PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
Synapse
⌘+K
Synapse
February 28, 2026Applied SciencesOpen Access

Prediction of Northeast China Cold Vortex Paths Based on Multi-Generator with Integrated Multimodal Features

View Full Paper
Ask AI
Bookmark
Share

Authors

YJYuanzhen JiaoDWDongyang Wu

Discussion

Loading...

Member takes

Overview

This research demonstrates improved forecasting accuracy of cold vortex paths in Northeast China, suggesting enhanced weather prediction methods.

Key Points

  • The aim is to enhance prediction accuracy of Northeast China Cold Vortex (NCCV) trajectories using artificial intelligence techniques.
  • Constructed a 23-year multi-modal spatiotemporal dataset of NCCV using ERA5 reanalysis data.
  • Developed an improved generative adversarial network model with a multi-encoder architecture.
  • Introduced a multi-generator structure to enhance prediction capability.
  • Implemented a selector module for optimal path selection.
  • Conducted ablation experiments comparing single- to multi-modal data inputs.
  • Achieved a reduction in average prediction error by 67.96 km, a 34.0% improvement over previous models.
  • Improved 24-hour prediction error by 39.7%.
  • Demonstrated superior trajectory prediction accuracy for intervals of 6 h, 12 h, 18 h, and 24 h.
  • Reduced prediction distance errors by 21.4%, 29.2%, 34.0%, and 37.0% compared to LSTM models.

Cite This Study

Jiao et al. (2026) studied this question.

synapsesocial.com/papers/69a286da0a974eb0d3c0226fhttps://doi.org/10.3390/app16052280
View Full Paper
Ask AI
Bookmark
Share