近年來因為全球暖化導致全球變遷，世界各地極端事件發生頻繁，臺灣也受到氣候變遷影響，颱風愈趨於強烈，強烈颱風出現次數逐漸上升，還有降雨時間、強度有改變，如降雨天數變少，總雨量不變，意即短延時強降雨事件次數增加，對臺灣各地可能造成災害，對水庫操作也是一種挑戰。
本研究以石門水庫集水區為研究區域，主要目的為探討空間分布差異與集流時間對降雨-逕流模式之影響，透過倒傳遞類神經網路以不同分區方式建置模型進行未來1-3小時入流量預測。本研究共建置三種模式，模式一以雨量站資料直接作為輸入因子進行模式訓練；模式二以常見的子集水區分區方法將石門水庫集水區進行分區，再將QPESUMS網格雨量資料進行分割進行訓練；模式三結合時間-面積法並考慮降雨時空分布特性進行分區進行訓練。為比較模式優劣，以RMSE、R^2、洪峰流量差、洪峰時間差等四種評估指標進行分析。
結果顯示將所蒐集到的QPESUMS資料繪製空間分布圖加以觀察，石門水庫集水區在季風型豪大雨事件之降雨時空分布受到西南季風或東北季風影響走向不同，降雨空間分布隨著降雨稽延呈現由東往西移動；為能更精準掌握集水區降雨量與分區集水時間對逕流量預報之影響，本研究探討兩種分區方法計算分需降雨量，一為常見的子集水區分區方法、另一為結合時間-面積法並考慮降雨時空分布特性進行分區，結果以後者有較好的表現；三種模式以評估指標分析比較後，以模式三有最佳結果，可推論降雨-逕流模式會受到空間分布差異與集流時間之影響。

In recent years, because global warming has led to global changes, extreme events have occurred frequently all over the world, and Taiwan has also been affected by climate change. Typhoons are becoming more and more intense, the occurrence times of strong typhoons are gradually increasing, and the rainfall time and intensity have changed. If the number of rainfall days decreases, the total rainfall remains unchanged, that is, the number of short delay heavy rainfall events increases, which may cause disasters to all parts of Taiwan, It is also a challenge for reservoir operation.
Taking the catchment area of Shimen Reservoir as the research area, the main purpose of this study is to explore the effects of spatial distribution differences and concentration time on rainfall runoff model, and build models in different zoning methods through back-propagation neural network to predict the inflow in the next 1-3 hours. There are three models in this study. The first model takes the rainfall station data as the input factor for model training; In model 2, the catchment area of Shimen Reservoir is partitioned by the common subset water area zoning method, and then the QPESUMS grid rainfall data is segmented for training; Model 3 combines the time area method and considers the temporal and spatial distribution characteristics of rainfall for zoning training. In order to compare the advantages and disadvantages of the model, four evaluation indexes such as RMSE, R^2, peak discharge difference and peak time difference are analyzed.
The results show that the spatial distribution of rainfall in the catchment area of Shimen Reservoir is affected by the southwest monsoon or northeast monsoon, and the spatial distribution of rainfall moves from east to west with the extension of rainfall; In order to more accurately grasp the impact of catchment rainfall and regional catchment time on runoff forecasting, this study discusses two zoning methods to calculate the divided rainfall demand, one is the common subset water area zoning method, the other is the zoning method combined with the time-area method and considering the temporal and spatial distribution characteristics of rainfall. The results show that the latter has a better performance; After analyzing and comparing the three models with evaluation indexes, model 3 has the best results. It can be inferred that the rainfall runoff model will be affected by the difference of spatial distribution and concentration time.

中文摘要I
AbstrastIII
目錄VI
圖目錄VIII
表目錄X
第一章、前言1
1.1研究動機1
1.2研究目的4
1.3論文架構5
第二章、文獻回顧6
2.1倒傳遞類神經網路之研究6
2.2降雨-逕流預測之相關研究7
第三章、理論概述9
3.1倒傳遞類神經網路9
3.2時間-面積法14
第四章 、研究案例15
4.1研究區域15
4.2 劇烈天氣監測系統17
4.3資料蒐集18
4.4探討集水區分區方式21
第五章、結果與討論26
5.1模式建置26
5.2評估指標定義29
5.3模式之結果31
第六章、結論與建議61
6.1結論61
6.2建議62
參考文獻63
附錄A模式一T+1~T+3之歷程圖與散佈圖整理66
附錄B 模式二T+1~T+3之歷程圖與散佈圖整理72
附錄C 模式三T+1~T+3之歷程圖與散佈圖整理78

圖目錄
圖3-1 倒傳遞類神經網路示意圖10
圖3-2 BP演算法正向傳播與負向傳播示意圖12
圖3-3 時間-面積法示意圖14
圖4-1 石門水庫集水區16
圖4-2 中央氣象局新一代劇烈天氣監測系統17
圖4-3 雨量站分布式意圖21
圖4-4 石門集水區次集水區示意圖22
圖4-5 2017年1013豪雨事件雨量散佈圖24
圖4-6 石門集水區時間-面積法分區示意圖25
圖5-1 模式三之QPESUMS網格點分布圖28
圖5-2 模式一T+1訓練、驗證、測試歷程圖39
圖5-3 因子編號示意圖43
圖5-4 模式二T+1訓練、驗證、測試歷程圖47
圖5-5 因子編號示意圖49
圖5-6 模式三T+1訓練、驗證、測試歷程圖53
圖5-7 RMSE結果長條圖55
圖5-8 R^2結果長條圖56
圖5-9 T+1~T+3洪峰流量差結果折線圖57
圖5-10 各模式T+1驗證之結果歷程圖59

表目錄
表4-1 豪雨場次總表20
表4-2 颱風場次總表20
表5-1 因子代號對應表31
表5-2 颱風、雨事件降雨-逕流T+1模式因子表33
表5-3 颱風事件降雨-逕流模式T+1結果表34
表5-4 豪雨事件降雨-逕流模式T+1結果表34
表5-5模式一降雨-逕流T+1模式因子表36
表5-6 模式一降雨-逕流模式T+1結果36
表5-7模式一降雨-逕流T+1~T+6模式輸入因子表37
表5-8 模式一T+1~T+6之結果38
表5-9 模式二降雨-逕流T+1模式因子表44
表5-10 模式二降雨-逕流模式T+1結果表45
表5-11 模式二降雨-逕流T+1~T+6模式輸入因子表46
表5-12 模式二T+1~T+6之結果46
表5-13 模式三降雨-逕流T+1模式因子表49
表5-14 模式三降雨-逕流模式T+1結果表50
表5-15 模式三降雨-逕流T+1~T+6模式輸入因子表51
表5-16模式三T+1~T+6之結果52
表5-17 各模式之RMSE結果表54
表5-18 各模式之R^2結果表56
表5-19 各模式之洪峰流量差結果表57
表5-20各模式之洪峰時間差結果表57

1.Chen, S. H., Lin, Y. H., Chang, L. C., & Chang, F. J., 2006. The strategy of building a flood forecast model by neuro‐fuzzy network. Hydrological Processes: An International Journal, 20(7), 1525-1540.
2.Chen, Y.H., Chang, F.J., 2009. Evolutionary artificial neural networks for hydrological systems forecasting. Journal of Hydrology 367, 125-137.
3.Chen, N., Xiong, C., Du, W., Wang, C., Lin, X., & Chen, Z., 2019. An improved genetic algorithm coupling a back-propagation neural network model (IGA-BPNN) for water-level predictions. Water, 11(9), 1795.
4.Chiang, Y. M., Chang, L. C., & Chang, F. J., 2004. Comparison of static-feedforward and dynamic-feedback neural networks for rainfall–runoff modeling. Journal of hydrology, 290(3-4), 297-311.
5.Dai, H., & MacBeth, C., 1997. Effects of learning parameters on learning procedure and performance of a BPNN. Neural networks, 10(8), 1505-1521.
6.Feng, Y., & Kitzmiller, D. H., 2006. A short-range quantitative precipitation forecast algorithm using back-propagation neural network approach. Advances in Atmospheric Sciences, 23(3), 405-414.
7.Ghose, D. K., Panda, S. S., & Swain, P. C., 2010. Prediction of water table depth in western region, Orissa using BPNN and RBFN neural networks. Journal of hydrology, 394(3-4), 296-304.
8.Hecht-Nielsen, R. (1992). Theory of the backpropagation neural network. In Neural networks for perception (pp. 65-93). Academic Press.
9.Hsu, K. L., Gupta, H. V., & Sorooshian, S., 1995. Artificial neural network modeling of the rainfall‐runoff process. Water resources research, 31(10), 2517-2530.
10.Jhong, Y. D., Chen, C. S., Lin, H. P., & Chen, S. T. (2018). Physical hybrid neural network model to forecast typhoon floods. Water, 10(5), 632.
11.Nourani, V., Komasi, M., & Mano, A., 2009. A multivariate ANN-wavelet approach for rainfall–runoff modeling. Water resources management, 23(14), 2877-2894.
12.Nourani, V., 2017. An emotional ANN (EANN) approach to modeling rainfall-runoff process. Journal of Hydrology, 544, 267-277.
13.Pal, S. S., & Kar, S., 2017. Time series forecasting using fuzzy transformation and neural network with back propagation learning. Journal of Intelligent & Fuzzy Systems, 33(1), 467-477.
14.Sharghi, E., Nourani, V., Najafi, H., & Molajou, A., 2018. Emotional ANN (EANN) and wavelet-ANN (WANN) approaches for Markovian and seasonal based modeling of rainfall-runoff process. Water resources management, 32(10), 3441-3456.
15.Wang, L., Zeng, Y., & Chen, T., 2015. Back propagation neural network with adaptive differential evolution algorithm for time series forecasting. Expert Systems with Applications, 42(2), 855-863.
16.Yang, S., Yang, D., Chen, J., & Zhao, B., 2019. Real-time reservoir operation using recurrent neural networks and inflow forecast from a distributed hydrological model. Journal of Hydrology, 579, 124229.
17.王如意，易任，2005，應用水文學，臺北，茂昌圖書公司。
18.蕭閔鍾，2012，類神經網路應用於颱風時期集水區流量預測之研究，碩士論文，淡江大學水資源及環境工程學系。
19.經濟部水利署北區水資源局，2013，石門水庫防洪、排淤及供水運轉系統建置及運轉操作諮詢，淡江大學水資源及環境工程學系
20.張斐章、張麗秋，2015，類神經網路導論：原理與應用(第二版)，滄海書局。