Machine learning model design for IoT-based flooding forecast

Qinghua Wang

doi:10.1109/CyberC55534.2022.00025

Machine learning model design for IoT-based flooding forecast

Qinghua Wang

Research output: Contribution to conference › Paper › peer-review

5 Citations (Scopus)

Abstract

Flooding risk is a threat to sea-level residential areas in southern Sweden. An Internet of things (IoT) project has been deployed to monitor weather and water pipe conditions in Kristianstad, Sweden. The IoT data however only monitors the current condition and does not tell the future threat. Machine learning models using deep learning neural networks have been developed to predict future threats based on IoT data and weather forecast. This paper presents multiple model architectures and their performances. All the models are explainable. Finally, a conclusion is made by selecting the best-functioning model in the context of flooding risk prediction in Kristianstad.

Original language	English
Pages	97-103
Number of pages	7
DOIs	https://doi.org/10.1109/CyberC55534.2022.00025
Publication status	Published - 2022
Event	2022 International Conference on Cyber-enabled Distributed Computing and Knowledge Discovery (CyberC) - Jiangsu, China, Suzhou, China Duration: 2022-Dec-15 → 2022-Dec-16 Conference number: 2022 https://conferences.computer.org/cybercpub/#!/toc/0

Conference

Conference	2022 International Conference on Cyber-enabled Distributed Computing and Knowledge Discovery (CyberC)
Abbreviated title	CyberC
Country/Territory	China
City	Suzhou
Period	22-12-15 → 22-12-16
Internet address	https://conferences.computer.org/cybercpub/#!/toc/0

Swedish Standard Keywords

Electrical Engineering, Electronic Engineering, Information Engineering (202)

Keywords

Flooding risk prediction
Time series forecast
Explainable AI
Neural network

Access to Document

10.1109/CyberC55534.2022.00025

5 Citations
1 Abstract
1 Paper

Flooding alert system for Kristianstad Municipality using machine learning
Abdelrahman, W., Thomasson, M. & Wang, Q., 2022.
Research output: Contribution to conference › Paper › peer-review

File
Smart Sewage Water Management and Data Forecast
Wang, Q., Westlund, V., Johansson, J. & Lindgren, M., 2021.
Research output: Contribution to conference › Abstract
6 Citations (Scopus)

1 Finished

Smart-VA: Smart real time monitoring of sewage water system with data analysis
Wang, Q. (PI), Mårtensson, L. (CoI), Abdelrahman, W. (Researcher), Veletanlic, B. (Administrator), Frisk, F. (Researcher), Johansson, O. (Researcher), Lindgren, M. (Researcher) & Wemmenborn, M. (Project coordinator)
21-01-15 → 23-01-14
Project: Research

Cite this

@conference{6886c988bf554477b2796928422b3f98,

title = "Machine learning model design for IoT-based flooding forecast",

abstract = "Flooding risk is a threat to sea-level residential areas in southern Sweden. An Internet of things (IoT) project has been deployed to monitor weather and water pipe conditions in Kristianstad, Sweden. The IoT data however only monitors the current condition and does not tell the future threat. Machine learning models using deep learning neural networks have been developed to predict future threats based on IoT data and weather forecast. This paper presents multiple model architectures and their performances. All the models are explainable. Finally, a conclusion is made by selecting the best-functioning model in the context of flooding risk prediction in Kristianstad.",

keywords = "Flooding risk prediction, Time series forecast, Explainable AI, Neural network",

author = "Qinghua Wang",

year = "2022",

doi = "10.1109/CyberC55534.2022.00025",

language = "English",

pages = "97--103",

note = "2022 International Conference on Cyber-enabled Distributed Computing and Knowledge Discovery (CyberC), CyberC ; Conference date: 15-12-2022 Through 16-12-2022",

url = "https://conferences.computer.org/cybercpub/\#!/toc/0",

}

TY - CONF

T1 - Machine learning model design for IoT-based flooding forecast

AU - Wang, Qinghua

N1 - Conference code: 2022

PY - 2022

Y1 - 2022

N2 - Flooding risk is a threat to sea-level residential areas in southern Sweden. An Internet of things (IoT) project has been deployed to monitor weather and water pipe conditions in Kristianstad, Sweden. The IoT data however only monitors the current condition and does not tell the future threat. Machine learning models using deep learning neural networks have been developed to predict future threats based on IoT data and weather forecast. This paper presents multiple model architectures and their performances. All the models are explainable. Finally, a conclusion is made by selecting the best-functioning model in the context of flooding risk prediction in Kristianstad.

AB - Flooding risk is a threat to sea-level residential areas in southern Sweden. An Internet of things (IoT) project has been deployed to monitor weather and water pipe conditions in Kristianstad, Sweden. The IoT data however only monitors the current condition and does not tell the future threat. Machine learning models using deep learning neural networks have been developed to predict future threats based on IoT data and weather forecast. This paper presents multiple model architectures and their performances. All the models are explainable. Finally, a conclusion is made by selecting the best-functioning model in the context of flooding risk prediction in Kristianstad.

KW - Flooding risk prediction

KW - Time series forecast

KW - Explainable AI

KW - Neural network

U2 - 10.1109/CyberC55534.2022.00025

DO - 10.1109/CyberC55534.2022.00025

M3 - Paper

SP - 97

EP - 103

T2 - 2022 International Conference on Cyber-enabled Distributed Computing and Knowledge Discovery (CyberC)

Y2 - 15 December 2022 through 16 December 2022

ER -

Machine learning model design for IoT-based flooding forecast

Abstract

Conference

Swedish Standard Keywords

Keywords

Access to Document

Fingerprint

Research output

Flooding alert system for Kristianstad Municipality using machine learning

Smart Sewage Water Management and Data Forecast

Projects

Smart-VA: Smart real time monitoring of sewage water system with data analysis

Cite this