SEARCH · Engineering Papers

Results for “ensemble 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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 361 records · Page 20

All sources NASA NTRS DOE OSTI

DOE OSTI2024

Prognostic analysis of high-flow nasal cannula therapy and non-invasive ventilation in mild to moderate hypoxemia patients and construction of a machine learning model for 48-h intubation prediction—a retrospective analysis of the MIMIC database

Background This study aims to investigate the clinical outcome between high-flow nasal cannula (HFNC) and non-invasive ventilation (NIV) therapy in mild to moderate hypoxemic patients on the first ICU day and to develop a predictive model of 48-h intubation. Methods The study included adult patients from the MIMIC III and IV databases who first initiated HFNC or NIV therapy due to mild to moderate hypoxemia (100 < PaO2/FiO2 ≤ 300). The 48-h and 30-day intubation rates were compared using cross-sectional and survival analysis. Nine machine learning and six ensemble algorithms were deployed to construct the 48-h intubation predictive models, of which the optimal model was determined by its prediction accuracy. The top 10 risk and protective factors were identified using the Shapley interpretation algorithm. Result A total of 123,042 patients were screened, of which, 673 were from the MIMIC IV database for ventilation therapy comparison (HFNC n = 363, NIV n = 310) and 48-h intubation predictive model construction (training dataset n = 471, internal validation set n = 202) and 408 were from the MIMIC III database for external validation. The NIV group had a lower intubation rate (23.1% vs. 16.1%, p = 0.001), ICU 28-day mortality (18.5% vs. 11.6%, p = 0.014), and in-hospital mortality (19.6% vs. 11.9%, p = 0.007) compared to the HFNC group. Survival analysis showed that the total and 48-h intubation rates were not significantly different. The ensemble AdaBoost decision tree model (internal and external validation set AUROC 0.878, 0.726) had the best predictive accuracy performance. The model Shapley algorithm showed Sequential Organ Failure Assessment (SOFA), acute physiology scores (APSIII), the minimum and maximum lactate value as risk factors for early failure and age, the maximum PaCO 2 and PH value, Glasgow Coma Scale (GCS), the minimum PaO 2 /FiO 2 ratio, and PaO 2 value as protective factors. Conclusion NIV was associated with lower intubation rate and ICU 28-day and in-hospital mortality. Further survival analysis reinforced that the effect of NIV on the intubation rate might partly be attributed to the other impact factors. The ensemble AdaBoost decision tree model may assist clinicians in making clinical decisions, and early organ function support to improve patients’ SOFA, APSIII, GCS, PaCO 2 , PaO 2 , PH, PaO 2 /FiO 2 ratio, and lactate values can reduce the early failure rate and improve patient prognosis.

Fu, Wei↗

DOE OSTI2024

Deep energy-pressure regression for a thermodynamically consistent EOS model

Abstract In this paper, we aim to explore novel machine learning (ML) techniques to facilitate and accelerate the construction of universal equation-Of-State (EOS) models with a high accuracy while ensuring important thermodynamic consistency. When applying ML to fit a universal EOS model, there are two key requirements: (1) a high prediction accuracy to ensure precise estimation of relevant physics properties and (2) physical interpretability to support important physics-related downstream applications. We first identify a set of fundamental challenges from the accuracy perspective, including an extremely wide range of input/output space and highly sparse training data. We demonstrate that while a neural network (NN) model may fit the EOS data well, the black-box nature makes it difficult to provide physically interpretable results, leading to weak accountability of prediction results outside the training range and lack of guarantee to meet important thermodynamic consistency constraints. To this end, we propose a principled deep regression model that can be trained following a meta-learning style to predict the desired quantities with a high accuracy using scarce training data. We further introduce a uniquely designed kernel-based regularizer for accurate uncertainty quantification. An ensemble technique is leveraged to battle model overfitting with improved prediction stability. Auto-differentiation is conducted to verify that necessary thermodynamic consistency conditions are maintained. Our evaluation results show an excellent fit of the EOS table and the predicted values are ready to use for important physics-related tasks.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

Uncertainty quantification of a deep learning fuel property prediction model

Deep learning models are being widely used in the field of combustion. Given the black-box nature of typical neural network based models, uncertainty quantification (UQ) is critical to ensure the reliability of predictions as well as the training datasets, and for a principled quantification of noise and its various sources. Deep learning surrogate models for predicting properties of chemical compounds and mixtures have been recently shown to be promising for enabling data-driven fuel design and optimization, with the ultimate goal of improving efficiency and lowering emissions from combustion engines. In this study, UQ is performed for a multi-task deep learning model that simultaneously predicts the research octane number (RON), Motor Octane Number (MON), and Yield Sooting Index (YSI) of pure components and multicomponent blends. The deep learning model is comprised of three smaller networks: Extractor 1, Extractor 2, and Predictor, and a mixing operator. The molecular fingerprints of individual components are encoded via Extractor 1 and Extractor 2, the mixing operator generates fingerprints for mixtures/blends based on linear mixing operation, and the predictor maps the fingerprint to the target properties. Two different classes of UQ methods, Monte Carlo ensemble methods and Bayesian neural networks (BNNs), are employed for quantifying the epistemic uncertainty. Combinations of Bernoulli and Gaussian distributions with DropConnect and DropOut techniques are explored as ensemble methods. All the DropConnect, DropOut and Bayesian layers are applied to the predictor network. Aleatoric uncertainty is modeled by assuming that each data point has an independent uncertainty associated with it. The results of the UQ study are further analyzed to compare the performance of BNN and ensemble methods. Although this study is confined to UQ of fuel property prediction, the methodologies are applicable to other deep learning frameworks that are being widely used in the combustion community.

33 ADVANCED PROPULSION SYSTEMS↗

NASA NTRS1984

Lagged average forecasting, some operational considerations

The Lagged Average Forecast (LAF) method differs from the Monte Carlo Forecast (MCF) method in the definition of the ensemble of initial states which are used to generate the ensemble of forecasts. The LAF initial states are the current analysis and the forecasts made from previous analyses verifying the current time. Thus the LAF ensemble is composed of forecasts which are made by a regular operational system of numerical weather prediction and the LAF method is therefore operationally attractive. The application of the authors' previous ideas and results to an operational model requires the resolution of what might be called the degrees of freedom problem, i.e., how to obtain a homogeneous sample large enough to calculate stable statistics. It is suggested that this problem may be solved by carefully modeling the required statistics in terms of a small set of parameters and then estimating only these few parameters from the data. It is noted that there may be considerable information in each initial ensemble relating to the predictability of each particular case, and that this information may be incorporated in the model of the statistics.

Hoffman, R. N.↗

DOE OSTI2023

Predicting Biomass Yields of Advanced Switchgrass Cultivars for Bioenergy and Ecosystem Services Using Machine Learning

The production of advanced perennial bioenergy crops within marginal areas of the agricultural landscape is gaining interest due to its potential to sustainably produce feedstocks for biofuels and bioproducts while also improving the sustainability and resilience of commodity crop production. However, predicting the biomass yields of this production system is challenging because marginal areas are often relatively small and spread around agricultural fields and are typically associated with various abiotic conditions that limit crop production. Machine learning (ML) offers a viable solution as a biomass yield prediction tool because it is suited to predicting relationships with complex functional associations. The objectives of this study were to (1) evaluate the accuracy of commonly applied ML algorithms in agricultural applications for predicting the biomass yields of advanced switchgrass cultivars for bioenergy and ecosystem services and (2) determine the most important biomass yield predictors. Datasets on biomass yield, weather, land marginality, soil properties, and agronomic management were generated from three field study sites in two U.S. Midwest states (Illinois and Iowa) over three growing seasons. The ML algorithms evaluated in the study included random forests (RFs), gradient boosting machines (GBMs), artificial neural networks (ANNs), K-neighbors regressor (KNR), AdaBoost regressor (ABR), and partial least squares regression (PLSR). Coefficient of determination (R 2 ) and mean absolute error (MAE) were used to evaluate the predictive accuracy of the tested algorithms. Results showed that the ensemble methods, RF (R 2 = 0.86, MAE = 0.62 Mg/ha), GBM (R 2 = 0.88, MAE = 0.57 Mg/ha), and GBM (R 2 = 0.78, MAE = 0.66 Mg/ha), were the most accurate in predicting biomass yields of the Independence, Liberty, and Shawnee switchgrass cultivars, respectively. This is in agreement with similar studies that apply ML to multi-feature problems where traditional statistical methods are less applicable and datasets used were considered to be relatively small for ANNs. Consistent with previous studies on switchgrass, the most important predictors of biomass yield included average annual temperature, average growing season temperature, sum of the growing season precipitation, field slope, and elevation. This study helps pave the way for applying ML as a management tool for alternative bioenergy landscapes where understanding agronomic and environmental performance of a multifunctional cropping system seasonally and interannually at the sub-field scale is critical.

09 BIOMASS FUELS↗

NASA NTRS1994

Stably stratified shear turbulence: A new model for the energy dissipation length scale

A model is presented to compute the turbulent kinetic energy dissipation length scale l(sub epsilon) in a stably stratified shear flow. The expression for l(sub epsilon) is derived from solving the spectral balance equation for the turbulent kinetic energy. The buoyancy spectrum entering such equation is constructed using a Lagrangian timescale with modifications due to stratification. The final result for l(sub epsilon) is given in algebraic form as a function of the Froude number Fr and the flux Richardson number R(sub f), l(sub epsilon) = l(sub epsilon)(Fr, R(sub f). The model predicts that for R(sub f) less than R(sub fc), l(sub epsilon) decreases with stratification. An attractive feature of the present model is that it encompasses, as special cases, some seemingly different models for l(sub epsilon) that have been proposed in the past by Deardorff, Hunt et al., Weinstock, and Canuto and Minotti. An alternative form for the dissipation rate epsilon is also discussed that may be useful when one uses a prognostic equation for the heat flux. The present model is applicable to subgrid-scale models, which are needed in large eddy simulations (LES), as well as to ensemble average models. The model is applied to predict the variation of l(sub epsilon) with height z in the planetary boundary layer. The resulting l(sub epsilon) versus z profile reproduces very closely the nonmonotonic profile of l(sub epsilon) exhibited by many LES calculations, beginning with the one by Deardorff in 1974.

Cheng, Y.↗

DOE OSTI2026

Uncertainty-Aware Machine Learning for Small-Angle X-ray Scattering Analysis in Autonomous Experimentation

Small-angle X-ray scattering (SAXS) is a powerful high-throughput characterization tool for probing nanoscale structure in native sample environments, providing real-time morphological information such as nanoparticle size and shape during synthesis. However, automated SAXS data analysis for extracting meaningful structural parameters is non-trivial and remains a bottleneck in closed-loop experimentation towards autonomous materials discovery, which demands fast, reliable, and uncertainty-aware data analysis. Here, we develop a machine-learning approach for automated SAXS analysis tailored to closed-loop nanoparticle synthesis. A Random Forest (RF) regression model is trained on 100,000 synthetic SAXS curves generated from polydisperse spherical nanoparticles with realistic background contributions. Using normalized one-dimensional SAXS intensity profiles as input, the RF model directly predicts nanoparticle radius, size polydispersity, and background parameters, while the ensemble standard deviation across trees provides built-in uncertainty quantification (UQ). On synthetic data, we show that combining fit-quality metrics (R 2 , MAE) with thresholds on prediction uncertainty reliably identifies accurate parameter estimates without access to ground truth. We then apply the trained model to 365 experimental SAXS profiles of citrate-reduced gold nanoparticles synthesized using an automated droplet-flow microreactor with in situ SAXS at a synchrotron beamline, classifying the results into high- and low-confidence subsets based on UQ metrics. Finally, we integrate RF-based SAXS analysis into a simulated closed-loop optimization campaign using Gaussian process Bayesian optimization to minimize nanoparticle polydispersity, benchmarking against conventional automated Levenberg–Marquardt fitting. The RF-guided campaign exhibits substantially faster convergence and lower relative opportunity cost (∼0.07 vs ∼0.3), demonstrating that uncertainty-aware machine-learning SAXS analysis significantly enhances the efficiency and robustness of autonomous nanomaterials synthesis workflows.

Bayesian optimization↗

NASA NTRS2020

Ensemble PM2.5 Forecasting during the 2018 Camp Fire Event Using the HYSPLIT Transport and Dispersion Model

Biomass burning releases a vast amount of aerosols into the atmosphere, often leading to severe air quality and health problems. Prediction of the air quality effects from biomass burning emissions is challenging due to uncertainties in fire emission, plume rise calculation, and other model inputs/processes. Ensemble forecasting is increasingly used to represent model uncertainties. In this paper, an ensemble forecast was conducted to predict surface PM2.5 during the 2018 California Camp Fire event using the NOAA HYSPLIT dispersion model at 0.1- degree horizontal resolution. Different combinations of four satellite-based fire emission datasets (FEER, FLAMBE, GBBEPx and GFAS), two plume rise schemes (Briggs and Sofiev), various meteorology inputs and model setup options were used to create the forecast ensemble, for a total of 112 experiments. The performance of each ensemble member and the ensemble mean were evaluated using ground-based observations, with four statistical metrics and an overall rank. The ensemble spread of the 112 members reached 1000 μg/m3, highlighting the large uncertainty in wildfire forecast. The ensemble mean displayed the best performance. Each fire emission product contributed to one or more members among the top ten performers, revealing the forecasting dependence on both the quality of fire emissions data and model representation of emission, transport and removal processes. In addition, an ensemble size reduction technique was introduced. With the help of this technique, the ensemble size was reduced from 112 to 28 members and still produced an ensemble mean that yielded comparable or even better performance to that of the full ensemble.

Biomass Burning↗

DOE OSTI2023

Urban Flood Modeling: Uncertainty Quantification and Physics‐Informed Gaussian Processes Regression Forecasting

Abstract Estimating uncertainty in flood model predictions is important for many applications, including risk assessment and flood forecasting. We focus on uncertainty in physics‐based urban flooding models. We consider the effects of the model's complexity and uncertainty in key input parameters. The effect of rainfall intensity on the uncertainty in water depth predictions is also studied. As a test study, we choose the Interconnected Channel and Pond Routing (ICPR) model of a part of the city of Minneapolis. The uncertainty in the ICPR model's predictions of the floodwater depth is quantified in terms of the ensemble variance using the multilevel Monte Carlo (MC) simulation method. Our results show that uncertainties in the studied domain are highly localized. Model simplifications, such as disregarding the groundwater flow, lead to overly confident predictions, that is, predictions that are both less accurate and uncertain than those of the more complex model. We find that for the same number of uncertain parameters, increasing the model resolution reduces uncertainty in the model predictions (and increases the MC method's computational cost). We employ the multilevel MC method to reduce the cost of estimating uncertainty in a high‐resolution ICPR model. Finally, we use the ensemble estimates of the mean and covariance of the flood depth for real‐time flood depth forecasting using the physics‐informed Gaussian process regression method. We show that even with few measurements, the proposed framework results in a more accurate forecast than that provided by the mean prediction of the ICPR model.

Kohanpur, Amir H.↗

DOE OSTI2021

A General Framework to Learn Tertiary Structure for Protein Sequence Characterization

During the past five years, deep-learning algorithms have enabled ground-breaking progress towards the prediction of tertiary structure from a protein sequence. Very recently, we developed SAdLSA, a new computational algorithm for protein sequence comparison via deep-learning of protein structural alignments. SAdLSA shows significant improvement over established sequence alignment methods. In this contribution, we show that SAdLSA provides a general machine-learning framework for structurally characterizing protein sequences. By aligning a protein sequence against itself, SAdLSA generates a fold distogram for the input sequence, including challenging cases whose structural folds were not present in the training set. About 70% of the predicted distograms are statistically significant. Although at present the accuracy of the intra-sequence distogram predicted by SAdLSA self-alignment is not as good as deep-learning algorithms specifically trained for distogram prediction, it is remarkable that the prediction of single protein structures is encoded by an algorithm that learns ensembles of pairwise structural comparisons, without being explicitly trained to recognize individual structural folds. As such, SAdLSA can not only predict protein folds for individual sequences, but also detects subtle, yet significant, structural relationships between multiple protein sequences using the same deep-learning neural network. The former reduces to a special case in this general framework for protein sequence annotation.

59 BASIC BIOLOGICAL SCIENCES↗

NASA NTRS2015

Improved Rainfall Estimates and Predictions for 21st Century Drought Early Warning

As temperatures increase, the onset and severity of droughts is likely to become more intense. Improved tools for understanding, monitoring and predicting droughts will be a key component of 21st century climate adaption. The best drought monitoring systems will bring together accurate precipitation estimates with skillful climate and weather forecasts. Such systems combine the predictive power inherent in the current land surface state with the predictive power inherent in low frequency ocean-atmosphere dynamics. To this end, researchers at the Climate Hazards Group (CHG), in collaboration with partners at the USGS and NASA, have developed i) a long (1981-present) quasi-global (50degS-50degN, 180degW-180degE) high resolution (0.05deg) homogenous precipitation data set designed specifically for drought monitoring, ii) tools for understanding and predicting East African boreal spring droughts, and iii) an integrated land surface modeling (LSM) system that combines rainfall observations and predictions to provide effective drought early warning. This talk briefly describes these three components. Component 1: CHIRPS The Climate Hazards group InfraRed Precipitation with Stations (CHIRPS), blends station data with geostationary satellite observations to provide global near real time daily, pentadal and monthly precipitation estimates. We describe the CHIRPS algorithm and compare CHIRPS and other estimates to validation data. The CHIRPS is shown to have high correlation, low systematic errors (bias) and low mean absolute errors. Component 2: Hybrid statistical-dynamic forecast strategies East African droughts have increased in frequency, but become more predictable as Indo- Pacific SST gradients and Walker circulation disruptions intensify. We describe hybrid statistical-dynamic forecast strategies that are far superior to the raw output of coupled forecast models. These forecasts can be translated into probabilities that can be used to generate bootstrapped ensembles describing future climate conditions. Component 3: Assimilation using LSMs CHIRPS rainfall observations (component 1) and bootstrapped forecast ensembles (component 2) can be combined using LSMs to predict soil moisture deficits. We evaluate the skill such a system in East Africa, and demonstrate results for 2013.

Funk, Chris↗

NASA NTRS2015

Improved Rainfall Estimates and Predictions for 21st Century Drought Early Warning

Funk, Chris↗

DOE OSTI2020

Ensembles of Networks Produced from Neural Architecture Search

Neural architecture search (NAS) is a popular topic at the intersection of deep learning and high performance computing. NAS focuses on optimizing the architecture of neural networks along with their hyperparameters in order to produce networks with superior performance. Much of the focus has been on how to produce a single best network to solve a machine learning problem, but as NAS methods produce many networks that work very well, this affords the opportunity to ensemble these networks to produce an improved result. Additionally, the diversity of network structures produced by NAS drives a natural bias towards diversity of predictions produced by the individual networks. This results in an improved ensemble over simply creating an ensemble that contains duplicates of the best network architecture retrained to have unique weights.

Herron, Emily↗

NASA NTRS1997

Interannual Fluctuations in Atmospheric Angular Momentum Simulated by the National Centers for Environmental Prediction Medium Range Forecast Model

An earlier study established the existence of globally coherent interannual fluctuations in atmospheric angular momentum (AAM), associated with the El Nino-Southern Oscillation (ENSO) cycle. In this paper, we pursue the origin and the structure of these fluctuations using an ensemble of experiments generated by the National Centers for Environmental Prediction, medium range forecast model version 9. In the control experiments, where the observed sea surface temperatures (SSTs) were used as the lower boundary conditions, the model captures the characteristic V-like structure in time-latitude plots of zonally averaged AAM, while experiments with climatological SSTs and those with either perpetual warm or cold ENSO conditions superimposed on the climatological SSTs failed to reproduce this structure. The numerical results indicate that these AAM structures are related to SST variations associated with transitions between different phases of the ENSO cycle and have both propagating and standing components. The largest zonal wind contribution from the levels studied (850, 500, and 200 hPa) is at 200 hPa, where the tropical convective outflow is the strongest. Composites of zonal wind and geopotential height show a clear relationship between the stages of the global AAM oscillation and the ENSO cycle. The strong similarity between the simulated and observed AAM series attests to the model's ability to realistically simulate the interannual response of the atmosphere to ENSO SST anomalies.

Mo, Kingtse C.↗

DOE OSTI2020

Data-driven Detection and Early Prediction of Thermoacoustic Instability in a Multi-nozzle Combustor

Thermoacoustic instability (TAI) is a critical issue in modern lean-burn gas-turbine combustors, which is induced by a strong coupling between the resonant combustor acoustics and fluctuations in the heat release rate. This instability may lead to high-amplitude pressure waves that generate undesirable noise levels as well as fatigue stresses in mechanical structures of the combustor. The intense pressure fluctuations due to TAI may also cause large flow perturbations and possibly flow reversal that may lead to flame oscillations, flame liftoff, and even flame blow-out. Hence, there is a strong need for exercising control actions in a timely fashion to mitigate the TAI phenomena. Anomaly detection is an essential prerequisite to the design of a good controller and such a detector must be able to reliably predict a forthcoming TAI. To detect and predict the onset of a TAI from an ensemble of pressure time series, this paper investigates three data-driven methods: Fast Fourier transform (FFT), symbolic time series analysis (STSA), and hidden Markov modeling (HMM). The main focus of the paper is to make a comparative evaluation of these three anomaly detection methods for classification of the current regime of operation into stable and unstable categories as well as for real-time identification of precursors to impending instabilities with short-length time series of measured variables (e.g., pressure oscillations). Finally, the results, generated on experimental data from a multi-nozzle combustor apparatus, have been compared to evaluate the performance of FFT, STSA, and HMM methods for TAI analysis.

42 ENGINEERING↗

DOE OSTI2020

A Clustering-based biased Monte Carlo Approach to Protein Titration Curve Prediction

We develop and implement a novel approach to computing the ensemble averages in systems characterized by pair-wise interactions between the entities. Methods involving full enumeration of the configuration space result in exponential complexity. Sampling methods such as Markov Chain Monte Carlo (MCMC) algorithms have been proposed to tackle the exponential complexity of these problems. In certain scenarios where significant energetic coupling exists between the entities, the accuracy of the such algorithms can be diminished. We propose a strategy to improve the accuracy of the MCMC runs by taking advantage of the cluster structure in the interaction energy matrix. We propose two different schemes for performing the biased MCMC runs on the partitioned systems and show that they are valid MCMC schemes. We then apply these algorithms to the problem of computing the protonation fractions and hence the titration curves of titratable protein residues that constitute a given protein. We leverage both synthesized and real-world systems and show the improved performance of our biased MCMC methods when compared to the regular MCMC method.

Visweswara Sathanur, Arun↗

DOE OSTI2026

Ensemble Kalman filter for data assimilation coupled with low-resolution computations techniques applied in fluid dynamics

This paper presents an innovative Reduced-order model (ROM) for merging experimental and simulation data using data assimilation (DA) to estimate the "True" state of a fluid dynamics system, leading to more accurate predictions. Our methodology introduces a novel approach by implementing the ensemble Kalman filter (EnKF) within a reduced-dimensional framework, grounded in a robust theoretical foundation and applied to fluid dynamics. To address the substantial computational demands of DA, the proposed ROM employs low-resolution (LR) techniques to drastically reduce computational costs. This innovative approach involves downsampling datasets for DA computations, followed by an advanced reconstruction technique based on low-cost singular value decomposition (lcSVD). The lcSVD method, a key innovation in this paper, has never been applied to DA before and offers a highly efficient way to enhance resolution with minimal computational resources. Our results demonstrate significant reductions in both computation time and RAM usage through these LR techniques without compromising the accuracy of the estimations. For instance, in a turbulent test case, for a data compression rate of 15.9, the LR approach can achieve a speed-up of 13.7 and a RAM compression of 90.9% while maintaining a low relative root mean square error (RRMSE) of 2.6%, compared to 0.8% in the high-resolution (HR) reference. Furthermore, we highlight the effectiveness of the EnKF in estimating and predicting the state of fluid flow systems based on limited observations and given low-fidelity numerical data. This paper highlights the potential of the proposed DA method in fluid dynamics applications, particularly for improving computational efficiency in CFD and related fields. Its ability to balance accuracy with low computational and memory costs makes it especially suitable for large-scale and real-time applications, such as environmental monitoring or engineering design. This method will be incorporated into ModelFLOWs-app.

Data Assimilation↗

DOE OSTI2025

Uncertainty quantification for neural network potential foundation models

Abstract For neural network potentials (NNPs) to gain widespread use, researchers must be able to trust model outputs. However, the blackbox nature of neural networks and their inherent stochasticity are often deterrents, especially for foundation models trained over broad swaths of chemical space. Uncertainty information provided at the time of prediction can help reduce aversion to NNPs. In this work, we detail two uncertainty quantification (UQ) methods. Readout ensembling, by finetuning the readout layers of an ensemble of foundation models, provides information about model uncertainty, while quantile regression, by replacing point predictions with distributional predictions, provides information about uncertainty within the underlying training data. We demonstrate our approach with the MACE-MP-0 model, applying UQ to the foundation model and a series of finetuned models. The uncertainties produced by the readout ensemble and quantile methods are demonstrated to be distinct measures by which the quality of the NNP output can be judged.

36 MATERIALS SCIENCE↗