The flood risk maps are important tools for the state government authorities to provide information for residents about potential flooding danger. The aim of this study is, therefore, to develop a flood risk map as the combination of vulnerability and hazard in the study area of Shanhua district located in Tainan city to understand the influence of different return period discharge, vulnerability resolution, and vulnerability weighting on final risk. The flood hazard was based on water depth which was calculated by HEC-RAS hydraulic model in 2D. Five typhoons were used for model calibration. Three different vulnerability importance weightings were applied to generate flood vulnerability maps. Two machine learning models, classification and regression tree (CART) and random forest (RF), were selected for feature importance calculation in this study. The machine learning results were compared with the weighted importance obtained from an Analytical hierarchy process (AHP) procedure for performance evaluation, where a total of 16 questioner respondents participated in the survey. The vulnerability indexes were selected based on literature review and data availability in the study area. The feasibility of the proposed approach was evaluated by pair-wise comparison of two different resolutions 25m and 100m of vulnerability and hazard maps. Fist, findings from vulnerability maps indicated that CART model tended to small underestimate and RF, on the other hand, tended to largely overestimate AHP result. Second, the vulnerability resolution had a much larger impact due to fact that rougher resolution accommodated more households. Lastly, finer flood model resolution provided more precise results in urban areas and extended risk zones

1) Accounting office of Shanhua district. (2019). The statistical yearbook of Shanhua district, Tainan City 2018.
2) Afifi, Z.; Chu, H.-J.; Kuo, Y.-L.; Hsu, Y.-C.; Wong, H.-K.; Zeeshan Ali, M. (2019). Residential Flood Loss Assessment and Risk Mapping from High-Resolution Simulation. Water 2019, 11, 751. doi: 10.3390/w11040751
3) Afshari, S., Tavakoly, A. A., Rajib, M. A., Zheng, X., Follum, M. L., Omranian, E., & Fekete, B. M. (2018). Comparison of new generation low-complexity flood inundation mapping tools with a hydrodynamic model. Journal of Hydrology, 556, 539–556. doi: 10.1016/j.jhydrol.2017.11.036
4) Australian Institute for Disaster Resilience. (2012). Technical flood risk management guideline: Flood hazard.
5) Breiman, L. (2001). Machine Learning, 45(1), 5–32. https://doi.org/10.1023/a:1010933404324
6) Brunner, G.W. (2015). Tuflow vs Mike DHI products vs HEC‐RAS 5.
7) Brunner, G. W. (2016). HEC-RAS River Analysis System: Hydraulic Reference Manual.
8) Chow, V.T., 1959. Open-Channel Hydraulics. McGraw-Hill, New York, N.Y., 680 pp.
9) Cutter, S. L., Boruff, B. J., & Shirley, W. L. (2003). Social Vulnerability to Environmental Hazards*. Social Science Quarterly, 84(2), 242–261. https://doi.org/10.1111/1540-6237.8402002
10) Darabi, H., Choubin, B., Rahmati, O., Torabi Haghighi, A., Pradhan, B., & Kløve, B. (2019). Urban flood risk mapping using the GARP and QUEST models: A comparative study of machine learning techniques. Journal of Hydrology, 569, 142–154. https://doi.org/10.1016/j.jhydrol.2018.12.002
11) Dey, P.K. (2002) Project Risk Management: A Combined Analytic Hierarchy Process and Decision Tree Approach. Cost Engineering, 44, 13-27.
12) Erena, S. H., Worku, H., & De Paola, F. (2018). Flood hazard mapping using FLO-2D and local management strategies of Dire Dawa city, Ethiopia. Journal of Hydrology: Regional Studies, 19, 224–239. https://doi.org/10.1016/j.ejrh.2018.09.005
13) Fekete, A. (2009). Validation of a social vulnerability index in context to river-floods in Germany. Natural Hazards and Earth System Sciences, 9(2), 393–403. https://doi.org/10.5194/nhess-9-393-2009
14) Feng, B., Wang, J., Zhang, Y., Hall, B., & Zeng, C. (2020). Urban flood hazard mapping using a hydraulic–GIS combined model. Natural Hazards, 100(3), 1089–1104. https://doi.org/10.1007/s11069-019-03850-7
15) Flanagan, B. E., Gregory, E. W., Hallisey, E. J., Heitgerd, J. L., & Lewis, B. (2011). A Social Vulnerability Index for Disaster Management. Journal of Homeland Security and Emergency Management, 8(1). https://doi.org/10.2202/1547-7355.1792
16) Flanagan, B. E., Gregory, E. W., Hallisey, E. J., Heitgerd, J. L., & Lewis, B. (2011). A Social Vulnerability Index for Disaster Management. Journal of Homeland Security and Emergency Management, 8(1). https://doi.org/10.2202/1547-7355.1792
17) Ghosh, A., & Kar, S. K. (2018). Application of analytical hierarchy process (AHP) for flood risk assessment: a case study in Malda district of West Bengal, India. Natural Hazards, 94(1), 349–368. https://doi.org/10.1007/s11069-018-3392-y
18) Goepel, K.D. (2018). Implementation of an Online Software Tool for the Analytic Hierarchy Process (AHP-OS). International Journal of the Analytic Hierarchy Process, Vol. 10 Issue 3 2018, pp 469-487, https://doi.org/10.13033/ijahp.v10i3.590
19) Gupta, H. V., S. Sorooshian, & P. O. Yapo. (1999). Status of automatic calibration for hydrologic models: Comparison with multilevel expert calibration. J. Hydrologic Eng. 4(2): 135-143
20) Google. (n.d.). [老人护理]. Retrieved September 5, 2019, from https://goo.gl/maps/zNDmskmHW8itXdqt7 & https://goo.gl/maps/pSNo6QfNKJVNr8Ru9
21) Hoeppe, P. (2016). Trends in weather related disasters – Consequences for insurers and society. Weather and Climate Extremes, 11, 70–79. https://doi.org/10.1016/j.wace.2015.10.002
22) Holand, I. S., & Lujala, P. (2013). Replicating and Adapting an Index of Social Vulnerability to a New Context: A Comparison Study for Norway. The Professional Geographer, 65(2), 312–328. https://doi.org/10.1080/00330124.2012.681509
23) Kim, Y. D., Tak, Y. H., Park, M. H., & Kang, B. (2019). Improvement of urban flood damage estimation using a high‐resolution digital terrain. Journal of Flood Risk Management, 13(S1). https://doi.org/10.1111/jfr3.12575
24) Kirby, R. H., Reams, M. A., Lam, N. S. N., Zou, L., Dekker, G. G. J., & Fundter, D. Q. P. (2019). Assessing Social Vulnerability to Flood Hazards in the Dutch Province of Zeeland. International Journal of Disaster Risk Science, 10(2), 233–243. https://doi.org/10.1007/s13753-019-0222-0
25) Komolafe, A. A., Herath, S., & Avtar, R. (2015). Sensitivity of flood damage estimation to spatial resolution. Journal of Flood Risk Management, 11, S370–S381. https://doi.org/10.1111/jfr3.12224
26) Leitão, J. P., & de Sousa, L. M. (2018). Towards the optimal fusion of high-resolution Digital Elevation Models for detailed urban flood assessment. Journal of Hydrology, 561, 651–661. https://doi.org/10.1016/j.jhydrol.2018.04.043
27) Leitão, J. P., Boonya-aroonnet, S., Prodanović, D., & Maksimović, Č. (2009). The influence of digital elevation model resolution on overland flow networks for modelling urban pluvial flooding. Water Science and Technology, 60(12), 3137–3149. https://doi.org/10.2166/wst.2009.754
28) Li H. C.; Yang, H. H.; Liao, K. M. & Shaw, D. (2008), Constructing Social Vulnerability Index of Flood Disaster, Conference of disaster management society of Taiwan, Taipei.
29) Lin, Y.-C., Hsu, M.-H., Chang, T.-J., Tsai, M.-Y., Chen, A., Hammond, M., Djordjevi_, S., & Butler, D. (2012). Flood vulnerability and risk maps in Taipei City, Taiwan. In Comprehensive Flood Risk Management. CRC Press. https://doi.org/10.1201/b13715-113
30) Lin, Y.-T., Chen, W.-B., Su, Y.-F., Han, J.-Y., & Jang, J.-H. (2018). Improving river stage forecast by bed reconstruction in sinuous bends. Journal of Hydroinformatics, 20(4), 960–974. https://doi.org/10.2166/hydro.2018.119
31) Mosavi, A., Ozturk, P., & Chau, K. (2018). Flood Prediction Using Machine Learning Models: Literature Review. Water, 10(11), 1536. https://doi.org/10.3390/w10111536
32) Nash, J. E., & Sutcliffe, J. V. (1970). River flow forecasting through conceptual models part I — A discussion of principles. Journal of Hydrology, 10(3), 282–290. https://doi.org/10.1016/0022-1694(70)90255-6
33) Neelz S. & Pender G. (2013). Benchmarking the latest generation of 2D hydraulic modelling packages. Environment Agency. ISBN: 978-1-84911-306-9
34) Muthusamy, M., Rivas Casado, M., Salmoral, G., Irvine, T., & Leinster, P. (2019). A Remote Sensing Based Integrated Approach to Quantify the Impact of Fluvial and Pluvial Flooding in an Urban Catchment. Remote Sensing, 11(5), 577. https://doi.org/10.3390/rs11050577
35) Oubennaceur, K., Chokmani, K., Nastev, M., Lhissou, R., & El Alem, A. (2019). Flood risk mapping for direct damage to residential buildings in Quebec, Canada. International Journal of Disaster Risk Reduction, 33, 44–54. doi: 10.1016/j.ijdrr.2018.09.007
36) Podhoranyi, M., Vojacek, L., & Vojtek, D. (2018, August). Flood Risk Monitoring by Using 2D Hydrodynamic Modeling: A Case Study of Frýdek-Místek City. 2018 1st International Cognitive Cities Conference (IC3). 2018 1st International Cognitive Cities Conference (IC3). https://doi.org/10.1109/ic3.2018.00-13
37) Ramesh, A. (2013). Response of Flood Events to Land Use and Climate Change. In Springer Theses. https://doi.org/10.1007/978-94-007-5527-7
38) Ronaghan S. (2018). The Mathematics of Decision Trees, Random Forest and Feature Importance in Scikit-learn and Spark. Retrieved from https://towardsdatascience.com
39) Rufat, S., Tate, E., Burton, C. G., & Maroof, A. S. (2015). Social vulnerability to floods: Review of case studies and implications for measurement. International Journal of Disaster Risk Reduction, 14, 470–486. https://doi.org/10.1016/j.ijdrr.2015.09.013
40) Saaty, T. L. (1977). A scaling method for priorities in hierarchical structures. Journal of Mathematical Psychology, 15(3), 234–281. https://doi.org/10.1016/0022-2496(77)90033-5
41) Sado-Inamura, Y., & Fukushi, K. (2019). Empirical analysis of flood risk perception using historical data in Tokyo. Land Use Policy, 82, 13–29. https://doi.org/10.1016/j.landusepol.2018.11.031
42) Shanhua Household Registration Office, Tainan City. (n.d.). Demographics of Shanhua District. Retrieved from https://shanhua.tainan.gov.tw/cl.aspx?n=18054
43) Sharma, S.V.S., Roy, P. S., Chakravarthi, V. & Rao, S.G. (2017) Flood risk assessment using multi-criteria analysis: a case study from Kopili River Basin, Assam, India, Geomatics, Natural Hazards and Risk, 9:1, 79-93, DOI: 10.1080/19475705.2017.1408705
44) Solin, L., Sladekova Madajova, M., & Michaleje, L. (2018). Vulnerability assessment of households and its possible reflection in flood risk management: The case of the upper Myjava basin, Slovakia. International Journal of Disaster Risk Reduction, 28, 640–652. https://doi.org/10.1016/j.ijdrr.2018.01.015
45) Tascón-González, L., Ferrer-Julià, M., Ruiz, M., & García-Meléndez, E. (2020). Social Vulnerability Assessment for Flood Risk Analysis. Water, 12(2), 558. https://doi.org/10.3390/w12020558
46) Thakkar, K.H., Shah, J., Prabhakar, R., Narayan, A., & Joshi, A. (2016). AHP and MACHINE LEARNING TECHNIQUES for Wine Recommendation.
47) Timofeev R (2004) Classifcation and regression trees (CART) theory and applications. In: Master Thesis. Center of Applied Statistics and Economics, Humboldt University, Berlin
48) U.S. Army Corps of Engineers, Hydrologic Engineering Center's River Analysis System HEC-RAS. http://www.hec.usace.army.mil/software/hec-ras/
49) U.S. Army Corps of Engineers. (2016). River Analysis System HEC-RAS version 5.0.2 release notes version.
50) UNDP. (2004). A Global Report Reducing Disaster Risk: A challenge for Development.
51) United Nations-SPIDER. (2020). Step-by-Step: Flood Hazard Assessment. Retrieved from http://www.un-spider.org/advisory-support/recommended-practices/recommended-practice-flood-hazard-assessment/step-by-step
52) Vaze, J., & Teng, J. (2007). Impact of DEM resolution on topographic indices and hydrological Modelling results. Modsim 2007. International Congress on Modelling and Simulation, 706–712.
53) Wang, Z., Lai, C., Chen, X., Yang, B.K., Zhao, S., & Bai, X. (2015). Flood hazard risk assessment model based on random forest. Journal of Hydrology, 527, 1130-1141.
54) Water Research Agency (WRA). (2019). Hydrological Information Network Integrated Service System. Retrieved September 2019, from https://gweb.wra.gov.tw/Hydroinfo
55) Water Resources Agency (WRA), Ministry of Economic Affairs. (2015). A Study on Climate Change Adaptation Strategy of Zeng-wen River (1/3)
56) Yang, H., Li, H., & Shaw, D. (2008). Analyzing Social Vulnerability Factors of Flood Disaster in Taiwan.
57) Yang, P., Ames, D. P., Fonseca, A., Anderson, D., Shrestha, R., Glenn, N. F., & Cao, Y. (2014). What is the effect of LiDAR-derived DEM resolution on large-scale watershed model results? Environmental Modelling & Software, 58, 48–57. https://doi.org/10.1016/j.envsoft.2014.04.005