Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Nov 5;22(21):8532.
doi: 10.3390/s22218532.

Development of an Artificial Neural Network Algorithm Embedded in an On-Site Sensor for Water Level Forecasting

Cheng-Han Liu  1 , Tsun-Hua Yang  1 , Obaja Triputera Wijaya  1   2
Affiliations

Development of an Artificial Neural Network Algorithm Embedded in an On-Site Sensor for Water Level Forecasting

Cheng-Han Liu et al. Sensors (Basel). .

Abstract

Extreme weather events cause stream overflow and lead to urban inundation. In this study, a decentralized flood monitoring system is proposed to provide water level predictions in streams three hours ahead. The customized sensor in the system measures the water levels and implements edge computing to produce future water levels. It is very different from traditional centralized monitoring systems and considered an innovation in the field. In edge computing, traditional physics-based algorithms are not computationally efficient if microprocessors are used in sensors. A correlation analysis was performed to identify key factors that influence the variations in the water level forecasts. For example, the second-order difference in the water level is considered to represent the acceleration or deacceleration of a water level rise. According to different input factors, three artificial neural network (ANN) models were developed. Four streams or canals were selected to test and evaluate the performance of the models. One case was used for model training and testing, and the others were used for model validation. The results demonstrated that the ANN model with the second-order water level difference as an input factor outperformed the other ANN models in terms of RMSE. The customized microprocessor-based sensor with an embedded ANN algorithm can be adopted to improve edge computing capabilities and support emergency response and decision making.

Keywords: ANN; decentralized; edge computing; microprocessor; water level prediction.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
The four study areas are the Shimen canal in Taoyuan County (upper left), the Yilan River in Yilan County (upper right), the Beinan River in Taitung County (bottom right), and the Toucian River in Hsinchu County (bottom left), Taiwan.
Figure 2
Figure 2
System data processing flowchart.
Figure 3
Figure 3
Details of the RPi-based ultrasonic water level sensor (left) and the installation of the sensor (right).
Figure 4
Figure 4
A three-layer ANN model and its data processing flowchart.
Figure 5
Figure 5
Research flowchart of the proposed ANN models.
Figure 6
Figure 6
(a–e) The hourly rainfall distribution for different return periods in the Yilan River basin at YR_R1-YR_R5.
Figure 6
Figure 6
(a–e) The hourly rainfall distribution for different return periods in the Yilan River basin at YR_R1-YR_R5.
Figure 7
Figure 7
Synthetic inflow hydrograph at YR_Q1 in the Yilan River basin for different return periods.
Figure 8
Figure 8
Comparison of the simulated and observed water levels at YR_R2 for (a) Typhoon Soulik; (b) Typhoon Dujuan; and (c) Typhoon Megi.
Figure 9
Figure 9
Comparison of simulated and observed water levels at YR_R2 for the ANN_1 model (left) and ANN_2 model (right) at Yutu (a), Mangkut (b), and Maria (c).
Figure 10
Figure 10
(a–c) Comparison of simulation and observed water levels at SC_S2 of Shimen canal for lead times t + 1 h, t + 2, and t + 3 h, respectively.
Figure 11
Figure 11
(a–c) Comparison of simulation and observed water levels at TR_S2 of the Touciaan River for lead times t + 1 h, t + 2, and t + 3 h, respectively.
Figure 11
Figure 11
(a–c) Comparison of simulation and observed water levels at TR_S2 of the Touciaan River for lead times t + 1 h, t + 2, and t + 3 h, respectively.
Figure 12
Figure 12
(a–c) Comparison of simulation and observed water levels at BR_S2 of the Beinan River for lead times t + 1 h, t + 2, and t + 3 h, respectively.
Figure 12
Figure 12
(a–c) Comparison of simulation and observed water levels at BR_S2 of the Beinan River for lead times t + 1 h, t + 2, and t + 3 h, respectively.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Centre for Research on the Epidemiology of Disasters (CRED) 2021 Disasters in Numbers. CRED; Brussels, Belgium: 2021.
    1. Okazawa Y., Yeh P.J.-F., Kanae S., Oki T. Development of a global flood risk index based on natural and socio-economic factors. Hydrol. Sci. J. 2011;56:789–804. doi: 10.1080/02626667.2011.583249. - DOI
    1. Yildirim E., Demir I. An Integrated Flood Risk Assessment and Mitigation Framework: A Case Study for Middle Cedar River Basin, Iowa, US. Int. J. Disaster Risk Reduct. 2021;56:102113. doi: 10.1016/j.ijdrr.2021.102113. - DOI
    1. United Nations Office for Disaster Risk Reduction . Global Assessment Report on Global Disaster Risk Reduction GAR 2022-Our World at Risk: Transforming Governance for a Resilient Future. United Nations Office for Disaster Risk Reduction; Geneva, Switzerland: 2022.
    1. Kang S., David D.S.K., Yang M., Yu Y.C., Ham S. Energy-Efficient Ultrasonic Water Level Detection System with Dual-Target Monitoring. Sens. Basel. 2021;21:2241. doi: 10.3390/s21062241. - DOI - PMC - PubMed

LinkOut - more resources