以數值模擬結合類神經網路探討減洪設施之影響

近年來因全球暖化加劇極端水文事件發生頻率，超級颱風、短延時強降雨之暴雨事件屢見不暇；隨著永續發展的意識抬頭，衍生化水患為助益與水共生存的水環境，提倡低衝擊開發技術以減緩對環境的衝擊、減少表面逕流量，及降低城市熱島效應。本研究主要目的是探討都市發展區中設置不同減洪設施對於不同暴雨事件之減洪成效。研究區域以土城區較易淹水之下游部分，設定四種不同的情境包括無減洪設施、入滲率改善(不同土壤組成)、渠道增設與蓄洪池設置，應用二維淹水之水理模擬模式(FLO-2D軟體)模擬不同情境淹水情況，探討不同設施對淹水減災之影響，並利用類神經自組特徵映射網路(SOM)具有視覺化之拓樸圖，展示區域淹水範圍及其嚴重程度之歷程變化，探討不同減洪設施因子與淹水情形及局部淹水變化之影響關係。淹水模擬結果顯示，坋質壤土(Silty Loam)在降雨強度達1.4mm/hr開始淹水；砂質黏壤土(Sandy Clay Loam)在降雨強度達1.7mm/hr開始淹水；蓄洪池則在平均降雨強度大於13mm/hr才有明顯之減洪功能。因此，入滲率改善對於一般降雨事件皆有降低地表逕流量，對於重現期2年、5年的暴雨事件皆能達到有效的減洪效果；蓄洪池則對大的暴雨事件如重現期100年或200年，可有效地發揮防洪減災之效。本研究另以4X4之自組性特徵映射網路分類淹水變化，可獲得具有代表區域淹水空間消長變化之拓樸圖，用以說明低衝擊開發設施對於空間淹水之減緩特徵，有效地分析減洪設施對局部地區淹水防治之效應。

關鍵字

類神經網路；自組特徵映射網路；數值模擬； FLO-2D ；減洪設施；淹水

並列摘要

In recent years, global warming increased the frequency and severity of extreme storm events,. super typhoons or short duration and high intensity rainfall events. Along with the growing awareness of sustainable development, Low Impact Development (LID) techniques are advocated to mitigate the impact on the environment, to reduce surface runoff, and to reduce heat island effect. The main purpose of this study is to investigate the effect of different stormwater facilities for different storm sizes on urban areas. The study area is the flood-prone areas of Tu-Cheng downstream. In this study, four different cases are designed for comparison with the LID approach, including non stormwater facilities, drainage channels with lower (silty loam) or higher (sandy clay load)　infiltration rate, and drainage channels with lower infiltration rate and retention storage ponds. The FLO-2D model is applied for two-dimension flood distribution on the study area of different designed cases, and the Self-Organizing Map (SOM) is used to categorize the simulation data into a meaningful and visible inundation topology for displaying the regional flood inundation extents and severity of these four cases. The simulation results show that onset of flooding occurs at rainfall intensity up to 1.4 mm/hr and 1.7 mm/hr for silty loam and sandy clay loam soils., while 13mm/hr for retention storage. The increase of infiltration rate can effectively achieve flood mitigation for 2-year, 5-year storm events; the existence of retention storage ponds can significantly reduce flood risk for 100-year or 200-year event. In this study, 4X4 size of SOM can categorize a large number of regional flood simulation data into a meaningful flood inundation topology. The flood inundation topology can show the characteristics of spatial change and distribution of regional flood inundation.

並列關鍵字

Artificial neural networks ； Self-organizing map (SOM) ； SOM ； Numerical Simulation ； FLO-2D ； Flood mitigation facilities ； Flood ； Inundation

參考文獻

21. 何宇申，2013，FLO-2D應用於中壢都會區的淹水分析，碩士論文，臺灣大學生物環境系統工程學研究所。

24. 蔡繼霆，2015，台灣南部地區淹水原因分析之研究，碩士論文，臺灣大學生物環境系統工程學研究所。

1. Batesa, P.D., Horrittb, M.S. and Fewtrella, T.J., 2010. A simple inertial formulation of the shallow water equations for efficient two-dimensional flood inundation modelling. Journal of Hydrology 387(1-2):33-45.

2. Chang, L. C., Shen, H. Y., Wang, Y. F., Huang, J. Y., & Lin, Y. T.(2010).Clustering-based hybrid inundation model for forecastingflood inundation depths. Journal of hydrology, 385(1), 257-268.

3. Chang, F. J., Chang, L. C., Kao, H. S., & Wu, G. R. (2010). Assessing the effort of meteorological variables for evaporation estimation by self-organizing map neural network. Journal of Hydrology, 384(1), 118-129.

國際替代計量

以數值模擬結合類神經網路探討減洪設施之影響

全文下載

主題瀏覽