Search NASA⌕ Search

SEARCH · Search NASA

Results for “Data Architecture & Analytics”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Integrated Operations for Nuclear: Work Reduction Opportunity Demonstration

Integrated Operations for Nuclear: Work Reduction Opportunity Demonstration The DI BCA document also identifies specific, digitally enabled WRO categories for further study. These were selected as most relevant by Reference Plant personnel from a larger list of WRO areas identified across the nuclear industry as captured INL/RPT-21-64134, “Process for Significant Nuclear Work Function Innovation Based on Integrated Operations Concepts.” This ION WRO demonstration report was developed to provide illustrative, specific, and actionable direction for intertwined PTPG changes associated with digital modernization efforts. The coordinated changes in these areas are intended to maximize safe plant operational and economic performance. This includes enabling WROs associated with detailed configuration, implementation, and use of digital systems and how they are supported over their lifecycle. Illustrating this direction through a minimum set of advanced technology examples establishes a model PTPG framework that can be leveraged across the spectrum of nuclear plant digital modernization efforts going forward. This document addresses many related concepts. To promote an integrated understanding of the topics that make up this work, this document contains an extensive set of internal hyperlinks. This set includes hyperlinks to page numbers in the table of contents, section numbers, items in lists, figures, tables, and references to other documents within the report. When hovering the cursor above hyperlinked text in Adobe, the cursor will change from “ ” to “ .” When the “ ” appears, a left mouse click will take the reader to the referenced location in the document. To return to the original location in the document, the reader need only press and hold the “alt” button on the keyboard and then simultaneously press the “<” directional key on the keyboard.

42 ENGINEERING↗
DOE OSTI2024

DICER: Data Intensive Computing Environment and Runtime for Evaluating Unprecedented Scale of Geospatial-Temporal Human Mobility Data

With the significant increase in sources and volume of human mobility data through commercial data vendors as well as microsimulation of cities, the scale of geospatial-temporal data to analyze and assess for mobility characterization has grown to the level of Big Data. There are mobility related commercial organizations deploying scalable computing, but often the system architecture, workflow, and intermediate processing components are not fully disclosed in relevant scope. Current research literature has a notable lack of studies demonstrating architectures and workflows for human mobility analytics that are implemented on a TeraByte scale of geospatial-temporal data. In this context, this paper presents a hyperscale-level system solution named DICER (Data Intensive Computing Environment and Runtime) for processing and analytics of geospatial-temporal data at big data scale. Although the cluster computing architecture of DICER with Apache Spark job running on Kubernetes cluster is not new, there are innovations in the workflow, hierarchical processing logic, and a wide range of intermediate preprocessing and mobility metrics calculation. We have performed case studies to validate the effectiveness of DICER system solution by performing detailed analytics and assessment of human mobility microsimulation output at three different scopes and scale, including a usecase with 16.97 TeraByte and 259.2 Billion rows of data. In addition, we have presented another case study of utilizing DICER to perform the same mobility processing and comparative analytics on large-scale commercially available geospatial-temporal data. All these case studies validate the efficiency and usefulness of DICER in computing population mobility characteristics from geospatial-temporal trajectory data at an unprecedented scale (not only just data volume, but also combination of: number of user entities, temporal frequency, spatial resolution, data duration).

De, Debraj↗
DOE OSTI2024

WELLBASE - An Interactive Platform for Wellbore Material Assessment

This project seeks to build an open-source wellbore material data repository with adequate material performance and contextual data to support Geological Carbon Storage (GCS). By appropriately evaluating the data types as mentioned earlier made available by the WELLBASE tool, stakeholders can make more informed decisions regarding well selections, risk assessment, and economic analysis for geologic carbon storage projects. Advanced Natural Language Processing models and other custom python scripts will be deployed in an automated process to extract unstructured data from documents, reports, and web applications and subsequently parse to more usable formats. The processed data will then be integrated into a robust and comprehensive database architecture, optimizing data accessibility, and usability for analytical purposes. The final data products will be accessible through a user-friendly visualization platform that will allow users to query and visualize the data, as well as download data in usable formats.

Tetteh, Daniel A.↗
DOE OSTI2024

Multi-Scale Integrated Monitoring System for Enhancing Methane Emission Detection, Quantification & Prediction

This report details the progress and findings of a comprehensive study on reviewing existing solutions, identifying technology gaps, and formulating an “all-in-one” integrated strategy for developing the next-generation multiscale methane monitoring and modeling platform, conducted under grant number DE-FE0032292. Co-led by Dr. David Ebert, Dr. Binbin Weng, and Dr. Chenghao Wang at the University of Oklahoma, the project’s goal was to develop an integrated approach for building this engineering platform to detect, quantify, and mitigate methane emissions across various temporal scale, spatial scales, and sectors. The planning grant study began with an extensive review of various methane sensing and monitoring technologies and systems, surveying over 100 technology providers globally. This review revealed the prevalence of optical methods over chemical methods in commercially available sensors, with Non-Dispersive Infrared (NDIR), Tunable Diode Laser Absorption Spectroscopy (TDLAS), and Optical Gas Imaging (OGI) cameras being the most prevalent options. A trend towards more advanced optical techniques was observed, driven by increased regulatory focus and technological advancements. The technical evaluation of these sensing technologies provided crucial insights into their capabilities and limitations. The study examined emerging technologies such as Differential Absorption LiDAR (DIAL), which show promise for high-precision and long-range detection. The team then investigated the features and application bandwidth of various sensing platforms, including handheld, fixed/stationary, mobile, aerials, and spaceborne monitors. Pilot field studies were conducted to assess the capabilities of solutions for different emission scenarios. Field work with sensor deployments was conducted at three distinct site types: an oil & gas industry site, a cattle ranching operation, and a waste processing facility. The team also conducted a thorough review of methane flux inverse modeling approaches, focused on physically based methods. These approaches were categorized into simple, intermediate, and advanced methods. A realtime WRF-GHG (Weather Research and Forecasting-Greenhouse Gas) modeling system was developed and applied, incorporating multiple data sources to guide field experiments and inform methane plume detection. The project identified and analyzed numerous categories of methane data sources, including satellite measurements, ground-based sensors, and inventory databases. Key platforms examined include EDGAR, EPA GHGI, NASA TROPOMI, Carbon Mapper, and Climate TRACE, among others. The team proposed an architecture for a comprehensive methane monitoring platform. This system incorporates multi-source data acquisition, advanced data processing and assimilation, interactive visualization tools, and analytical capabilities for emissions forecasting and scenario analysis. The proposed platform aims to provide a user-friendly interface catering to various stakeholders, from researchers to policymakers. The architecture includes sophisticated data ingestion methods, a centralized data warehouse, and advanced analytical tools for data fusion and interpretation. To ensure the relevance and effectiveness of the proposed system, a comprehensive survey was conducted to gather stakeholder input on system requirements. Key findings include a strong need for integrating various data types and formats, a preference for real-time data updates and advanced visualization tools, and a demand for user-friendly interfaces catering to different expertise levels.

03 NATURAL GAS↗
DOE OSTI2025

Network Slicing for Federated Learning in Operational Technology Environment

Industrial Control Systems (ICS) and Supervisory Control and Data Acquisition (SCADA) environments are essential to modern infrastructure, facing challenges in ensuring low-latency, high-throughput communication while mitigating cyber threats. This paper presents a framework integrating Federated Learning (FL) and network slicing with Quality of Service (QoS) to enable real-time monitoring without disrupting OT operations. Leveraging digital twin technology and Network Function Virtualization (NFV), the architecture supports predictive analytics and Industry 4.0 requirements. FL facilitates decentralized model training, preserving data privacy and scalability, though it introduces potential throughput constraints. Network slicing addresses this by creating dedicated virtualized segments optimized for performance and security. Advanced fault tolerance at the container and instance levels enhances system reliability. The proposed architecture ensures high throughput, low latency, and secure orchestration for real-time anomaly detection in OT networks. Performance evaluations validate its efficiency in throughput, deployment, and learning accuracy, providing a robust foundation for future ICS automation and data-driven decision-making.

Delgado, Brian G. Rodiles [University of Texas at ↗
DOE OSTI2026

Three-Dimensional Grid Visualization for Planning Activities: A Dubai Case Study

National Laboratory of the Rockies (NLR), in collaboration with the Dubai Electricity and Water Authority (DEWA) and Infra-X, has undertaken the Energy Visualization Analysis Project. The aim of this project is to enhance analytical and 3D visualization capabilities for distribution network planning and renewable energy integration. As modern grid continues to evolve with large-scale solar PV deployment and emerging distributed energy resources (DERs), the ability to effectively analyze, visualize, and communicate complex grid behaviors has become increasingly critical. The project focuses on developing empirical use cases based on real distribution feeder data and engineering workflows, ensuring the outcomes are directly aligned with operational environment. Through time-series power flow simulations and nodal hosting capacity analysis, the study quantifies the impacts of high PV penetration on voltage and thermal limits within representative 11 kV feeders. These analyses identify specific nodes and conditions where DER integration challenges arise. Furthermore, a Battery Energy Storage System (BESS) optimization algorithm was applied to determine the optimal size and placement of storage systems that can mitigate network constraints and enhance hosting capacity. The comparative results between base-case and BESS-augmented scenarios clearly demonstrate improvements in network stability and load management efficiency. In parallel, the NLR team developed an immersive 3D visualization framework, enabling interactive exploration of grid simulations using commodity head-mounted display (HMD) systems. This framework transforms conventional 2D simulation data into spatially intuitive visual environments - allowing engineers to analyze feeder conditions, PV hosting potential, and BESS effects in real time. This report represents the first foundational phase in establishing a visualization-driven analytical ecosystem. It provides a methodological foundation for data integration, visualization architecture, and simulation-based decision support, paving the way for large-scale adoption of immersive visualization across DEWA's Smart Grid Initiative, R&D activities, and future network resilience studies.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2026

Bridging Cloud and Edge Computing at NREL Using CONNECT: Cloud Optimized Networking for Next-Gen Edge Computing Technologies [Slides]

CONNECT is an innovative on-premise hardware and software solution that integrates edge and cloud computing infrastructure at NREL. Built on the AWS Greengrass middleware and leveraging the MQTT protocol, CONNECT enables real-time data streaming from IoT devices and gateways to both cloud and local services, empowering researchers to rapidly capture, analyze, and act upon edge-generated data while leveraging cloud capabilities. The platform addresses research infrastructure challenges by providing a pre-approved platform which is already configured with the correct networking and cybersecurity baselines thus eliminating procurement delays and enabling on-demand availability. CONNECT's hybrid architecture efficiently manages burstable workloads, allowing research teams to dynamically scale computational capacity, handle peak data loads, and reduce operational bottlenecks. Advanced capabilities include built-in GPU support for executing machine learning models which enables low-latency inference at the edge from models trained in the cloud. This architecture supports real-time analytics and filtering, providing a mechanism to allow only transmitting and processing high-value data. Cloud-based configuration management permits engineers to manage on-premise systems remotely, optimizing operational efficiency. By bridging edge and cloud computing, CONNECT provides NREL researchers with a flexible, scalable platform that accelerates scientific discovery while maintaining robust security and performance standards.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Capturing Historic Reliability Performance Through Graph Databases: A Model Based System Engineering Approach

With the goal of improving the performance and reliability of high dependable technological systems such as nuclear power plants, advanced monitoring and health management systems are employed to inform system engineers on observed degradation processes and anomalous behaviors of assets and components. This information is captured in the form of large amount of data which can be heterogenous in nature (e.g., numeric, textual). Such large data availability poses challenges when system engineers are required to parse and analyze them in order to track historic reliability performance of assets and components. This paper tackles directly this challenge by providing means to organize data in the form of a graph: a knowledge graph. The presented approach distinguish itself from current knowledge graph-based methods by the fact that model-based system engineering (MBSE) models are used to “put data into context”. In particular, MBSE models are used as skeleton of a knowledge graph; numeric and textual data elements, once processed, are associated to MBSE model elements. Thus, a knowledge graph captures both system architecture (though MBSE models) and health/performance data. Such feature opens the door to new data analytics methods designed to identify causal relations between observed phenomena.

97 - MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Cybersecurity for the Operational Technology Environment (CyOTE) (Final Technical Report)

Electric grids have historically been susceptible to both physical attacks and environmental hazards but the implementation of smart grids, remote management, and self-healing networks, has now made the grid vulnerable to cyber attacks. To address risks introduced by routable connectivity, utilities must establish dynamic solutions to identify, protect, detect, respond to, and recover from cyber security threats and vulnerabilities. In response to the evolving threat landscape U.S. Department of Energy-Office of Cybersecurity, Energy Security, and Emergency Response (DOE CESER) initiated the Cybersecurity for the OT Environment (CyOTE) pilot program, a U.S. Department of Energy (DOE) effort designed to leverage U.S. intelligence capabilities to prevent, detect, or mitigate a cyber attack on utility operational technology (OT) networks. As part of the CyOTE pilot, The Southern Company (Southern Company or Southern) researched, evaluated and deployed emerging Commercial off the Shelf (COTS) technologies and cyber security monitoring architectures to provide previously unrealized network visibility and situational awareness through deep packet inspection and data analytics. This Final Scientific/Technical Report documents the objectives, methodology, lessons learned, and results of Southern Company’s participation in the CyOTE pilot from December 2018 to September 2023.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Engineering Privacy at the Edge: A Practical Guide to Differential Privacy in System Architectures

The rapid expansion of distributed and edge computing platforms—spanning autonomous vehicles, IoT sensors, and healthcare monitors—has heightened concerns about data privacy. Differential Privacy (DP) offers a rigorous mathematical framework to protect sensitive information while retaining analytical utility. This tutorial introduces the foundations of DP for both numerical and categorical datasets and extends the discussion to correlation-aware techniques tailored for structured and high-dimensional data. Hands-on demonstrations will begin with the PETINA (Privacy prEservaTIoN Algorithms) package for numerical data and continue with MIC-DP (Maximum Information Correlated Differential Privacy) for tabular data. Designed for researchers and practitioners in secure systems, embedded architectures, and AI accelerators, the tutorial emphasizes practical and scalable methods for integrating DP into real-world system designs.

Kotevska, Olivera [ORNL] (ORCID:0000000316772243)↗
DOE OSTI2025

Architecture-Aware Models of AI Engines for High-Performance Matrix Matrix Multiplication

The AI Engine (AIE) architecture, available in systems from mobile SoCs to server-class FPGAs, aims to efficiently execute AI/ML tasks through a two-dimensional array of compute tiles. Previous work on AIEs has explored different approaches to mapping computation across spatial arrays, but the compute kernel running on each tile has not been the focus. Additionally, the AIE-ML architecture introduces memory tiles and omits programmable logic, requiring new approaches to staging and moving data throughout the array. In this work we update analytical models developed for CPUs to produce the design of high performance kernels while introducing new model considerations such as memory structure, throughput, and latency as required by the AIE hardware. We evaluate our models by developing AIE-ML kernels for matrix multiplication in low-precision data types showing performance up to 95% of compute peak for the kernel when data resides in local memory and above 90% of compute peak when data resides in main memory.

Binder, Elliott D. [Carnegie Mellon University, Pi↗
DOE OSTI2026

OpenSAMPL: An Open Source Library for Timing and Synchronization Measurements and Analytics

Today's power grid operators are implementing timing and synchronization solutions that provide resilience to Global Navigation Satellite System (GNSS) vulnerabilities. These vendor-specific solutions often come with additional software applications that are designed to monitor that vendor's synchronization performance data. However, resilient timing architectures often resulting in multi-vendor solutions, including approaches that blend terrestrial clocks with space-based subscription services. In such an environment, collecting, analyzing, and visualizing data from a variety of sources within a single platform was heretofore not possible. To address this need, the US Department of Energy's Center for Alternative Synchronization and Timing (CAST) developed OpenSAMPL, the Open Synchronized Analytics and Monitoring Platform, an open-source Python framework for processing, loading, and observing clock measurement data from distributed devices. OpenSAMPL enables the ingestion of diverse clock-probe sources into a scalable time-series database and applies robust analytics. OpenSAMPL currently supports two vendor data pipelines, and will be extended to more in the near future, enabling seamless monitoring of a variety of timing and synchronization devices in a common environment.

Grant, Josh [ORNL] (ORCID:0000000163475060)↗
DOE OSTI2025

AI-Enabled Operations at Fermi Complex: Multivariate Time Series Prediction for Outage Prediction and Diagnosis

The Main Control Room of the Fermilab accelerator complex continuously gathers extensive time-series data from thousands of sensors monitoring the beam. However, unplanned events such as trips or voltage fluctuations often result in beam outages, causing operational downtime. This downtime not only consumes operator effort in diagnosing and addressing the issue but also leads to unnecessary energy consumption by idle machines awaiting beam restoration. The current threshold-based alarm system is reactive and faces challenges including frequent false alarms and inconsistent outage-cause labeling. To address these limitations, we propose an AI-enabled framework that leverages predictive analytics and automated labeling. Using data from $2,703$ Linac devices and $80$ operator-labeled outages, we evaluate state-of-the-art deep learning architectures, including recurrent, attention-based, and linear models, for beam outage prediction. Additionally, we assess a Random Forest-based labeling system for providing consistent, confidence-scored outage annotations. Our findings highlight the strengths and weaknesses of these architectures for beam outage prediction and identify critical gaps that must be addressed to fully harness AI for transitioning downtime handling from reactive to predictive, ultimately reducing downtime and improving decision-making in accelerator management.

Jain, Milan [PNL, Richland] (ORCID:000000021676111↗
DOE OSTI2026

Grid Operator Analytics and Assessment Tools for Inverter- Based Resources Dominated Grid (GOAAT-IBR) Project Update

This presentation provides an update on the OPTIMA GOAAT project, with emphasis on the cloud-native data platform developed in-house to ingest, manage, and operationalize high-resolution power system data. Since our last NASPI presentation, accessible via OSTI ID #2671437, the project team advanced the design and deployment of a scalable architecture capable of handling both synchronized and non-synchronized streams, including PMU, point-on-wave (POW), COMTRADE, and SCADA data. These materials review the project status, recent progress, and key lessons learned. The core of the presentation examines the architecture and engineering of our cloud-native ingestion and data management platform. We then explain how pipelines were designed to collect, normalize, time-align, store, and serve heterogeneous data at scale. We will discuss design choices such as data models, streaming versus batch ingestion, storage tiers, and interoperability with analytics applications. Practical experiences with cloud-native technologies were shared during the event, including benefits, limitations, and integration challenges in a utility environment, along with methods used to improve performance, reduce latency, and optimize resource usage. The presentation also showcases user interface designs and visualization tools that convert raw measurements and analytics results into intuitive, actionable insights for operators and engineers. During the presentation examples were provided demonstrating how visualization, event views, and summarized analytics enhance situational awareness and support operational decision-making. These use cases illustrate how a well-designed data infrastructure can bridge the gap between high-volume measurements and practical grid operations.

Aminifar, Farrokh↗
DOE OSTI2026

Generative AI in Supply Chain Management: Applications, Challenges, and Future Directions

Supply chain management (SCM) is undergoing rapid transformation due to increasing global complexity, demand volatility, and operational disruptions. Generative Artificial Intelligence (GenAI) has emerged as a powerful paradigm capable of synthesizing data, simulating operational scenarios, and enabling adaptive decision-making across supply chain networks. This paper presents a survey of GenAI’s role in SCM, focusing on its applications in predictive analytics, autonomous logistics, and fraud detection. Unlike traditional AI systems that rely primarily on predictive analytics, GenAI models, including large language models, generative adversarial networks, and diffusion-based architectures, enable the creation of synthetic supply chain scenarios and autonomous optimization strategies. This survey provides (1) a taxonomy of GenAI techniques for supply chain applications, (2) a comparative analysis of generative AI approaches with traditional machine learning, reinforcement learning, and blockchain-based methods, and (3) a discussion of key challenges such as data privacy, interpretability, and integration with legacy enterprise systems. Furthermore, we outline open research problems and propose directions for future research toward autonomous, resilient, and sustainable AI-driven supply chains.

15 - GEOTHERMAL ENERGY↗
DOE OSTI2026

Optimization-based approaches to control of connected and automated vehicles: Principles, complexities, applications, challenges, and outlook

Safe and optimal motion control for connected and automated vehicles (CAVs) poses a fundamental optimization challenge at the intersection of system complexity, environmental uncertainty, and stringent real-time constraints. Existing surveys address this challenge in isolation – focusing either on specific control techniques or individual uncertainty sources – without providing a unified framework that characterizes the trade-offs among computational tractability, performance verifiability, and adaptive generalization across paradigms. This review addresses that gap by presenting a cohesive analytical framework concentrated on the decision-making and trajectory optimization layers of the CAV autonomy stack. We systematically analyze three major optimization paradigms – first-principles model-based optimization, data-driven methods, and hybrid synergistic architectures – evaluating each against four core complexity axes: problem formulation, constraint handling, optimality guarantees, and robustness. Key applications including platooning, trajectory planning, collision avoidance, and cooperative control are examined to reveal recurring methodological patterns and critical operational constraints that limit real-world performance. Our synthesis identifies verifiable hybrid architectures, incentive-aligned multi-agent cooperation, and hardware-algorithm co-design as the defining research frontiers, and distills a targeted agenda for developing CAV control systems that are simultaneously safe, computationally efficient, and deployable in the full complexity of real-world traffic environments.

Muzahid, Abu Jafar Md [University of Tennessee, Kn↗
DOE OSTI2025

Enhancing Security and Resiliency in Operational Technology Environments Through Network Slicing and Federated Learning

The growing convergence of Information Technology (IT) and Operational Technology (OT) within Industry 4.0 environments has introduced new demands on industrial network infrastructure. As cyber-physical systems become increasingly interconnected, ensuring the secure, timely, and efficient exchange of critical data is essential. This thesis explores how network slicing, a method of creating isolated virtual network segments, can be applied within OT environments to address challenges such as latency, security, and resource allocation. The first research question addressed in this thesis is: How can OT networks take advantage of NFV and SDN technology to become cyber resilient? This study examines the operational, security, and architectural implications of introducing network slicing into traditionally static OT infrastructures such as Industrial Control Systems (ICS) and SCADA. Through simulated deployments and case studies, the research demonstrates how slicing enables better isolation between critical and non-critical services, thereby improving response time, throughput, and security in sensitive environments. The second question considers: How to dynamically implement network slicing and take advantage of network resources towards integrating decentralized machine learning? In response, this thesis proposes a framework that combines Software-Defined Networking (SDN), Network Function Virtualization (NFV), and Federated Learning (FL) to enable real-time analytics while maintaining data locality. The proposed approach reduces the burden on centralized infrastructure and minimizes privacy risks by supporting on-site training of models across distributed OT nodes, coordinated through dynamically allocated network slices. The third focus explores: How slicing helps to increase the resiliency of OT networks through the orchestration of a dynamic DMZ? To answer this, the thesis presents a method for creating and managing Dynamic Demilitarized Zones (DMZs) using network slicing. This enables flexible and automated isolation of sensitive subsystems during threat scenarios or high-risk operations. Coupled with intelligent orchestration and containerized security services, the dynamic DMZ significantly enhances the system's ability to respond to cyber incidents without halting production. Ultimately, this thesis contributes a comprehensive architecture that blends network slicing with machine learning, secure segmentation, and automation, paving the way for resilient, adaptive, and intelligent OT environments. Performance evaluations across multiple scenarios show improvements in system reliability, threat response time, model accuracy, and resource utilization, providing a strong foundation for future industrial automation systems.

Rodiles Delgado, Brian G↗
DOE OSTI2024

Analyzing inference workloads for spatiotemporal modeling

Ensuring power grid resiliency, forecasting climate conditions, and optimization of transportation infrastructure are some of the many application areas where data is collected in both space and time. Spatiotemporal modeling is about modeling those patterns for forecasting future trends and carrying out critical decision-making by leveraging machine learning/deep learning. Once trained offline, field deployment of trained models for near real-time inference could be challenging because performance can vary significantly depending on the environment, available compute resources and tolerance to ambiguity in results. Users deploying spatiotemporal models for solving complex problems can benefit from analytical studies considering a plethora of system adaptations to understand the associated performance-quality trade-offs. To facilitate the co-design of next-generation hardware architectures for field deployment of trained models, it is critical to characterize the workloads of these deep learning (DL) applications during inference and assess their computational patterns at different levels of the execution stack. In this paper, we develop several variants of deep learning applications that use spatiotemporal data from dynamical systems. We study the associated computational patterns for inference workloads at different levels, considering relevant models (Long short-term Memory, Convolutional Neural Network and Spatio-Temporal Graph Convolution Network), DL frameworks (Tensorflow and PyTorch), precision (FP16, FP32, AMP, INT16 and INT8), inference runtime (ONNX and AI Template), post-training quantization (TensorRT) and platforms (Nvidia DGX A100 and Sambanova SN10 RDU). Overall, our findings indicate that although there is potential in mixed-precision models and post-training quantization for spatiotemporal modeling, extracting efficiency from contemporary GPU systems might be challenging. Instead, co-designing custom accelerators by leveraging optimized High Level Synthesis frameworks (such as SODA High-Level Synthesizer for customized FPGA/ASIC targets) can make workload-specific adjustments to enhance the efficiency.

97 MATHEMATICS AND COMPUTING↗