a comprehensive comparison of our methods to other methods available in the literature and apply this method to additional battery datasets.

42 ENGINEERING↗
DOE OSTI2025

Transition Zones at the Changing Coastal Terrestrial‐Aquatic Interface

Coastal soils are a significant but highly uncertain component of global biogeochemical cycles. These systems experience spatial and temporal variability in biogeochemical processes, driven by marsh‐to‐upland gradients and hydrological fluctuations. These fluctuations make it difficult to understand and predict biogeochemical processes in these highly dynamic systems. We studied coastal soil biogeochemistry and its variability (a) at regional scales and (b) across transects from upland forest to marsh, in two contrasting regions—Lake Erie, a freshwater lacustrine system, and Chesapeake Bay, a saltwater estuarine system. Salinity‐related analytes were a key source of variability in soil biogeochemistry, not just in the saltwater system, but surprisingly, also in the freshwater system. We had hypothesized linear trends in biogeochemical parameters along the TAI—however, contrary to expectations, transition soils were not consistently intermediate between upland and marsh endmembers; the non‐monotonic trends of C, P, Fe along our transects suggest that these do not behave as expected and may be difficult to model and predict—thus these are key analytes to study in our regions. Rapidly changing soil factors across coastal gradients (e.g., Ca, K, CEC, and TS) may act as precursors to ecosystem shifts. Our comprehensive soil characterization represents a snapshot of a single timepoint of surface soils and provides essential data for mechanistic modeling of ecosystem dynamics across coastal transects.

Patel, Kaizad F. [Pacific Northwest National Labor↗
DOE OSTI2024

Data-driven closure modeling for hypersonic turbulent flows

The Reynolds-averaged Navier–Stokes (RANS) equations remain a workhorse technology for simulating compressible fluid flows of practical interest. Due to model-form errors, however, RANS models can yield erroneous predictions that preclude their use on mission-critical problems. This report summarizes work performed from FY22-FY24 focused on improving RANS models for hypersonic flows using data-driven modeling and scientific machine learning. In this work we: 1. Investigate the current capabilities of RANS models in Sandia’s parallel aerodynamics and re-entry code (SPARC) for hypersonic flows with a focus on shock boundary layer interactions (SBLIs), 2. Assess several established corrections that exist in the literature aimed at improving predictions for SBLIs, 3. Develop improved models for the Reynolds stress tensor using tensor-basis neural networks, 4. Develop a neural-network-based variable turbulent Prandtl number model to reduce errors in wall heating in SBLIs. 5. Begin future investigations including employing the LIFE framework to improve wall heating predictions in SBLIs as well as the ensemble Kalman filter. We find that current RANS models in SPARC are deficient for complex SBLI flows. In particular, no current model jointly predicts wall heat flux, wall shear stress, and wall pressure with reasonable accuracy. Existing corrections help, but do not alleviate this issue altogether. The development of improved models for the Reynolds stress tensor via tensor-basis neural networks results in more predictive RANS models across a suite of low-speed and high-speed cases. For hypersonic boundary layers, the inclusion of the wall-normal Reynolds stress via TBNNs has an appreciable impact on the wall-normal momentum balance and wall quantities. However, we find that improvements to the Reynolds stress tensor do not address the over-prediction in wall heat flux in SBLIs. We find that a neural-network-based variable turbulent Prandtl number model systematically and substantially improves wall heating predictions for a range of SBLI cases.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Linking the subseasonal variability of the East Asia winter monsoon and the Madden-Julian Oscillation through wave disturbances along the subtropical jet

Despite an urgent demand for reliable subseasonal-to-seasonal (S2S) predictions to guide disaster preparedness, our current climate models show limited S2S prediction skill, particularly for precipitation, due to an inadequate understanding of the key processes that drive regional S2S variability. Here we demonstrate that the leading subseasonal variability mode of precipitation over the East Asian Winter Monsoon (EAWM) region is not only closely tied to the activity of the Madden-Julian Oscillation (MJO), but also linked to precipitation and temperature extremes worldwide, influenced by a circumglobal Rossby wave-train along the subtropical westerly jet. Despite a close phase-lock relationship between the MJO and subseasonal EAWM precipitation, our findings indicate that the MJO itself may only play a minor role in the subseasonal EAWM variability. Given its significant impact on the S2S variability of global weather extremes, we call for coordinated community efforts to enhance the understanding and prediction of the circumglobal Rossby wave-train.

Atmospheric science↗
DOE OSTI2020

Projected changes in the terrestrial and oceanic regulators of climate variability across sub-Saharan Africa

Future changes in the sign and intensity of ocean–land–atmosphere interactions have been insufficiently studied, despite implications for regional climate change projections, extreme event statistics, and seasonal climate predictability. In response to this deficiency, the present study focuses on projected responses to the enhanced greenhouse effect in: (1) the mean state of the atmosphere and land surface; (2) oceanic and terrestrial drivers of sub-Saharan climate variability; and (3) total seasonal climate predictability of sub-Saharan Africa, a region known for its pronounced land–atmosphere coupling. Analysis focuses on output from 23 Earth System Models in the Coupled Model Intercomparison Project Phase Five for the late twentieth and twenty-first centuries. It is projected that the greatest warming across sub-Saharan Africa will occur over the Sahel, the monsoon season will become more persistent into late summer and autumn, short rains in the Horn of Africa (HOA) will intensify, and leaf area index will increase across the HOA. Stepwise Generalized Equilibrium Feedback Assessment, i.e. a multivariate statistical approach, is applied to the model output over sub-Saharan Africa in order to explore the oceanic and terrestrial drivers of regional climate. The models indicate that the study region’s climate variability is dominated by oceanic drivers, with secondary contributions from soil moisture and very modest impacts from vegetation. Overall, the general model consensus of future projections indicates a concerning diminished seasonal predictability of sub-Saharan African regional climate based on key oceanic and terrestrial predictors and an elevated role of the land surface (associated with soil moisture anomalies) compared to oceanic drivers in regulating regional climate variability.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Predicting Rare Earth Element Potential in Produced and Geothermal Waters of the United States via Emergent Self-Organizing Maps

This work applies emergent self-organizing map (ESOM) techniques, a form of machine learning, in the multidimensional interpretation and prediction of rare earth element (REE) abundance in produced and geothermal waters in the United States. Visualization of the variables in the ESOM trained using the input data shows that each REE, with the exception of Eu, follows the same distribution patterns and that no single parameter appears to control their distribution. Cross-validation, using a random subsample of the starting data and only using major ions, shows that predictions are generally accurate to within an order of magnitude. Using the same approach, an abridged version of the U.S. Geological Survey Produced Waters Database, Version 2.3 (which includes both data from produced and geothermal waters) was mapped to the ESOM and predicted values were generated for samples that contained enough variables to be effectively mapped. Results show that in general, produced and geothermal waters are predicted to be enriched in REEs by an order of magnitude or more relative to seawater, with maximum predicted enrichments in excess of 1000-fold. Cartographic mapping of the resulting predictions indicates that maximum REE concentrations exceed values in seawater across the majority of geologic basins investigated and that REEs are typically spatially co-associated. The factors causing this co-association were not determined from ESOM analysis, but based on the information currently available, REE content in produced and geothermal waters is not directly controlled by lithology, reservoir temperature, or salinity.

Engle, Mark A. (ORCID:0000000152587374)↗
DOE OSTI2021

Forecasting Solar-Thermal Systems Performance under Transient Operation Using a Data-Driven Machine Learning Approach Based on the Deep Operator Network Architecture

Modeling and prediction of the dynamic behavior of thermal systems operating under intermittent energy input and variable load requirements represent one of the greatest challenges in the development of efficient and reliable renewable-based power generation technologies. In this work, a data-driven machine learning modeling framework was developed based on a modified version of the Deep Operator Network architecture where the time coordinate in the trunk net is replaced with historical data of the predicting quantity. The modeling framework can be used to accurately predict the performance of renewable-based energy conversion technologies including wind- and solar-based power plants. This novel framework was applied on a solar-thermal system that consists of a solar collection loop using a flat plate collector, a power generation loop comprising an Organic Rankine Cycle, and a thermal energy storage tank connecting both loops. Variable solar irradiance, air temperature, and power load profiles were used by the Deep Operator Network to predict the State-of-Charge and the efficiency of the thermal system for several days. The results were compared with the State-of-Charge and efficiency functions calculated using a physics-based model. For a simple operation scenario, characterized by a clear sky solar irradiance profile and constant load, the standard deviation in the State-of-Charge prediction by Deep Operator Network is below 0.9% during a seven-day prediction time horizon. For the most realistic operation scenario that considers real solar irradiance and a rough load profile, the maximum standard deviation in the predictions for the State-of-Charge and efficiency are below 6.8% and 2.5%, respectively. A comparison between Deep Operator Network and Long Short Term Memory network was also performed. In general, both networks predict very well the State-of-Charge for different data density conditions; however, a higher accuracy, with a standard deviation below 2.0%, is obtained by the Deep Operator Network during three and half days using sparser training data of 20-minute points. The same accuracy for the State-of-Charge prediction with the Long Short Term Memory network is achieved only for 14 h. Average standard deviations for the State-of-Charge prediction of 1.1% with the Deep Operator Network and 1.5% with the Long Short Term Memory network are obtained for a four-day prediction time using a denser training data of 5-minute points.

DeepONet↗
DOE OSTI2022

KGML-ag: a modeling framework of knowledge-guided machine learning to simulate agroecosystems: a case study of estimating N<sub>2</sub>O emission using data from mesocosm experiments

Abstract. Agricultural nitrous oxide (N2O) emission accounts for a non-trivial fraction of global greenhouse gas (GHG) budget. To date, estimating N2O fluxes from cropland remains a challenging task because the related microbial processes (e.g., nitrification and denitrification) are controlled by complex interactions among climate, soil, plant and human activities. Existing approaches such as process-based (PB) models have well-known limitations due to insufficient representations of the processes or uncertainties of model parameters, and due to leverage recent advances in machine learning (ML) a new method is needed to unlock the “black box” to overcome its limitations such as low interpretability, out-of-sample failure and massive data demand. In this study, we developed a first-of-its-kind knowledge-guided machine learning model for agroecosystems (KGML-ag) by incorporating biogeophysical and chemical domain knowledge from an advanced PB model, ecosys, and tested it by comparing simulating daily N2O fluxes with real observed data from mesocosm experiments. The gated recurrent unit (GRU) was used as the basis to build the model structure. To optimize the model performance, we have investigated a range of ideas, including (1) using initial values of intermediate variables (IMVs) instead of time series as model input to reduce data demand; (2) building hierarchical structures to explicitly estimate IMVs for further N2O prediction; (3) using multi-task learning to balance the simultaneous training on multiple variables; and (4) pre-training with millions of synthetic data generated from ecosys and fine-tuning with mesocosm observations. Six other pure ML models were developed using the same mesocosm data to serve as the benchmark for the KGML-ag model. Results show that KGML-ag did an excellent job in reproducing the mesocosm N2O fluxes (overall r2=0.81, and RMSE=3.6 mgNm-2d-1 from cross validation). Importantly, KGML-ag always outperforms the PB model and ML models in predicting N2O fluxes, especially for complex temporal dynamics and emission peaks. Besides, KGML-ag goes beyond the pure ML models by providing more interpretable predictions as well as pinpointing desired new knowledge and data to further empower the current KGML-ag. We believe the KGML-ag development in this study will stimulate a new body of research on interpretable ML for biogeochemistry and other related geoscience processes.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Investigation of Site Amplifications Using Ambient-Noise-Derived Shallow Velocity Structures Under a Dense Array in Oklahoma

The shear-wave velocity (V S ) structure plays an important role in characterizing site amplification. The Large-n Seismic Survey in Oklahoma (LASSO; 1820 stations) revealed large vertical ground-motion variability in a 25 km × 32 km area in northern Oklahoma. The LASSO array has a relatively simple and flat topography, typical in a sedimentary basin environment in the central United States. In this study, we use the dense array to investigate the velocity structure under the LASSO array and how vertical ground motions relate to the shallow-to-deep structures. We extract the fundamental-mode Rayleigh wave by cross-correlating one month of ambient noise (0.7–5 Hz). We use double-beamforming to measure the group and phase velocities and anisotropy. By jointly inverting the group and phase velocities, we obtain the V S structure. Here, we observe correlations between V S at depths of 0.1–1.5 km and vertical ground motions using sites on the stiffer Permian formations. The shallow Quaternary alluvium and terrace deposits can amplify vertical ground motions by a factor of 2–4.5 between 2 and 25 Hz and attenuate signals above 25 Hz. We use 1D V S profiles to simulate the SV-wave transfer functions. An average V S of 250 m/s in the upper 20–40 m may cause the observed amplification between 2 and 40 Hz. V S estimated by topographic slopes cannot predict the relative amplification. Our results highlight the large variability of site-dependent ground motion in a small local region and the importance of characterizing shallow structures to estimate seismic hazards. Small thickness variations of the shallow formation can significantly change the resonance amplitude and frequency, which likely reduces the coherency of the Rayleigh waves extracted from ambient noise.

Chang, Hilary [Massachusetts Inst. of Technology (↗
DOE OSTI2021

Spatio-Temporal Modeling of Field Surveyed Backsheet Degradation

Assessing photovoltaic module backsheet durability is critical to increasing module lifetime. Lab based accelerating testing has recently failed to predict large scale failures of widely adopted polymeric materials. Field surveyed data is critical to assess the performance of component lifetime. Using a documented field survey protocol, 13 field surveys where conducted. Each measurement is encoded with it's spatial location in respect to the other modules. By combining field survey data on degradation predictors with real time satellite weather data, data-driven predictive models of backsheet degradation were trained. LOESS models were constructed to investigate the spatial dependence of measurements. It was found that micro-climatic effects like tree-lines, ground surface changes, and elevation changes effected the magnitude and variance of the measurements. A GAM model was created to predict the value of degradation based on measured predictors. The model includes variables on the climate of the system and the location of each measurement in the PV mounting structure. The model performed well with an adj.R 2 of 0.95 for yellowness index prediction. The model was cross-validated using k-folds.

backsheet↗
DOE OSTI2025

Guiding Principles for Geochemical/Thermodynamic Model Development and Validation in Nuclear Waste Disposal: A Close Examination of Recent Thermodynamic Models for H + —Nd 3+ —NO 3 - (—Oxalate) Systems

Development of a defensible source-term model (STM), usually a thermodynamical model for radionuclide solubility calculations, is critical to a performance assessment (PA) of a geologic repository for nuclear waste disposal. Such a model is generally subjected to rigorous regulatory scrutiny. In this article, we highlight key guiding principles for STM model development and validation in nuclear waste management. We illustrate these principles by closely examining three recently developed thermodynamic models with the Pitzer formulism for aqueous H + —Nd 3+ —NO 3 - (—oxalate) systems in a reverse alphabetical order of the authors: the XW model developed by Xiong and Wang, the OWC model developed by Oakes et al., and the GLC model developed by Guignot et al., among which the XW model deals with trace activity coefficients for Nd(III), while the OWC and GLC models are for concentrated Nd(NO 3 ) 3 electrolyte solutions. The principles highlighted include the following: (1) Principle 1. Validation against independent experimental data: A model should be validated against experimental data or field observations that have not been used in the original model parameterization. We tested the XW model against multiple independent experimental data sets including electromotive force (EMF), solubility, water vapor, and water activity measurements. The results show that the XW model is accurate and valid for its intended use for predicting trace activity coefficients and therefore Nd solubility in repository environments. (2) Principle 2. Testing for relevant and sensitive variables: Solution pH is such a variable for an STM and easily acquirable. All three models are checked for their ability to predict pH conditions in Nd(NO 3 ) 3 electrolyte solutions. The OWC model fails to provide a reasonable estimate for solution pH conditions, thus casting serious doubt on its validity for a source-term calculation. In contrast, both the XW and GLC models predict close-to-neutral pH values, in agreement with experimental measurements. (3) Principle 3. Honoring physical constraints: Upon close examination, it is found that the Nd(III)-NO 3 association schema in the OWC model suffers from two shortcomings. Firstly, its second stepwise stability constant for Nd(NO 3 ) 2+ (log K 2 ) is much higher than the first stepwise stability constant for NdNO 3 2+ (log K 1 ), thus violating the general rule of (log K 2 –log K 1 ) < 0, or $\frac{K1}{K2}$>1. Secondly, the OWC model predicts abnormally high activity coefficients for Nd(NO 3 ) 2 + (up to ~900) as the concentration increases. (4) Principle 4. Minimizing degrees of freedom for model fitting: The OWC model with nine fitted parameters is compared with the GLC model with five fitted parameters, as both models apply to the concentrated region for Nd(NO 3 ) 3 electrolyte solutions. The latter appears superior to the former because the latter can fit osmotic coefficient data equally well with fewer model parameters. The work presented here thus illustrates the salient points of geochemical model development, selection, and validation in nuclear waste management.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗