dorsal/arxiv
View SchemaStatistical modelling of tropical cyclone tracks: a comparison of models for the variance of trajectories
| Authors | Tim Hall, Stephen Jewson |
|---|---|
| Categories | |
| ArXiv ID | physics/0505103 |
| URL | https://arxiv.org/abs/physics/0505103 |
Abstract
We describe results from the second stage of a project to build a statistical model for hurricane tracks. In the first stage we modelled the unconditional mean track. We now attempt to model the unconditional variance of fluctuations around the mean. The variance models we describe use a semi-parametric nearest neighbours approach in which the optimal averaging length-scale is estimated using a jack-knife out-of-sample fitting procedure. We test three different models. These models consider the variance structure of the deviations from the unconditional mean track to be isotropic, anisotropic but uncorrelated, and anisotropic and correlated, respectively. The results show that, of these models, the anisotropic correlated model gives the best predictions of the distribution of future positions of hurricanes.
{
"annotation_id": "e4a23d9a-157d-4b23-a23b-3bce26bd7abe",
"date_created": "2026-03-02T18:00:57.227000Z",
"date_modified": "2026-03-02T18:00:57.227000Z",
"file_hash": "c8d0d7c6812315840290116ac323867ba48c263b776629d0da52972810e8cbea",
"private": false,
"record": {
"abstract": "We describe results from the second stage of a project to build a statistical\nmodel for hurricane tracks. In the first stage we modelled the unconditional\nmean track. We now attempt to model the unconditional variance of fluctuations\naround the mean. The variance models we describe use a semi-parametric nearest\nneighbours approach in which the optimal averaging length-scale is estimated\nusing a jack-knife out-of-sample fitting procedure. We test three different\nmodels. These models consider the variance structure of the deviations from the\nunconditional mean track to be isotropic, anisotropic but uncorrelated, and\nanisotropic and correlated, respectively. The results show that, of these\nmodels, the anisotropic correlated model gives the best predictions of the\ndistribution of future positions of hurricanes.",
"arxiv_id": "physics/0505103",
"authors": [
"Tim Hall",
"Stephen Jewson"
],
"categories": [
"physics.ao-ph"
],
"title": "Statistical modelling of tropical cyclone tracks: a comparison of models for the variance of trajectories",
"url": "https://arxiv.org/abs/physics/0505103"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "af26e7d6-c97c-47ba-a8e6-917430296f90",
"id": "arXiv Dataset IDs",
"type": "Model",
"variant": "snapshot-2026-03-01",
"version": "0.1.0"
},
"user_id": 1000002
}