Data-Driven Integration Kernels for Interpretable Nonlocal Operator Learning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Ferretti, Savannah L., Lin, Jerry, Shamekh, Sara, Baldwin, Jane W., Pritchard, Michael S., Beucler, Tom
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910213522587648
author Ferretti, Savannah L.
Lin, Jerry
Shamekh, Sara
Baldwin, Jane W.
Pritchard, Michael S.
Beucler, Tom
author_facet Ferretti, Savannah L.
Lin, Jerry
Shamekh, Sara
Baldwin, Jane W.
Pritchard, Michael S.
Beucler, Tom
contents Machine learning models can represent climate processes that are nonlocal in horizontal space, height, and time, often by combining information across these dimensions in highly nonlinear ways. While this can improve predictive skill, it makes learned relationships difficult to interpret and prone to overfitting as the extent of nonlocal information grows. We address this challenge by introducing data-driven integration kernels, a framework that adds structure to nonlocal operator learning by explicitly separating nonlocal information aggregation from local nonlinear prediction. Each spatiotemporal predictor field is first integrated using learnable kernels (defined as continuous weighting functions over horizontal space, height, and/or time), after which a local nonlinear mapping is applied only to the resulting kernel-integrated features and optional local inputs. This design confines nonlinear interactions to a small set of integrated features and makes each kernel directly interpretable as a weighting pattern that reveals which horizontal locations, vertical levels, and past timesteps contribute most to the prediction. We demonstrate the framework for South Asian monsoon precipitation using a hierarchy of neural network models with increasing structure, including baseline, nonparametric kernel, and parametric kernel models. Across this hierarchy, kernel models achieve near-baseline performance with far fewer trainable parameters, indicating that much of the relevant nonlocal information can be captured through a small set of interpretable integrations when appropriate structural constraints are imposed.
format Preprint
id arxiv_https___arxiv_org_abs_2603_10305
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Data-Driven Integration Kernels for Interpretable Nonlocal Operator Learning
Ferretti, Savannah L.
Lin, Jerry
Shamekh, Sara
Baldwin, Jane W.
Pritchard, Michael S.
Beucler, Tom
Machine Learning
Atmospheric and Oceanic Physics
Machine learning models can represent climate processes that are nonlocal in horizontal space, height, and time, often by combining information across these dimensions in highly nonlinear ways. While this can improve predictive skill, it makes learned relationships difficult to interpret and prone to overfitting as the extent of nonlocal information grows. We address this challenge by introducing data-driven integration kernels, a framework that adds structure to nonlocal operator learning by explicitly separating nonlocal information aggregation from local nonlinear prediction. Each spatiotemporal predictor field is first integrated using learnable kernels (defined as continuous weighting functions over horizontal space, height, and/or time), after which a local nonlinear mapping is applied only to the resulting kernel-integrated features and optional local inputs. This design confines nonlinear interactions to a small set of integrated features and makes each kernel directly interpretable as a weighting pattern that reveals which horizontal locations, vertical levels, and past timesteps contribute most to the prediction. We demonstrate the framework for South Asian monsoon precipitation using a hierarchy of neural network models with increasing structure, including baseline, nonparametric kernel, and parametric kernel models. Across this hierarchy, kernel models achieve near-baseline performance with far fewer trainable parameters, indicating that much of the relevant nonlocal information can be captured through a small set of interpretable integrations when appropriate structural constraints are imposed.
title Data-Driven Integration Kernels for Interpretable Nonlocal Operator Learning
topic Machine Learning
Atmospheric and Oceanic Physics
url https://arxiv.org/abs/2603.10305