海堤溯升計算一直是海岸建設規劃重要的一環，準確的溯升計算能使工程設計達到安全與預算間的最佳平衡，本研究使用政府計畫中大範圍海氣象數值模式重現過去颱風事件海平面波浪條件的結果，配合斷面數值模式模擬近岸海堤溯升結果建立溯升資料庫，並使用機器學習法建立外海觀測資料與海堤溯升間的連結。

本研究依據海底地形及海堤斷面設計圖建立一個長度1公里，垂直於高雄彌陀海堤岸線的一維底床作為斷面溯升模擬使用，斷面模擬的造波條件以及初始水深使用大範圍風浪模擬結果中離岸1公里處的資料提取點，資料類型為示性波高、尖峰週期及水位。

機器學習採用高斯過程法，其已在Beuzen et al. (2019)中被使用來推估沙灘上的溯升高度；訓練資料使用大範圍風浪模擬結果中離海堤6 公里外的位置提取出的示性波高、尖峰週期、波向與水位資料來和溯升高度組成訓練集，以此建立外海資料與海堤溯升間的迴歸模型。

最後將2021年燦樹颱風期間觀測得到之溯升高度與外海資料作為測試集，使用訓練出的迴歸模型作推估比較其與實際觀測溯升之差異。作為斷面數值模式結果所建立廻歸模型的對照，使用經驗公式取代斷面模擬直接從外海資料提取點進行波浪淺化再計算溯升高度，並建立一組對照的迴歸模型與數值模式之廻歸模型作推估溯升比較，兩者間的比較結果顯示使用數值模式計算溯升所建立的迴歸模型較經驗公式有略高的準確性，雖有建立訓練集較為耗時的缺點，但在建立沿海防護預警系統時可作為一個值得參考的溯升資料來源。

Runup estimation has always been an important part of coastal engineering. An accurate runup estimation can make seawall design achieve the balance between protective effect and budget. This study uses the result of the large-scale marine meteorological model to simulate the surface conditions during past typhoon events and the result is used as input for the cross-sectional numerical model SWASH to simulate the runup on the seawall. Finally, use machine learning method is applied to learn the relationship between the offshore wave data and runup on seawalls.
In this study, a 1-kilometer-long, numerical cross-section sea bottom perpendicular to the shoreline of the Mito seawall in Kaohsiung is established based on the seabed topography and the seawall section design diagram. The wave conditions and initial water level of the cross-section simulations are extracted from the extraction point from the result of the large-scale marine meteorological model, which includes significant wave height, peak period, and water level.
The machine learning method uses the Gaussian process method, which has been used in Beuzen et al. (2019) to estimate the runup on sandy beaches. The training dataset used in machine learning contains significant wave height, peak wave period, mean wave direction, water level, and runup height, based on this training set, the regression model is established between offshore data and runup on the seawall.
After training the regression model, the observation data is used during the Chanthu typhoon in 2021 as the testing dataset to assess the difference between estimation runup height and observation runup height. As a control group of the regression model based on the cross-sectional model result, build another regression model using empirical runup equations to calculate runup as the training set. The result of the comparison shows that the regression model based on the cross-section model has slightly higher accuracy on runup estimates, which can be used in coastal protection early warning system.

[1] Abolfathi, S., Yeganeh-Bakhtiary, A., Hamze-Ziabari, S.M., &Borzooei, S., 2016. Wave runup prediction using M5′ model tree algorithm. Ocean Eng. 112, 76–81.
[2] Bakhtyar, R., Yeganeh Bakhtiary, A., &Ghaheri, A., 2008. Application of neuro-fuzzy approach in prediction of runup in swash zone. Appl. Ocean Res. 30, 17–27.
[3] Camus, P., Mendez, F.J., Medina, R., &Cofiño, A.S., 2011. Analysis of clustering and selection algorithms for the study of multivariate wave climate. Coast. Eng. 58, 453–462.
[4] Deppermann, C.E., 1947. Notes on the Origin and Structure of Philippine Typhoons. Bull. Am. Meteorol. Soc. 28, 399–404.
[5] Demirbilek, Z., Nwogu, O., &Ward, D., 2007. Laboratory Study of Wind Effect on Runup over Fringing Reefs-Report 1: Data Report. Surge Wave Isl. Model. Stud. Progr. Coast. Inlets Res. Progr. ERDC/CHL TR-07-4.
[6] Doong, D.J., Tsai, C.H., Chen, Y.C., Peng, J.P., &Huang, C.J., 2015. Statistical analysis on the long-Term observations of typhoon waves in the Taiwan sea. J. Mar. Sci. Technol. 23, 893–900.
[7] Hersbach, H., Bell, B., Berrisford, P., Hirahara, S., Horányi, A., Muñoz-Sabater, J., Nicolas, J., Peubey, C., Radu, R., Schepers, D., Simmons, A., Soci, C., Abdalla, S., Abellan, X., Balsamo, G., Bechtold, P., Biavati, G., Bidlot, J., Bonavita, M., DeChiara, G., Dahlgren, P., Dee, D., Diamantakis, M., Dragani, R., Flemming, J., Forbes, R., Fuentes, M., Geer, A., Haimberger, L., Healy, S., Hogan, R.J., Hólm, E., Janisková, M., Keeley, S., Laloyaux, P., Lopez, P., Lupu, C., Radnoti, G., deRosnay, P., Rozum, I., Vamborg, F., Villaume, S., &Thépaut, J.-N., 2020. The ERA5 global reanalysis. Q. J. R. Meteorol. Soc. 146, 1999–2049.
[8] Holman, R.A., 1986. Extreme value statistics for wave run-up on a natural beach. Coast. Eng. 9, 527–544.
[9] Hsiao, S.-C., Chen, H., Chen, W.-B., Chang, C.-H., &Lin, L.-Y., 2019. Quantifying the contribution of nonlinear interactions to storm tide simulations during a super typhoon event. Ocean Eng. 194, 106661.
[10] Kalnay, E., Kanamitsu, M., Kistler, R., Collins, W., Deaven, D., Gandin, L., Iredell, M., Saha, S., White, G., Woollen, J., Zhu, Y., Chelliah, M., Ebisuzaki, W., Higgins, W., Janowiak, J., Mo, K.C., Ropelewski, C., Wang, J., Leetmaa, A., Reynolds, R., Jenne, R., &Joseph, D., 1996. The NCEP/NCAR 40-Year Reanalysis Project. Bull. Am. Meteorol. Soc. 77, 437–472.
[11] Kobayashi, S., Ota, Y., Harada, Y., Ebita, A., Moriya, M., Onoda, H., Onogi, K., Kamahori, H., Kobayashi, C., Endo, H., Miyaoka, K., &Takahashi, K., 2015. The JRA-55 Reanalysis: General Specifications and Basic Characteristics. 気象集誌. 第2輯 93, 5–48.
[12] Lakhan, V.C., 2003. Advances in coastal modeling. Elsevier.
[13] Martínez Pés, V., 2013. Applicability and Limitations of the SWASH model to predict wave overtopping.
[14] Mase, H., 1989. Random Wave Runup Height on Gentle Slope. J. Waterw. Port, Coastal, Ocean Eng. 115, 649–661.
[15] Mase, H., 1995. Frequency down-shift of swash oscillations compared to incident waves. J. Hydraul. Res. 33, 397–411.
[16] Molod, A., Takacs, L., Suarez, M., &Bacmeister, J., 2015. Development of the GEOS-5 atmospheric general circulation model: evolution from MERRA to MERRA2. Geosci. Model Dev. 8, 1339–1356.
[17] Passarella, M., Goldstein, E.B., DeMuro, S., &Coco, G., 2018. The use of genetic programming to develop a predictor of swash excursion on sandy beaches. Nat. Hazards Earth Syst. Sci. 18, 599–611.
[18] Roelvink, D., McCall, R., Mehvar, S., Nederhoff, K., &Dastgheib, A., 2018. Improving predictions of swash dynamics in XBeach: The role of groupiness and incident-band runup. Coast. Eng. 134, 103–123.
[19] Saha, S., Moorthi, S., Wu, X., Wang, J., Nadiga, S., Tripp, P., Behringer, D., Hou, Y.-T., Chuang, H., Iredell, M., Ek, M., Meng, J., Yang, R., Mendez, M.P., van denDool, H., Zhang, Q., Wang, W., Chen, M., &Becker, E., 2014. The NCEP Climate Forecast System Version 2. J. Clim. 27, 2185–2208.
[20] Scott, F., Antolinez, J.A.A., McCall, R., Storlazzi, C., Reniers, A., &Pearson, S., 2020. Hydro-Morphological Characterization of Coral Reefs for Wave Runup Prediction. Front. Mar. Sci. 7, 1–20.
[21] Shao, Z., Liang, B., Li, H., Wu, G., &Wu, Z., 2018. Blended wind fields for wave modeling of tropical cyclones in the South China Sea and East China Sea. Appl. Ocean Res. 71, 20–33.
[22] U.S. Army Corps of Engineers., 2020. Coastal engineering manual. Washington, D.C.
[23] Zhang, Y.J., Ye, F., Stanev, E.V., &Grashorn, S., 2016. Seamless cross-scale modeling with SCHISM. Ocean Model. 102, 64–81.
[24] Zhang, Y., &Baptista, A.M., 2008. SELFE: A semi-implicit Eulerian–Lagrangian finite-element model for cross-scale ocean circulation. Ocean Model. 21, 71–96.
[25] Zijlema, M., Stelling, G., &Smit, P., 2011. SWASH: An operational public domain code for simulating wave fields and rapidly varied flows in coastal waters. Coast. Eng. 58, 992–1012.
[26] 陳彥彰, 2004. “應用 Boussinesq 方程式計算斜坡上之波浪溯升及反射”. 國立成功大學水利及海洋工程研究所碩士論文
[27] 程嘉彥, 劉邦輝, 陳陽益, 2000. “新型消波塊模型試驗,”. 第 22 屆海洋工程研討會論文集
[28] 經濟部水利署第六河川局,2021. “110年第六河川局河川監測資訊管理精進計畫”
[29] 經濟部水利署第六河川局,2021. “110年度臺南市一般性海堤風險評估計畫”