题名

應用類神經網路於颱風災損預測

并列篇名

Application of neural networks to typhoon loss prediction

DOI

10.6149/JDM.201903_8(1).0003

作者

張哲敏(Che-Min Chang)；陳佳正(Chia-Jeng Chen)

关键词

巨災 ； 風險分析 ； 機器學習 ； 統計模式 ； catastrophe ； risk analysis ； machine learning ； statistical modeling

期刊名称

災害防救科技與管理學刊

卷期/出版年月

8卷1期（2019 / 03 / 01）

页次

55 - 87

内容语文

繁體中文
中文摘要

根據行政院農委會公布之統計資料顯示，農、林、漁及畜牧業在2006至2015年間受到颱風侵襲導致的災害損失共計約新台幣843億元。對應此份災損資料，本研究彙整颱風同期間全台風速與降雨數據，以超越機率閾值將數據分為5等級，並配合地區的土地利用概況，分析氣象變量、暴露量和災損間之關聯性。本研究亦利用淺層機器學習方法之倒傳遞類神經網路建立兩種空間尺度的災損預測模式。模式訓練結果顯示可有效模擬災損金額，Nash－Sutcliffe efficiency（NSE）最高為0.95，而全國平均可達0.7，而驗證結果顯示模式雖無法精確反映極端值，但在部分地區的NSE指數仍可達0.6以上，且合理地表現災損風險的空間分佈。本研究成果可予政府相關單位在颱風期間作為決策依據。
英文摘要

According to the statistics released by the Council of Agriculture, Executive Yuan, the aggregate typhoon losses in agriculture, forestry, fishery and animal husbandry were approximately $84.3 billion NTD from 2006 to 2015. This study acquired wind speed and rainfall data corresponding to each typhoon event in this period, and divided the data into five levels using exceedance probabilities as the thresholds. In conjunction with land-use data, correlations among weather variables, exposure, and losses were analyzed. Afterwards, a shallow machine learning method--back-propagation neural networks--was applied to the development of loss prediction models at different spatial scales. Calibration results showed that the models perform well at loss prediction with the highest Nash-Sutcliffe efficiency (NSE) as 0.95 and the national average ≥ 0.7. In validation, while upmost accuracy cannot be achieved for the prediction of extreme events, the cross-validated NSE can still reach 0.6 in certain regions, and a reasonable spatial distribution of typhoon risk is presented. This work is expected to provide guidance for relative government agencies prior to and during typhoon invasions.
主题分类 基礎與應用科學 > 大氣科學
工程學 > 市政與環境工程
参考文献
  1. Bengio, Y.,Simard, P.,Frasconi, P.(1994).Learning long-term dependencies with gradient descent is difficult.IEEE Transactions on Neural Networks,5(2),157-166.
  2. Chang, F. J.,Chiang, Y. M.,Cheng, W. G.(2013).Self-organizing radial basis neural network for predicting typhoon-induced losses to rice.Paddy Water Environ,11(1-4),369-380.
  3. Chen, C. J.,Lee, T. Y.,Chang, C. M.,Lee, J. Y.(2018).Assessing typhoon damages to Taiwan in the recent decade: return period analysis and loss prediction.Natural Hazards,91(2),759-783.
  4. Chiang, Y. M.,Cheng, W. G.,Chang, F. J.(2012).A hybrid artificial neural networkbased agri-economic model for predicting typhoon-induced losses.Natural Hazards,63(2),769-787.
  5. Hallegatte, S.(2012).Policy Research Working PaperPolicy Research Working Paper,Washington DC, USA:World Bank.
  6. Hinton, G. E.,Salakhutdinov, R.(2006).Reducing the Dimensionality of Data with Neural Networks.Science,313(5786),504-507.
  7. Hiroi, K.,Kawaguchi, N.(2016).FloodEye: Real-time flash flood prediction system for urban complex water flow.2016 Conference for IEEE SENSORS,Orlando, FL, USA:
  8. Hong, S.,Kim, S.,Joh, M.,Song, S.(2017).GlobeNet: Convolutional Neural Networks for Typhoon Eye Tracking from Remote Sensing Imagery.7th International Workshop on Climate Informatics,Boulder, CO:
  9. Huang, S. K.,Wang, J. J.(2015).Typhoon damage assessment model and analysis in Taiwan.Natural Hazards,79(1),497-510.
  10. Kim, S.,Hong, S.,Joh, M.,Song, S.(2017).DeepRain: ConvLSTM Network for Precipitation Prediction using Multichannel Radar Data.7th International Workshop on Climate Informatics,Boulder, CO:
  11. LeCun, Y.,Bengio, Y.,Hinton, G. E.(2015).Deep learning.Nature,521,436-444.
  12. Li, C.,Bai, Y.,Zeng, B.(2016).Deep Feature Learning Architectures for Daily Reservoir Inflow Forecasting.Water Resources Management,30(14),5145-5161.
  13. Pascanu, R.,Mikolov, T.,Bengio, Y.(2012).Pascanu, R., Mikolov, T. & Bengio, Y., 2012. Understanding the exploding gradient problem. Computing Research Repository (CoRR) abs/1211.5063..
  14. Rosenblatt, F.(1957).Rosenblatt, F., 1957. The Perceptron — A Perceiving and Recognizing Automaton. Tech. Rep. 85-460-1 (Cornell Aeronautical Laboratory)..
  15. Rumelhart, D. E.,Hinton, G. E.,Williams, R. J.(1986).Learning Representations by Back-Propagating Errors.Nature,323,533-536.
  16. Shi, X.,Chen, Z.,Wang, H.,Yeung, D.,Wong, W.,Woo, W.(2015).Shi, X., Chen, Z., Wang, H., Yeung, D., Wong, W. & Woo, W., 2015. Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting. Computing Research Repository (CoRR) abs/1506.04214..
  17. UN/ISDR(2004).Living with risk, a global review of disaster reduction initiatives.Geneva:United Nations International Strategy for Disaster Reduction.
  18. Werbos, P. J.(1981).Applications of advances in nonlinear sensitivity analysis.10th IFIP conference,NYC:
  19. 王俊明,李心平,李鎮,臧運忠,謝正倫(2010)。莫拉克颱風災害綜覽。中華防災學刊，2(1)，27-34。
  20. 林詩偉,陳士杰,林欣志(2006)。模擬退火法應用於倒傳遞類神經網路之參數調整。資訊管理學術與實務研討會論文集
  21. 陳志寬(2012)。逢甲大學水利工程與資源保育學系。
  22. 陳禹銘、蘇昭郎、黃詩倩，2009，〈災害風險評估研究之探討〉《災害防救電子報》，2009年7月，48期，摘錄自http://ncdr.nat.gov.tw/news/newsletter2/048/048.pdf
  23. 楊惠萱,張芝苓,李香潔(2015)。,新北市:國家災害防救科技中心。
  24. 溫振宇(2005)。成功大學地球科學研究所。
  25. 劉少軍,張京紅,何政偉,蔡大鑫,田光輝(2010)。基於GIS的颱風災害損失評估模型研究。災害學，25(2)，64-67。
  26. 冀樹勇,鄭錦桐,林伯勳,沈哲緯,張州男(2008)。淺談天然災害風險管理。中國土木水利工程學刊，35(2)，104-111。
  27. 謝承憲、蘇昭郎、吳佳容，2010，〈災害風險評估－災害風險管理與減災之工具〉《災害防救電子報》，2010年6月，59期，摘錄自http://www.ncdr.nat.gov.tw/upload/epaper/059.pdf
print cancel