Structure Prediction from Neutron Scattering Profiles: A Data Sciences Approach
Explore the source record for details and available documents.
Computer Science↗
SEARCH · Search NASA
Results for “synthetic network models”
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.
Spatial Graph Attention and Curiosity-driven Policy for Antiviral Drug Discovery
We developed Distilled Graph Attention Policy Networks (DGAPNs), a curiosity-driven reinforcement learning model to generate novel graph-structured chemical representations that optimize user-defined objectives by efficiently navigating a physically constrained domain. The framework is examined on the task of generating molecules that are designed to bind, noncovalently, to functional sites of SARS-CoV-2 proteins. We present a spatial Graph Attention Network (sGAT) that leverages self-attention over both node and edge attributes as well as encoding spatial structure -- this capability is of considerable interest in areas such as molecular and synthetic biology and drug discovery. An attentional policy network is then introduced to learn decision rules for a dynamic, fragment-based chemical environment, and state-of-the-art policy gradient techniques are employed to train the network with enhanced stability. Exploration is efficiently encouraged by incorporating innovation reward bonuses learned and proposed by random network distillation. In experiments, our framework achieved outstanding results compared to state-of-the-art algorithms, while increasing the diversity of proposed molecules and reducing the complexity of paths to chemical synthesis.
Wu, Yulun↗
Genetic circuit design automation for yeast
Cells can be programmed to monitor and react to their environment using genetic circuits. Design automation software maps a desired circuit function to a DNA sequence, a process that requires units of gene regulation (gates) that are simple to connect and behave predictably. This poses a challenge for eukaryotes due to their complex mechanisms of transcription and translation. To this end, we have developed gates for yeast (Saccharomyces cerevisiae) that are connected using RNA polymerase flux as the signal carrier and are insulated from each other and host regulation. They are based on minimal constitutive promoters (~120 base pairs), for which rules are developed to insert operators for DNA-binding proteins. Using this approach, in this work we constructed nine NOT/NOR gates with nearly identical response functions and 400-fold dynamic range. In circuits, they are transcriptionally insulated from each other by placing ribozymes downstream of terminators to block nuclear export of messenger RNAs resulting from RNA polymerase readthrough. Based on these gates, Cello 2.0 was used to build circuits with up to 11 regulatory proteins. A simple dynamic model predicts the circuit response over days. Genetic circuit design automation for eukaryotes simplifies the construction of regulatory networks as part of cellular engineering projects, whether it be to stage processes during bioproduction, serve as environmental sentinels or guide living therapeutics.
59 BASIC BIOLOGICAL SCIENCES↗
Device Classification for Industrial Control Systems Using Predicted Traffic Features
To achieve a secure interconnected Industrial Control System (ICS) architecture, security practitioners depend on accurate identification of network host behavior. However, accurate machine learning based host identification methods depends on the availability of significant quantities of network traffic data, which can be difficult to obtain due to system constraints such as network security, data confidentiality, and physical location. In this work, we propose a network traffic feature prediction method based on a generative model, which achieves high host identification accuracy. Furthermore, we develop a joint training algorithm to improve host identification performance compared to separate training of the generative model and the classifier responsible for host identification.
97 MATHEMATICS AND COMPUTING↗
Spatial Graph Attention and Curiosity-driven Policy for Antiviral Drug Discovery
We developed Distilled Graph Attention Policy Networks (DGAPNs), a curiosity-driven reinforcement learning model to generate novel graph-structured chemical representations that optimize user-defined objectives by efficiently navigating a physically constrained domain. Here, the framework is examined on the task of generating molecules that are designed to bind, noncovalently, to functional sites of SARS-CoV-2 proteins. We present a spatial Graph Attention Network (sGAT) that leverages self-attention over both node and edge attributes as well as encoding spatial structure -- this capability is of considerable interest in areas such as molecular and synthetic biology and drug discovery. An attentional policy network is then introduced to learn decision rules for a dynamic, fragment-based chemical environment, and state-of-the-art policy gradient techniques are employed to train the network with enhanced stability. Exploration is efficiently encouraged by incorporating innovation reward bonuses learned and proposed by random network distillation. In experiments, our framework achieved outstanding results compared to state-of-the-art algorithms, while increasing the diversity of proposed molecules and reducing the complexity of paths to chemical synthesis.
Wu, Yulun↗
Bayesian sparse learning with preconditioned stochastic gradient MCMC and its applications
Deep neural networks have been successfully employed in an extensive variety of research areas, including solving partial differential equations. Despite its significant success, there are some challenges in effectively training DNN, such as avoiding overfitting in over-parameterized DNNs and accelerating the optimization in DNNs with pathological curvature. Here, we propose a Bayesian type sparse deep learning algorithm. The algorithm utilizes a set of spike-and-slab priors for the parameters in the deep neural network. The hierarchical Bayesian mixture will be trained using an adaptive empirical method. That is, one will alternatively sample from the posterior using preconditioned stochastic gradient Langevin Dynamics (PSGLD), and optimize the latent variables via stochastic approximation. The sparsity of the network is achieved while optimizing the hyperparameters with adaptive searching and penalizing. A popular SG-MCMC approach is Stochastic gradient Langevin dynamics (SGLD). However, considering the complex geometry in the model parameter space in nonconvex learning, updating parameters using a universal step size in each component as in SGLD may cause slow mixing. To address this issue, we apply a computationally manageable preconditioner in the updating rule, which provides a step-size parameter to adapt to local geometric properties. Moreover, by smoothly optimizing the hyperparameter in the preconditioning matrix, our proposed algorithm ensures a decreasing bias, which is introduced by ignoring the correction term in the preconditioned SGLD. According to the existing theoretical framework, we show that the proposed algorithm can asymptotically converge to the correct distribution with a controllable bias under mild conditions. Numerical tests are performed on both synthetic regression problems and learning solutions of elliptic PDE, which demonstrate the accuracy and efficiency of the present work.
71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
wa-hls4ml: A Benchmark and Surrogate Models for hls4ml Resource and Latency Estimation
As machine learning (ML) is increasingly implemented in hardware to address real-time challenges in scientific applications, the development of advanced toolchains has significantly reduced the time required to iterate on various designs. These advancements have solved major obstacles, but also exposed new challenges. For example, processes that were not previously considered bottlenecks, such as hardware synthesis, are becoming limiting factors in the rapid iteration of designs. To mitigate these emerging constraints, multiple efforts have been undertaken to develop an ML-based surrogate model that estimates resource usage of ML accelerator architectures. We introduce wa-hls4ml, a benchmark for ML accelerator resource and latency estimation, and its corresponding initial dataset of over 680,000 fully connected and convolutional neural networks, all synthesized using hls4ml and targeting Xilinx FPGAs. The benchmark evaluates the performance of resource and latency predictors against several common ML model architectures, primarily originating from scientific domains, as exemplar models, and the average performance across a subset of the dataset. Additionally, we introduce GNN- and transformer-based surrogate models that predict latency and resources for ML accelerators. We present the architecture and performance of the models and find that the models generally predict latency and resources for the 75% percentile within several percent of the synthesized resources on the synthetic test dataset.
Hawks, Benjamin [Fermilab] (ORCID:0000000157000288↗
wa-hls4ml: A Benchmark and Surrogate Models for hls4ml Resource and Latency Estimation
As machine learning (ML) is increasingly implemented in hardware to address real-time challenges in scientific applications, the development of advanced toolchains has significantly reduced the time required to iterate on various designs. These advancements have solved major obstacles, but also exposed new challenges. For example, processes that were not previously considered bottlenecks, such as hardware synthesis, are becoming limiting factors in the rapid iteration of designs. To mitigate these emerging constraints, multipleefforts have been undertaken to develop an ML-based surrogate model that estimates resource usage of synthesized ML accelerator architectures. We introduce wa-hls4ml, a benchmark for ML accelerator resource and latency estimation, and its corresponding initial dataset of over 680 000 fully connected and convolutional neural networks, all synthesized using hls4ml and targeting Xilinx FPGAs. The benchmark evaluates the performance of resource and latency predictors against several common ML model architectures, primarily originating from scientific domains, as exemplar models, and the average performance across a subset of the dataset. Additionally, we introduce GNN- and transformer-based surrogate models that predict latency and resources for ML accelerators. We present the architecture and performance of the models and find that the models generally predict latency and resources for the 75% percentile within several percent of the synthesized resources on the synthetic test dataset.
Hawks, Benjamin G. [Fermilab]↗
Aperture and roughness govern iron oxide passivation in olivine fractures during carbon mineralization
Efficient carbon dioxide mineralization in silicate-rich formations depends on reaction rates within fracture networks, yet the role of fracture microstructure remains poorly constrained. We investigated how fracture aperture and surface roughness influence mineralization by reacting synthetic forsteritic olivine fractures with controlled apertures (0.5–1.6 millimeters) and roughness (6–16 micrometers) with supercritical carbon dioxide at 13.7 megapascals and 185 degrees Celsius. Optical microscopy and Raman spectroscopy showed that rougher fracture surfaces promoted iron oxide precipitation, which passivated olivine surfaces, limiting magnesium availability for carbonate formation while removing iron as a reactant. These effects were more pronounced in smaller-aperture fractures. A geochemical model incorporating surface topography and passivation reproduced the observed trends, confirming that increased roughness can reduce reactivity despite greater surface area. Our results demonstrate that fracture microstructure strongly influences iron oxide passivation and carbon dioxide mineralization, with important implications for predicting long-term performance of engineered carbon dioxide storage systems.
54 ENVIRONMENTAL SCIENCES↗
Oracle-Preserving Latent Flows
A fundamental task in data science is the discovery, description, and identification of any symmetries present in the data. We developed a deep learning methodology for the simultaneous discovery of multiple non-trivial continuous symmetries across an entire labeled dataset. The symmetry transformations and the corresponding generators are modeled with fully connected neural networks trained with a specially constructed loss function, ensuring the desired symmetry properties. The two new elements in this work are the use of a reduced-dimensionality latent space and the generalization to invariant transformations with respect to high-dimensional oracles. The method is demonstrated with several examples on the MNIST digit dataset, where the oracle is provided by the 10-dimensional vector of logits of a trained classifier. We find classes of symmetries that transform each image from the dataset into new synthetic images while conserving the values of the logits. We illustrate these transformations as lines of equal probability (“flows”) in the reduced latent space. These results show that symmetries in the data can be successfully searched for and identified as interpretable non-trivial transformations in the equivalent latent space.
97 MATHEMATICS AND COMPUTING↗
Classical analog of quantum models in synthetic dimensions
We introduce a classical analog of quantum matter in ultracold molecule-synthetic or Rydberg atom-synthetic dimensions, by extending the Potts model to include interactions J 1 between atoms adjacent in both real and synthetic space and studying its finite-temperature properties. For intermediate values of J 1 , the resulting phases and phase diagrams are similar to those of the clock and Villain models, in which three phases emerge. There exists a sheet phase analogous to that found in quantum synthetic dimension models between the high-temperature disordered phase and the low-temperature ferromagnetic phase. Furthermore, we also employ machine learning to uncover nontrivial features of the phase diagram using the learning by confusion approach, which is able to discern several successive phase transitions.
75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
Resiliency-based restoration optimization for dependent network systems against cascading failures
Due to the increasing importance of large-scale and complex network systems and the potential for massive cascading failures in these real-world systems, modeling of system resiliency and optimization of restoration strategies to mitigate system performance loss caused by diverse disruptions is of significant interest among researchers and practitioners. Although society has experienced many incidents that demonstrate the influence of cascading failures aggravated by dependencies inside network systems, existing resiliency-based restoration optimization research rarely if ever jointly considers the impact of system dependencies on cascading failures. In this paper, different restoration prioritization strategies are applied to network systems subject to cascading failures that take into account system dependencies. By conducting case studies on synthetic networks and the U.S. airport network system, the effects of restoration strategies are evaluated using a system resiliency metric and two system performance measurements. Furthermore, the influence of system dependency characteristics and the interplay between them and restoration strategies on system resiliency regarding cascading failures are also investigated. This work demonstrates the distinct effects of restoration prioritization actions against cascading failures to mitigate the performance loss in network systems with different properties. It also provides insights about restoration improvement by considering dependency impacts to effectively reduce the intensity and extent of cascading failures.
42 ENGINEERING↗
Feedback regulation of crystal growth by buffering monomer concentration
Abstract Crystallization is a ubiquitous means of self-assembly that can organize matter over length scales orders of magnitude larger than those of the monomer units. Yet crystallization is notoriously difficult to control because it is exquisitely sensitive to monomer concentration, which changes as monomers are depleted during growth. Living cells control crystallization using chemical reaction networks that offset depletion by synthesizing or activating monomers to regulate monomer concentration, stabilizing growth conditions even as depletion rates change, and thus reliably yielding desired products. Using DNA nanotubes as a model system, here we show that coupling a generic reversible bimolecular monomer buffering reaction to a crystallization process leads to reliable growth of large, uniformly sized crystals even when crystal growth rates change over time. Buffering could be applied broadly as a simple means to regulate and sustain batch crystallization and could facilitate the self-assembly of complex, hierarchical synthetic structures.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
A Sparse Tensor Benchmark Suite for CPUs and GPUs
Tensor computations present significant performance chal- lenges that impact a wide spectrum of applications ranging from machine learning, healthcare analytics, social network analysis, data mining to quantum chemistry and signal processing. Efforts to improve the perfor- mance of tensor computations include exploring data layout, execution scheduling, and parallelism in common tensor kernels. This work presents a benchmark suite for arbitrary-order sparse tensor kernels using state- of-the-art tensor formats: coordinate (COO) and hierarchical coordinate (HiCOO) on CPUs and GPUs. It presents a set of reference tensor kernel implementations that are compatible with real-world tensors and power law tensors extended from synthetic graph generation techniques. We also propose Roofline performance models for these kernels to provide insights of computer platforms from sparse tensor view. This benchmark suite along with the synthetic tensor generator is publicly available.
Li, Jiajia↗
STOCHASTIC OPTIMAL POWER FLOW FOR REAL-TIME MANAGEMENT OF DISTRIBUTED RENEWABLE GENERATION AND DEMAND RESPONSE (Final Report)
To meet the grand challenge of a sustainable energy future, there has been a surge of interest in renewable energy. Today, the uncertainty associated with renewable resources is handled by using operating reserves. The high penetration of renewable resources, however, introduces difficult-to-control dynamics and challenges for power system operation. Decision support tools are necessary at the bulk system operational level to recognize and efficiently utilize renewable resources and distributed demand response products in concert with traditional grid resources. It is envisaged that responsive load can potentially have very significant cost advantages over either spinning or non-spinning ramping reserve. Critical decisions are made during hour(s)-ahead and real-time power system operation regarding the commitment and dispatch of generators to ensure power delivery is both reliable and economic. These decisions are typically made by a security constrained optimal flow, which determines future generator commitments, dispatches, and ensures adequate reserves are available in the event of a contingency (unexpected outage) or if future system conditions deviate from forecasts. However, security has been always based on a pre-specified subset of contingency constraints whose enforcement does not guarantee security under all possible future possibilities while also giving little or no weight to the likelihood of each contingent event or the severity of its consequences. Existing tools, which are based exclusively on deterministic optimization models, do not yield optimal operational decisions to address these new challenges, in terms of both reliability and cost-effectiveness. This project has focused on developing a stochastic optimal power flow (SOPF) framework, which integrates renewable resource uncertainty, load uncertainty, distributed storage (DS), demand response (DR) products, in a holistic manner to address the uncertainty associated with ever-increasing renewable resources, along with the inclusion of distributed demand response products in future power systems. A proof-of-concept problem was created using the Pennsylvania-Jersey-Maryland (PJM) power system network. Synthetic wind generation was added to the system to simulate 50% wind penetration. A 1-hour test of SOPF operation indicated more than 6% operational cost savings. The project continued by adding the Midwestern Independent System Operator (MISO) as a partner, with focus shifting from SOPF to Stochastic Look-Ahead Unit Commitment (SLAC). Unlike PJM, MISO is faced with significant renewable energy resources within its footprint and is challenged with substantial uncertainty in its operations. The SLAC distinguishes itself from existing tools that operators use. At best, today’s tools solve two to three cases independently, where one or two system parameters, such as forecasted load level (e.g., a low, base, and high forecast), are varied and the resulting scenarios are analyzed independently. The stochastic-based optimization of SLAC leverages statistical information from an ensemble of potential operational scenarios and their respective likelihood. The SLAC output can be translated into valuable information to the operator such as suggested commitments, optimal scheduling and dispatch of resources, reserve requirements at both locational and zonal resolutions, ramping availability and requirements, availability of demand response including operational guidance concerning the near-term and real-time coordination between distributed energy resources, and utilization of distributed storage resources. The developed SOPF/SLAC tool, a stand-alone tool compatible with existing EMSs, will provide system operators with unprecedented visibility, flexibility and predictability to these resources and operational guidance concerning the real-time coordination between DERs and DR/DS products. The game changing and practical impact of this disruptive technology will be dramatic and will usher in a new era in the electric power industry, wherein green energy concepts are fully embraced, and electric power costs are lowered throughout the nation.
42 ENGINEERING↗
Optimization of Integrated Energy Systems
Integrated energy systems that couple nuclear power plants with additional products including hydrogen, storage, or synthetic fuels provide a more flexible energy source that can be more economical than generating electricity alone. Determining the size and shape of these systems and optimizing their operation is challenging. INL, through the IES program, has developed optimization software to help solve these challenges. Holistic Energy Resource Optimization Network (HERON) is a software tool to optimize the size and capacity of integrated energy systems using stochastic optimization. Optimization of Real-time Capacity Allocation (ORCA) is a software tool under development to perform real-time economic optimization of these systems using economic model predictive control. An overview of these tools and a discussion of their optimization methods will be presented in this talk.
97 MATHEMATICS AND COMPUTING↗
Deep Learning Experiments for Tropical Cyclone Intensity Forecasts
Reducing tropical cyclone (TC) intensity forecast errors is a challenging task that has interested the operational forecasting and research community for decades. To address this, we developed a deep learning (DL)-based multilayer perceptron (MLP) TC intensity prediction model. The model was trained using the global Statistical Hurricane Intensity Prediction Scheme (SHIPS) predictors to forecast the change in TC maximum wind speed for the Atlantic basin. In the first experiment, a 24-h forecast period was considered. To overcome sample size limitations, we adopted a leave one year out (LOYO) testing scheme, where a model is trained using data from all years except one and then evaluated on the year that is left out. When tested on 2010–18 operational data using the LOYO scheme, the MLP outperformed other statistical–dynamical models by 9%–20%. Additional independent tests in 2019 and 2020 were conducted to simulate real-time operational forecasts, where the MLP model again outperformed the statistical–dynamical models by 5%–22% and achieved comparable results as HWFI. The MLP model also correctly predicted more rapid intensification events than all the four operational TC intensity models compared. In the second experiment, we developed a lightweight MLP for 6-h intensity predictions. When coupled with a synthetic TC track model, the lightweight MLP generated realistic TC intensity distribution in the Atlantic basin. Therefore, the MLP-based approach has the potential to improve operational TC intensity forecasts, and will also be a viable option for generating synthetic TCs for climate studies.
58 GEOSCIENCES↗
Using porous random fields to predict the elastic modulus of unoxidized and oxidized superfine graphite
Nuclear graphite is a candidate material for Generation IV nuclear power plants. Porous materials such as graphite can contain complex networks of pores that influence the material's mechanical and irradiation response. A methodology known as the random finite element method (RFEM) was adapted to create synthetic microstructures and predict the influence of porosity on the elastic properties of graphite during oxidation. RFEM combines random field theory and the finite element method in a Monte Carlo framework to estimate the mechanical response of a given grade of graphite. In this research, the random fields were verified through experimental characterization to predict the elastic response of three nuclear graphite grades, ETU-10, IG-110, and 2114. Finite element models (FEM) were generated using segmentations of x-ray computed tomography (XCT) data known as image-based models (IBMs) to validate and compare with the RFEM results and better understand the effects of uniform oxidation in these graphite grades. The RFEM predictions appear to correlate well with the experimental values of the measured Young’s modulus of the three graphite grades and display the same trends as IBMs.
11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗