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,...

Full description

Saved in:
Bibliographic Details
Main Authors: Jin Li, Wentao Hu, Zhigang Zhou
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!
_version_ 1849309562522304512
author Jin Li
Wentao Hu
Zhigang Zhou
author_facet Jin Li
Wentao Hu
Zhigang Zhou
author_sort Jin Li
collection DOAJ
description 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.
format Article
id doaj-art-120afb6bb1a346aaa2aac24bb3adfa5b
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-120afb6bb1a346aaa2aac24bb3adfa5b2025-08-20T03:54:07ZengIEEEIEEE Access2169-35362025-01-0113886008860810.1109/ACCESS.2025.357144011007152MRIE: Enhanced Rainfall Intensity Estimation With Two-Stage Multimodal Deep LearningJin Li0https://orcid.org/0009-0004-0845-3001Wentao Hu1https://orcid.org/0009-0001-4335-4429Zhigang Zhou2https://orcid.org/0009-0003-2525-1906School of Electronics and Information Engineering, Hangzhou Dianzi University, Hangzhou, ChinaSchool of Electronics and Information Engineering, Hangzhou Dianzi University, Hangzhou, ChinaSchool of Electronics and Information Engineering, Hangzhou Dianzi University, Hangzhou, ChinaAccurate 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.https://ieeexplore.ieee.org/document/11007152/Rainfall intensity estimationmultimodal sensorsnoise robustnessenvironmental monitoringdeep learning
spellingShingle Jin Li
Wentao Hu
Zhigang Zhou
MRIE: Enhanced Rainfall Intensity Estimation With Two-Stage Multimodal Deep Learning
IEEE Access
Rainfall intensity estimation
multimodal sensors
noise robustness
environmental monitoring
deep learning
title MRIE: Enhanced Rainfall Intensity Estimation With Two-Stage Multimodal Deep Learning
title_full MRIE: Enhanced Rainfall Intensity Estimation With Two-Stage Multimodal Deep Learning
title_fullStr MRIE: Enhanced Rainfall Intensity Estimation With Two-Stage Multimodal Deep Learning
title_full_unstemmed MRIE: Enhanced Rainfall Intensity Estimation With Two-Stage Multimodal Deep Learning
title_short MRIE: Enhanced Rainfall Intensity Estimation With Two-Stage Multimodal Deep Learning
title_sort mrie enhanced rainfall intensity estimation with two stage multimodal deep learning
topic Rainfall intensity estimation
multimodal sensors
noise robustness
environmental monitoring
deep learning
url https://ieeexplore.ieee.org/document/11007152/
work_keys_str_mv AT jinli mrieenhancedrainfallintensityestimationwithtwostagemultimodaldeeplearning
AT wentaohu mrieenhancedrainfallintensityestimationwithtwostagemultimodaldeeplearning
AT zhigangzhou mrieenhancedrainfallintensityestimationwithtwostagemultimodaldeeplearning