Saved in:
Bibliographic Details
Main Authors: Rautela, Mahindra Singh, Most, Alexander, Mansingh, Siddharth, Love, Bradley C., Scheinker, Alexander, Oyen, Diane, Debardeleben, Nathan, Lawrence, Earl, Biswas, Ayan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.21670
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908797329473536
author Rautela, Mahindra Singh
Most, Alexander
Mansingh, Siddharth
Love, Bradley C.
Scheinker, Alexander
Oyen, Diane
Debardeleben, Nathan
Lawrence, Earl
Biswas, Ayan
author_facet Rautela, Mahindra Singh
Most, Alexander
Mansingh, Siddharth
Love, Bradley C.
Scheinker, Alexander
Oyen, Diane
Debardeleben, Nathan
Lawrence, Earl
Biswas, Ayan
contents We introduce MORPH, a modality-agnostic, autoregressive foundation model for partial differential equations (PDEs). MORPH is built on a convolutional vision transformer backbone that seamlessly handles heterogeneous spatiotemporal datasets of varying data modality (1D--3D) at different resolutions, and multiple fields with mixed scalar and vector components. The architecture combines (i) component-wise convolution, which jointly processes scalar and vector channels to capture local interactions, (ii) inter-field cross-attention, which models and selectively propagates information between different physical fields, (iii) axial attentions, which factorize full spatiotemporal self-attention along individual spatial and temporal axes to reduce computational burden while retaining expressivity. We pretrain multiple model variants on a diverse collection of heterogeneous PDE datasets and evaluate transfer to a range of downstream prediction tasks. Using both full-model fine-tuning and parameter-efficient low-rank adapters, MORPH outperforms models trained from scratch. Across extensive evaluations, MORPH matches or surpasses strong baselines and recent state-of-the-art models. Collectively, these capabilities present a flexible and powerful backbone for learning from the heterogeneous and multimodal nature of scientific observations, charting a path toward scalable and data-efficient scientific machine learning. The source code, datasets, and models are publicly available at https://github.com/lanl/MORPH.
format Preprint
id arxiv_https___arxiv_org_abs_2509_21670
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MORPH: PDE Foundation Models with Arbitrary Data Modality
Rautela, Mahindra Singh
Most, Alexander
Mansingh, Siddharth
Love, Bradley C.
Scheinker, Alexander
Oyen, Diane
Debardeleben, Nathan
Lawrence, Earl
Biswas, Ayan
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Computational Physics
We introduce MORPH, a modality-agnostic, autoregressive foundation model for partial differential equations (PDEs). MORPH is built on a convolutional vision transformer backbone that seamlessly handles heterogeneous spatiotemporal datasets of varying data modality (1D--3D) at different resolutions, and multiple fields with mixed scalar and vector components. The architecture combines (i) component-wise convolution, which jointly processes scalar and vector channels to capture local interactions, (ii) inter-field cross-attention, which models and selectively propagates information between different physical fields, (iii) axial attentions, which factorize full spatiotemporal self-attention along individual spatial and temporal axes to reduce computational burden while retaining expressivity. We pretrain multiple model variants on a diverse collection of heterogeneous PDE datasets and evaluate transfer to a range of downstream prediction tasks. Using both full-model fine-tuning and parameter-efficient low-rank adapters, MORPH outperforms models trained from scratch. Across extensive evaluations, MORPH matches or surpasses strong baselines and recent state-of-the-art models. Collectively, these capabilities present a flexible and powerful backbone for learning from the heterogeneous and multimodal nature of scientific observations, charting a path toward scalable and data-efficient scientific machine learning. The source code, datasets, and models are publicly available at https://github.com/lanl/MORPH.
title MORPH: PDE Foundation Models with Arbitrary Data Modality
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Computational Physics
url https://arxiv.org/abs/2509.21670