Estimating rainfall intensity based on surveillance audio and deep-learning

Rainfall data with high spatial and temporal resolutions are essential for urban hydrological modeling. Ubiquitous surveillance cameras can continuously record rainfall events through video and audio, so they have been recognized as potential rain gauges to supplement professional rainfall observati...

Full description

Saved in:
Bibliographic Details
Main Authors: Meizhen Wang, Mingzheng Chen, Ziran Wang, Yuxuan Guo, Yong Wu, Wei Zhao, Xuejun Liu
Format: Article
Language:English
Published: Elsevier 2024-11-01
Series:Environmental Science and Ecotechnology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666498424000644
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846166909014245376
author Meizhen Wang
Mingzheng Chen
Ziran Wang
Yuxuan Guo
Yong Wu
Wei Zhao
Xuejun Liu
author_facet Meizhen Wang
Mingzheng Chen
Ziran Wang
Yuxuan Guo
Yong Wu
Wei Zhao
Xuejun Liu
author_sort Meizhen Wang
collection DOAJ
description Rainfall data with high spatial and temporal resolutions are essential for urban hydrological modeling. Ubiquitous surveillance cameras can continuously record rainfall events through video and audio, so they have been recognized as potential rain gauges to supplement professional rainfall observation networks. Since video-based rainfall estimation methods can be affected by variable backgrounds and lighting conditions, audio-based approaches could be a supplement without suffering from these conditions. However, most audio-based approaches focus on rainfall-level classification rather than rainfall intensity estimation. Here, we introduce a dataset named Surveillance Audio Rainfall Intensity Dataset (SARID) and a deep learning model for estimating rainfall intensity. First, we created the dataset through audio of six real-world rainfall events. This dataset's audio recordings are segmented into 12,066 pieces and annotated with rainfall intensity and environmental information, such as underlying surfaces, temperature, humidity, and wind. Then, we developed a deep learning-based baseline using Mel-Frequency Cepstral Coefficients (MFCC) and Transformer architecture to estimate rainfall intensity from surveillance audio. Validated from ground truth data, our baseline achieves a root mean absolute error of 0.88 mm h-1 and a coefficient of correlation of 0.765. Our findings demonstrate the potential of surveillance audio-based models as practical and effective tools for rainfall observation systems, initiating a new chapter in rainfall intensity estimation. It offers a novel data source for high-resolution hydrological sensing and contributes to the broader landscape of urban sensing, emergency response, and resilience.
format Article
id doaj-art-8390c4d9273d47f4b3c01988108709c4
institution Kabale University
issn 2666-4984
language English
publishDate 2024-11-01
publisher Elsevier
record_format Article
series Environmental Science and Ecotechnology
spelling doaj-art-8390c4d9273d47f4b3c01988108709c42024-11-15T06:15:13ZengElsevierEnvironmental Science and Ecotechnology2666-49842024-11-0122100450Estimating rainfall intensity based on surveillance audio and deep-learningMeizhen Wang0Mingzheng Chen1Ziran Wang2Yuxuan Guo3Yong Wu4Wei Zhao5Xuejun Liu6Key Laboratory of Virtual Geographic Environment (Nanjing Normal University), Ministry of Education, Nanjing, 210023, China; State Key Laboratory Cultivation Base of Geographical Environment Evolution (Jiangsu Province), Nanjing, 210023, China; Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application, Nanjing, 210023, ChinaKey Laboratory of Virtual Geographic Environment (Nanjing Normal University), Ministry of Education, Nanjing, 210023, China; State Key Laboratory Cultivation Base of Geographical Environment Evolution (Jiangsu Province), Nanjing, 210023, China; Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application, Nanjing, 210023, ChinaKey Laboratory of Virtual Geographic Environment (Nanjing Normal University), Ministry of Education, Nanjing, 210023, China; State Key Laboratory Cultivation Base of Geographical Environment Evolution (Jiangsu Province), Nanjing, 210023, China; Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application, Nanjing, 210023, China; School of Information Engineering, Nanjing Normal University Taizhou College, Taizhou 225300, ChinaKey Laboratory of Virtual Geographic Environment (Nanjing Normal University), Ministry of Education, Nanjing, 210023, China; State Key Laboratory Cultivation Base of Geographical Environment Evolution (Jiangsu Province), Nanjing, 210023, China; Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application, Nanjing, 210023, ChinaInstitute of Geography, Fujian Normal University, Fuzhou, 350000, ChinaKey Laboratory of Virtual Geographic Environment (Nanjing Normal University), Ministry of Education, Nanjing, 210023, China; State Key Laboratory Cultivation Base of Geographical Environment Evolution (Jiangsu Province), Nanjing, 210023, China; Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application, Nanjing, 210023, ChinaKey Laboratory of Virtual Geographic Environment (Nanjing Normal University), Ministry of Education, Nanjing, 210023, China; State Key Laboratory Cultivation Base of Geographical Environment Evolution (Jiangsu Province), Nanjing, 210023, China; Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application, Nanjing, 210023, China; Corresponding author. Key Laboratory of Virtual Geographic Environment (Nanjing Normal University), Ministry of Education, Nanjing, 210023, China.Rainfall data with high spatial and temporal resolutions are essential for urban hydrological modeling. Ubiquitous surveillance cameras can continuously record rainfall events through video and audio, so they have been recognized as potential rain gauges to supplement professional rainfall observation networks. Since video-based rainfall estimation methods can be affected by variable backgrounds and lighting conditions, audio-based approaches could be a supplement without suffering from these conditions. However, most audio-based approaches focus on rainfall-level classification rather than rainfall intensity estimation. Here, we introduce a dataset named Surveillance Audio Rainfall Intensity Dataset (SARID) and a deep learning model for estimating rainfall intensity. First, we created the dataset through audio of six real-world rainfall events. This dataset's audio recordings are segmented into 12,066 pieces and annotated with rainfall intensity and environmental information, such as underlying surfaces, temperature, humidity, and wind. Then, we developed a deep learning-based baseline using Mel-Frequency Cepstral Coefficients (MFCC) and Transformer architecture to estimate rainfall intensity from surveillance audio. Validated from ground truth data, our baseline achieves a root mean absolute error of 0.88 mm h-1 and a coefficient of correlation of 0.765. Our findings demonstrate the potential of surveillance audio-based models as practical and effective tools for rainfall observation systems, initiating a new chapter in rainfall intensity estimation. It offers a novel data source for high-resolution hydrological sensing and contributes to the broader landscape of urban sensing, emergency response, and resilience.http://www.sciencedirect.com/science/article/pii/S2666498424000644Surveillance audioRainfall intensityDatasetRegressionDeep learning
spellingShingle Meizhen Wang
Mingzheng Chen
Ziran Wang
Yuxuan Guo
Yong Wu
Wei Zhao
Xuejun Liu
Estimating rainfall intensity based on surveillance audio and deep-learning
Environmental Science and Ecotechnology
Surveillance audio
Rainfall intensity
Dataset
Regression
Deep learning
title Estimating rainfall intensity based on surveillance audio and deep-learning
title_full Estimating rainfall intensity based on surveillance audio and deep-learning
title_fullStr Estimating rainfall intensity based on surveillance audio and deep-learning
title_full_unstemmed Estimating rainfall intensity based on surveillance audio and deep-learning
title_short Estimating rainfall intensity based on surveillance audio and deep-learning
title_sort estimating rainfall intensity based on surveillance audio and deep learning
topic Surveillance audio
Rainfall intensity
Dataset
Regression
Deep learning
url http://www.sciencedirect.com/science/article/pii/S2666498424000644
work_keys_str_mv AT meizhenwang estimatingrainfallintensitybasedonsurveillanceaudioanddeeplearning
AT mingzhengchen estimatingrainfallintensitybasedonsurveillanceaudioanddeeplearning
AT ziranwang estimatingrainfallintensitybasedonsurveillanceaudioanddeeplearning
AT yuxuanguo estimatingrainfallintensitybasedonsurveillanceaudioanddeeplearning
AT yongwu estimatingrainfallintensitybasedonsurveillanceaudioanddeeplearning
AT weizhao estimatingrainfallintensitybasedonsurveillanceaudioanddeeplearning
AT xuejunliu estimatingrainfallintensitybasedonsurveillanceaudioanddeeplearning