台灣位處於太平洋颱風經常侵襲之地，每當颱風來襲或有強降雨事件發生往往會造成土石流與淹水的災情，為了將此類傷害降至最低，發展出一套準確的降雨預報系統是一個很重要的課題。本研究選擇2016至2018年的5場颱風與1場熱低壓強降雨事件，利用中央氣象局之整合雷達回波圖配合地面雨量站進行雷達估計雨量之修正與預測，目的是希望能有效提升雷達估計雨量於山區之準確性，並保有雷達回波高空間與時間解析度的優點。研究首先以倒傳遞類神經網路(BPNN)結合包括地面雨量站X座標與Y座標、地面雨量站高程與地面雨量站和七股雷達站之距離在內的地理空間因子進行雷達回波估計降雨量的修正，並以均方根誤差及相關係數評估其修正結果；接著以遞迴類神經網路中的長短期記憶(LSTM)進行未來1~3小時的時雨量預測，探討其預測效果，最後再應用於山崩早期預警。研究結果顯示經倒傳遞類神經網路結合雷達回波與地面雨量站修正後之雨量與原本雷達估計的雨量相比，其均方根誤差最少可以減少29.80%，最多可減少90.44%，而相關係數大部分也都可提升至0.80 ~ 0.97之間，說明了經修正後的降雨量其準確度較單使用雷達回波估計的效果佳；而使用LSTM進行雨量預測以預測未來1小時的時雨量可得到最精確且最穩定之預報效果。

To reduce the damage of landslide disasters and flooding caused by heavy rainfall, the development of an accurate rainfall forecasting system is necessary. This study uses radar reflectivity provided by Central Weather Bureau (CWB) in Taiwan, combining with the information from 134 ground rainfall stations to correct and predict rainfall in future time steps. The approach we used is machine learning, including back propagation neural network (BPNN) and long short-term memory (LSTM), which is a special case of recurrent neural network (RNN). There are two purposes in this study, one is to enhance the accuracy of radar estimated rainfall in potential landslide areas and preserve the advantages of high spatial and temporal resolution of radar reflectivity. The other one is to predict rainfall accurately so that we can reduce the error of predicting disasters. Results show that the root-mean-square error of corrected rainfall by BPNN can reduce at least 29.80%, and at most 90.44% compares to traditional radar estimated rainfall. Most of the correlation coefficients can increase the estimate accuracy to the range in between 0.80 and 0.97. When apply this corrected result to rainfall prediction which is processed by LSTM, and it shows highly prediction accurate that when rainfall rate is under 10 mm/hr; however, if the rainfall rate exceeds 20 mm/hr, the deviation will be much large. Through the experiments, we also find that the most accurate and stable forecast is to make the prediction an hour before weather front reaches. This rainfall prediction model could help in landslide analysis and also to construct a landslide early warning system to reduce losses caused by landslide disasters in Taiwan.

中央氣象局氣象衛星中心(2015)，氣象遙測觀測-氣象衛星與氣象雷達。
丘台光、陳嘉榮、張保亮、林品芳(2010)，劇烈天氣監測系統QPESUMS 之服務與應用，中央氣象局15-26頁，檢自:
http://qpesums.thb.gov.tw/taiwan-html/thb/QPESUMS_doc.pdf
牟庭辰(2019)，基於遞迴神經網路於多重裝置下之硬舉動作辨識及應用，國立中央大學通訊工程學系，碩士論文，共71頁。
吳家佑(2016)，雷達回波圖做短期降雨預測，國立屏東大學資訊科學系，碩士論文，共33頁。
林建發(2000)，颱風降雨量之統計迴歸預測，國立中央大學統計研究所，碩士論文，共75頁。
林焜詳(2016)，支撐向量機與隨機森林應用於颱風時雨量預報之比較，國立成功大學水利工程研究所，碩士論文，共105頁。
周乃昉、鄭子璉、林柏承(2000)，應用類神經網路於颱風降雨量的推估，第十一屆水利工程研討會論文集，檢自:
http://www.tlcheng.tk/Paper/rain00/rain00.htm
周仲島、鍾吉俊、修榮光(2015)，S波段雙偏極化雷達在梅雨季豪大雨天氣系統定量降雨估計之應用，大氣科學期刊，第43期，第2號，91-113。
張智昌(2006)，整合氣象雷達與即時降雨資料於颱風降雨推估之研究，國立台灣大學地理環境資源研究所，碩士論文，共90頁。
張永欣(2007)，以多變量地質統計方法進行雨量空間內插，國立中央大學應用地質研究所，碩士論文，共187頁。
張保亮(2016)，中央氣象局氣象雷達的最新發展，中央氣象局，第四組雷達科。
黃威雄(2000)，應用類神經網路於颱風期間雷達降雨模擬之研究，國立臺灣大學土木工程學系，碩士論文，共76頁。
黃明宏(2008)，格網型類神經網路颱風降雨量模擬模式，國立成功大學水利工程研究所，碩士論文，共110頁。
童偉安(2015)，以類神經網路及複迴歸分析建構颱風降雨量及地下水位預測模式，國立中興大學水土保持學系，碩士學位論文，共113頁。
曾奕超(2017)，土石流警戒值之訂定，農業委員會水土保持局，共69頁。
楊宇恩(2016)，1961-1990臺灣的30年月均溫與月雨量空間推估-導入地形特徵，國立台灣師範大學地理學系，第四十五屆碩士論文，共75頁。
楊健生(2004)，認識都卜勒氣象雷達─基本原理與性能，飛航天氣，第二卷，50-56頁。
傅囿蓉(2012)，應用遺傳運算樹模式改進雷達回波推估 石門水庫集水區颱風降雨量準確度之研究，中華大學，碩士論文，共123頁。
陳正斌(2004)，應用模糊理論於颱風降雨量之推估，國立成功大學水利工程研究所，碩士論文，共69頁。
陳憲宗、劉鑌鋈、游保杉(2010)，應用支撐向量機與輻狀基底神經網路修正QPESUMS 雨量，農業工程學報，第56卷，第3期，1-14。
廖宇慶(2019)，氣象雷達簡介以及在劇烈天氣監測與研究上的應用，國立中央大學大氣科學系，雷達氣象實驗室。
蔡孟蓉(2006)，類神經網路結合衛星影像預報颱風降雨量，國立臺灣大學生物環境系統工程學研究所，碩士論文，共87頁。
蔡國榮(2010)，2008 年台灣西南部地區TRMM 降雨雷達與七股雷達回波觀測比較分析及降雨估計應用研究，國立中央大學大氣物理研究所，碩士論文，共69頁。
蔡曜丞(2019)，基於遞迴神經網路之聲學回聲消除技術，國立中央大學通訊工程學系，碩士論文，共56頁。
劉鑌鋈(2009)，利用機器學習修正QPESUMS雷達估計降雨，國立成功大學水利工程研究所，碩士論文，共102頁。
羅竣文(2010)，應用類神經網路於颱風降雨量即時預報之研究，國立台灣大學工學院土木工程研究所，碩士論文，共90頁。
蘇良石、郭漱泠、陳文恭、陳來發、李南文、林宏聖、魏運寶(1993)，雷達輔助之降水強度估算─楊希颱風個案(1990)，中正理工學院，共15頁。
Atlas, D., & Ulbrich, C. W. (1977). Path-and area-integrated rainfall measurement by microwave attenuation in the 1–3 cm band. Journal of Applied Meteorology, 16(12), 1322-1331.
Austin, P. M. (1987). Relation between measured radar reflectivity and surface rainfall. Monthly Weather Review, 115(5), 1053-1070.
Ayzel, G., Heistermann, M., Sorokin, A., Nikitin, O., & Lukyanova, O. (2019). All convolutional neural networks for radar-based precipitation nowcasting. Procedia Computer Science, 150, 186-192.
Agrawal, S., Barrington, L., Bromberg, C., Burge, J., Gazen, C., & Hickey, J. (2019). Machine Learning for Precipitation Nowcasting from Radar Images. arXiv preprint arXiv:1912.12132.
Battan, L. J. (1973). Radar Observation of the Atmosphere. The University of Chicago Press, Chicago, 324.
Bech, J., Codina, B., Lorente, J., & Bebbington, D. (2003). The sensitivity of single polarization weather radar beam blockage correction to variability in the vertical refractivity gradient. Journal of Atmospheric and Oceanic Technology, 20(6), 845-855.
Castaño, L. (2017). Short-Term Quantitative Precipitation Forecasting Using Radar Data and Neural Network. Freie Universität Berlin, Department of Computer Science & Mathematics, Institute for Computer Science, 1-51.
Hitschfeld, W., & Bordan, J. (1954). Errors inherent in the radar measurement of rainfall at attenuating wavelengths. Journal of Meteorology, 11(1), 58-67.
Harrold, T. W., and Kitchingman, P. G. (1975). Measurement of surface rainfall using radar when the beam intersects the melting layer. Preprints, 16th Radar Meteorology Conference (Houston), AMS, Boston, 473-478.
Hu, C., Wu, Q., Li, H., Jian, S., Li, N., & Lou, Z. (2018). Deep learning with a long short-term memory networks approach for rainfall-runoff simulation. Water, 10(11), 1543.
Jordan, P. W., Seed, A. W., & Weinmann, P. E. (2003). A stochastic model of radar measurement errors in rainfall accumulations at catchment scale. Journal of Hydrometeorology, 4(5), 841-855.
Kang, J., Wang, H., Yuan, F., Wang, Z., Huang, J., & Qiu, T. (2020). Prediction of Precipitation Based on Recurrent Neural Networks in Jingdezhen, Jiangxi Province, China. Atmosphere, 11(3), 246.
Lan, L. (2017), Levenberg-Marquardt算法淺談，檢自:
https://blog.csdn.net/liu14lang/article/details/53991897
Madsen, K., Nielsen, H. B., & Tingleff, O. (2004). Methods for non-linear least squares problems. Informatics and Mathematical Modelling, Technical University of Denmark, 2nd Edition, 17-28.
Majani, B. S. (2007). Analysis of external drift kriging algorithm with application to precipitation estimation in complex orography. ITC.
McKee, J. L., & Binns, A. D. (2016). A review of gauge–radar merging methods for quantitative precipitation estimation in hydrology. Canadian Water Resources Journal/Revue canadienne des ressources hydriques, 41(1-2), 186-203.
Probert‐Jones, J. R. (1962). The radar equation in meteorology. Quarterly Journal of the Royal Meteorological Society, 88(378), 485-495.
Poornima, S., & Pushpalatha, M. (2019). Prediction of Rainfall Using Intensified LSTM Based Recurrent Neural Network with Weighted Linear Units. Atmosphere, 10(11), 668.
Rico-Ramirez, M. A., & Cluckie, I. D. (2008). Classification of ground clutter and anomalous propagation using dual-polarization weather radar. IEEE Transactions on Geoscience and Remote Sensing, 46(7), 1892-1904.
Sachidananda, M., & Zrnic', D. S. (1985). Z_DR measurement considerations for a fast scan capability radar. Radio Science, 20(4), 907-922.
Shi, X., Chen, Z., Wang, H., Yeung, D. Y., Wong, W. K., & Woo, W. C. (2015). Convolutional LSTM network: A machine learning approach for precipitation nowcasting. In Advances in neural information processing systems, 802-810.
Toth, E., Brath, A., & Montanari, A. (2000). Comparison of short-term rainfall prediction models for real-time flood forecasting. Journal of hydrology, 239(1-4), 132-147.
Verworn, A., & Haberlandt, U. (2011). Spatial interpolation of hourly rainfall-effect of additional information, variogram inference and storm properties. Hydrology and Earth System Sciences 15 (2011), Nr. 2, 15(2), 569-584.
Wilson, J. W., & Brandes, E. A. (1979). Radar measurement of rainfall—A summary. Bulletin of the American Meteorological Society, 60(9), 1048-1060.
Xin, L., Reuter, G., & Larochelle, B. (1997). Reflectivity‐rain rate relationships for convective rainshowers in Edmonton: Research note. Atmosphere-Ocean, 35(4), 513-521.