Search NASA⌕ Search

SEARCH · Search NASA

Results for “long memory”

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 217 records · Page 12

Equation‐Free Surrogate Modeling of Geophysical Flows at the Intersection of Machine Learning and Data Assimilation

Abstract There is a growing interest in developing data‐driven reduced‐order models for atmospheric and oceanic flows that are trained on data obtained either from high‐resolution simulations or satellite observations. The data‐driven models are non‐intrusive in nature and offer significant computational savings compared to large‐scale numerical models. These low‐dimensional models can be utilized to reduce the computational burden of generating forecasts and estimating model uncertainty without losing the key information needed for data assimilation (DA) to produce accurate state estimates. This paper aims at exploring an equation‐free surrogate modeling approach at the intersection of machine learning and DA in Earth system modeling. With this objective, we introduce an end‐to‐end non‐intrusive reduced‐order modeling (NIROM) framework equipped with contributions in modal decomposition, time series prediction, optimal sensor placement, and sequential DA. Specifically, we use proper orthogonal decomposition (POD) to identify the dominant structures of the flow, and a long short‐term memory network to model the dynamics of the POD modes. The NIROM is integrated within the deterministic ensemble Kalman filter (DEnKF) to incorporate sparse and noisy observations at optimal sensor locations obtained through QR pivoting. The feasibility and the benefit of the proposed framework are demonstrated for the NOAA Optimum Interpolation Sea Surface Temperature (SST) V2 data set. Our results indicate that the NIROM is stable for long‐term forecasting and can model dynamics of SST with a reasonable level of accuracy. Furthermore, the prediction accuracy of the NIROM gets improved by almost one order of magnitude by the DEnKF algorithm.

Pawar, Suraj↗

A phononic interface between a superconducting quantum processor and quantum networked spin memories

We introduce a method for high-fidelity quantum state transduction between a superconducting microwave qubit and the ground state spin system of a solid-state artificial atom, mediated via an acoustic bus connected by piezoelectric transducers. Applied to present-day experimental parameters for superconducting circuit qubits and diamond silicon-vacancy centers in an optimized phononic cavity, we estimate quantum state transduction with fidelity exceeding 99% at a MHz-scale bandwidth. By combining the complementary strengths of superconducting circuit quantum computing and artificial atoms, the hybrid architecture provides high-fidelity qubit gates with long-lived quantum memory, high-fidelity measurement, large qubit number, reconfigurable qubit connectivity, and high-fidelity state and gate teleportation through optical quantum networks.

47 OTHER INSTRUMENTATION↗

Phononic bus for coherent interfaces between a superconducting quantum processor, spin memory, and photonic quantum networks

A hybrid quantum system performs high-fidelity quantum state transduction between a superconducting (SC) microwave qubit and the ground state spin system of a solid-state artificial atom. This transduction is mediated via an acoustic bus connected by piezoelectric transducers to the SC microwave qubit. For SC circuit qubits and diamond silicon vacancy centers in an optimized phononic cavity, the system can achieve quantum state transduction with fidelity exceeding 99% at a MHz-scale bandwidth. By combining the complementary strengths of SC circuit quantum computing and artificial atoms, the hybrid quantum system provides high-fidelity qubit gates with long-lived quantum memory, high-fidelity measurement, large qubit number, reconfigurable qubit connectivity, and high-fidelity state and gate teleportation through optical quantum networks.

Englund, Dirk Robert↗

T-FSM: A Scalable Distributed Task-Based System for Frequent Subgraph Pattern Mining from a Big Graph

Finding frequent subgraph patterns in a big graph is an important problem with many applications such as classifying chemical compounds and building indexes to speed up graph queries. Since this problem is NP-hard, some recent parallel and distributed systems have been developed to accelerate the mining. However, they often have a huge memory cost, very long running time, suboptimal load balancing, poor scale-out capability, and possibly inaccurate results. In this article, we propose an efficient system called T-FSM for parallel mining of frequent subgraph patterns in a big graph. T-FSM supports a new anti-monotonic frequentness measure called Fraction-Score, which is more accurate than the widely used MNI measure. The execution engine of T-FSM supports both intra-machine parallelism and inter-machine parallelism. For intra-machine parallelism, T-FSM adopts a novel task-based execution model to ensure high multithreading concurrency, bounded memory consumption, and effective load balancing. For inter-machine parallelism, T-FSM ensures good scale-out performance with a lightweight pattern rebalancing approach that reduces workload skewness of pattern evaluations among machines. To avoid recomputing the contexts for migrated patterns, we design a novel context cache table to support concurrent and asynchronous requesting and caching of remote context data, which can timely evict and garbage collect used pattern contexts that are no longer needed to keep memory consumption bounded. Extensive experiments show that T-FSM is orders of magnitude faster than existing state-of-the-art parallel systems (more than 10×, 51×, 131×, 55× speedup over ScaleMine, DistGraph, Pangolin and Peregrine, respectively) and distributed systems (more than 42× and 88× over ScaleMine and DistGraph, respectively) for frequent subgraph pattern mining, and it scales out satisfactorily to 512 CPU cores on the Polaris supercomputer at Argonne National Laboratory.

97 MATHEMATICS AND COMPUTING↗

Development of novel dynamic machine learning-based optimization of a coal-fired power plant

The increasing fraction of intermittent renewable energy in the electrical grid is resulting in coal-fired boilers now routinely ramp up and down. The current state-of-the-art operation for such boilers is to apply steady-state, neural network-based optimization to make control decisions in real-time, and this report demonstrates the feasibility of extending this to dynamic, neural network-based optimization using a long short-term memory neural network. A simplified numerical simulation of a t-fired coal boiler and supporting equipment is used to represent a real plant subjected to both steady-state, neural network-based optimization and dynamic, neural network-based optimization. Using the same intervals and a particle swarm optimization algorithm, the dynamic optimization outperforms the steady-state optimization and realizes up to 4.58% improvement in thermal efficiency. Dynamic optimization with a long short-term memory neural network is shown to both be feasible and beneficial for operation of a coal-fired boiler under changing load.

42 ENGINEERING↗

Reduced Dynamics of Full Counting Statistics

We present a theory of modified reduced dynamics in the presence of counting fields. Reduced dynamics techniques are useful for describing open quantum systems at long emergent timescales when the memory timescales are short. However, they can be difficult to formulate for observables spanning the system and its environment, such as those characterizing transport properties. A large variety of mixed system--environment observables, as well as their statistical properties, can be evaluated by considering counting fields. Given a numerical method able to simulate the field-modified dynamics over the memory timescale, we show that the long-lived full counting statistics can be efficiently obtained from the reduced dynamics. We demonstrate the utility of the technique by computing the long-time current in the nonequilibrium Anderson impurity model from short-time Monte Carlo simulations.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

FLYING SERVING: On-the-Fly Parallelism Switching for Large Language Model Serving

Production LLM serving must simultaneously deliver high throughput, low latency, and sufficient context capacity under non-stationary traffic and mixed request requirements. Data parallelism (DP) maximizes throughput by running independent replicas, while tensor parallelism (TP) reduces per-request latency and pools memory for long-context inference. However, existing serving stacks typically commit to a static parallelism configuration at deployment; adapting to bursts, priorities, or long-context requests is often disruptive and slow. We present Flying Serving, a vLLM-based system that enables online DP-TP switching without restarting engine workers. Flying Serving makes reconfiguration practical by virtualizing the state that would otherwise force data movement: (i) a zero-copy Model Weights Manager that exposes TP shard views on demand, (ii) a KV Cache Adaptor that preserves request KV state across DP/TP layouts, (iii) an eagerly initialized Communicator Pool to amortize collective setup, and (iv) a deadlock-free scheduler that coordinates safe transitions under execution skew. Across three popular LLMs and realistic serving scenarios, Flying Serving improves performance by up to 4.79 × under high load and 3.47 × under low load while supporting latency- and memory-driven requests.

Gao, Shouwei [ORNL]↗

Timescales of Soil Moisture Anomalies: Results from Two GCMs

Soil moisture anomalies dissipate over timescales that may span weeks to months. Characterizing the geographical and seasonal variations in these timescales can have important practical benefit; significant soil moisture "memory" allows long-lead forecasts of soil moisture, which have been found in recent studies to be essential for useful Ion--lead forecasts of precipitation in many regions. In this talk, we will present and compare the soil moisture timescales derived in two separate general circulation model (GCM) studies. Both studies employ multiple ensembles of short-term climate simulations. Timescales at a given point are effectively estimated by determining how quickly the soil moisture distribution generated in one ensemble of simulations (characterized by a unique set of initial soil moisture conditions) approaches that produced by another ensemble (characterized by a different set of initial soil moisture conditions). The talk will include a discussion of why the timescales produced by the two GCMs differ in some regions, and it will also describe the impact of soil moisture memory on simulated precipitation.

Koster, Randal D.↗

Optimization and Parallelization of the Thermal-Hydraulic Sub-channel Code CTF for High-Fidelity Multi-physics Applications

This paper describes major improvements to the computational infrastructure of the CTF sub-channel code so that full-core sub-channel-resolved simulations can now be performed in much shorter run-times, either in stand-alone mode or as part of coupled-code multi-physics calculations. These improvements support the goals of the Department Of Energy (DOE) Consortium for Advanced Simulations of Light Water (CASL) Energy Innovation Hub to develop high fidelity multi-physics simulation tools for nuclear energy design and analysis. A set of serial code optimizations--including fixing computational inefficiencies, optimizing the numerical approach, and making smarter data storage choices--are first described and shown to reduce both execution time and memory usage by about a factor of ten. Next, a Single Program Multiple Data (SPMD) parallelization strategy targeting distributed memory Multiple Instruction Multiple Data (MIMD) platforms and utilizing domain-decomposition is presented. In this approach, data communication between processors is accomplished by inserting standard MPI calls at strategic points in the code. The domain decomposition approach implemented assigns one MPI process to each fuel assembly, with each domain being represented by its own CTF input file. The creation of CTF input files, both for serial and parallel runs, is also fully automated through use of a pre-processor utility that takes a greatly reduced set of user input over the traditional CTF input file. To run CTF in parallel, two additional libraries are currently needed; MPI, for inter-processor message passing, and the Parallel Extensible Toolkit for Scientific Computation (PETSc), which is leveraged to solve the global pressure matrix in parallel. Results presented include a set of testing and verification calculations and performance tests assessing parallel scaling characteristics up to a full core, sub-channel-resolved model of Watts Bar Unit 1 under hot full-power conditions (193 17x17 assemblies, ~56,000 pins, ~59,000 sub-channels, ~2.8 million thermal-hydraulic (TH) control volumes). Results demonstrate that CTF can now perform full core analysis (not previously possible due to excessively long runtimes and memory requirements) on the order of 20 minutes. This new capability is not only useful to standalone CTF users, but is also being leveraged in support of coupled code multi-physics calculations being done in the CASL program.

COBRA-TF↗

Machine Learning Assisted Reservoir Operation Model for Long–Term Water Management Simulation

This study explores strategies for long-term reservoir simulations by combining generic rule-based reservoir management model (RMM) and machine learning (ML) models for two major multipurpose reservoirs — Allatoona Lake and Lake Sidney Lanier in the southeastern United States. First, a standalone RMM is developed to simulate daily release and storage during Water Year 1981–2015. Next, using Long-Short Term Memory (LSTM) as the ML technique, a standalone LSTM model is trained based on reservoir inflow and meteorological observations to simulate reservoir release and estimate reservoir storage through water balance calculation. Three hybrid modeling strategies are developed, one using RMM output as an additional LSTM input (H1), another using LSTM as the initial release estimate in RMM (H2), and the third combining the first two strategies (H3). The Nash–Sutcliffe efficiency (NSE) for release (NSE-r), storage (NSE-s), and their mean (NSE-avg) are used for model evaluation. Overall, H1 improves NSE-r to 0.65 and 0.54 for Allatoona and Lanier, respectively, compared to standalone RMM (0.44 and 0.21); however, its storage trajectory did not produce a physically feasible solution, similar to LSTM. H2 and especially H3 show that they can retain the best features from RMM and LSTM, with H3 NSE-avg being 0.695 and 0.55 for Allatoona and Lanier outperforming RMM (0.615 and 0.29). In conclusion, the findings suggest a robust simulation capacity for large-scale water management in future studies.

54 ENVIRONMENTAL SCIENCES↗

Dynamic Control of Sodium Cold Trap Purification Temperature Using LSTM System Identification

This study investigates the dynamic regulation of the sodium cold trap purification temperature at Argonne National Laboratory’s liquid sodium test facility, employing long short-term memory (LSTM) system identification techniques. The investigation introduces an innovative hybrid approach by integrating model predictive control (MPC) based on first principles dynamic models with a multi-step time–frequency LSTM model in predicting the temperature profiles of a sodium cold trap purification system. The long short-term memory–model predictive controller (LSTM-MPC) model employs a sliding window scheme to gather training samples for multi-step prediction, leveraging historical data to construct predictive models that capture the non-linearities of the complex system dynamics without explicitly modeling the underlying physical processes. The performance of the LSTM-MPC and MPC were evaluated through simulation experiments, where both models were assessed on their capacity to maintain the cold trap temperature within predefined set-points while minimizing deviations and overshoots. Results obtained show how the data-driven LSTM-MPC model demonstrates stability and adaptability. In contrast, the traditional MPC model exhibits irregularities, particularly evident as overshoots around set-point limits, which can potentially compromise its effectiveness over long prediction time intervals. The findings obtained offer valuable insights into integrating data-driven techniques for enhancing real-time monitoring systems.

LSTM-MPC↗

Why it is Unfortunate that Linear Machine Learning “Works” so well in Electromechanical Switching of Ferroelectric Thin Films

Machine learning (ML) is relied on for materials spectroscopy. It is challenging to make ML models fail because statistical correlations can mimic the physics without causality. Here, using a benchmark band-excitation piezoresponse force microscopy polarization spectroscopy (BEPS) dataset the pitfalls of the so-called “better”, “faster”, and “less-biased” ML of electromechanical switching are demonstrated and overcome. Using a toy and real experimental dataset, it is demonstrated how linear nontemporal ML methods result in physically reasonable embedding (eigenvalues) while producing nonsensical eigenvectors and generated spectra, promoting misleading interpretations. A new method of unsupervised multimodal hyperspectral analysis of BEPS is demonstrated using long-short-term memory (LSTM) β-variational autoencoders (β-VAEs) . By including LSTM neurons, the ordinal nature of ferroelectric switching is considered. Further, to improve the interpretability of the latent space, a variational Kullback–Leibler-divergency regularization is imposed . Finally, regularization scheduling of β as a disentanglement metric is leveraged to reduce user bias. Combining these experiment-inspired modifications enables the automated detection of ferroelectric switching mechanisms, including a complex two-step, three-state one. Ultimately, this work provides a robust ML method for the rapid discovery of electromechanical switching mechanisms in ferroelectrics and is applicable to other multimodal hyperspectral materials spectroscopies.

36 MATERIALS SCIENCE↗

Structure‐Aware Representation Learning for Effective Performance Prediction

ABSTRACT Application performance is a function of several unknowns stemming from the interactions between the application, runtime, OS, and underlying hardware, making it challenging to model performance using deep learning techniques, especially without a large labeled dataset. Collecting such labeled longitudinal datasets can take weeks. Intuitively, developers could save analysis time during code development by taking a comparative approach between multiple applications. However, the unknown dynamic interactions between applications and execution environments make it difficult for deep learning‐based models to predict the performance of new applications. In this paper, we address these problems by presenting a labeled dataset for the community and taking a comparative analysis approach to explore the source code differences between different correct implementations of the same problem. This paper assesses the feasibility of using purely static information, for example, Abstract Syntax Tree (AST), of applications to predict performance change based on code structure. We evaluate several deep learning‐based representation learning techniques for source code and propose an architecture for the tree‐based Long Short‐Term Memory (LSTM) models to discover latent representations for a source code's hierarchical structure. We demonstrate that our proposed architecture enables feed‐forward predictive models to predict change in performance using source code with up to 84% accuracy.

Ramadan, Tarek [Department of Computer Science Tex↗

Effects of input gradient regularization on neural networks time-series forecasting of thermal power systems

This study proposes using neural networks, specifically gated recurrent unit (GRU), long-short-term memory (LSTM), and transformer networks, to improve control strategies in a 450 MW coal-fired power plant. However, neural networks face issues of becoming overly dependent on just a few variables to make predictions, which negatively impacts control decisions that rely on the model to determine the value of all manipulated variables. The paper introduces regularization techniques, including noise injection and input gradient regularization, during the training phase. Here, the work presents novel contributions in adapting neural networks to control industrial systems and applying regularization techniques from computer vision to industrial process control. Results demonstrate the effectiveness of input gradient regularization in reducing model dependence on subsets of variables, emphasizing the balance between fidelity and controllability. Further exploration is recommended, including the development of recurrent transformers, closed-loop control testing, and a sensitivity analysis on computer models to provide further insight.

20 FOSSIL-FUELED POWER PLANTS↗

Time series anomaly detection in power electronics signals with recurrent and ConvLSTM autoencoders

The anomalies in the high voltage converter modulator (HVCM) remain a major down time for the spallation neutron source facility, that delivers the most intense neutron beam in the world for scientific materials research. In this work, we propose neural network architectures based on Recurrent AutoEncoders (RAE) to detect anomalies ahead of time in the power signals coming from the HVCM. Bi-directional gated recurrent unit, bi-directional long-short term memory (LSTM), and convolutional LSTM (ConvLSTM) are developed, trained, and tested using real experimental signals from the HVCM module. The results show a good performance of the proposed RAE models, achieving precision up to 91%, recall up to 88%, false omission rate as low as 20% (i.e. 80% of the anomalies were detected), and area under the ROC curve up to 0.9. The three RAE models provide very comparable performance, with LSTM showing slightly better performance than GRU and ConvLSTM. The RAE models are benchmarked against other anomaly detection methods, including isolation forest, support vector machine, local outlier factor, feedforward and convolutional autoencoders, and others; showing a better performance. Here, the results of this study demonstrate the promising potential of RAE in anomaly detection for real-world power systems, and for increasing the reliability of the HVCM modules in the spallation neutron source.

42 ENGINEERING↗

Variational data augmentation for a learning-based granular predictive model of power outages

As the trend in climate change continues, extreme weather events are expected to occur with increasing frequency and severity and pose a significant threat to the electric power infrastructure. Regardless of the efforts a utility puts towards hardening the grid, storm-induced damage to the utility assets such as cables and distributed energy resources (DERs) that are particularly vulnerable to such events is unavoidable. Access to a highly granular, in space and time, outage forecasting tool with long lead times (i.e., days ahead) will enhance the efficiency of service restoration efforts. Here, in this study, we propose to develop and implement a multi-model framework as an operational tool based on a granular and multi-day outage forecasting model using operational numerical weather prediction model forecasts and detailed component outage information. An innovative two-layered recurrent neural network, i.e., a long-short-term-memory (LSTM)-based variational autoencoder (VAE) framework and a sliding window are used to address the uneven distribution of different types of weather events and make better use of the time-series data. Case studies are performed to demonstrate the performance of the new framework.

54 ENVIRONMENTAL SCIENCES↗

GrainGNN: A dynamic graph neural network for predicting 3D grain microstructure

We propose GrainGNN, a surrogate model for the evolution of polycrystalline grain structure under rapid solidification conditions in metal additive manufacturing. High fidelity simulations of solidification microstructures are typically performed using multicomponent partial differential equations (PDEs) with moving interfaces. The inherent randomness of the PDE initial conditions (grain seeds) necessitates ensemble simulations to predict microstructure statistics, e.g., grain size, aspect ratio, and crystallographic orientation. Here, currently such ensemble simulations are prohibitively expensive and surrogates are necessary.In GrainGNN, we use a dynamic graph to represent interface motion and topological changes due to grain coarsening. We use a reduced representation of the microstructure using hand-crafted features; we combine pattern finding and altering graph algorithms with two neural networks, a classifier (for topological changes) and a regressor (for interface motion). Both networks have an encoder-decoder architecture; the encoder has a multi-layer transformer long-short-term-memory architecture; the decoder is a single layer perceptron.We evaluate GrainGNN by comparing it to high-fidelity phase field simulations for in-distribution and out-of-distribution grain configurations for solidification under laser power bed fusion conditions. GrainGNN results in 80%–90% pointwise accuracy; and nearly identical distributions of scalar quantities of interest (QoI) between phase field and GrainGNN simulations compared using Kolmogorov-Smirnov test. GrainGNN's inference speedup (PyTorch on single x86 CPU) over a high-fidelity phase field simulation (CUDA on a single NVIDIA A100 GPU) is 150×–2000× for 100-initial grain problem. Further, using GrainGNN, we model the formation of 11,600 grains in 220 seconds on a single CPU core.

36 MATERIALS SCIENCE↗

Can artificial intelligence and data-driven machine learning models match or even replace process-driven hydrologic models for streamflow simulation?: A case study of four watersheds with different hydro-climatic regions across the CONUS

With recent developments in computational techniques, Data-driven Machine Learning Models (DMLs) have shown great potential in simulating streamflow and capturing the rainfall-runoff relationship in given watersheds, which are traditionally fulfilled by Process-based Hydrologic Models (PHMs). There are debates on whether the DMLs can outperform and possibly replace the classical PHMs for streamflow simulation and river forecasting, but no clear conclusions have been made. This study aims to investigate whether the newer DMLs have any potential in further improving the simulation accuracy of classical PHMs, and vice versa. To do this, we compared a few popular PHMs and DMLs over four watersheds across the Continental US (CONUS) that are associated with different input, climate, and regional conditions. A total of five hydrologic models were chosen, including (1) two classical lumped models, i.e., the Sacramento Soil Moisture Accounting (SAC-SMA) and Xinanjiang (XAJ); (2) one modern distributed model, termed Coupled Routing and Excess Storage (CREST); (3) and two DMLs including an Artificial Neural Networks (ANN) and a deep learning model, termed Long Short Term Memory (LSTM). Our results demonstrated that the DMLs still significantly biased when using the baseline input scenario with the PHMs. However, the DMLs fed with delayed input scenarios had great potential and can reach high simulation accuracy. The DMLs, especially the ANN, outperformed other employed models under the rainfall-runoff relationship in which rainfall dominantly drives. Furthermore, the DMLs also showed better performance in the high-flow regime, while the PHMs had a better performance for the low-flow regime, implying both PHMs and DMLs have their own merits and are worthy of joint development. In general, our study indicated a great potential of using DMLs to simulate streamflow, but further studies are still needed to verify the transferability and scalability of DMLs in large-scale experiments, such as the Distributed Model Intercomparison Projects 1&2 conducted by National Weather Services but to compare modern DMLs and PHMs.

58 GEOSCIENCES↗