---
title: "Nowcasting of Tropical Cyclone Wind Fields and Intensity from Geostationary Imagery"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.08255v1"
permalink: "https://feed.astralor.com/items/itm_5e938b67019c8a3564045727"
published: "2026-11-05T16:31:38.000Z"
score: 55
channel: "tech"
tags: ["RAG","Nowcasting","Tropical Cyclone Wind","Fields","Intensity","Geostationary Imagery High-resolution","SAR","High-resolution"]
---

# Nowcasting of Tropical Cyclone Wind Fields and Intensity from Geostationary Imagery

## 速览

High-resolution tropical cyclone surface wind speeds derived from synthetic aperture radar (SAR) observations can support storm structure and intensity modelling, but remain spatially and temporally sparse and unavailab…

## 关键点

- High-resolution tropical cyclone surface wind speeds derived from synthetic aperture radar (SAR) observations can support storm structure and intensity modelling, but remain spatially and temporally sparse and unavailab…
- Geostationary satellites capture cloud tops continuously in space and time, but do not directly resolve surface winds.
- Here, we present simple neural networks to predict 2D wind fields and storm-scale intensity metrics from geostationary imagery.

## 全文

High-resolution tropical cyclone surface wind speeds derived from synthetic aperture radar (SAR) observations can support storm structure and intensity modelling, but remain spatially and temporally sparse and unavailable near-real-time. Geostationary satellites capture cloud tops continuously in space and time, but do not directly resolve surface winds. Here, we present simple neural networks to predict 2D wind fields and storm-scale intensity metrics from geostationary imagery. Through a series of ablation studies, we find that joint prediction of 2D fields and scalar metrics from the model latent space improves the retrieval of the (radius of) maximum wind, especially for rapid intensification events.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_5e938b67019c8a3564045727