mlsanityData to 7 Oct 2026

Using Machine Learning at Scale in HPC Simulations with SmartSim: An Application to Ocean Climate Modeling

arXiv 2104.09355 ↗First posted 13 Apr 2021cs.CE cs.DC cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

We demonstrate the first climate-scale, numerical ocean simulations improved through distributed, online inference of Deep Neural Networks (DNN) using SmartSim. SmartSim is a library dedicated to enabling online analysis and Machine Learning (ML) for traditional HPC simulations. In this paper, we detail the SmartSim architecture and provide benchmarks including online inference with a shared ML model on heterogeneous HPC systems. We demonstrate the capability of SmartSim by using it to run a 12-member ensemble of global-scale, high-resolution ocean simulations, each spanning 19 compute nodes, all communicating with the same ML architecture at each simulation timestep. In total, 970 billion inferences are collectively served by running the ensemble for a total of 120 simulated years. Finally, we show our solution is stable over the full duration of the model integrations, and that the inclusion of machine learning has minimal impact on the simulation runtimes.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 9 of its 33 references that are in the map. First posted on arXiv 13 Apr 2021.

Builds on

9 of 33 references.

References · 9

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Wide Residual Networkscited by 3,057
  3. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  4. 2018Deep learning to represent sub-grid processes in climate modelscited by 156
  5. 2017Earth System Modeling 2.0: A Blueprint for Models That Learn From Observations and Targeted High-Resolution Simulationscited by 51
  6. 2019Achieving Conservation of Energy in Neural Network Emulators for Climate Modelingcited by 27
  7. 2018Quantifying model form uncertainty in Reynolds-averaged turbulence models with Bayesian deep neural networkscited by 20
  8. 2020A Fortran-Keras Deep Learning Bridge for Scientific Computingcited by 16
  9. 2018CosmoFlow: Using Deep Learning to Learn the Universe at Scalecited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 2; 2023: 0; 2024: 2; 2025: 0; 2026: 1.

7 papers.

  1. 2022Deep Reinforcement Learning for Turbulence Modeling in Large Eddy Simulationscited by 16
  2. 2021Bridging observation, theory and numerical simulation of the ocean using Machine Learningcited by 15
  3. 2021Colmena: Scalable Machine-Learning-Based Steering of Ensemble Simulations for High Performance Computingcited by 10
  4. 2022Deep Reinforcement Learning for Computational Fluid Dynamics on HPC Systemscited by 6
  5. 2024Towards Active Flow Control Strategies Through Deep Reinforcement Learningcited by 1
  6. 2024Global Estimation of Subsurface Eddy Kinetic Energy of Mesoscale Eddies Using a Multiple-input Residual Neural Networkcited by 0
  7. 2026Online Reinforcement Learning in the Met Office Unified Model through Distributed Model-Agent Couplingcited by 0