近年來，台灣降雨強度更加極端，淹水災害的衝擊與規模也更加嚴峻。除了氣象條件的嚴峻之外，台灣的高度都市化發展程度，更是加劇淹水衝擊的元凶。因此，加強淹水預警與監測功能更是刻不容緩的議題。自2017年開始，政府預計投入8年總共2,508億元進行水環境建設中，其中除了傳統的防洪工程與水資源管理外，更首先納入了水資源智慧管理的工作項目，期望透過物聯網（IoT，Internet of Things）的技術，建置與推廣智慧防汛網。本研究主要目標有二，其一為應用物聯網技術開發淹水感測器，目前已經利用低功耗廣域網(Low Power Wide Area Network, LPWAN)技術，開發完成第一代之淹水感測器，以台南市安南區為研究區域進行佈設，但因都市建築林立影響傳輸效率，導致成效有限。其二為應用機器學習方法建置淹水預測模型，首先以淹水模式產製各重現年淹水深度，作為機器學習模型支撐向量回歸(Support Vector Regression)訓練資料庫，再以實際事件之淹水感測觀測值，作為模式測試驗證之用。結果顯示，所開發之淹水預測模型，除了可以合理推估單點之淹水深度外，更可利用有限的點之感測資訊，成功推估整個集水區域之淹水範圍。可以提供即時且可靠的淹水深度預報結果，作為政府防災單位作為都市淹水預警分析之用，對於颱風期間進行預警發布、避難路線規劃、疏散撤離決策有極大的助益。

Under the influence of climate change, the scale and impact of flood disasters have become more and more severe in Taiwan due to the increase in rainfall intensity and urbanization. Since 2017, the government is expected to invest a total of 250.8 billion yuan into the construction of the water environment in 8 years. In addition to traditional flood control projects and water resources management ; furthermore the smart management was bring in.
There are two main goals of this study. The first is to develop a flood sensor based on Low Power Wide Area Network (LPWAN) technology. It was deployed in Annan of Tainan City as the research area, but the effectiveness of transmission efficiency was limited due to the impact of urban buildings on transmission efficiency. The second is to develop a flood prediction model based on support vector regression (SVR) technology. In this study, the 2D inundation model is to provide inundation depth as the training data. Then use the observation events for model testing data. The results show that the SVR model can not only estimate the flooding depth of a single point, but also use the limited point data to estimate the flooding range of the entire catchment area. It can provide real-time and reliable flood depth estimate results. As a government disaster prevention unit, it is used for urban flooding early warning analysis. It is of great help for early warning release, evacuation route planning, and evacuation decision-making during typhoons.

1. 陳鴻烈、蔡大偉。以主成分分析法探討水庫優養化之動力研究，2008。
2. 陳榮松、王國樑、楊國賢、張順竹。改良式水筒模式於坡地旱田之降雨－逕流研究，中華水土保持學報, 第四十卷，第二期，147-157頁，2009。
3. 經濟部。前瞻基礎建設計畫-水環境建設：全國水環境改善計畫，2017。
4. 經濟部水利署。「主動式民眾淹水預警系統應用技術之研發(2/2)」，中華電信股份有限公司台灣南區電信分公司，2012。
5. 經濟部水利署。三爺溪排水及西機場排水治理計畫，2010。
6. 經濟部水利署。台江流域社群與水規所0823淹水事件議題討論，2018。
7. Al-Fuqaha, M. Guizani, M. Mohammadi, M. Aledhari and M. Ayyash, (2015). Internet of Things: A Survey on Enabling Technologies, Protocols, and Applications, in IEEE Communications Surveys & Tutorials, vol. 17, no. 4, pp. 2347-2376, Fourthquarter, doi: 10.1109/COMST.2015.2444095.
8. A.Y. Sun and B. R. Scanlon, (2019). How can big data and machine learning benefit environment and water management: A survey of methods, applications, and future directions. Environ. Res. Lett., vol. 14, no. 7, p. 28.
9. Abdullahi S.I., Habaebi M.H., Malik N.A., (2019). Intelligent flood disaster warning on the fly: developing IoT-based management platform and using 2-class neural network to predict flood status. Bulletin of Electrical Engineering and Informatics, 8(2), 706–717.
10. Alfarra, H.A. and Alsibai, M.H. (2017). A wireless smart sensor network for flood management optimization, International Journal of Engineering Technology and Sciences,Vol.7(1). doi: 10.15282/ijets.7.2017.1.5.1067
11. Alfonso, L., He, L., Lobbrecht, A., Price, R. (2013). Information theory applied to evaluate the discharge monitoring network of the Magdalena River. J. Hydoinform., 15, 211–228.
12. Alfonso, L., Lobbrecht, A., Price, R. (2010). Information theory based approach for location of monitoring water level gauges in polders. Water Resour. Res., 46, W03528
13. Anbarasan M., Muthu B., Sivaparthipan C.B., Sundarasekar R., Kadry S., Krishnamoorthy S.D.J. Samuel R., Dasel A.A., (2019). Detection of flood disaster system based on IoT, big data and convolutional deep neural network. Computer Communications, 150, 150–157
14. Aral, M.M., Guan, J., Maslia, M.L. (2010). Optimal design of sensor placement in water distribution networks. J. Water Resour. Plan. Manag., 136, 5–18.
15. ASCE Task Committee, (2000). Artificial neural networks in hydrology. I: Preliminary concepts. J Hydrol Eng 5: 115–123.
16. Bande S., Shete V.V. (2017). Smart flood disaster prediction system using IoT & neural networks; Proceedings of the 2017 International Conference on Smart Technologies for Smart Nation (Smart Tech Con); Bangalore, India. 17–19.
17. Berkhahn, S., Fuchs, L., Neuweiler, I., (2019). An ensemble neural network model for realtime prediction of urban floods. J. Hydrol. 575, 743–754.
18. Bermúdez, M., Ntegeka, V., Wolfs, V.et al. (2018). Development and Comparison of Two Fast Surrogate Models for Urban Pluvial Flood Simulations. Water Resour Manage 32, 2801–2815
19. Bermúdez,M.,Cea,L.,Puertas,J., (2019). A rapid flood inundation model for hazard mapping based on least squares support vector machine regression. J.FloodRisk Manage.,e12522
20. Chang, L. C., Shen, H. Y. and Chang, F. J. (2014). Regional flood inundation nowcast using hybrid SOM and dynamic neural networks. Journal of hydrology, 519, pp.476-489.
21. Chen, J., Hu, K., Wang, Q., Sun, Y., Shi, Z., & He, S. (2017). Narrowband Internet of Things: Implementations and Applications. IEEE Internet of Things Journal 4: 2309-2314.
22. Cruz F.R.G., Binag M.G., Ga M.R.G., Uy F.A.A., (2018). Flood Prediction Using Multi-Layer Artificial Neural Network in Monitoring System with Rain Gauge, Water Level, Soil Moisture Sensors. In Proceedings of the TENCON 2018-2018 IEEE Region 10 Conference, pp. 2499-2503, doi:10.1109/TENCON.2018.8650387.
23. Gustavo Furquim, Geraldo P. R. Filho (2018). How to Improve Fault Tolerance in Disaster Predictions: A Case Study about Flash Floods Using IoT, ML and Real Data. Sensors, 18, 907
24. Hsiao-Yun Huang ,Jin-Chenf Fu,An-Chi Hsueh (2010). Real-time River Stage Forecasting With MART-A Case of Bajhang River.
25. Imrie C.E., Durucan S., Korre A., (2000). River flow prediction using artificial neural networks: generalization beyond the calibration range. J Hydrol 233(1–4): 138–153
26. Jang, J.H. (2015). An advanced method to apply multiple rainfall thresholds for urban flood warnings. Water, 7, 6056–6078.
27. Jang, J.H., Yu, P.S., Yeh, S.H., Fu, J.C., Huang, C.J. (2012). A probabilistic model for realtime flood warning based on deterministic flood inundation mapping. Hydrol. Process., 26, 7, 1079–1089.
28. Jhong, B.-C., Wang, J.-H., & Lin, G.-F. (2017). An integrated two-stage support vector machine approach to forecast inundation maps during typhoons. Journal of Hydrology, 547, 236–252.
29. Kafli N., Isa K., (2017). Internet of Things (IoT) for measuring and monitoring sensors data of water surface platform. In Proceedings of the 2017 IEEE 7th International Conference on Underwater System Technology: Theory and Applications (USYS), Kuala Lumpur, Malaysia, 18–20.
30. Khan T.A., Alam M., Kadir K., Shahid Z., Mazliham S.M., (2018). A Novel approach for the investigation of flash floods using soil flux and CO2: An implementation of MLP with less false alarm rate. In Proceedings of the 2018 2nd International Conference on Smart Sensors and Application (ICSSA), Kuching, Malaysia, 24–26.
31. L. Lopez-Fuentes, C. Rossi and H. Skinnemoen, (2017). River segmentation for flood monitoring. IEEE International Conference on Big Data (Big Data), Boston, MA, pp. 3746-3749, doi: 10.1109/BigData.2017.8258373
32. Loftis D., Forrest D., Katragadda S., Spencer K., Organski T., Nguyen C., Rhee S., (2018). StormSense: A New Integrated Network of IoT Water Level Sensors in the Smart Cities of Hampton Roads, VA. Mar Technol Soc J., 52: . doi:10.4031/MTSJ.52.2.7.
33. M. Khalaf et al., (2020) IoT-Enabled Flood Severity Prediction via Ensemble Machine Learning Models, in IEEE Access, vol. 8, pp. 70375-70386, doi: 10.1109/ACCESS.2020.2986090
34. M. Mohammadi, A. Al-Fuqaha, S. Sorour and M. Guizani,(2018). Deep Learning for IoT Big Data and Streaming Analytics: A Survey, in IEEE Communications Surveys & Tutorials, vol. 20, no. 4, pp. 2923-2960, Fourthquarter, doi: 10.1109/COMST.2018.2844341.
35. Mason, S.J., (1982). A model for assessment of weather forecasts. Aust. Meteorol. Mag. 30, 291–303.
36. Mousa, M.; Zhang, X.; Claudel, C (2016). Flash Flood Detection in Urban Cities Using Ultrasonic and Infrared Sensors. IEEE Sensors Journal, vol. 16, no. 19, pp. 7204-7216, Oct.1, doi: 10.1109/JSEN.2016.2592359.
37. Abou Rjeily Y, Abbas O, Sadek M, Shahrour I, Hage Chehade F. (2017). Flood forecasting within urban drainage systems using NARX neural network. Water Sci Technol. 76(9-10):2401-2412. doi:10.2166/wst.2017.409
38. Rumelhart,D. E. ,Hinton,G. E. (1986). Learning representations by back-propagation error. Nature. Vol. 323, pp. 533-536.
39. Shien-Tsung Chen, Pao-Shan Yu, Yi-Hsuan Tang (2010). Statistical downscaling of daily precipitation using support vector machines and multivariate analysis. J. Hydrol. 385 (1–4), 13–22.
40. Terzic J., Nagarajah C., Alamgir M., (2010). Fluid level measurement in dynamic environments using a single ultrasonic sensor and Support Vector Machine (SVM). Sens. Actuators A Phys., 161, 278–287.
41. U. K. Panchal, H. Ajmani, and S. Y. Sait, (2019). Flooding level classification by gait analysis of smartphone sensor data, IEEE Access, vol. 7, pp. 181678–181687
42. Vapnik V.N., (1995). The Nature of Statistical Learning Theory. Springer, New York
43. Vapnik V.N., (1998). Statistical Learning Theory. Wiley
44. Widiasari I.R., Nugroho L.E., (2017). Deep learning multilayer perceptron (MLP) for flood prediction model using wireless sensor network based hydrology time series data mining. In Proceedings of the 2017 International Conference on Innovative and Creative Information Technology (ICITech), Salatiga, Indonesia, 2–4.
45. Wu J.S,, Jun H., Annambhotla S., Bryant S., (2005). Artificial neural networks for forecasting watershed runoff and stream flows. J Hydrol Eng 10(3): 216–222
46. Yu P.S., Yang T.C.. Chen S.Y., Kuo C.M., Tseng H.W., (2017). Comparison of random forests and support vector machine for real-time radar-derived rainfall forecasting. J. Hydrol., 552, 92– 104.
47. Zhang Guoqiang, B. Eddy Patuwo and Michael Y. Hu (1998). Forecasting with artificial neural networks: The state of the art, International Journal of Forecasting, Vol.14 (1), pp.35-62