PreprintarXiv licencearXiv
A Non-Stationary Spatio-Temporal Covariance Model with Dynamic Advection Effects for Rainfall Data
Abstract
We propose a non-stationary model constructed using a mixture of spatio-temporal covariance models with advection effects; namely, models that have larger covariance values along an orientation vector in the spatio-temporal index set, that simulate wind direction and cloud movement. We show that a mixture of such models can allow for wind direction change in data during (estimated) time intervals, unlike traditional models that use rigid advection effects. We construct a MCMC procedure for Bayesian estimation, and illustrate the method with the analysis of a severe rainfall event from the southeastern region of Brazil.
Related
- Concentration of Stationary Measures onto Large Scales in the Fast-Advection Limit of the Stochastically Forced Two-Dimensional Navier-Stokes Equations
- COSTA: Covariance-Optimized Design and Causal Inference under Network-Temporal Interference
- Independently Verified Causal Spatio-Temporal Covariance Under Correlated Amplitude and Pointing Noise in Fractional Nonlocal Photo-Thermoelastic Semiconductors
- Fundamental Limits of Dynamic Tracking and Communication: A Stationary Policy Formulation
- Dynamic Policy Evaluation and Learning with Spatio-temporal Data
BibTeX
@misc{ramos2026nonstationary,
title = {{A Non-Stationary Spatio-Temporal Covariance Model with Dynamic Advection Effects for Rainfall Data}},
author = {Pedro Nasevicius Ramos and Guilherme Ludwig},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2606.24076},
eprint = {2606.24076},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.24076},
}
RIS
TY - UNPB
TI - A Non-Stationary Spatio-Temporal Covariance Model with Dynamic Advection Effects for Rainfall Data
AU - Pedro Nasevicius Ramos
AU - Guilherme Ludwig
PY - 2026
DA - 2026/10/11
PB - arXiv
DO - 10.48550/arxiv.2606.24076
UR - https://arxiv.org/abs/2606.24076
AB - We propose a non-stationary model constructed using a mixture of spatio-temporal covariance models with advection effects; namely, models that have larger covariance values along an orientation vector in the spatio-temporal index set, that simulate wind direction and cloud movement. We show that a mixture of such models can allow for wind direction change in data during (estimated) time intervals, unlike traditional models that use rigid advection effects. We construct a MCMC procedure for Bayesian estimation, and illustrate the method with the analysis of a severe rainfall event from the southeastern region of Brazil.
ER -