Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Model Inference”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

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

At least 1,315 records · Page 73
All sourcesNASA NTRSDOE OSTI
NASA NTRS2016

Nitrogen Dioxide Observations from the Geostationary Trace Gas and Aerosol Sensor Optimization (GeoTaso) Airborne Instrument: Retrieval Algorithm and Measurements During DISCOVER-AQ Texas 2013

The Geostationary Trace gas and Aerosol Sensor Optimization (GeoTASO) airborne instrument is a test bed for upcoming air quality satellite instruments that will measure backscattered ultraviolet, visible and near-infrared light from geostationary orbit. GeoTASO flew on the NASA Falcon aircraft in its first intensive field measurement campaign during the Deriving Information on Surface Conditions from Column and Vertically Resolved Observations Relevant to Air Quality (DISCOVER-AQ) Earth Venture Mission over Houston, Texas, in September 2013. Measurements of backscattered solar radiation between 420 and 465 nm collected on 4 days during the campaign are used to determine slant column amounts of NO2 at 250 m x 250 m spatial resolution with a fitting precision of 2.2 x 10(exp 15) molecules/sq cm. These slant columns are converted to tropospheric NO2 vertical columns using a radiative transfer model and trace gas profiles from the Community Multiscale Air Quality (CMAQ) model. Total column NO2 from GeoTASO is well correlated with ground-based Pandora observations (r = 0.90 on the most polluted and cloud-free day of measurements and r = 0.74 overall), with GeoTASO NO2 slightly higher for the most polluted observations. Surface NO2 mixing ratios inferred from GeoTASO using the CMAQ model show good correlation with NO2 measured in situ at the surface during the campaign (r = 0.85). NO2 slant columns from GeoTASO also agree well with preliminary retrievals from the GEO-CAPE Airborne Simulator (GCAS) which flew on the NASA King Air B200 (r = 0.81, slope = 0.91). Enhanced NO2 is resolvable over areas of traffic NOx emissions and near individual petrochemical facilities.

Aerosol Sensor Optimization↗
DOE OSTI2020

Evidence for quark-matter cores in massive neutron stars

The theory governing the strong nuclear force—quantum chromodynamics—predicts that at sufficiently high energy densities, hadronic nuclear matter undergoes a deconfinement transition to a new phase of quarks and gluons. Although this has been observed in ultrarelativistic heavy-ion collisions, it is currently an open question whether quark matter exists inside neutron stars. By combining astrophysical observations and theoretical ab initio calculations in a model-independent way, we find that the inferred properties of matter in the cores of neutron stars with mass corresponding to 1.4 solar masses (M ⊙ ) are compatible with nuclear model calculations. However, the matter in the interior of maximally massive stable neutron stars exhibits characteristics of the deconfined phase, which we interpret as evidence for the presence of quark-matter cores. For the heaviest reliably observed neutron stars with mass M ≈ 2M ⊙ , the presence of quark matter is found to be linked to the behaviour of the speed of sound cs in strongly interacting matter. If the conformal bound ${c}_{\rm{s}}^{2}\le 1/3$ is not strongly violated, massive neutron stars are predicted to have sizable quark-matter cores. This finding has important implications for the phenomenology of neutron stars and affects the dynamics of neutron star mergers with at least one sufficiently massive participant.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
NASA NTRS1999

Properties of QBO and SAO Generated by Gravity Waves

We present an extension for the 2D (zonal mean) version of our Numerical Spectral Mode (NSM) that incorporates Hines' Doppler spread parameterization (DSP) for small scale gravity waves (GW). This model is applied to describe the seasonal variations and the semi-annual and quasi-biennial oscillations (SAO and QBO). Our earlier model reproduced the salient features of the mean zonal circulation in the middle atmosphere, including the QBO extension into the upper mesosphere inferred from UARS measurements. In the present model we incorporate also tropospheric heating to reproduce the upwelling at equatorial latitudes associated with the Brewer-Dobson circulation that affects significantly the dynamics of the stratosphere as Dunkerton had pointed out. Upward vertical winds increase the period of the QBO observed from the ground. To compensate for that, one needs to increase the eddy diffusivity and the GW momentum flux, bringing the latter closer to values recommended in the DSP. The QBO period in the model is 30 months (mo), which is conducive to synchronize this oscillation with the seasonal cycle of solar forcing. Multi-year interannual oscillations are generated through wave filtering by the solar driven annual oscillation in the zonal circulation. Quadratic non-linearities generate interseasonal variations to produce a complicated pattern of variability associated with the QBO. The computed temperature amplitudes for the SAO and QBO are in substantial agreement with observations at equatorial and extratropical latitudes. At high latitudes, however, the observed QBO amplitudes are significantly larger, which may be a signature of propagating planetary waves not included in the present model. The assumption of hydrostatic equilibrium not being imposed, we find that the effects from the vertical Coriolis force associated with the equatorial oscillations are large for the vertical winds and significant for the temperature variations even outside the tropics but are relatively small for the zonal winds.

Mayr, H. G.↗
NASA NTRS2020

Dynamic Medical Risk Assessment Supported by Inference Networks

The Human Research Program's next generation risk model, the Medical Extensible Dynamic Probabilistic Risk Assessment Tool (MEDPRAT), provides researchers with estimates of astronaut medical and health risk. MEDPRATs Susceptibility Inference Network (SIN) facilitates the dynamic component of this tool. The SIN provides MEDPRAT with a "memory" that allows the system to use knowledge of what simulation events have occurred to alter the representative probability that future simulation events will occur during a given trial. The SIN allows for the medical events being simulated to be related to, and influence the likelihood of one another, providing a more robust risk estimate. We present initial work of our efforts to mathematically quantify and represent these dependent relationships between medical events.

McIntyre, L.↗
DOE OSTI2025

A Parameter-masked Mock Data Challenge for Beyond-two-point Galaxy Clustering Statistics

The past few years have seen the emergence of a wide array of novel techniques for analyzing high-precision data from upcoming galaxy surveys, which aim to extend the statistical analysis of galaxy clustering data beyond the linear regime and the canonical two-point (2pt) statistics. We test and benchmark some of these new techniques in a community data challenge named “Beyond-2pt,” initiated during the Aspen 2022 Summer Program “Large-Scale Structure Cosmology beyond 2-Point Statistics,” whose first round of results we present here. The challenge data set consists of high-precision mock galaxy catalogs for clustering in real space, in redshift space, and on a light cone. Participants in the challenge have developed end-to-end pipelines to analyze mock catalogs and extract unknown (“masked”) cosmological parameters of the underlying ΛCDM models with their methods. The methods represented are density-split clustering, nearest neighbor statistics, BACCO power spectrum emulator, void statistics, LEFTfield field-level inference using effective field theory (EFT), and joint power spectrum and bispectrum analyses using both EFT and simulation-based inference. In this work, we review the results of the challenge, focusing on problems solved, lessons learned, and future research needed to perfect the emerging beyond-2pt approaches. The unbiased parameter recovery demonstrated in this challenge by multiple statistics and the associated modeling and inference frameworks supports the credibility of cosmology constraints from these methods. The challenge data set is publicly available, and we welcome future submissions from methods that are not yet represented.

Krause, Elisabeth [Univ. of Arizona, Tucson, AZ (U↗
DOE OSTI2020

In-Situ Inference: Bringing Advanced Data Science Into Exascale Simulations

As simulations generate ever-increasing amounts of data, there are correspondingly richer opportunities for analysis and scientific discovery - discoveries that will be missed if most of the data must be discarded before it is analyzed. Because future exascale architectures will be increasingly storage-limited, it will not be possible to save the vast majority of simulation data for later analysis, requiring analysis to occur “in-situ” within the simulation. However, existing in-situ data analysis frameworks provide little or no support for one of the most sophisticated forms of data science: probabilistic statistical modeling or uncertainty quantification (UQ), and the accompanying challenge of inference - fitting those statistical models to massive simulation output. Our goal is to develop the fundamental statistical algorithms and computer science needed to perform statistical inference in-situ (in HPC simulations) to the full stream of data those simulations generate.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

SPT-3G D1: A Measurement of Secondary Cosmic Microwave Background Anisotropy Power

We report new measurements of millimeter-wave temperature power spectra in the angular multipole range $1700 \le \ell \le 11,000$ (wavelengths $13^\prime \gtrsim λ\gtrsim 2^\prime$). We use two years of data in three observing bands centered near 95, 150, and 220 GHz from the SPT-3G receiver on the South Pole Telescope that cover a 1646 deg$^2$ region of the Southern sky. Using the measured power spectra, we present constraints on the thermal and kinematic Sunyaev-Zel'dovich (SZ) effects, radio galaxies, and cosmic infrared background (CIB). We find that inferred SZ powers are dependent on the detailed modeling of the thermal SZ-CIB correlation, and to a lesser extent on the assumed angular dependence of the SZ spectra. We report constraints for simulation-based model templates as well as fits where the angular dependencies of the SZ and CIB power spectra are allowed to vary. In the latter case at $\ell=3000$, we find thermal SZ power at 143 GHz of $D_{3000}^{\rm tSZ} = 4.91\pm0.37\, μ{\rm K}^2$ and kinematic SZ power of $D_{3000}^{\rm kSZ} =1.75\pm0.86\, μ{\rm K}^2$. We use the measured kinematic SZ power to estimate the duration of reionization, noting that the reionization inferences are sensitive to the model choices and assumed level of homogeneous kinematic SZ power from the late-time universe. We find a 95% limit on the duration from an ionization fraction of 25% to 75% of $Δ^{50} z_{\rm re} <\,3.8$ based on a semi-analytic model, or a limit on the duration from an ionization fraction of 5% to 95% of $Δ^{90} z_{\rm re} <\,6.1$ based on the AMBER simulations.

Chaubal, P. [Melbourne U.]↗
DOE OSTI2025

Bayesian Inference for the Seismic Moment Tensor Using Regional Waveforms and Teleseismic- P Polarities with a Data-Derived Distribution of Velocity Models and Source Locations

The largest source of uncertainty in any source inversion is the velocity model used in the transfer function that relates observed ground motion to the seismic moment tensor. However, standard inverse procedure often does not quantify uncertainty in the seismic moment tensor due to error in the Green’s functions from uncertain event location and Earth structure. Here, we incorporate this uncertainty into an estimation of the seismic moment tensor using a data-derived distribution of velocity models based on complementary geophysical data sets, including thickness constraints, velocity profiles, gravity data, surface-wave group velocities, and regional body-wave travel times. The data-derived distribution of velocity models is then used as a prior distribution of Green’s functions for use in Bayesian inference of an unknown seismic moment tensor using regional and teleseismic-P waveforms. The use of multiple data sets is important for gaining resolution to different components of the moment tensor. The combined likelihood is estimated using data-specific error models and the posterior of the seismic moment tensor is estimated and interpreted in terms of the most probable source type.

58 GEOSCIENCES↗
DOE OSTI2022

Privacy policy robustness to reverse engineering

Differential privacy policies allow one to preserve data privacy while sharing and analyzing data. However, these policies are susceptible to an array of attacks. In particular, often a portion of the data desired to be privacy protected is exposed online. Access to these pre-privacy protected data samples can then be used to reverse engineer the privacy policy. With knowledge of the generating privacy policy, an attacker can use machine learning to approximate the full set of originating data. Bayesian inference is one method for reverse engineering both model and model parameters. We present a methodology for evaluating and ranking privacy policy robustness to Bayesian inference-based reverse engineering, and demonstrated this method across data with a variety of temporal trends.

Kusne, Aaron Gilad↗
DOE OSTI2024

Soil incubation methods lead to large differences in inferred methane production temperature sensitivity

Abstract Quantifying the temperature sensitivity of methane (CH 4 ) production is crucial for predicting how wetland ecosystems will respond to climate warming. Typically, the temperature sensitivity (often quantified as a Q 10 value) is derived from laboratory incubation studies and then used in biogeochemical models. However, studies report wide variation in incubation-inferred Q 10 values, with a large portion of this variation remaining unexplained. Here we applied observations in a thawing permafrost peatland (Stordalen Mire) and a well-tested process-rich model ( ecosys ) to interpret incubation observations and investigate controls on inferred CH 4 production temperature sensitivity. We developed a field-storage-incubation modeling approach to mimic the full incubation sequence, including field sampling at a particular time in the growing season, refrigerated storage, and laboratory incubation, followed by model evaluation. We found that CH 4 production rates during incubation are regulated by substrate availability and active microbial biomass of key microbial functional groups, which are affected by soil storage duration and temperature. Seasonal variation in substrate availability and active microbial biomass of key microbial functional groups led to strong time-of-sampling impacts on CH 4 production. CH 4 production is higher with less perturbation post-sampling, i.e. shorter storage duration and lower storage temperature. We found a wide range of inferred Q 10 values (1.2–3.5), which we attribute to incubation temperatures, incubation duration, storage duration, and sampling time. We also show that Q 10 values of CH 4 production are controlled by interacting biological, biochemical, and physical processes, which cause the inferred Q 10 values to differ substantially from those of the component processes. Terrestrial ecosystem models that use a constant Q 10 value to represent temperature responses may therefore predict biased soil carbon cycling under future climate scenarios.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

Model-based, in-situ, non-destructive qualification and certification of parts made by autonomous additive manufacturing

To address the significant productivity challenges associated with the qualification and certification (Q&C) tasks of additively manufactured (AM) parts, which have traditionally relied on rigorous post‐build inspection and testing, we propose an integrated framework that combines model‐based qualification and certification (MBQ&C) with autonomous additive manufacturing (AAM). MBQ&C employs high‐fidelity predictive models, developed within the Integrated Computational Materials Engineering (ICME) paradigm, to simulate process–structure–property–performance relationships for assessing a part’s fitness for use. Since predictive models are commonly machine learning (ML)-based or reduced-order surrogates of validated physics models, they run efficiently, enabling timely inference. In parallel, the self-driving AAM utilises ML-based adaptive, closed‐loop control strategies to avoid, mitigate, or repair defects and anomalies during fabrication, thereby increasing the likelihood of producing acceptable parts. A key feature of the combined AAM-MBQ&C framework is that predictive models explicitly incorporate defects or anomalies that persist after the build, using instance-specific data captured via in-situ sensing. This customisation enables a build‐specific assessment of fitness for use, rather than relying on nominal or generic parameters. Such individualised evaluation provides a robust basis for Q&C-related acceptance decisions relating to each build. Additionally, the rapid solution capabilities of ML or reduced-order models enable the determination of a part’s suitability for service shortly after build completion. As the framework matures, it has the potential to substantially reduce reliance on conventional point‐design approaches—such as time‐consuming post‐build computed tomography scanning and costly destructive testing. Thus, the AAM-MBQ&C framework represents a transformative, scalable strategy for quality assurance of AM components, as parts produced within a stable, validated, and certified envelope can be certified with reduced testing. Key benefits include: (1) significant gains in Q&C productivity through efficient, model-centric assessment; (2) performance-based classification of defects into critical and non-critical categories; (3) the ability to predict potential deviations in the performance of parts affected by real-time, adaptive process control interventions relative to those produced under a certified process, and (4) the enabling of virtual Q&C for service environments that are difficult, hazardous, or impractical to access or reproduce experimentally. Collectively, these capabilities strengthen the business case for AM, particularly for high‐consequence and mission‐critical applications. Finally, although this work focuses on powder-based AM, the proposed techniques could be extended to AM processes employing alternative feedstock forms.

Gunasegaram, Dayalan↗
DOE OSTI2022

Multifidelity Ensemble Kalman Filtering Using Surrogate Models Defined by Theory-Guided Autoencoders

Data assimilation is a Bayesian inference process that obtains an enhanced understanding of a physical system of interest by fusing information from an inexact physics-based model, and from noisy sparse observations of reality. The multifidelity ensemble Kalman filter (MFEnKF) recently developed by the authors combines a full-order physical model and a hierarchy of reduced order surrogate models in order to increase the computational efficiency of data assimilation. The standard MFEnKF uses linear couplings between models, and is statistically optimal in case of Gaussian probability densities. This work extends the MFEnKF into to make use of a broader class of surrogate model such as those based on machine learning methods such as autoencoders non-linear couplings in between the model hierarchies. We identify the right-invertibility property for autoencoders as being a key predictor of success in the forecasting power of autoencoder-based reduced order models. We propose a methodology that allows us to construct reduced order surrogate models that are more accurate than the ones obtained via conventional linear methods. Numerical experiments with the canonical Lorenz'96 model illustrate that nonlinear surrogates perform better than linear projection-based ones in the context of multifidelity ensemble Kalman filtering. We additionality show a large-scale proof-of-concept result with the quasi-geostrophic equations, showing the competitiveness of the method with a traditional reduced order model-based MFEnKF.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2011

Large Eddy Simulation Study for Fluid Disintegration and Mixing

A new modeling approach is based on the concept of large eddy simulation (LES) within which the large scales are computed and the small scales are modeled. The new approach is expected to retain the fidelity of the physics while also being computationally efficient. Typically, only models for the small-scale fluxes of momentum, species, and enthalpy are used to reintroduce in the simulation the physics lost because the computation only resolves the large scales. These models are called subgrid (SGS) models because they operate at a scale smaller than the LES grid. In a previous study of thermodynamically supercritical fluid disintegration and mixing, additional small-scale terms, one in the momentum and one in the energy conservation equations, were identified as requiring modeling. These additional terms were due to the tight coupling between dynamics and real-gas thermodynamics. It was inferred that if these terms would not be modeled, the high density-gradient magnitude regions, experimentally identified as a characteristic feature of these flows, would not be accurately predicted without the additional term in the momentum equation; these high density-gradient magnitude regions were experimentally shown to redistribute turbulence in the flow. And it was also inferred that without the additional term in the energy equation, the heat flux magnitude could not be accurately predicted; the heat flux to the wall of combustion devices is a crucial quantity that determined necessary wall material properties. The present work involves situations where only the term in the momentum equation is important. Without this additional term in the momentum equation, neither the SGS-flux constant-coefficient Smagorinsky model nor the SGS-flux constant-coefficient Gradient model could reproduce in LES the pressure field or the high density-gradient magnitude regions; the SGS-flux constant- coefficient Scale-Similarity model was the most successful in this endeavor although not totally satisfactory. With a model for the additional term in the momentum equation, the predictions of the constant-coefficient Smagorinsky and constant-coefficient Scale-Similarity models were improved to a certain extent; however, most of the improvement was obtained for the Gradient model. The previously derived model and a newly developed model for the additional term in the momentum equation were both tested, with the new model proving even more successful than the previous model at reproducing the high density-gradient magnitude regions. Several dynamic SGS-flux models, in which the SGS-flux model coefficient is computed as part of the simulation, were tested in conjunction with the new model for this additional term in the momentum equation. The most successful dynamic model was a "mixed" model combining the Smagorinsky and Gradient models. This work is directly applicable to simulations of gas turbine engines (aeronautics) and rocket engines (astronautics).

Bellan, Josette↗
NASA NTRS2005

Bayesian Inference in Satellite Gravity Inversion

To solve a geophysical inverse problem means applying measurements to determine the parameters of the selected model. The inverse problem is formulated as the Bayesian inference. The Gaussian probability density functions are applied in the Bayes's equation. The CHAMP satellite gravity data are determined at the altitude of 400 kilometer altitude over the South part of the Pannonian basin. The model of interpretation is the right vertical cylinder. The parameters of the model are obtained from the minimum problem solved by the Simplex method.

Kis, K. I.↗
DOE OSTI2016

SICK: THE SPECTROSCOPIC INFERENCE CRANK

There exists an inordinate amount of spectral data in both public and private astronomical archives that remain severely under-utilized. The lack of reliable open-source tools for analyzing large volumes of spectra contributes to this situation, which is poised to worsen as large surveys successively release orders of magnitude more spectra. In this article I introduce sick, the spectroscopic inference crank, a flexible and fast Bayesian tool for inferring astrophysical parameters from spectra. sick is agnostic to the wavelength coverage, resolving power, or general data format, allowing any user to easily construct a generative model for their data, regardless of its source. sick can be used to provide a nearest-neighbor estimate of model parameters, a numerically optimized point estimate, or full Markov Chain Monte Carlo sampling of the posterior probability distributions. This generality empowers any astronomer to capitalize on the plethora of published synthetic and observed spectra, and make precise inferences for a host of astrophysical (and nuisance) quantities. Model intensities can be reliably approximated from existing grids of synthetic or observed spectra using linear multi-dimensional interpolation, or a Cannon-based model. Additional phenomena that transform the data (e.g., redshift, rotational broadening, continuum, spectral resolution) are incorporated as free parameters and can be marginalized away. Outlier pixels (e.g., cosmic rays or poorly modeled regimes) can be treated with a Gaussian mixture model, and a noise model is included to account for systematically underestimated variance. Combining these phenomena into a scalar-justified, quantitative model permits precise inferences with credible uncertainties on noisy data. I describe the common model features, the implementation details, and the default behavior, which is balanced to be suitable for most astronomical applications. Using a forward model on low-resolution, high signal-to-noise ratio spectra of M67 stars reveals atomic diffusion processes on the order of 0.05 dex, previously only measurable with differential analysis techniques in high-resolution spectra. sick is easy to use, well-tested, and freely available online through GitHub under the MIT license.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

A Differentiable Hydrology Approach for Modeling With Time-Varying Parameters

In the analysis of observational data with mathematical models, it is often desirable to let one or more model parameters vary with time to account for changing environmental conditions or to offer more flexibility. A standard approach for dynamic models is to allow for the number of parameters to grow as a function of time, leading to a high-dimensional inference problem for long data records. We propose using Hamiltonian Monte Carlo, a gradient-based Markov chain Monte Carlo (MCMC) method, to perform Bayesian inference for time-varying parameters (TVP) in hydrology models. As derivatives of model error functions with regard to parameters are not available in closed form, we implemented the GR4J rainfall-runoff models in Theano/PyMC3, and Jax/NumPyro, allowing for the application of automatic differentiation techniques. A simulation experiment assessing the viability of these methods for recovering underlying temporal variation in parameters indicates that a discrete Gaussian random walk-based prior appears to be best suited across a range of scenarios while the continuous-time Gaussian process compares relatively poorly. In an analysis of 20 years of daily real-world streamflow records from the Model Parameter Estimation Experiment (MOPEX) hydrology data set with increasing data sparsity and at multiple temporal resolutions, we find that TVP inference with gradient-based MCMC is a flexible and reliable approach for analyzing hydrology models with dynamic parameter sets.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Turbulence model reduction by deep learning

A defining problem of turbulence theory is to produce a predictive model for turbulent fluxes. These have profound implications for virtually all aspects of the turbulence dynamics. In magnetic confinement devices, drift-wave turbulence produces anomalous fluxes via cross-correlations between fluctuations. In this work, we introduce an alternative, data-driven method for parametrizing these fluxes. The method uses deep supervised learning to infer a reduced mean-field model from a set of numerical simulations. We apply the method to a simple drift-wave turbulence system and find a significant new effect which couples the particle flux to the local gradient of vorticity. Notably, here, this effect is much stronger than the oft-invoked shear suppression effect. We also recover the result via a simple calculation. The vorticity gradient effect tends to modulate the density profile. In addition, our method recovers a model for spontaneous zonal flow generation by negative viscosity, stabilized by nonlinear and hyperviscous terms. We highlight the important role of symmetry to implementation of the new method.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2021

Anomaly Attribution with Likelihood Compensation

This paper addresses the task of explaining anomalous predictions of a black-box regression model. When using a black-box model, such as one to predict building energy consumption from many sensor measurements, we often have a situation where some observed samples may significantly deviate from their prediction. It may be due to a sub-optimal black-box model, or simply because those samples are outliers. In either case, one would ideally want to compute a responsibility score indicative of the extent to which an input variable is responsible for the anomalous output. In this work, we formalize this task as a statistical inverse problem: Given model deviation from the expected value, infer the responsibility score of each of the input variables. We propose a new method called likelihood compensation (LC), which is founded on the likelihood principle and computes a correction to each input variable. To the best of our knowledge, this is the first principled framework that computes a responsibility score for real valued anomalous model deviations. We apply our approach to a real-world building energy prediction task and confirm its utility based on expert feedback.

Idé, Tsuyoshi↗