Reconstructing Tornadoes in 3D with Gaussian Splatting

2025-06-23

AI Summary

This study addresses the challenge of achieving high-fidelity 3D reconstruction of tornadoes’ complex, transient structures. We first establish a multi-view synchronized dataset of laboratory-generated tornadoes under controlled conditions—a novel benchmark for atmospheric flow reconstruction. Leveraging this dataset, we propose and validate 3D Gaussian Splatting (3DGS) for reconstructing unsteady meteorological flow fields, demonstrating its superiority over conventional voxel-based and neural radiance field (NeRF) approaches in reconstruction accuracy, geometric detail preservation, and rendering efficiency. Our method achieves high-quality, dynamic 3D visualization of tornado structures at millimeter-scale resolution. This work provides the first publicly available, reproducible dataset and reconstruction framework specifically designed for tornado modeling—enabling rigorous validation of numerical simulations, mechanistic analysis of vortex dynamics, and training of data-driven severe-weather forecasting and early-warning systems.

Technology Category

• Computer Vision: 3D Computer Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Machine Learning: Feature Construction/Reformulation

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Security and Privacy: Data transparency and provenance

Abstract

Accurately reconstructing the 3D structure of tornadoes is critically important for understanding and preparing for this highly destructive weather phenomenon. While modern 3D scene reconstruction techniques, such as 3D Gaussian splatting (3DGS), could provide a valuable tool for reconstructing the 3D structure of tornados, at present we are critically lacking a controlled tornado dataset with which to develop and validate these tools. In this work we capture and release a novel multiview dataset of a small lab-based tornado. We demonstrate one can effectively reconstruct and visualize the 3D structure of this tornado using 3DGS.

Problem

• Reconstructing 3D tornado structures accurately
• Lacking controlled tornado datasets for validation
• Developing 3D Gaussian splatting for tornado visualization

Innovation

• Uses 3D Gaussian splatting for tornado reconstruction
• Introduces lab-based multiview tornado dataset
• Validates 3D structure visualization with 3DGS