Spatio-temporal modeling and forecasting with Fourier neural operators

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nag, Pratik, Zammit-Mangion, Andrew, Singh, Sumeetpal, Cressie, Noel
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909981268246528
author Nag, Pratik
Zammit-Mangion, Andrew
Singh, Sumeetpal
Cressie, Noel
author_facet Nag, Pratik
Zammit-Mangion, Andrew
Singh, Sumeetpal
Cressie, Noel
contents Spatio-temporal process models are often used for modeling dynamic physical and biological phenomena that evolve across space and time. These phenomena may exhibit environmental heterogeneity and complex interactions that are difficult to capture using traditional statistical process models such as Gaussian processes. This work proposes the use of Fourier neural operators (FNOs) for constructing statistical dynamical spatio-temporal models for forecasting. An FNO is a flexible mapping of functions that approximates the solution operator of possibly unknown linear or non-linear partial differential equations (PDEs) in a computationally efficient manner. It does so using samples of inputs and their respective outputs, and hence explicit knowledge of the underlying PDE is not required. Through simulations from a nonlinear PDE with known solution, we compare FNO forecasts to those from state-of-the-art statistical spatio-temporal-forecasting methods. Further, using sea surface temperature data over the Atlantic Ocean and precipitation data across Europe, we demonstrate the ability of FNO-based dynamic spatio-temporal (DST) statistical modeling to capture complex real-world spatio-temporal dependencies. Using collections of testing instances, we show that the FNO-DST forecasts are accurate with valid uncertainty quantification.
format Preprint
id arxiv_https___arxiv_org_abs_2601_01813
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Spatio-temporal modeling and forecasting with Fourier neural operators
Nag, Pratik
Zammit-Mangion, Andrew
Singh, Sumeetpal
Cressie, Noel
Methodology
Machine Learning
Spatio-temporal process models are often used for modeling dynamic physical and biological phenomena that evolve across space and time. These phenomena may exhibit environmental heterogeneity and complex interactions that are difficult to capture using traditional statistical process models such as Gaussian processes. This work proposes the use of Fourier neural operators (FNOs) for constructing statistical dynamical spatio-temporal models for forecasting. An FNO is a flexible mapping of functions that approximates the solution operator of possibly unknown linear or non-linear partial differential equations (PDEs) in a computationally efficient manner. It does so using samples of inputs and their respective outputs, and hence explicit knowledge of the underlying PDE is not required. Through simulations from a nonlinear PDE with known solution, we compare FNO forecasts to those from state-of-the-art statistical spatio-temporal-forecasting methods. Further, using sea surface temperature data over the Atlantic Ocean and precipitation data across Europe, we demonstrate the ability of FNO-based dynamic spatio-temporal (DST) statistical modeling to capture complex real-world spatio-temporal dependencies. Using collections of testing instances, we show that the FNO-DST forecasts are accurate with valid uncertainty quantification.
title Spatio-temporal modeling and forecasting with Fourier neural operators
topic Methodology
Machine Learning
url https://arxiv.org/abs/2601.01813