Cyber-physical-system-based smart water system to prevent flood hazards
© The Author(s). 2018
Received: 27 November 2017
Accepted: 8 February 2018
Published: 26 February 2018
Extreme weather and climate events such as super typhoons and unprecedented recorded high intensity rainfall events have increased in recent years due to climate change. Such extreme weather events generate floods and cause loss of life and property. Therefore, efficient strategies and measures for flood mitigation and prevention are essential. Computer-aided techniques can increase the speed of emergency response and reduce the impacts of a flood.
This study applied the cyber-physical system concept to develop a smart flood information system, called Dayu Smart Water System. The system includes an on-site monitoring network and software for rapid flood modeling to provide updated information. With the utilization of Internet of Things and artificial intelligence, the system not only provides forecast information but also plays an active role by enabling users to take emergency response measures before, during, and after a flood. The system is aimed at accelerating emergency responses during a flood without requiring any human intervention.
The system was deployed in a high-tech industrial park in central Taiwan. Experimental results revealed that the system could increase the response efficiency of the emergency operations center during a few extreme events in 2017. To enable the system to respond to a wide range of flood induced threats in a more effective manner, a few advanced functions are under development and discussed in this paper.
This study utilized Dayu Smart Water System that integrates on-site monitoring sensors and advanced modeling tools to provide optimal flood forecasts. However, the proposed system has implemented only the first three levels—connection, conversion, and cyber levels. The higher the number of levels is, the more added value is the system provides. The fourth and fifth levels, namely the cognition and configuration levels, were not discussed in the study. Further developments in these two levels will be conducted.
Various disasters such as typhoons, floods, and earthquakes may occur simultaneously and cause catastrophic loss of life and property. In certain scenarios, disasters can be sequential, in that the first disaster may trigger the second one, which may trigger subsequent disasters (EISNER, 2014). Historical events such as the Thailand flood in 2011 and Fukushima Daiichi nuclear disaster in 2011 are examples of such scenarios. For example, the Thailand flood in 2011 caused over hundreds of deaths, and millions of people were affected. The economic damage was estimated to be over US$40 billion, according to a World Bank survey (Mahul, 2017). Taiwan is located in the northwestern Pacific Ocean and is struck by typhoons three to four times a year. Typhoon Morakot in 2009 is another example of such scenarios. This typhoon first engendered a considerable amount of rainfall and subsequently triggered large-scale landslides, resulting in more than hundreds of deaths in the south of Taiwan. Extreme weather and climate events such as super typhoons and unprecedented high-intensity rainfall events will attract more attention in the future because of the impact of climate change. Structural measures, including the construction of structures such as dams and river bifurcation, are proven to be effective for flood mitigation. However, the failure of structural measures may cause greater disasters. Nonstructural measures such as early warning systems can enable first responders to take necessary actions for reducing damage and losses. Most early warning systems only provide passive information such as flood forecasts or real-time observations (Thielen et al., 2009; Lopez-Trujillo, 2010; Yang et al., 2015).
The rapid development of artificial intelligence (AI) and Internet of Things (IoT) can transform early warning systems from passive information provides to active systems that implement necessary actions during a disaster. AI has been applied to disaster forecasting, prevention, and mitigation. For example, Augello et al. (2016) used an agent model and a monitoring network to propose preventive measures and provide alerts before the occurrence of an event. A chatbot was created at the front end of the system to interact with users. Various studies have proved that AI can accelerate complicated processes and generate efficient solutions not only in disaster-related fields but also in many other fields (e.g., Monostori 2003; Alemdar et al., 2017). IoT was introduced in 2005 and is mostly applied to supply chain management, environmental monitoring, and other nonstress environments. Yang et al. (2015) identified that the IoT technology can match identified information requirements and provide added value to emergency response operations in terms of obtaining efficient cooperation, accurate situational awareness, and complete resource visibility. Therefore, this study utilized AI and IoT to develop a cyber-physical-system (CPS)-based smart water system—called Dayu Smart Water System (DayuSWS)—that integrates on-site monitoring sensors and advanced modeling tools to provide optimal flood forecasts. In addition, the system analyzes all the collected information and forecasts to trigger active actions based on the situation; for example, the system controls the start or stop function of water pumps. The remainder of this paper is organized as follows. Study area section briefly describes the study area in which the system was deployed. Components of the CPS-based smart flood information system section explains the concept of a CPS and its application in the study. Case and discussion section presents the case study and discussion. Finally, Conclusions section concludes the paper.
Components of the CPS-based smart flood information system
The connection and conversion levels transform real-time observations to useful information for decision-makers. The information obtained is highly accurate because it is based on on-site observations. However, information with an adequate lead time could not be provided. Therefore, the cyber level is employed to provide forecasts with a longer lead time. In this study, the cyber level was determined to provide flood forecasts with a lead time of 6 h. To obtain the forecasts, a 1D–1D dual drainage model was included, with rainfall forecasts in numerical format serving as the model input. The details are discussed in the following subsections.
Numerical rainfall forecasts
Conversion level 1D–1D dual drainage model
Governing equation of the RUNOFF module
where i is the rainfall rate, e is the surface evaporation, f is the infiltration rate, q is the runoff rate (refer to Eq. (2)), W is the average channel width, S is the average slope of the catchment, A is the surface area of the catchment, n is a surface roughness coefficient, and d s is the storage depth.
Governing equation for the 1D–1D dual drainage model
where Q is the discharge in the sewer or street, t is the time, g is the gravitational acceleration, A is the cross-sectional area of the sewer or street, H is the hydraulic head of water in the sewer or street, S f is the friction slope from Manning’s equation, and U is the velocity of water in the sewer or street. Details about solving Eq. (3) were provided by Rossman (2015).
Description of the model setup in Huawei Science Park
Case and discussion
The study proposes an innovative CPS-based smart water system for providing real-time flood observations and forecasts with a 6-h lead time. The system integrates AI and IoT technologies to transform observed data to useful information. The system not only provides monitoring data to users but also enables them to actively take necessary measures to mitigate the impacts of floods. The system was implemented in a science park located in central Taiwan. A few events tested the capabilities of the system and proved the system’s potential for future applications in disaster prevention and mitigation. However, the CPS concept is developed on the basis of the 5C levels, and the system has implemented only the first three levels—connection, conversion, and cyber levels. The higher the number of levels is, the more added value is the system provides. The fourth and fifth levels, namely the cognition and configuration levels, were not discussed in the study. Further developments in these two levels will be conducted. For example, optimized operating rules for water pumps can be identified on the basis of future flood forecasts by using AI techniques. The optimized operation rules can mitigate or decrease the flooding area of a flood by using the minimum cost. This feature belongs to the cognition level. The water pumps can be automatically operated using the IoT through any optimized operating rule. Thus, the system can replace users and can perform an active role in taking necessary response measures; this belongs to the configuration level. Other applications such as providing optimized traffic route information by employing UAVs during a flood will also be included in the future applications. The CPS-based system has proved its potential to help in decision-making processes during a disaster. Future applications will offer more help to users and increase the efficiency of disaster relief. More applications of AI and IoT will be employed in next-generation hazard-related response systems.
The research was part of plan (grant no. 105f600191) funded by the Central Taiwan Science Park, Taiwan. The authors would like to thank its supporting.
The Central Taiwan Science Park (grant no. 105f600191).
Availability of data and materials
So far, the authors would not share research-related data or materials because we will do extended studies. We hope you can understand us. Many thanks!
The manuscript demonstrates a smart water system that integrates the concept of CPS and IOT. The purpose of this system is to provide more efficient and reliable flood forecasts and help decision-makers rapidly respond the threat of the flood. The system has been implemented in the Central Taiwan Science Park (CTSP). The experimental results revealed that the system could increase the response efficiency of the emergency operations center during a few extreme events in 2017. Thank you for your consideration of my work!. All authors read and approved the final manuscript.
The authors declare that they have no competing interests.
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Open AccessThis article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.
- Alemdar H, Leroy V, Prost-Boucle A, Pétrot F (2017) Ternary neural networks for resource-efficient AI applications. In neural networks (IJCNN), 2017 international joint conference on (pp. 2547-2554). IEEEGoogle Scholar
- Augello A, Maniscalco U, Pilato G, Vella F (2016) Disaster prevention virtual advisors through soft sensor paradigm. In: Pietro G, Gallo L, Howlett R, Jain L (eds) Intelligent Interactive Multimedia Systems and Services 2016. Smart innovation, systems and technologies, vol 55. Springer, ChamGoogle Scholar
- Chang TJ, Wang CH, Chen AS (2015) A novel approach to model dynamic flow interactions between storm sewer system and overland surface for different land covers in urban areas. J Hydrol 524:662–679View ArticleGoogle Scholar
- Eisner R (2014) Managing the risk of compound disasters. Chapter 5. In: Disaster risk management in Asia and the Pacific. Routledge, London, UKGoogle Scholar
- Hsiao LF, Chen DS, Kuo YH, Guo YR, Yeh TC, Hong JS, Fong CT, Lee CS (2012) Application of WRF 3DVAR to operational typhoon prediction in Taiwan: impact of outer loop and partial cycling approaches. Weather Forecast 27(5):1249–1263View ArticleGoogle Scholar
- Hsiao LF, Yang MJ, Lee CS, Kuo HC, Shih DS, Tsai CC, Wang CJ, Chang LY, Chen DYC, Feng L, Hong JS, Fong CT, Chen DS, Yeh TC, Huang CY, Guo WD, Lin GF (2013) Ensemble forecasting of typhoon rainfall and floods over a mountainous watershed in Taiwan. J Hydrol 506:55–68View ArticleGoogle Scholar
- Hsu MH, Chen SH, Chang TJ (2000) Inundation simulation for urban drainage basin with storm sewer system. J Hydrol 234:21–37View ArticleGoogle Scholar
- Lee J, Bagheri B, Kao HA (2015) A cyber-physical systems architecture for industry 4.0-based manufacturing systems. Manufacturing Letters 3:18–23View ArticleGoogle Scholar
- Lopez-Trujillo D (2010) Real time flood alert system (RTFAS) for Puerto Rico. US Department of Interior, US Geological SurveyGoogle Scholar
- Mahul O (2017) Toward a regional approach for disaster risk finance in Asia. ICRM Symposium 2017, 3-4 August 2017, Dermatol SinGoogle Scholar
- Monostori L (2003) AI and machine learning techniques for managing complexity, changes and uncertainties in manufacturing. Eng Appl Artif Intell 16(4):277–291View ArticleGoogle Scholar
- Monostori L, Kádár B, Bauernhansl T, Kondoh S, Kumara S, Reinhart G, Sauer O, Schuh G, Sihn W, Ueda K (2016) Cyber-physical systems in manufacturing. CIRP Annals-Manufacturing Technology 65(2):621–641View ArticleGoogle Scholar
- Rho S, Vasilakos A, Chen W (2016) Cyber physical systems technologies and applications. Futur Gener Comput Syst 56:436–437View ArticleGoogle Scholar
- Rossman LA (2015) Storm water management model. User’s manual Ver. 5.1. U. S. Environmental Protection AgencyGoogle Scholar
- Sun JZ, Wang HL, Tong WX, Zhang Y, Lin CY, Xu DM (2016) Comparison of the impacts of momentum control variables on high-resolution variational data assimilation and precipitation forecasting. Mon Weather Rev 144(1):149–169View ArticleGoogle Scholar
- Thielen J, Bartholmes J, Ramos MH, de Roo A (2009) The European flood alert system – part 1: concept and development. Hydrol Earth Syst Sci 13:125–140View ArticleGoogle Scholar
- Wu MC, Lin GF (2017) The very short-term rainfall forecasting for a mountainous watershed by means of an ensemble numerical weather prediction system in Taiwan. J Hydrol 546:60–70View ArticleGoogle Scholar
- Wu MC, Lin GF, Hwang LR, Chen DYC, Chiang CC, Wang YC (2016) Optimal integration of the ensemble forecasts from an ensemble quantitative precipitation forecast experiment. Procedia Eng 154:1291–1297View ArticleGoogle Scholar
- Yang TH, Yang SC, Ho JY, Lin GF, Hwang GD, Lee CS (2015) Flash flood warnings using the ensemble precipitation forecasting technique: a case study on forecasting floods in Taiwan caused by typhoons. J Hydrol 520:367–378View ArticleGoogle Scholar