Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “network performance evaluation”

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 1,081 records · Page 60
All sourcesNASA NTRSDOE OSTI
NASA NTRS2011

Metrics for Operator Situation Awareness, Workload, and Performance in Automated Separation Assurance Systems

A research consortium of scientists and engineers from California State University Long Beach (CSULB), San Jose State University Foundation (SJSUF), California State University Northridge (CSUN), Purdue University, and The Boeing Company was assembled to evaluate the impact of changes in roles and responsibilities and new automated technologies, being introduced in the Next Generation Air Transportation System (NextGen), on operator situation awareness (SA) and workload. To meet these goals, consortium members performed systems analyses of NextGen concepts and airspace scenarios, and concurrently evaluated SA, workload, and performance measures to assess their appropriateness for evaluations of NextGen concepts and tools. The following activities and accomplishments were supported by the NRA: a distributed simulation, metric development, systems analysis, part-task simulations, and large-scale simulations. As a result of this NRA, we have gained a greater understanding of situation awareness and its measurement, and have shared our knowledge with the scientific community. This network provides a mechanism for consortium members, colleagues, and students to pursue research on other topics in air traffic management and aviation, thus enabling them to make greater contributions to the field

Strybel, Thomas Z.↗
NASA NTRS1981

Data base management system analysis and performance testing with respect to NASA requirements

Several candidate Data Base Management Systems (DBM's) that could support the NASA End-to-End Data System's Integrated Data Base Management System (IDBMS) Project, later rescoped and renamed the Packet Management System (PMS) were evaluated. The candidate DBMS systems which had to run on the Digital Equipment Corporation VAX 11/780 computer system were ORACLE, SEED and RIM. Oracle and RIM are both based on the relational data base model while SEED employs a CODASYL network approach. A single data base application which managed stratospheric temperature profiles was studied. The primary reasons for using this application were an insufficient volume of available PMS-like data, a mandate to use actual rather than simulated data, and the abundance of available temperature profile data.

Martin, E. A.↗
DOE OSTI2021

Potential energy surfaces for high-energy N + O 2 collisions

Potential energy surfaces for high-energy collisions between an oxygen molecule and a nitrogen atom are useful for modeling chemical dynamics in shock waves. In the present work, we present doublet, quartet, and sextet potential energy surfaces that are suitable for studying collisions of O 2 ( 3 Σ$^{–}_{g}$) with N( 4 S) in the electronically adiabatic approximation. Two sets of surfaces are developed, one using neural networks (NNs) with permutationally invariant polynomials (PIPs) and one with the least-squares many-body (MB) method, where a two-body part is an accurate diatomic potential and the three-body part is expressed with connected PIPs in mixed-exponential-Gaussian bond order variables (MEGs). We find, using the same dataset for both fits, that the fitting performance of the PIP-NN method is significantly better than that of the MB-PIP-MEG method, even though the MB-PIP-MEG fit uses a higher-order PIP than those used in previous MB-PIP-MEG fits of related systems (such as N 4 and N 2 O 2 ). However, the evaluation of the PIP-NN fit in trajectory calculations requires about 5 times more computer time than is required for the MB-PIP-MEG fit.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Fast and accurate reduced-order modeling of a MOOSE-based additive manufacturing model with operator learning

One predominant challenge in additive manufacturing (AM) is to achieve specific material properties by manipulating manufacturing process parameters during the runtime. Such manipulation tends to increase the computational load imposed on existing simulation tools employed in AM. The goal of the present work is to construct a fast and accurate reduced-order model (ROM) for an AM model developed within the Multiphysics Object-Oriented Simulation Environment (MOOSE) framework, ultimately reducing the time/cost of AM control and optimization processes. Our adoption of the operator learning (OL) approach enabled us to learn a family of differential equations produced by altering process variables in the laser’s Gaussian point heat source. More specifically, we used the Fourier neural operator (FNO) and deep operator network (DeepONet) to develop ROMs for time-dependent responses. Furthermore, we benchmarked the performance of these OL methods against a conventional deep neural network (DNN)-based ROM. Ultimately, we found that OL methods offer comparable performance and, in terms of accuracy and generalizability, even outperform DNN at predicting scalar model responses. The DNN-based ROM afforded the fastest training time. Furthermore, all the ROMs were faster than the original MOOSE model yet still provided accurate predictions. FNO had a smaller mean prediction error than DeepONet, with a larger variance for time-dependent responses. Unlike DNN, both FNO and DeepONet were able to simulate time series data without the need for dimensionality reduction techniques. Finally, the present work can help facilitate the AM optimization process by enabling faster execution of simulation tools while still preserving evaluation accuracy.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Enhanced Electrochemical Performance of Disordered Rocksalt Cathodes Enabled by a Graphite Conductive Additive

Cobalt-free cation-disordered rocksalt (DRX) cathodes are a promising class of materials for next-generation Li-ion batteries. Although they have high theoretical specific capacities (>300 mA h/g) and moderate operating voltages (~3.5 V vs Li/Li + ), DRX cathodes typically require a high carbon content (up to 30 wt %) to fully utilize the active material which has a detrimental impact on cell-level energy density. To assess pathways to reduce the electrode’s carbon content, the present study investigates how the carbon’s microstructure and loading (10–20 wt %) influence the performance of DRX cathodes with the nominal composition Li 1.2 Mn 0.5 Ti 0.3 O 1.9 F 0.1 . While electrodes prepared with conventional disordered carbon additives (C65 and ketjenblack) exhibit rapid capacity fade due to an unstable cathode/electrolyte interface, DRX cathodes containing 10 wt % graphite show superior cycling performance (e.g., reversible capacities ~260 mA h/g with 85% capacity retention after 50 cycles) and rate capability (~135 mA h/g at 1000 mA/g). Furthermore, a suite of characterization tools was employed to evaluate the performance differences among these composite electrodes. Overall, these results indicate that the superior performance of the graphite-based cathodes is largely attributed to the: (i) formation of a uniform graphitic coating on DRX particles which protects the surface from parasitic reactions at high states of charge and (ii) homogeneous dispersion of the active material and carbon throughout the composite cathode which provides a robust electronically conductive network that can withstand repeated charge–discharge cycles. Overall, this study provides key scientific insights on how the carbon microstructure and electrode processing influence the performance of DRX cathodes. Based on these results, exploration of alternative routes to apply graphitic coatings is recommended to further optimize the material performance.

25 ENERGY STORAGE↗
NASA NTRSDate not supplied

A Novel Machine Learning Method for Surface PM2.5 Estimations from Geostationary Satellites

Particulate matter (PM) with a diameter of less or equal to 2.5 μm, known as PM , affects human health as it penetrates the respiratory system. The Environmental Protection Agency (EPA) measures the atmospheric concentration of PM using air quality monitors stationed throughout the Continental United States (CONUS). Such measurements are points on a spatial domain and therefore, might not be representative of the air quality at nearby areas considering that the composition of the atmosphere is highly variable from place to place. Satellite based AOD permits a spatially uniform means of estimating PM and new geostationary satellites provide high temporal and spatial resolution estimation of AOD. However, the concentration of PM is non-linearly dependent on other atmospheric parameters that include relative humidity, temperature, and height of the planetary boundary layer. This information may be estimated at similar spatial and temporal resolutions as AOD from numerical modeling such as from the National Oceanic and Atmospheric Administration’s (NOAA) High Resolution Rapid Refresh (HRRR) model which resolves near real-time atmospheric conditions over the CONUS. The estimation of PM concentration is a multi-parametric problem that considers the effect of temporal dependencies among the different parameters. Deep learning approaches are appropriate for such complex estimation problems as they intrinsically capture relations among multiple non-linear parameters. This study compares deep-learning methods to traditional regression analysis to demonstrate the capabilities of these methods in predicting PM2.5 concentrations. Additionally, a novel ensemble learning approach is employed to identify scientific processes that could further improve the estimation of PM concentration. Utilizing Long Short-Term Memory (LSTM) neural networks, which are suitable for multivariate time series estimation problems as they are capable of learning long-term dependencies, individual models are created for each EPA station and trained on the aforementioned dataset collocated over each station. Individual station models are merged if the model's performance is improved by reducing the root mean squared error (RMSE) metric. This ensemble training method ultimately reduces the RMSE value. Evaluation of these results provide insights into physical processes and related observable parameters that may contribute to PM concentrations. Identified parameters evaluated to be statistically different between the merged and unmerged models are expected to improve overall performance. These new parameters are then utilized for reevaluation of the deep learning methods with an extreme gradient boosting model with an RMSE of 5.5 providing the best results.

George Priftis↗
NASA NTRSDate not supplied

Lunar Node – 1: Initial Flight Results and the Role of Surface Psuedolites in Lunar Navigation

On February 22, 2024, the Intuitive Machines IM-1 NOVA-C lander, nick-named Odysseus, landed on the lunar surface, carrying with it a cadre of NASA scientific and technology demonstration payloads. These payloads and missions marked the first delivery of NASA instruments to operate from the lunar surface since the Apollo landings. One of these payloads is Lunar Node -1 (LN-1), a navigation beacon demonstration mission. The payload was designed and built by NASA’s Marshall Space Flight Center. The payload’s main goal was to demonstrate and provide insight into the use of lunar surface-based radio navigation aids. As part of the mission, LN-1 successfully conducted multiple one-way transmissions from the NOVA-C vehicle to Deep Space Network ground receivers using its onboard S-band transmitter, while being disciplined by an onboard Space Chip Scale Atomic Clock. LN-1 transmitted to DSN on an almost daily basis during transit to the moon, including two surface passes. The payload was originally plan to conduct 7-10 days of surface operation as an always-on beacon. These passes focused on evaluating two main navigation approaches: performance and stability of ranging using time-based transfer techniques on a cubesat size and grade platform, as well as one-way psuedonoise ranging approaches. To assess performance, the measurements were compared to independent navigation solutions using multiple approaches including: one-way Doppler tracking, two-way Doppler Tracking, and visual verification of the landing location provided by visual observations from orbital platforms. While the mission only conducted limited surface operations, the data provides some initial insight to performance form the lunar surface. These results are compared with initial ground-based testing as well as continued evaluation of the flight-space platform using multiple grades of oscillators for maintaining clock and frequency stability. These focus on the timing stability of platform in a deep-space environment as well variations in state determination. Given these insights, this paper provides additional description and evaluation of how this approach can be utilized as part of a broader lunar navigation architecture, such as being developed and deployed across multiple international space agencies. Analysis is provided to develop overall timing requirements and assessment of operational scenarios, such as orbit and surface location determination. In addition, the results support discussion as to how surface pseudolites could best be used within existing standard signal definitions, such as defined in the LunaNet Interoperability Specifications. This will consider concerns such as the near-/far- problem as well as operational considerations, including whether a beacon is better suited as two- or one-way ranging platform. The use cases are focused on how these psuedolites can provide additional coverage to augment and support planned operational coverage. For example, this analysis provides analysis of mid-latitude surface missions, where there may be limited geometry and availability of orbital relays. The results will show how these navigation psuedolites can fit within the developing architecture to provide additional robustness, capability, and support multiple use cases. Lastly, the paper will discuss challenges and next steps to be addressed in the implementation and testing of a follow-on payload and a continued path towards demonstration and integration of this capability into Lunar PNT architectures.

Evan Anzalone↗
NASA NTRSDate not supplied

Lunar Node – 1: Initial Flight Results and the Role of Surface Psuedolites in Lunar Navigation

On February 22, 2024, Intuitive Machines NOVA-C lander, nick-named Odysseus, landed on the lunar surface, carrying with it a cadre of NASA scientific and technology demonstration payloads. These payloads and missions marked the first delivery of NASA instruments to operate from the lunar surface since the Apollo landings. One of these payloads is Lunar Node -1 (LN-1), a navigation beacon demonstration mission. The payload was designed and built by NASA’s Marshall Space Flight Center. The payload’s main goal was to demonstrate and provide insight into the use of lunar surface-based radio navigation aids. As part of the mission, LN-1 successfully conducted multiple one-way transmissions from the NOVA-C vehicle to Deep Space Network ground receivers using its onboard S-band transmitter, while being disciplined by an onboard Space Chip Scale Atomic Clock. LN-1 transmitted to DSN on an almost daily basis during transit to the moon, including two surface passes. The payload was originally plan to conduct 7-10 days of surface operation as an always-on beacon. These passes focused on evaluating two main navigation approaches: performance and stability of ranging using time-based transfer techniques on a cubesat size and grade platform, as well as one-way psuedonoise ranging approaches. To assess performance, the measurements were compared to independent navigation solutions using multiple approaches including: one-way Doppler tracking, two-way Doppler Tracking, and visual verification of the landing location provided by visual observations from orbital platforms. While the mission only conducted limited surface operations, the data provides some initial insight to performance form the lunar surface. These results are compared with initial ground-based testing as well as continued evaluation of the flight-space platform using multiple grades of oscillators for maintaining clock and frequency stability. These focus on the timing stability of platform in a deep-space environment as well variations in state determination. Given these insights, this paper provides additional description and evaluation of how this approach can be utilized as part of a broader lunar navigation architecture, such as being developed and deployed across multiple international space agencies. Analysis is provided to develop overall timing requirements and assessment of operational scenarios, such as orbit and surface location determination. In addition, the results support discussion as to how surface pseudolites could best be used within existing standard signal definitions, such as defined in the LunaNet Interoperability Specifications. This will consider concerns such as the near-/far- problem as well as operational considerations, including whether a beacon is better suited as two- or one-way ranging platform. The use cases are focused on how these psuedolites can provide additional coverage to augment and support planned operational coverage. For example, this analysis provides analysis of mid-latitude surface missions, where there may be limited geometry and availability of orbital relays. The results will show how these navigation psuedolites can fit within the developing architecture to provide additional robustness, capability, and support multiple use cases. Lastly, the paper will discuss challenges and next steps to be addressed in the implementation and testing of a follow-on payload and a continued path towards demonstration and integration of this capability into Lunar PNT architectures.

Evan J Anzalone↗
DOE OSTI2021

Evaluation of AC optimal power flow on graphical processing units

This paper investigates the performance of alternating current optimal power flow (ACOPF) on hardware accelerators such as graphical processing units (GPUs). We describe the strategies employed and the software used to port the ACOPF application to GPU. Through reorganizing the flow of fundamental calculations, restructuring data organization for the GPUs, and using portability libraries, maximum utilization of GPU is attempted. We present details of our efforts with representative results on 200, 500, and 2000-bus networks.

Abhyankar, Shrirang G.↗
DOE OSTI2026

Benchmarking the performance of uncertainty quantification methods for neural network-based interatomic potentials

Machine-learned interatomic potentials (ML-IAPs) continue to gain popularity as accurate, computationally efficient replacements for traditional, physics-based interatomic potentials and expensive ab initio methods. Uncertainty quantification (UQ) of ML-IAPs is a growing area of research as UQ is critical in many applications of IAPs, such as developing curated datasets, active learning-based data augmentation, self-improving models, and estimating the uncertainty of molecular dynamics simulations. In this paper, we construct and benchmark a series of different neural network potentials (NNPs) with varying network architectures to determine the performance of these models with respect to both the mean and uncertainty calibration error. Each NNP method is specifically designed to predict either epistemic or aleatoric uncertainty with particular focus on the differences in behavior between the epistemic and aleatoric uncertainty estimates. We benchmark these methods using multiple datasets common in the ML-IAP literature. The results show that the aleatoric uncertainty from single-shot model architectures is a competitive alternative to ensemble-based epistemic uncertainty predictions in regions of sufficient data-density. However, in regions where the representative data is sparse, aleatoric uncertainty models tend to overpredict and epistemic methods tend to underpredict the actual model error. We conclude that the type of UQ is crucial when discussing performance of probabilistic model results as different methods have different performance characteristics depending on the regime in which they are evaluated. Therefore, the type of UQ method should be carefully evaluated against both the data characteristics and requirements for the intended application.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Report on the AAPM grand challenge on deep generative modeling for learning medical image statistics

Abstract Background The findings of the 2023 AAPM Grand Challenge on Deep Generative Modeling for Learning Medical Image Statistics are reported in this Special Report. Purpose The goal of this challenge was to promote the development of deep generative models for medical imaging and to emphasize the need for their domain‐relevant assessments via the analysis of relevant image statistics. Methods As part of this Grand Challenge, a common training dataset and an evaluation procedure was developed for benchmarking deep generative models for medical image synthesis. To create the training dataset, an established 3D virtual breast phantom was adapted. The resulting dataset comprised about 108 000 images of size 512 512. For the evaluation of submissions to the Challenge, an ensemble of 10 000 DGM‐generated images from each submission was employed. The evaluation procedure consisted of two stages. In the first stage, a preliminary check for memorization and image quality (via the Fréchet Inception Distance [FID]) was performed. Submissions that passed the first stage were then evaluated for the reproducibility of image statistics corresponding to several feature families including texture, morphology, image moments, fractal statistics, and skeleton statistics. A summary measure in this feature space was employed to rank the submissions. Additional analyses of submissions was performed to assess DGM performance specific to individual feature families, the four classes in the training data, and also to identify various artifacts. Results Fifty‐eight submissions from 12 unique users were received for this Challenge. Out of these 12 submissions, 9 submissions passed the first stage of evaluation and were eligible for ranking. The top‐ranked submission employed a conditional latent diffusion model, whereas the joint runners‐up employed a generative adversarial network, followed by another network for image superresolution. In general, we observed that the overall ranking of the top 9 submissions according to our evaluation method (i) did not match the FID‐based ranking, and (ii) differed with respect to individual feature families. Another important finding from our additional analyses was that different DGMs demonstrated similar kinds of artifacts. Conclusions This Grand Challenge highlighted the need for domain‐specific evaluation to further DGM design as well as deployment. It also demonstrated that the specification of a DGM may differ depending on its intended use.

Radiology, Nuclear Medicine & Medical Imaging↗
DOE OSTI2020

Adversarial super-resolution of climatological wind and solar data

Accurate and high-resolution data reflecting different climate scenarios are vital for policy makers when deciding on the development of future energy resources, electrical infrastructure, transportation networks, agriculture, and many other societally important systems. However, state-of-the-art long-term global climate simulations are unable to resolve the spatiotemporal characteristics necessary for resource assessment or operational planning. We introduce an adversarial deep learning approach to super resolve wind velocity and solar irradiance outputs from global climate models to scales sufficient for renewable energy resource assessment. Using adversarial training to improve the physical and perceptual performance of our networks, we demonstrate up to a 50 × resolution enhancement of wind and solar data. In validation studies, the inferred fields are robust to input noise, possess the correct small-scale properties of atmospheric turbulent flow and solar irradiance, and retain consistency at large scales with coarse data. An additional advantage of our fully convolutional architecture is that it allows for training on small domains and evaluation on arbitrarily-sized inputs, including global scale. We conclude with a super-resolution study of renewable energy resources based on climate scenario data from the Intergovernmental Panel on Climate Change’s Fifth Assessment Report.

14 SOLAR ENERGY↗
DOE OSTI2026

L-VISP: LSTM Visualization for Interpretable Symptom Prediction in Patient Cohorts

Symptom modelling in head and neck cancer is challenged by the complexity of heterogeneous patient data, leading to an interest in deep learning approaches. Although Long Short-Term Memory Networks (LSTMs) have shown great results in patient risk prediction, their low interpretability requires data modellers to collaborate with clinical experts to validate the results. We present L-VISP, a human–machine solution that uses visual analytics for LSTM modelling in clinical research. L-VISP uses custom visual encodings to make multiple LSTM variants interpretable, supporting a full range of analysis, from understanding model operations and evaluating performance to interpreting results in a clinical context. We evaluate L-VISP with data modellers and a clinical oncologist and present the takeaways from this multidisciplinary collaboration.

LSTM modeling↗
NASA NTRS1993

Performances of a date dissemination code on telephone lines using commercial modems

A coded time/date information dissemination system (CTD), based on telephone lines and commercial modems, is now in its experimental phase in Italy at IEN. This service, born from a cooperation with other metrological laboratories (TUG, Austria, SNT, Sweden, VSL, The Netherlands), represents an attempt towards an European standardization. Some results of an experimental analysis in which a few modems were tested, both in laboratory conditions and connected to the telephone network, in order to evaluate the timing capability of the system are given. When the system is used in a one-way mode, in many practical cases the modems delay turns out to be the main factor which limits the accuracy, even more than the telephone line delays. If the two-way mode is used, the modems asymmetry, i.e., the delay difference between transmission and reception, is almost always the most important source of uncertainty, provided the link is not including a space segment. Comparing the widely used V.22 modems to the old V.21 ones, the latters turn out to be better both in delay time (30-100 ms V.22, and 7-15 ms V.21) and asymmetry (10-50 micro-s V.22, and 10 ms V.22). Time transfer accuracies of 10 micron-s (same turn) to 100 micro-s (long distance calls) were obtained in two-way mode with commercial V.21 modems.

Cordara, F.↗
NASA NTRS2009

DSN Simulator

The DSN Simulator (wherein DSN signifies NASA's Deep Space Network) is an updated version of the software described in DSN Array Simulator (NPO-44506), Software Tech Briefs (Special supplement to NASA Tech Briefs), Vol. 32, No. 9 (September 2008), page 26. To recapitulate: This software is used for computational modeling of proposed DSN facilities comprising arrays of antennas and transmitting and receiving equipment for microwave communication with spacecraft on interplanetary missions. Such modeling is performed to estimate facility performance, evaluate requirements that govern facility design, and evaluate proposed improvements in hardware and/or software. The software includes a Monte Carlo simulation component that enables rapid generation of key mission-set metrics (e.g., numbers of links, data rates, and data volumes), and statistical distributions thereof as functions of time. The prior version of the software could model only one DSN facility at a time and included hard-coded, unconfigurable metrics. The present updated version is capable of modeling the entire DSN and provides for configurable metrics, making it possible to perform loading analyses for alternative future DSN architectures and mission-set scenarios. The present version also features an improved user interface and interfaces for exchange of data with other DSN software and with a DSN mission model database.

Fijany, Amir↗
DOE OSTI2025

Using "AI Poincare" to analyze non-linear integrable optics

This study dives into the applicability of using automated discovery of conserved quantities in dynamical systems relevant to accelerator physics. Specifically, we explore the performance of AI Poincaré in analyzing numerical trajectory data obtained using the McMillan system of non-linear integrable optics. A comprehensive evaluation of the algorithm's performance is conducted through diverse methodologies. These include the analysis of the estimated number of conserved quantities embedded in a dataset and the deviation of interpolated points on the inferred manifold with respect to points in actually in the dataset. the investigation identifies an optimal range of perturbation distances where the underlying manifold extraction algorithm inside AI Poincaré exhibits optimal performance. Additionally, an improved neural network architecture is proposed based on the observed results. Finally, we apply the algorithm to preliminary experimental data from the Integrable Optics Test Accelerator at Fermilab to successfully infer the number of conserved quantities even in the presence of fast decoherence of the measured signal.

Osmanov, Lazare [Free U. Tbilisi]↗
DOE OSTI2024

CO 2 storage site characterization using ensemble-based approaches with deep generative models

Estimating spatially distributed properties such as permeability from available sparse measurements is a great challenge in efficient subsurface CO 2 storage operations. In this paper, a deep generative model that can accurately capture complex subsurface structure is tested with an ensemble-based inversion method for accurate and accelerated characterization of CO 2 storage sites. We chose Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) for its realistic reservoir property representation and Ensemble Smoother with Multiple Data Assimilation (ES-MDA) for its robust data fitting and uncertainty quantification capability. WGAN-GP are trained to generate high-dimensional permeability fields from a low-dimensional latent space and ES-MDA then updates the latent variables by assimilating available measurements. Several subsurface site characterization examples including Gaussian, channelized, and fractured reservoirs are used to evaluate the accuracy and computational efficiency of the proposed method and the main features of the unknown permeability fields are characterized accurately with reliable uncertainty quantification. Furthermore, the estimation performance is compared with a widely-used variational, i.e., optimization-based, inversion approach, and the proposed approach outperforms the variational inversion method in several benchmark cases. We explain such superior performance by visualizing the objective function in the latent space: because of nonlinear and aggressive dimension reduction via generative modeling, the objective function surface becomes extremely complex while the ensemble approximation can smooth out the multi-modal surface during the minimization. This suggests that the ensemble-based approach works well over the variational approach when combined with deep generative models at the cost of forward model runs unless convergence-ensuring modifications are implemented in the variational inversion.

42 ENGINEERING↗
DOE OSTI2025

Global and regional perspectives on optimizing thermo-responsive dynamic windows for energy-efficient buildings

Architectural thermo-responsive dynamic windows offer an autonomous solution for solar heat regulation, thereby reducing building energy consumption. Previous work has emphasized the significance of thermo-responsive windows in hot climates due to their role in solar heat control and subsequent energy conservation; conversely, our study provides a different perspective. Through a global-scale analysis, we explore over 100 material samples and execute more than 2.8 million simulations across over two thousand global locations. World heatmap results, derived from well-trained artificial neural network models, reveal that thermo-responsive windows are especially useful in climates where buildings demand both heating and cooling energy, whereas thermo-responsive windows with optimal transition temperatures show no dynamic features in most of low-latitude tropical regions. Additionally, this study provides a practical guideline and an open-source mapping tool to optimize the intrinsic properties of thermo-responsive materials and evaluate their energy performance for sustainable buildings at various geographical scales.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗