Modeling nonstationary spatial processes with normalizing flows

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Nag, Pratik, Zammit-Mangion, Andrew, Sun, Ying
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911695293644800
author Nag, Pratik
Zammit-Mangion, Andrew
Sun, Ying
author_facet Nag, Pratik
Zammit-Mangion, Andrew
Sun, Ying
contents Nonstationary spatial processes can often be represented as stationary processes on a warped spatial domain. Selecting an appropriate spatial warping function for a given application is often difficult and, as a result of this, warping methods have largely been limited to two-dimensional spatial domains. In this paper, we introduce a novel approach to modeling nonstationary, anisotropic spatial processes using neural autoregressive flows (NAFs), a class of invertible mappings capable of generating complex, high-dimensional warpings. Through simulation studies we demonstrate that a NAF-based model has greater representational capacity than other commonly used spatial process models. We apply our proposed modeling framework to a subset of the 3D Argo Floats dataset, highlighting the utility of our framework in real-world applications.
format Preprint
id arxiv_https___arxiv_org_abs_2509_12884
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Modeling nonstationary spatial processes with normalizing flows
Nag, Pratik
Zammit-Mangion, Andrew
Sun, Ying
Methodology
Machine Learning
Nonstationary spatial processes can often be represented as stationary processes on a warped spatial domain. Selecting an appropriate spatial warping function for a given application is often difficult and, as a result of this, warping methods have largely been limited to two-dimensional spatial domains. In this paper, we introduce a novel approach to modeling nonstationary, anisotropic spatial processes using neural autoregressive flows (NAFs), a class of invertible mappings capable of generating complex, high-dimensional warpings. Through simulation studies we demonstrate that a NAF-based model has greater representational capacity than other commonly used spatial process models. We apply our proposed modeling framework to a subset of the 3D Argo Floats dataset, highlighting the utility of our framework in real-world applications.
title Modeling nonstationary spatial processes with normalizing flows
topic Methodology
Machine Learning
url https://arxiv.org/abs/2509.12884