請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/71341
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 吳健銘 | |
dc.contributor.author | Shih-Wen Tsou | en |
dc.contributor.author | 鄒適文 | zh_TW |
dc.date.accessioned | 2021-06-17T05:59:06Z | - |
dc.date.available | 2019-02-15 | |
dc.date.copyright | 2019-02-15 | |
dc.date.issued | 2019 | |
dc.date.submitted | 2019-02-14 | |
dc.identifier.citation | 參考文獻
Arakawa, A., & Schubert, W. H. (1974). Interaction of a cumulus cloud ensemble with the large-scale environment, Part I. Journal of the Atmospheric Sciences, 31(3), 674-701. Arakawa, A., Jung, J. H., & Wu, C. M. (2011). Toward unification of the multiscale modeling of the atmosphere. Atmospheric Chemistry and Physics, 11(8), 3731-3742. Arakawa, A., & Wu, C. M. (2013). A unified representation of deep moist convection in numerical modeling of the atmosphere. Part I. Journal of the Atmospheric Sciences, 70(7), 1977-1992. Bengio, Y., & LeCun, Y. (2007). Scaling learning algorithms towards AI. Large-scale kernel machines, 34(5), 1-41. Chien, M. H., & Wu, C. M. (2016). Representation of topography by partial steps using the immersed boundary method in a vector vorticity equation model (VVM). Journal of Advances in Modeling Earth Systems, 8(1), 212-223. Delalleau, O., & Bengio, Y. (2011). Shallow vs. deep sum-product networks. In Advances in Neural Information Processing Systems (pp. 666-674). Goodfellow, I., Bengio, Y., Courville, A., & Bengio, Y. (2016). Deep learning (Vol. 1). Cambridge: MIT press. Gers, F. A., Schmidhuber, J., & Cummins, F. (1999). Learning to forget: Continual prediction with LSTM. Holloway, C. E., & Neelin, J. D. (2009). Moisture vertical structure, column water vapor, and tropical deep convection. Journal of the atmospheric sciences, 66(6), 1665-1683. Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780. Jung, J. H., & Arakawa, A. (2008). A three-dimensional anelastic model based on the vorticity equation. Monthly Weather Review, 136(1), 276-294. Ji, S., Xu, W., Yang, M., & Yu, K. (2013). 3D convolutional neural networks for human action recognition. IEEE transactions on pattern analysis and machine intelligence, 35(1), 221-231. Jim, K. C., Giles, C. L., & Horne, B. G. (1996). An analysis of noise in recurrent neural networks: convergence and generalization. IEEE Transactions on neural networks, 7(6), 1424-1438. Lee, H. Y. (2018). Structured Learning. From http://speech.ee.ntu.edu.tw/~tlkagk/courses/MLDS_2018/Lecture/rule.pdf LeCun, Y., & Bengio, Y. (1995). Convolutional networks for images, speech, and time series. The handbook of brain theory and neural networks, 3361(10), 1995. LeCun, Y. (1989). Generalization and network design strategies. Connectionism in perspective, 143-155. Montúfar, G. F. (2014). Universal approximation depth and errors of narrow belief networks with discrete units. Neural computation, 26(7), 1386-1407. O'Gorman, P. A., & Dwyer, J. G. (2018). Using Machine Learning to Parameterize Moist Convection: Potential for Modeling of Climate, Climate Change, and Extreme Events. Journal of Advances in Modeling Earth Systems, 10(10), 2548-2563. Pan, D. M., & Randall, D. D. (1998). A cumulus parameterization with a prognostic closure. Quarterly Journal of the Royal Meteorological Society, 124(547), 949-981. Pascanu, R., Gulcehre, C., Cho, K., & Bengio, Y. (2013). How to construct deep recurrent neural networks. arXiv preprint arXiv:1312.6026. Tsai, W. M., & Wu, C. M. (2017). The environment of aggregated deep convection. Journal of Advances in Modeling Earth Systems, 9(5), 2061-2078. Venugopalan, S., Rohrbach, M., Donahue, J., Mooney, R., Darrell, T., & Saenko, K. (2015). Sequence to sequence-video to text. In Proceedings of the IEEE international conference on computer vision (pp. 4534-4542). Wu, C. M., & Arakawa, A. (2011). Inclusion of surface topography into the vector vorticity equation model (VVM). Journal of Advances in Modeling Earth Systems, 3(2). Wu, C. M., & Arakawa, A. (2014). A unified representation of deep moist convection in numerical modeling of the atmosphere. Part II. Journal of the Atmospheric Sciences, 71(6), 2089-2103. Yanai, M., Esbensen, S., & Chu, J. H. (1973). Determination of bulk properties of tropical cloud clusters from large-scale heat and moisture budgets. Journal of the Atmospheric Sciences, 30(4), 611-627. 附錄reference Michalski, R. S., Carbonell, J. G., & Mitchell, T. M. (Eds.). (2013). Machine learning: An artificial intelligence approach. Springer Science & Business Media. Neter, J., Kutner, M. H., Nachtsheim, C. J., & Wasserman, W. (1996). Applied linear statistical models (Vol. 4, p. 318). Chicago: Irwin. Pearson, K. (1901). LIII. On lines and planes of closest fit to systems of points in space. The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science, 2(11), 559-572. Rosenblatt, F. (1958). The perceptron: a probabilistic model for information storage and organization in the brain. Psychological review, 65(6), 386. Russell, S. J., & Norvig, P. (2016). Artificial intelligence: a modern approach. Malaysia; Pearson Education Limited,. Samuel, A. L. (1959). Some studies in machine learning using the game of checkers. IBM Journal of research and development, 3(3), 210-229. Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., Van Den Driessche, G., ... & Dieleman, S. (2016). Mastering the game of Go with deep neural networks and tree search. nature, 529(7587), 484. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/71341 | - |
dc.description.abstract | 濕對流過程參數化是造成氣候模式和數值天氣模式不確定性的主要原因。隨著硬體和技術的發展,前人嘗試使用機器學習藉由高解析雲解析模式的結果求得特定網格解析度下的濕對流效應(機器學習濕對流參數化),並期待未來能夠取代現存模式中由積雲參數化所診斷的濕對流效應。
而另一方面,氣候模式及數值天氣模式的發展潮流為增加水平解析度,以獲得更局部的氣象資訊並期望更準確的預測濕對流的發展過程。然而現存的積雲參數化在模式解析度逐步上升至~O(10km)尺度時,濕對流過程該由積雲參數化處理或是由網格尺度的物理過程處理變得模糊不清(grey zone resolution)。在這樣的水平解析度下,網格內可能不再同時包含對流以及其環境,意即決定網格對流效應的環境將延伸至相鄰網格。 然而,至今仍未有研究評估在grey zone resolution下以相鄰網格作為決定對流效應之環境對於模擬結果的影響。因此本研究嘗試利用高解析雲解析模式(VVM)的資料,並使用一種可掃描區域內參數梯度的3D卷積神經網路,在Grey zone resolution利用各個網格及其相鄰網格的資訊,預測各個網格的對流效應。為了證實在grey zone resolution鄰近網格資訊對於預測對流效應的助益,本研究呈現多元線性回歸(Multiple Linear Regression)及深度神經網路(Deep Neural Networks, DNN)的結果作為對照組,它們分別是機器學習模型的最低標準,及最基礎的深度學習模型。研究結果指出,由3D卷積神經網路所預測的對流效應在對流位置、對流強度高度分布及對流效應對可降水量的反應皆較另兩種模型有更好的表現,其中在對流效應對可降水量的反應的預測中,3D卷積神經網路甚至在環境濕度較高的環境下的預測,可以捕捉到5公里處freezing level非常細節的對流特徵,這是其他模型較難掌握的現象。 | zh_TW |
dc.description.abstract | The parameterization of moist convection contributes to the uncertainty in climate modeling and numerical weather prediction. As the improvement of computational resources and the theory of machine learning, building parameterization of moist convection based on machine learning method becomes feasible nowadays. In the meanwhile, the grid size used by GCMs become finer in order to represent processes at finer scale, in which more accurate representation of moist convection is expected. However, the ambiguity between subgrid-scale and resolved scale processes is introduced which arouses the grey zone problem. In such resolution ~O(10km), the relationship between moist convection and its environment may not be distinguishable upon the same grid box. This study tries to apply the machine learning method to evaluate the model that considers the adjacent grid boxes in grey zone resolution. We use 3-Dimension Convolutional Neural Networks (3D-CNN) as our model to predict the effect of moist convection according to the meteorology parameters from both the target grid box and its surroundings. The high-resolution data is obtained from the results of a vector vorticity equation cloud-resolving model (VVM) under various environmental conditions. The unique aspect of 3D-CNN is that it can detect the gradient of each fields between adjacent grids within a certain domain. The result based on two other models, which are Multiple Linear Regression and Deep Neural Network is also shown in this study to manifest our findings. The result shows that 3D-CNN predicts more reasonable spatial distribution and vertical distribution of the effect of moist convection, and the response of the effect of moist convection to total precipitable water compared to the other models. | en |
dc.description.provenance | Made available in DSpace on 2021-06-17T05:59:06Z (GMT). No. of bitstreams: 1 ntu-108-R05229014-1.pdf: 4369816 bytes, checksum: c00e84bfee6a976ba0f16947d59392cb (MD5) Previous issue date: 2019 | en |
dc.description.tableofcontents | 目錄
口試委員會審定書 i 誌謝 ii 摘要 iii Abstract iv 目錄 v 圖目錄 vii 1. 前言 1 2. 資料與方法 4 2.1 資料 4 2.2 機器學習模型之輸入及輸出 5 2.3 三維深度卷積神經網路(3D Deep Convolutional Neural Networks, 3D-CNN) 6 3. 機器學習模型評估 8 3.1對流位置 8 3.2對流垂直強度分布 10 3.3網格可降水量與對流強度的關係 12 4. 結論與討論 15 圖片 18 參考文獻 43 附錄 46 機器學習及監督式學習 46 多變量線性回歸(Multiple Linear Regression) 48 深度學習(Deep Learning) 49 深度神經網路(Deep Neural Networks) 50 激勵函數(Activation function) 51 對流可用位能(CAPE) 51 垂直積分水氣輻散(MDC) 51 濕靜能(MSE) 52 主成分分析(Principal components analysis, PCA) 52 附錄reference 53 | |
dc.language.iso | zh-TW | |
dc.title | 應用三維卷積神經網路在濕對流的參數化 | zh_TW |
dc.title | The representation of moist convection using 3D Convolutional Neural Networks | en |
dc.type | Thesis | |
dc.date.schoolyear | 107-1 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 陳維婷,蘇世顥,郭鴻基 | |
dc.subject.keyword | 機器學習,深度學習,三維卷積神經網路,濕對流參數化,雲解析模式,VVM, | zh_TW |
dc.subject.keyword | Machine Learning,Deep Learning,3D-Convolutional Neural Networks,representation of moist convection,cloud-resolving model,VVM, | en |
dc.relation.page | 53 | |
dc.identifier.doi | 10.6342/NTU201900572 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2019-02-14 | |
dc.contributor.author-college | 理學院 | zh_TW |
dc.contributor.author-dept | 大氣科學研究所 | zh_TW |
顯示於系所單位: | 大氣科學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-108-1.pdf 目前未授權公開取用 | 4.27 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。