A Trainable-by-Parts Operator Learning Framework: Bridging DeepONet and Karhunen-Loeve Expansions for Large-Scale Applications

• URL: http://arxiv.org/abs/2606.28519v1
• Date: Fri, 26 Jun 2026 18:15:24 GMT
• Title: A Trainable-by-Parts Operator Learning Framework: Bridging DeepONet and Karhunen-Loeve Expansions for Large-Scale Applications
• Abstract summary: We propose a scalable operator-learning framework based on the Karhunen-Loeve Deep Neural Network (KL-DNN)<n>The model is trained on a dataset comprising 100 samples of large-scale simulations in a three-dimensional domain with 1.7 million cells and 50 time steps.
• Score: 46.07145155913717
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Training operator-learning models for large-scale problems governed by partial differential equations (PDEs) is challenging due to the curse of dimensionality, memory constraints, and limited training data. These challenges arise in many scientific and engineering applications, including subsurface flow, climate modeling, and geological carbon storage (GCS). In this work, we propose a scalable operator-learning framework based on the Karhunen-Loeve Deep Neural Network (KL-DNN) and demonstrate its performance for modeling GCS. The model is trained on a dataset comprising 100 samples of large-scale simulations in a three-dimensional domain with 1.7 million cells and 50 time steps. The KL-DNN method constructs latent spaces using low-rank singular value decomposition of static properties and a nested Karhunen-Loeve expansion for dynamic pressure fields, enabling full-resolution predictions without subsampling or spatial coarsening. The KL-DNN model achieves an average root mean square error (RMSE) of 1.1 psi for pressure (0.04% relative error with respect to the average pressure in the domain) and RMSE of 0.0146 for CO2 saturation (5% relative error with respect to the average saturation inside the plume). The model requires 20 minutes of training on a single GPU, representing a 19% reduction in the pressure errors, 7% reduction in the saturation error, and a two-order-of-magnitude speedup compared to DeepONet trained on the same dataset. These results, along with inference time of less than one minute, establish the proposed model as a practical and accurate solution for large-scale PDE problems, enabling rapid uncertainty quantification, history matching, and real-time decision support.

Related papers

• Interactive Atmospheric Composition Emulation for Next-Generation Earth System Models [0.0]
  Interactive simulations in Earth System Models (ESMs) are computationally expensive as they transport numerous gaseous and aerosols at each timestep.<n>We extend the ModelE NINT tracer version using machine learning (ML) to create SmartINT, which emulates interactive emissions.<n>Smart NINT interactively calculates concentrations using ML with surface emissions meteorological data as inputs, avoiding full physics parameterizations.
  arXiv  Detail & Related papers  (2025-10-12T15:18:37Z)
• Scale-Consistent Learning for Partial Differential Equations [79.48661503591943]
  We propose a data augmentation scheme based on scale-consistency properties of PDEs.<n>We then design a scale-informed neural operator that can model a wide range of scales.<n>With scale-consistency, the model trained on $Re$ of 1000 can generalize to $Re$ ranging from 250 to 10000.
  arXiv  Detail & Related papers  (2025-07-24T21:29:52Z)
• TensorGRaD: Tensor Gradient Robust Decomposition for Memory-Efficient Neural Operator Training [91.8932638236073]
  We introduce textbfTensorGRaD, a novel method that directly addresses the memory challenges associated with large-structured weights.<n>We show that sparseGRaD reduces total memory usage by over $50%$ while maintaining and sometimes even improving accuracy.
  arXiv  Detail & Related papers  (2025-01-04T20:51:51Z)
• Principal Component Flow Map Learning of PDEs from Incomplete, Limited, and Noisy Data [0.0]
  We present a computational technique for modeling the evolution of dynamical systems in a reduced basis.<n>We focus on the challenging problem of modeling partially-observed partial differential equations (PDEs) on high-dimensional non-uniform grids.<n>We present a neural network structure that is suitable for PDE modeling with noisy and limited data available only on a subset of the state variables or computational domain.
  arXiv  Detail & Related papers  (2024-07-15T16:06:20Z)
• Graph Neural Networks for Pressure Estimation in Water Distribution Systems [44.99833362998488]
  Pressure and flow estimation in Water Distribution Networks (WDN) allows water management companies to optimize their control operations. We combine physics-based modeling and Graph Neural Networks (GNN), a data-driven approach, to address the pressure estimation problem. Our GNN-based model estimates the pressure of a large-scale WDN in The Netherlands with a MAE of 1.94mH$$O and a MAPE of 7%.
  arXiv  Detail & Related papers  (2023-11-17T15:30:12Z)
• Multi-fidelity Fourier Neural Operator for Fast Modeling of Large-Scale Geological Carbon Storage [0.0]
  We propose to use a multi-fidelity Fourier neural operator (FNO) to solve large-scale carbon storage problems. We first test the model efficacy on a GCS reservoir model being discretized into 110k grid cells. The multi-fidelity model can predict with accuracy comparable to a high-fidelity model trained with the same amount of high-fidelity data with 81% less data generation costs.
  arXiv  Detail & Related papers  (2023-08-17T17:44:59Z)
• Score-based Diffusion Models in Function Space [137.70916238028306]
  Diffusion models have recently emerged as a powerful framework for generative modeling.<n>This work introduces a mathematically rigorous framework called Denoising Diffusion Operators (DDOs) for training diffusion models in function space.<n>We show that the corresponding discretized algorithm generates accurate samples at a fixed cost independent of the data resolution.
  arXiv  Detail & Related papers  (2023-02-14T23:50:53Z)
• Solving High-Dimensional PDEs with Latent Spectral Models [74.1011309005488]
  We present Latent Spectral Models (LSM) toward an efficient and precise solver for high-dimensional PDEs. Inspired by classical spectral methods in numerical analysis, we design a neural spectral block to solve PDEs in the latent space. LSM achieves consistent state-of-the-art and yields a relative gain of 11.5% averaged on seven benchmarks.
  arXiv  Detail & Related papers  (2023-01-30T04:58:40Z)
• Real-time high-resolution CO$_2$ geological storage prediction using nested Fourier neural operators [58.728312684306545]
  Carbon capture and storage (CCS) plays an essential role in global decarbonization. Scaling up CCS deployment requires accurate and high-resolution modeling of the storage reservoir pressure buildup and the gaseous plume migration. We introduce Nested Fourier Neural Operator (FNO), a machine-learning framework for high-resolution dynamic 3D CO2 storage modeling at a basin scale.
  arXiv  Detail & Related papers  (2022-10-31T04:04:03Z)
• LordNet: An Efficient Neural Network for Learning to Solve Parametric Partial Differential Equations without Simulated Data [47.49194807524502]
  We propose LordNet, a tunable and efficient neural network for modeling entanglements. The experiments on solving Poisson's equation and (2D and 3D) Navier-Stokes equation demonstrate that the long-range entanglements can be well modeled by the LordNet.
  arXiv  Detail & Related papers  (2022-06-19T14:41:08Z)
• Deep-learning-based coupled flow-geomechanics surrogate model for CO$_2$ sequestration [4.635171370680939]
  The 3D recurrent R-U-Net model combines deep convolutional and recurrent neural networks to capture the spatial distribution and temporal evolution of saturation, pressure and surface displacement fields. The surrogate model is trained to predict the 3D CO2 saturation and pressure fields in the storage aquifer, and 2D displacement maps at the Earth's surface.
  arXiv  Detail & Related papers  (2021-05-04T07:34:15Z)
• Statistical Downscaling of Temperature Distributions from the Synoptic Scale to the Mesoscale Using Deep Convolutional Neural Networks [0.0]
  One of the promising applications is developing a statistical surrogate model that converts the output images of low-resolution dynamic models to high-resolution images. Our study evaluates a surrogate model that downscales synoptic temperature fields to mesoscale temperature fields every 6 hours. If the surrogate models are implemented at short time intervals, they will provide high-resolution weather forecast guidance or environment emergency alerts at low cost.
  arXiv  Detail & Related papers  (2020-07-20T06:24:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.