PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
March 12, 2026Geophysical Research Letters2 citationsOpen Access

Advancing Convective Precipitation Nowcasting via 3D Polarimetric Radar Data and Physics‐Constrained Deep Learning Model

View Full Paper
XPXiang PanYLYinghui LuHHHao Huang

Key Points

  • The central aim is to enhance the accuracy of nowcasting severe convective precipitation using deep learning with physical constraints.
  • Introduced FURECast, a deep learning model combining 3D polarimetric radar inputs.
  • Utilized an encoder-translator-decoder architecture with late fusion for multi-level inputs.
  • Implemented a unique physical loss term to ensure microphysical consistency during model training.
  • Achieved a 14.1% improvement in the 90-min critical success index at a 35 dBZ threshold.
  • Reduced physical inconsistency by two orders of magnitude compared to the baseline model.

Abstract

Abstract Accurate nowcasting of severe convective precipitation is critical for early warning yet still remains challenging. Although deep learning methods show promise, most models lack physical constraints, limiting their consistency with atmospheric processes. We introduce FURECast, a deep learning model that not only leverages three‐dimensional structure of polarimetric radar variables ( Z H , Z DR , K DP ) but also embeds their intrinsic self‐consistency relation as a physical constraint. The model employs an encoder‐translator‐decoder architecture, integrating multi‐level inputs via late fusion and evolving features through cascaded multiscale blocks. Moreover, a novel physical loss term is introduced to enforce microphysical consistency during training. Evaluated on S‐band (GD‐SPOL) and C‐band (NJU‐CPOL) radar data sets, FURECast achieves a 14.1% improvement in 90‐min critical success index (35 dBZ threshold) over the 2D reflectivity‐only baseline, while reducing physical inconsistency by two orders of magnitude. These results underscore the value of 3D polarimetric structure and physics‐guided learning in advancing convective precipitation nowcasting.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Pan et al. (2026) studied this question.

synapsesocial.com/papers/69b257ec96eeacc4fcec7133https://doi.org/10.1029/2025gl120431
Ask AI
Helpful
Bookmark
Share
View Full Paper