Skip to main content

PNNL

  • About
  • News & Media
  • Careers
  • Events
  • Research
    • Scientific Discovery
      • Biology
        • Chemical Biology
        • Computational Biology
        • Ecosystem Science
        • Human Health
          • Cancer Biology
          • Exposure Science & Pathogen Biology
        • Integrative Omics
          • Advanced Metabolomics
          • Chemical Biology
          • Mass Spectrometry-Based Measurement Technologies
          • Spatial and Single-Cell Proteomics
          • Structural Biology
        • Microbiome Science
          • Biofuels & Bioproducts
          • Human Microbiome
          • Soil Microbiome
          • Synthetic Biology
        • Predictive Phenomics
      • Chemistry
        • Computational Chemistry
        • Chemical Separations
        • Chemical Physics
        • Catalysis
      • Earth & Coastal Sciences
        • Global Change
        • Atmospheric Science
          • Atmospheric Aerosols
          • Human-Earth System Interactions
          • Modeling Earth Systems
        • Coastal Science
        • Ecosystem Science
        • Subsurface Science
        • Terrestrial Aquatics
      • Materials Sciences
        • Materials in Extreme Environments
        • Precision Materials by Design
        • Science of Interfaces
        • Solid Phase Processing
          • Cold Spray
          • Friction Stir Welding & Processing
          • ShAPE
      • Nuclear & Particle Physics
        • Dark Matter
        • Fusion Energy Science
        • Neutrino Physics
      • Quantum Information Sciences
    • Energy Resiliency
      • Electric Grid Modernization
        • Emergency Response
        • Grid Analytics
          • AGM Program
          • Tools and Capabilities
        • Grid Architecture
        • Grid Cybersecurity
        • Grid Energy Storage
        • Transmission
        • Distribution
      • Energy Efficiency
        • Appliance and Equipment Standards
        • Building Energy Codes
        • Building Technologies
          • Advanced Building Controls
          • Advanced Lighting
          • Building-Grid Integration
        • Building and Grid Modeling
        • Commercial Buildings
        • Federal Buildings
          • Federal Performance Optimization
          • Resilience and Security
        • Residential Buildings
          • Building America Solution Center
          • Energy Efficient Technology Integration
          • Home Energy Score
        • Energy Efficient Technology Integration
      • Energy Storage
        • Electrochemical Energy Storage
        • Flexible Loads and Generation
        • Grid Integration, Controls, and Architecture
        • Regulation, Policy, and Valuation
        • Science Supporting Energy Storage
        • Chemical Energy Storage
      • Environmental Management
        • Waste Processing
        • Radiation Measurement
        • Environmental Remediation
      • Fossil Energy
        • Subsurface Energy Systems
        • Carbon Management
          • Carbon Capture
          • Carbon Storage
          • Carbon Utilization
        • Advanced Hydrocarbon Conversion
      • Nuclear Energy
        • Fuel Cycle Research
        • Advanced Reactors
        • Reactor Operations
        • Reactor Licensing
      • Renewable Energy
        • Solar Energy
        • Wind Energy
          • Wind Resource Characterization
          • Wildlife and Wind
          • Community Values and Ocean Co-Use
          • Wind Systems Integration
          • Wind Data Management
          • Distributed Wind
        • Marine Energy
          • Environmental Monitoring for Marine Energy
          • Marine Biofouling and Corrosion
          • Marine Energy Resource Characterization
          • Testing for Marine Energy
          • The Blue Economy
        • Hydropower
          • Environmental Performance of Hydropower
          • Hydropower Cybersecurity and Digitalization
          • Hydropower and the Electric Grid
          • Materials Science for Hydropower
          • Pumped Storage Hydropower
          • Water + Hydropower Planning
        • Grid Integration of Renewable Energy
        • Geothermal Energy
      • Transportation
        • Bioenergy Technologies
          • Algal Biofuels
          • Aviation Biofuels
          • Waste-to-Energy and Products
        • Hydrogen & Fuel Cells
        • Vehicle Technologies
          • Emission Control
          • Energy-Efficient Mobility Systems
          • Lightweight Materials
          • Vehicle Electrification
          • Vehicle Grid Integration
    • National Security
      • Chemical & Biothreat Signatures
        • Contraband Detection
        • Pathogen Science & Detection
        • Explosives Detection
        • Threat-Agnostic Biodefense
      • Cybersecurity
        • Discovery and Insight
        • Proactive Defense
        • Trusted Systems
      • Nuclear Material Science
      • Nuclear Nonproliferation
        • Radiological & Nuclear Detection
        • Nuclear Forensics
        • Ultra-Sensitive Nuclear Measurements
        • Nuclear Explosion Monitoring
        • Global Nuclear & Radiological Security
      • Stakeholder Engagement
        • Disaster Recovery
        • Global Collaborations
        • Legislative and Regulatory Analysis
        • Technical Training
      • Systems Integration & Deployment
        • Additive Manufacturing
        • Deployed Technologies
        • Rapid Prototyping
        • Systems Engineering
      • Threat Analysis
        • Advanced Wireless Security
          • 5G Security
          • RF Signal Detection & Exploitation
        • Internet of Things
        • Maritime Security
        • Millimeter Wave
        • Mission Risk and Resilience
    • Data Science & Computing
      • Artificial Intelligence
      • Graph and Data Analytics
      • Software Engineering
      • Computational Mathematics & Statistics
      • Future Computing Technologies
        • Adaptive Autonomous Systems
    • Publications & Reports
    • Featured Research
  • People
    • Inventors
    • Lab Leadership
    • Lab Fellows
    • Staff Accomplishments
  • Partner with PNNL
    • Education
      • Undergraduate Students
      • Graduate Students
      • Post-graduate Students
      • University Faculty
      • University Partnerships
      • K-12 Educators and Students
      • STEM Education
        • STEM Workforce Development
        • STEM Outreach
        • Meet the Team
      • Internships
    • Community
      • Regional Impact
      • Philanthropy
      • Volunteering
    • Industry
      • Available Technologies
      • Industry
      • Industry Partnerships
      • Licensing & Technology Transfer
      • Entrepreneurial Leave
      • Visual Intellectual Property Search (VIPS)
  • Facilities & Centers
    • All Facilities
      • Atmospheric Radiation Measurement User Facility
      • Electricity Infrastructure Operations Center
      • Energy Sciences Center
      • Environmental Molecular Sciences Laboratory
      • Grid Storage Launchpad
      • Institute for Integrated Catalysis
      • Interdiction Technology and Integration Laboratory
      • PNNL Portland Research Center
      • PNNL Seattle Research Center
      • PNNL-Sequim (Marine and Coastal Research)
      • Radiochemical Processing Laboratory
      • Shallow Underground Laboratory

Scalable, Efficient and Accelerated Causal Reasoning Operators, Graphs and Spikes for Earth and Embedded Systems (SEA-CROGS)

  • News
  • Webinars
  • Research
  • Team
  • Publications
    • Presentations
    • Keynotes and Invited Talks
  • Software
  • Outreach and Internships

Breadcrumb

  1. Home
  2. Projects
  3. Scalable, Efficient and Accelerated Causal Reasoning Operators, Graphs and Spikes for Earth and Embedded Systems (SEA-CROGS)

Software

Software Catalog

E3SM-DeepONet Online Machine Learning Bias Correction Workflow
Integrating Nvidia’s PyTorch FORTRAN binding package with E3SM

Most machine learning models are developed in Python. To use these machine learning models in models like E3SM, it's necessary to call the Python packages in FORTRAN through linkage. Our team modified the Fortran proxy library (for CXX libraries of PyTorch source) to easily integrate with any FORTRAN-based solver. We added routines to read in traced .pt (PyTorch saved model structure) files and modified the build system to account for machine dependent MPI compilers. The result allows for learning the bias correction improving the simulation of large-scale environments of E3SM at ~100 km resolution.

DeepXDE: A Deep Learning Library for Solving Differential Equations
DeepXDE

Deep learning has achieved remarkable success in diverse applications; however, its use in solving partial differential equations (PDEs) has emerged only recently. Here, we present an overview of physics-informed neural networks (PINNs), which embed a PDE into the loss of the neural network using automatic differentiation. The PINN algorithm is simple, and it can be applied to different types of PDEs, including integro- differential equations, fractional PDEs, and stochastic PDEs. Moreover, from the implementation point of view, PINNs solve inverse problems as easily as forward problems. We propose a new residual-based adaptive refinement (RAR) method to improve the training efficiency of PINNs. For pedagogical reasons, we compared the PINN algorithm to a standard finite element method. We also present a Python library for PINNs, DeepXDE, which is designed to serve both as an education tool to be used in the classroom as well as a research tool for solving problems in computational science and engineering. Specifically, DeepXDE can solve forward problems with given initial and boundary conditions, as well as inverse problems when extra measurements are available. DeepXDE supports complex-geometry domains based on the technique of constructive solid geometry, and enables the user code to be compact, resembling closely the mathematical formulation. We introduce the usage of DeepXDE and its customizability, and we also demonstrate the capability of PINNs and the user-friendliness of DeepXDE for five different examples. More broadly, DeepXDE contributes to the more rapid development of the emerging Scientific Machine Learning field.

DeepXDE is a deep learning library for solving differential equations over TensorFlow. More details are documented here.

Total downloads: >400,000 as of December 2023

  • PyPI
  • Anaconda
Computational Hypergraph Discovery: A Novel Method for Uncovering Unknown Functional Relationships Between Variables Within Datasets
electric circuit

Machine learning tasks typically involve predicting outputs Y from inputs X, a process that can be represented by X→Y. We can think of this case as a graph with two nodes and one edge. However, in many problems, there is not one input-output relationship but instead a web of interactions between the different variables. We can think of these variables as nodes of a graph. Similarly to X→Y in the machine learning case, when there exists a function taking a set of variables to another variable, we can draw an edge in our graph between these variables. Since these edges can connect more than two nodes depending on the underlying function, we call them hyperedges and a hypergraph. The nuance between a graph and a hypergraph is not essential for understanding this post, so it is safe to think of a hypergraph as a regular graph.

CHD is the source code for the paper "Computational Hypergraph Discovery: A Gaussian process framework for connecting the dots".

Please see the companion blog post for a gentle introduction to the method and the code.

Lab-Level Communications Priority Topics

Computing

PNNL

  • Get in Touch
    • Contact
    • Careers
    • Doing Business
    • Environmental Reports
    • Security & Privacy
    • Vulnerability Disclosure Policy
  • Research
    • Scientific Discovery
    • Energy Resiliency
    • National Security
Subscribe to PNNL News
Department of Energy Logo Battelle Logo
Pacific Northwest National Laboratory (PNNL) is managed and operated by Battelle for the Department of Energy
  • YouTube
  • Facebook
  • X (formerly Twitter)
  • Instagram
  • LinkedIn