A Physics-Constrained Implicit Profile Network for Continuous Reconstruction of Tropical Cyclone Near-Surface Wind Profiles
Abstract
Near the ocean surface, tropical cyclone winds change rapidly with height, but direct measurements are limited because aircraft dropsondes provide only sparse and irregular observations. Continuous wind profiles are important for understanding hurricane boundary-layer processes, improving storm-surge prediction, supporting offshore engineering, and assessing coastal hazards. In this study, we developed an artificial intelligence model that combines machine learning with physical principles to reconstruct continuous wind profiles from sparse observations. The model is designed to preserve the observed surface winds while generating realistic changes in wind speed and direction with height. Tests using more than two decades of NOAA hurricane observations show that the method accurately reproduces the vertical structure of tropical cyclone winds over a wide range of storm intensities. The framework can also extend satellite-derived surface wind measurements into three-dimensional near-surface wind fields, providing new opportunities for hurricane research, operational forecasting, and engineering applications.
Related
- Causal-prior-constrained deep learning for rapid-intensification warning of western North Pacific tropical cyclones
- Efficient One-Step Surface-Wave Tomography through Implicit Differentiation and Jacobian Factorization
- An AI-assisted conditioning and geological interpretation workflow for usage in implicit geological modeling
- Efficient Uncertainty Quantification for Marine CSEM via Swi-DREI: A Physics-Driven Deep Reparameterization Ensemble Approach with Implicit Regularization
- Skillful Seasonal Tropical Cyclone Prediction with AI Weather--Climate Models Forced by Dynamically Predicted SSTs
BibTeX
@misc{ma2026physicsconstrained,
title = {{A Physics-Constrained Implicit Profile Network for Continuous Reconstruction of Tropical Cyclone Near-Surface Wind Profiles}},
author = {Jian Ma and Yilin Yang and Robert Rogers and Jun A. Zhang and Jie Tang},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.11405},
eprint = {2610.11405},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.11405},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - A Physics-Constrained Implicit Profile Network for Continuous Reconstruction of Tropical Cyclone Near-Surface Wind Profiles
AU - Jian Ma
AU - Yilin Yang
AU - Robert Rogers
AU - Jun A. Zhang
AU - Jie Tang
PY - 2026
DA - 2026/10/08
PB - arXiv
DO - 10.48550/arxiv.2610.11405
UR - https://arxiv.org/abs/2610.11405
AB - Near the ocean surface, tropical cyclone winds change rapidly with height, but direct measurements are limited because aircraft dropsondes provide only sparse and irregular observations. Continuous wind profiles are important for understanding hurricane boundary-layer processes, improving storm-surge prediction, supporting offshore engineering, and assessing coastal hazards. In this study, we developed an artificial intelligence model that combines machine learning with physical principles to reconstruct continuous wind profiles from sparse observations. The model is designed to preserve the observed surface winds while generating realistic changes in wind speed and direction with height. Tests using more than two decades of NOAA hurricane observations show that the method accurately reproduces the vertical structure of tropical cyclone winds over a wide range of storm intensities. The framework can also extend satellite-derived surface wind measurements into three-dimensional near-surface wind fields, providing new opportunities for hurricane research, operational forecasting, and engineering applications.
ER -