MRIE: Enhanced Rainfall Intensity Estimation With Two-Stage Multimodal Deep Learning
Accurate rainfall intensity estimation is crucial for environmental monitoring and urban planning. However, the reliability of existing methods in practical applications is relatively low due to certain deficiencies in data processing and noise resistance. To address these issues, MRIE is proposed,...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11007152/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Accurate rainfall intensity estimation is crucial for environmental monitoring and urban planning. However, the reliability of existing methods in practical applications is relatively low due to certain deficiencies in data processing and noise resistance. To address these issues, MRIE is proposed, a two-stage multimodal framework that integrates data from environmental sensors and audio recordings to improve estimation accuracy. MRIE effectively fuses complementary information from multiple sensor modalities and demonstrates strong robustness with the help of a cross-modal guidance module and advanced feature fusion techniques. Experimental results show that the MAE and RMSE of MRIE are reduced by 40.7% and 29.1% respectively, and the <inline-formula> <tex-math notation="LaTeX">$R^{2}$ </tex-math></inline-formula> is increased by 17.3%, compared with the best baseline. These research findings highlight the potential of MRIE as a powerful and reliable tool for sensor-based rainfall monitoring systems. |
|---|---|
| ISSN: | 2169-3536 |