Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “network shape”

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 397 records · Page 22
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Machine learning neutrino-nucleus cross sections

Neutrino-nucleus scattering cross sections are critical theoretical inputs for long-baseline neutrino oscillation experiments. However, robust modeling of these cross sections remains challenging. For a simple but physically motivated toy model of the DUNE experiment, we demonstrate that an accurate neural-network model of the cross section—leveraging only Standard-Model symmetries—can be learned from near-detector data. We perform a neutrino oscillation analysis with simulated far-detector events, finding that oscillation analysis results enabled by our data-driven cross-section model approach the theoretical limit achievable with perfect prior knowledge of the cross section. We further quantify the effects of flux shape and detector resolution uncertainties as well as systematics from cross-section mismodeling. This proof-of-principle study highlights the potential of future neutrino near-detector datasets and data-driven cross-section models.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

Knowledge Oriented Graph Unified Transformer (KOGUT) v0.1

KOGUT — Knowledge Oriented Graph Unified Transformer KOGUT implements the Relational Graph Transformer (RelGT) architecture for knowledge graph link prediction in biological domains, with a primary focus on microbial growth media prediction. While the original RelGT (arXiv:2505.10960) targets relational tables, time series, and multi-table databases, KOGUT adapts this architecture for heterogeneous biological knowledge graphs, providing first-in-class AI predictive models for microbial cultivation. Key Adaptations Beyond Original RelGT: - Knowledge Graph Focus: Applied to biological KGs with semantic node types (taxa, chemicals, media, phenotypes, environments) versus generic relational database tables, trained on the KG-Microbe knowledge graph (1.3M entities, 2.9M edges, 24 relation types). - Multimodal Node Encoding: Integrates node labels, categories, descriptions, and synonyms from KG metadata through learned embedding layers—adapting relational column features to graph node attributes with textual semantics. - Extended K-Hop Subgraph Strategy: Optimized neighborhood sampling (3-hop default, configurable up to 200 nodes) tuned for sparse biological networks, building on the original local-global attention framework with biological relation preservation. - Biolink Predicate Preservation: Type-specific transformations for 24 biological edge semantics (occurs_in, consumes, produces, has_phenotype, subclass_of) beyond standard relational foreign keys, enabling multi-relation link prediction. - Inductive Learning Support: Enables zero-shot predictions for novel taxa through feature-based embeddings (temperature, oxygen requirements, gram stain, cell shape), extending the original transductive relational benchmark scope to uncultured microorganisms. CheapSOTA Performance Optimizations (This Distribution): - VQ-EMA Centroid Attention: Vector quantization with exponential moving average for improved global context modeling (+5-10% MRR improvement). - HDF5 Precomputed Data Loading: One-time preprocessing of k-hop subgraphs to eliminate redundant graph traversals (2-5× training speedup). - Distributed Data Parallel Training: Multi-GPU support for scaling to larger knowledge graphs (tested on 4× NVIDIA A100 GPUs at NERSC Perlmutter). - Mixed Precision Training: Automatic mixed precision (AMP) for memory efficiency and faster training. Advantages Over Standard Knowledge Graph Embedding Models: Combines RelGT's proven multi-element tokenization (features, type, hop, structure) with graph-native biological representations, enabling interpretable link prediction across heterogeneous entities that standard embedding models (TransE, RotatE, ComplEx) and table-based transformers cannot directly model. Achieves near-perfect performance on microbial growth media prediction (MRR: 0.9966, Precision@1: 0.9932, Hit@10: 1.0000) while maintaining explainability through attention-based reasoning over biological pathways. Training Data: - KG-Microbe merged knowledge graph: 1,379,337 nodes, 2,960,472 edges - 24 biological relation types including taxonomic hierarchies, metabolic interactions, phenotype associations, and environmental relationships - Primary prediction task: Growth media suitability for microbial taxa (biolink:occurs_in, 50K edges) - Multi-relation capability: Predicts links for any of the 24 relation types, including chemical consumption/production, phenotype associations, and taxonomic classification Citation: Original RelGT Architecture: Dwivedi et al., "Relational Graph Transformer", arXiv:2505.10960, 2025 KOGUT Implementation: Knowledge Oriented Graph Unified Transformer for Microbial Growth Media Prediction Developed at Lawrence Berkeley National Laboratory (LBNL) Trained on NERSC Perlmutter supercomputer

Joachimiak, Marcin [Lawrence Berkeley National Lab↗
DOE OSTI2026

Machine Learning Neutrino-Nucleus Cross Sections

Neutrino-nucleus scattering cross sections are critical theoretical inputs for long-baseline neutrino oscillation experiments. However, robust modeling of these cross sections remains challenging. For a simple but physically motivated toy model of the DUNE experiment, we demonstrate that an accurate neural-network model of the cross section—leveraging only Standard-Model symmetries— can be learned from near-detector data. We perform a neutrino oscillation analysis with simulated far-detector events, finding that oscillation analysis results enabled by our data-driven cross-section model approach the theoretical limit achievable with perfect prior knowledge of the cross section. We further quantify the effects of flux shape and detector resolution uncertainties as well as systematics from cross-section mismodeling. This proof-of-principle study highlights the potential of future neutrino near-detector datasets and data-driven cross-section models.

Tame-Narvaez, Karla [Fermilab] (ORCID:000000022249↗
DOE OSTI2020

Data optimization for large batch distributed training of deep neural networks

Distributed training in deep learning (DL) is common practice as data and models grow. The current practice for distributed training of deep neural networks faces the challenges of communication bottlenecks when operating at scale, and model accuracy deterioration with an increase in global batch size. Present solutions focus on improving message exchange efficiency as well as implementing techniques to tweak batch sizes and models in the training process. The loss of training accuracy typically happens because the loss function gets trapped in a local minima. We observe that the loss landscape minimization is shaped by both the model and training data and propose a data optimization approach that utilizes machine learning to implicitly smooth out the loss landscape resulting in fewer local minima. Our approach filters out data points which are less important to feature learning, enabling us to speed up the training of models on larger batch sizes to improved accuracy.

Gahlot, Shubhankar↗
DOE OSTI2021

Performance of Pulsed Thermal Tomography Imaging with Machine Learning-Based Classification of Defects in Additively Manufactured Structures

Additive manufacturing (AM) is an emerging method for cost-efficient fabrication of complex topology nuclear reactor parts from high-strength corrosion resistance alloys, such as stainless steel and Inconel. AM of metallic structures for nuclear energy applications is currently based on laser powder bed fusion (LPBF) process. Some of the challenges with using LPBF method for nuclear manufacturing include the possibility of introducing pores into metallic structures. Integrity of AM structures needs to be evaluated nondestructively because material flaws could lead to premature failures in high temperature nuclear reactor environment. Currently, there exist limited capabilities to evaluate actual AM structures non-destructively. Pulsed Thermal Tomography Imaging (PTT) provides a capability for non-destructive evaluation (NDE) of subsurface defects in arbitrary size structures. The PTT method is based on recording material surface temperature transients with infrared (IR) camera following thermal pulse delivered on material surface with flash light. The PTT method has advantages for NDE of actual AM structures because the method involves one-sided non-contact measurements and fast processing of large sample areas captured in one image. Following initial qualification of an AM component for deployment in a nuclear reactor, a PTT system can also be used for in-service nondestructive evaluation (NDE) applications. In this report, we describe recent progress in enhancing PTT capabilities in detecting and visualizing microscopic defects in metallic specimens. The thermal tomography (TT) algorithm obtains depth reconstructions of spatial effusivity from the data cube of sequentially recorded surface temperatures. However, interpretation of TT images is non-trivial because of blurring of images with increasing depth. To address this challenge, we have developed a deep learning convolutional neural network (CNN) to classify size and orientation subsurface defects in simulated TT images. CNN is trained on a database of TT images created for a set of simulated metallic structures with elliptical subsurface voids. Test of CNN performance demonstrate the ability to classify radii and angular orientation of subsurface defects in TT images. In addition, we have shown that CNN trained on elliptical defects is capable of classifying irregular-shaped defects obtained from scanning electron microscopy (SEM) of stainless steel sections printed with LPBF.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2022

Performance Study of Virtual Frisch Grid CdZnTeSe Detectors

Nuclear detectors for x-ray and gamma-ray spectroscopy and imaging are a vital tool in many homeland security, medical imaging, astrophysics and other applications. Most of these applications require room-temperature operation due to the operational constraints imposed by a cryogenic cooling system. CdZnTe (CZT) has been the main material with the desired detection properties, and CZT crystals have been used commercially for three decades. However, CdZnTe still suffers from long-standing issues of high densities of performance-limiting intrinsic defects such as Te inclusions and networks of dislocation walls (sub-grain boundaries). A recently invented new quaternary material CdZnTeSe showed excellent material properties for radiation detection. The material was found to be free from dislocation networks, possess reduced Te inclusions, and have better compositional homogeneity. Virtual Frisch grid detectors were fabricated from crystals taken from a CdZnTeSe ingot that was grown by the traveling heater method. The detectors were fabricated from an as-grown ingot, bypassing the post-growth annealing process commonly practiced for industrial-grade CZT. The performances of the detectors were studied with different Frisch grid lengths using an amplifier shaping time ranging from 1–6 µs. The detectors showed high-quality spectroscopic performance with an as-measured energy resolution of ~1.1% at 662 keV for an optimum Frisch grid length of 3 mm. The charge collection was observed to enhance for longer Frisch grids.

47 OTHER INSTRUMENTATION↗
DOE OSTI2020

Optical measure of disorder: Why Urbach analysis works for amorphous silicon but fails for amorphous carbon

We investigate the basis for the Paradox where the Urbach-slope disorder parameter disagrees with the Raman width in amorphous diamond-like carbon (DLC) materials (lower Urbach-Eo yet greater Raman width). We examined the bandgap and Urbach-slope measurement issues. While significant errors are identified, ultimately these cannot resolve the Paradox. This resolution involves large changes in shape of DLC's absorption band resulting from large energy shifts. To solidify the understanding of band energy shifts, we examined their properties using a-Si:H, well known for its agreement between Raman and Urbach-slope disorder parameters. Using Tauc-Lorentz (T-L) dispersion functions, the Urbach method works for a-Si:H because small changes in shape occur, as measured by (i) peak position, (ii) peak width, (iii) peak amplitude, and (iv) and gap energies. Moreover, for a-Si:H, a 5th condition (v) there is no other feature below the principal band to interfere with its fall. All 5 of these conditions fail for DLCs. Because T-L dispersions accommodate asymmetry, we traced the Paradox to a steepening of the band shape as it pushes toward lower energy. This steepening is unrelated to disorder, but to a boundary value problem where energy cannot be negative. We conclude that Urbach analysis is invalid for DLC materials, but the T-L width is a good measure instead. We also examined another disorder measure, where π bonds should be considered as disorder relative to the σ bonds in an idealized “amorphous diamond” sp 3 network: superconvergence can be used to quantify these π transitions. Finally, further molecular orbital calculations are needed to properly interpret the changes in T-L widths.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Crystal structure of a cap-independent translation enhancer RNA

In eukaryotic messenger RNAs, the 5' cap structure binds to the translation initiation factor 4E to facilitate early stages of translation. Although many plant viruses lack the 5' cap structure, some contain cap-independent translation elements (CITEs) in their 3' untranslated region. The PTE (Panicum mosaic virus translation element) class of CITEs contains a G-rich asymmetric bulge and a C-rich helical junction that were proposed to interact via formation of a pseudoknot. SHAPE analysis of PTE homologs reveals a highly reactive guanosine residue within the G-rich region proposed to mediate eukaryotic initiation factor 4E (eIF4E) recognition. Here we have obtained the crystal structure of the PTE from Pea enation mosaic virus 2 (PEMV 2 ) RNA in complex with our structural chaperone, Fab BL3–6. The structure reveals that the G-rich and C-rich regions interact through a complex network of interactions distinct from those expected for a pseudoknot. The motif, which contains a short parallel duplex, provides a structural mechanism for how the guanosine is extruded from the core stack to enable eIF4E recognition. Homologous PTE elements harbor a G-rich bulge and a three-way junction and exhibit covariation at crucial positions, suggesting that the PEMV 2 tertiary architecture is conserved among these homologs.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

A Misalignment Tolerant Magnetic Coupler Design and Implementation for Wireless Charging of Unmanned Aerial Vehicles (UAVs)

Wireless power transfer technology is getting more attention these days as a part of expanded battery charging infrastructure and network at a wide range of power levels. Charging Unmanned aerial vehicles (UAVs) is one wireless charging application, and charging their batteries can be challenging because they have short flight times and are frequently charged. For wireless charging of UAVs, the misalignment performance of the magnetic coupler pads is critical because landing on a charging pad at a perfectly aligned position is difficult and can be time-consuming. Different coil shapes and system structures have been proposed in the literature to overcome this challenge. A new design with a high misalignment tolerance is needed; therefore, to fill this gap, a wireless power transfer system has been designed for a 250 W UAV battery charging system with a new magnetic coupler design. A 3D model of the proposed design was created, and finite element simulations were performed. To prove the proposed design, the magnetic coupler prototypes were developed, and experimental results are presented herein. The misalignment tolerance of the proposed system was observed for various rotational positions of the secondary coil, from 0° to 360°. The results demonstrate that DC–DC efficiency varies between 80% and 85% within full 360° rotation of the receiver coil. This result enables the proposed system to address the misalignment problem for wireless charging of UAVs.

UAVs↗
DOE OSTI2025

Rheo–Electric Foundations and Engineering of Carbon Slurry Flow Electrodes

Flowable carbon slurry electrodes promise continuous, scalable electrochemical desalination and energy storage when their rheology (flow and stability) and electronic connectivity are jointly optimized. This report integrates six complementary thrusts that we executed under the Laboratory Directed Research and Development (LDRD) project: (i) a fast, ex situ, centrifuge-compatible method to quantify pellet (packed slurry) electronic conductivity, with a validated cell constant (“shape factor”) and quantitative structure–property insights for carbon mixtures; (ii) a controlled circulation study showing that peristaltic pumping can irreversibly alter particle size and morphology over laboratory-relevant durations; (iii) development of a miniature jet pump that preserves particle integrity while achieving entrainment ratios of 2–4 at practical flow rates; (iv) a comprehensive mapping of how a representative non-ionic surfactant (Tween 20) collapses the carbon gel network, separating network-percolation losses from intrinsic particle contact resistance; (v) in-situ visualization revealing how gravitational settling and flow-driven mixing compete to control charge transport, with dynamic bed layers preventing saturation while achieving 30-fold local concentration enhancement; and (vi) a simple, widely adoptable fabrication route to structured, gas-nitrided titanium nitride (TiN) titanium current collectors that dramatically lower interfacial losses and enable geometry-driven performance gains. Together, these results provide a coherent toolchain and design rules to accelerate formulation screening, de-risk device prototyping, and standardize characterization for carbon slurry electrodes in flow-electrode capacitive deionization (FCDI), electrochemical flow capacitor (EFC), and related systems.

25 ENERGY STORAGE↗
DOE OSTI2025

Local Cation-Ordered Superlattice Stabilizing Ni-Rich Single-Crystalline Cathodes

Ni-rich single-crystalline cathodes are pivotal for advancing lithium-ion battery technology due to their high energy density and mechanical stability. However, Ni-rich single-crystalline particles face intrinsic structural heterogeneity due to excessively high sintering temperature required to shape micron-sized morphologies─typically over 150 °C above the polycrystalline optimum, leading to rapid electrochemical decay and unsatisfied rate performance that hinder their practical application. Here, in this work, we propose a lithium-deficient presintering strategy to synthesize cation-ordered single-crystalline LiNi 0.83 Co 0.12 Mn 0.05 O 2 (S-NCM83), effectively minimizing lattice chemical heterogeneity and defect formation. The resulting cation-ordered percolation network enhances the structural stability of the bulk, reduces the energy barrier for Li + migration, and stabilizes Li + diffusion pathways. Consequently, S-NCM83 demonstrates significantly improved cycling stability across various operating temperatures and achieves exceptional rate performance, delivering 206 mAh g –1 at 0.1 C and 170 mAh g –1 at 5 C, without requiring surface coatings or doping. This work introduces a universal strategy to address the long-standing structural instability issues in single-crystalline cathodes, paving the way for simplified and scalable approaches to long-life and high-energy lithium-ion batteries.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Physics-informed machine-learning model of temperature evolution under solid phase processes

We model temperature dynamics during Shear Assisted Proccess Extrusion (ShAPE), a solid phase process that plasticizes feedstock with a rotating tool and subsequently extrudes it into a consolidated tube, rod, or wire. Control of temperature is critical during ShAPE processing to avoid liquefaction, ensure smooth extrusion, and develop desired material properties in the extruded products. Accurate modeling of the complicated thermo-mechanical feedbacks between process inputs, material temperature, and heat generation presents a significant barrier to predictive modeling and process design. In particular, connecting micro-structural scale mechanisms of heat generation to macro-scale predictions of temperature can become computationally intractable. In this work we use a neural network (NN) model of heat generation to bridge this gap, by combining it with a simplified model of the temperature dynamics due to conduction and convection to capture the macro scale evolution of temperature. We inform the construction of the NN heat generation model using crystal plasticity simulations at the micro-structural scale to model the effects of process inputs on generation of heat. We achieved close fits of the temperature dynamics model to a diverse experimental data-set. Further, the relationships learned by the NN model between process inputs and heat generation showed qualitative agreement with those predicted by crystal plasticity simulations.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Evaluation of U-net-based Image Segmentation Model to Digital Mammography

Detecting suspicious lesions in medical imaging is the important first step in computer-aided detection (CAD) systems. However, detecting abnormalities in breast tissue is difficult due to the lesion's varying size, shape, margin, and contrast with the background tissue. We focused on mass segmentation, a method that provides notable morphological features by outlining contours of masses. Accurate segmentation is crucial for correct diagnosis. Recent advancements in deep learning have improved object detection and segmentation, and these techniques are also being applied to medical imaging studies. We focused on U-net, which is a recently developed mass segmentation algorithm based on a fully convolutional network. The U-net architecture consists of (1) a contracting path to increase the resolution of the output and (2) a symmetric expanding path to better locate the region of interest. The performance of a U-net model was tested with 63 digital mammograms from INbreast, a publicly available database. We trained the model with images resized to 40x40 pixels and conducted 10-fold cross-validation to prevent overfitting. The model's performance with respect to breast density and the lesion's BI-RADS rating was also investigated. Dice coefficients (DC) were used as a performance measure to compare the predicted segmentation of the model with the ground truth. Logistic regression and an analysis of variance were performed to determine the significance of the DCs with regards to breast density and lesion behavior and to calculate the 95% confidence interval. The average DC was 0.80. The difference between DCs for BI-RADS 2 and 4c and for BI-RADS 2 and 5 were significant, suggesting that the model has more difficulty in segmenting benign lesions.

Cho, Priscilla↗
DOE OSTI2022

Host genotype controls ecological change in the leaf fungal microbiome

Leaf fungal microbiomes can be fundamental drivers of host plant success, as they contain pathogens that devastate crop plants and taxa that enhance nutrient uptake, discourage herbivory, and antagonize pathogens. We measured leaf fungal diversity with amplicon sequencing across an entire growing season in a diversity panel of switchgrass ( Panicum virgatum ). We also sampled a replicated subset of genotypes across 3 additional sites to compare the importance of time, space, ecology, and genetics. We found a strong successional pattern in the microbiome shaped both by host genetics and environmental factors. Further, we used genome-wide association (GWA) mapping and RNA sequencing to show that 3 cysteine-rich receptor-like kinases (crRLKs) were linked to a genetic locus associated with microbiome structure. We confirmed GWAS results in an independent set of genotypes for both the internal transcribed spacer (ITS) and large subunit (LSU) ribosomal DNA markers. Fungal pathogens were central to microbial covariance networks, and genotypes susceptible to pathogens differed in their expression of the 3 crRLKs, suggesting that host immune genes are a principal means of controlling the entire leaf microbiome.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Structural organization of the spongy mesophyll

Summary Many plant leaves have two layers of photosynthetic tissue: the palisade and spongy mesophyll. Whereas palisade mesophyll consists of tightly packed columnar cells, the structure of spongy mesophyll is not well characterized and often treated as a random assemblage of irregularly shaped cells. Using micro‐computed tomography imaging, topological analysis, and a comparative physiological framework, we examined the structure of the spongy mesophyll in 40 species from 30 genera with laminar leaves and reticulate venation. A spectrum of spongy mesophyll diversity encompassed two dominant phenotypes: first, an ordered, honeycomblike tissue structure that emerged from the spatial coordination of multilobed cells, conforming to the physical principles of Euler’s law; and second, a less‐ordered, isotropic network of cells. Phenotypic variation was associated with transitions in cell size, cell packing density, mesophyll surface‐area‐to‐volume ratio, vein density, and maximum photosynthetic rate. These results show that simple principles may govern the organization and scaling of the spongy mesophyll in many plants and demonstrate the presence of structural patterns associated with leaf function. This improved understanding of mesophyll anatomy provides new opportunities for spatially explicit analyses of leaf development, physiology, and biomechanics.

3D↗
DOE OSTI2022

Topology optimization of an airfoil fin microchannel heat exchanger using artificial intelligence

High-performance microchannel heat exchangers are needed to supply heat for power conversion for nuclear microreactors. An airfoil fin microchannel design, constructed of Alloy 617 with helium as the working fluid, is analyzed and optimized using a design of experiments with artificial intelligence techniques. The use of airfoil fins offers the potential to reduce pressure drop across the heat exchanger, as compared to other types of channel configurations. A framework for topology optimization of airfoil fin printed circuit heat exchangers (PCHEs) has been developed that can be readily extended to different fin sizes and shapes, as well as different inlet and operating conditions, materials of construction, and working fluids. An optimization procedure is developed that employs computational fluid dynamics for a set of design points identified using Latin hypercube sampling. Computational fluid dynamics is used to analyze a simplified two-channel configuration where five design parameters are varied – inlet angle, fin scale, extent of staggering, transverse and longitudinal pitches. Two methods (a 5D polynomial and a regression neural network) are compared for generating surrogate models and the resulting response surface approximation is input to a genetic algorithm that is used to identify a set of optimal parameters. The optimal geometries are found across six channel Reynolds numbers ranging from 1000 to 5000, since inlet conditions affect flow through the heat exchanger. Additionally, a set of optimal designs that maximizes heat transfer and minimizes pressure drop is identified, and a thermal stress analysis is performed on the optimal design. Correlations for the Nusselt number and Darcy friction factor are developed that can be useful for thermal hydraulic analyses using system codes. Thermal stresses are analyzed and a brief discussion of the status of code cases of PCHEs for nuclear applications is given. Testing and thermomechanical modeling is needed to facilitate future code compliance of PCHEs for high pressure and high temperature applications.

42 ENGINEERING↗
DOE OSTI2026

Dark Energy Survey Year 3 results: optimized $w$CDM simulation-based inference with weak lensing map-level hybrid statistics

We present cosmological constraints from the Dark Energy Survey Year 3 (DES Y3) weak lensing data using hierarchical hybrid statistics within a Bayesian simulation-based inference framework that is based on the Gower Street simulations. To maximize the precision of the inference, we have developed a new, information-theory based, data compression of the weak lensing maps to just seven highly informative summary statistics. The hybrid scheme exploits the high information content of the power spectrum, compressing both the power spectrum and neural-based summaries that are designed to extract further information. Our simulation-based approach enables principled forward modelling of all major sources of systematic uncertainty and survey properties into realistic mock observations, including the survey mask, photometric redshift uncertainties, intrinsic galaxy alignments, multiplicative shear calibration bias, source galaxy clustering, non-Gaussian shape noise, and non-linear structure formation. The summary statistics are then used in a Bayesian simulation-based inference pipeline. The inference is validated through coverage tests and checks for robustness against baryonic feedback. Assuming a $w$CDM cosmology, our analysis yields $S_8 = 0.808 \pm 0.017$, $Ω_{\rm m} = 0.325 \pm 0.024$, and $w < -0.766$ (marginalized posterior 68 per cent credible intervals). This rigorous combination of information theory, physics- and neural network-based extreme data compression, and principled Bayesian analysis improves the figure of merit for $(Ω_{\rm m}, S_8, w)$ by 60 per cent over the previous state-of-the-art, and by almost a factor of 3 over two-point analyses of the same data. They are the most precise joint constraints on $(Ω_{\rm m}, S_8, w)$ from weak gravitational lensing data alone of any survey to date. We intend to apply this analysis to the more recent DES Y6 data.

Williamson, J. [University Coll. London]↗
DOE OSTI2023

Efficient learning of power grid voltage control strategies via model-based deep reinforcement learning

Here this article proposes a model-based deep reinforcement learning (DRL) method to design emergency control strategies for short-term voltage stability problems in power systems. Recent advances show promising results for model-free DRL-based methods in power systems control problems. But in power systems applications, these model-free methods have certain issues related to training time (clock time) and sample efficiency; both are critical for making state-of-the-art DRL algorithms practically applicable. DRL-agent learns an optimal policy via a trial-and-error method while interacting with the real-world environment. It is also desirable to minimize the direct interaction of the DRL agent with the real-world power grid due to its safety-critical nature. Additionally, the state-of-the-art DRL-based policies are mostly trained using a physics-based grid simulator where dynamic simulation is computationally intensive, lowering the training efficiency. We propose a novel model-based DRL framework where a deep neural network (DNN)-based dynamic surrogate model (SM), instead of a real-world power grid or physics-based simulation, is utilized within the policy learning framework, making the process faster and more sample efficient. However, having stable training in model-based DRL is challenging because of the complex system dynamics of large-scale power systems. We addressed these issues by incorporating imitation learning to have a warm start in policy learning, reward-shaping, and multi-step loss in surrogate model training. Finally, we achieved 97.5% reduction in samples and 87.7% reduction in training time for an application to the IEEE 300-bus test system.

24 POWER TRANSMISSION AND DISTRIBUTION↗