極端天氣事件對航空安全構成重大威脅。 天氣模式的快速變化給飛行員帶來了巨大的壓力，並使飛機難以保持對運行的控制。 本論文提出了一種利用長短期記憶（LSTM）來增強天氣預報的方法。 在本研究中，網絡學習中使用了 12 個颱風的 10 個天氣特徵的數據集，其中 11 個用於訓練，1 個用於測試。 2010年至2020年台灣颱風數據來自台灣中央氣象局，並通過數據歸一化應用於最大陣風速度預測。 將皮爾森積差相關係數、交叉驗證的遞歸特徵消除和隨機森林這三種特徵選擇方法與 LSTM 集成來比較它們的性能。 結果表明，採用隨機森林的 LSTM 優於不採用特徵選擇的 LSTM，最大陣風速度預報的均方根誤差 (RMSE) 和平均絕對百分比誤差 (MAPE) 可以從 2.1244 降低到 1.5559，從 24.5849 降低% 至14.0684 %。 有效的特徵選擇和數值數據的結合可以實現精確的航空天氣探索。

Extreme weather events pose a significant threat to aviation safety. The rapid shifts in weather patterns create immense pressure on pilots and make aircraft challenging to maintain control over operations. This thesis proposes an approach that utilizes long short-term memory (LSTM) to enhance weather forecasts. In this study, a dataset of 9 weather features from 12 typhoons is used in the network learning, 11 for training and 1 for testing. The typhoon data in Taiwan from 2010 to 2020 was collected from the Central Weather Bureau of Taiwan and applied to the maximum wind gust speed forecasting by using data normalization. Three feature selection methods: the Pearson product-moment correlation coefficient, recursive feature elimination with cross-validation and random forest are integrated with LSTM to compare their performance. The results show that three types of feature selection can improve forecast performance compared to LSTM models without feature selection. LSTM with random forest achieves the best model performance, the root square mean error (RMSE) and the mean absolute percentage error (MAPE) of the maximum wind gust speed forecast can be reduced from 2.1244 to 1.5559 and 24.5849% to 14.0684%, respectively. The combination of effective feature selection and numerical data enables accurate aviation weather exploration.

[1] Anaman, K. A., Quaye, R., and Owusu-Brown, B. 2017. Benefits of Aviation Weather Services: A Review of International Literature. Research in World Economy Research in World Economy, 8(1), 45-58.
[2] Ummenhofer, C. C., and Meehl, G. A. 2017. Extreme Weather and Climate Events with Ecological Relevance: A Review. Philosophical Transactions of the Royal Society B: Biological Sciences, 372(1723), 20160135.
[3] Ren, X., Li, X., Ren, K., Song, J., Xu, Z., Deng, K., and Wang, X. 2021. Deep Learning-Based Weather Prediction: A Survey. Big Data Research, 23, 100178.
[4] Dong, Z., Yang, D., Reindl, T., and Walsh, W. M. 2014. Satellite Image Analysis and a Hybrid ESSS/ANN Model to Forecast Solar Irradiance in the Tropics. Energy Conversion and Management, 79, 66-73.
[5] Si, Z., Yu, Y., Yang, M., and Li, P. 2020. Hybrid Solar Forecasting Method Using Satellite Visible Images and Modified Convolutional Neural Networks. IEEE Transactions on Industry Applications, 57(1), 5-16.
[6] Xie, F., Shi, M., Shi, Z., Yin, J., and Zhao, D. 2017. Multilevel Cloud Detection in Remote Sensing Images Based on Deep Learning. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 10(8), 3631-3640.
[7] Yang, J., Guo, J., Yue, H., Liu, Z., Hu, H., and Li, K. 2019. CDnet: CNN-based Cloud Detection for Remote Sensing Imagery. IEEE Transactions on Geoscience and Remote Sensing, 57(8), 6195-6211.
[8] Segal-Rozenhaimer, M., Li, A., Das, K., and Chirayath, V. 2020. Cloud detection Algorithm for Multi-Modal Satellite Imagery Using Convolutional Neural-Networks (CNN). Remote Sensing of Environment, 237, 111446.
[9] Biswas, S. K., Sinha, N., Purkayastha, B., and Marbaniang, L. 2014. Weather Prediction by Recurrent Neural Network Dynamics. International Journal of Intelligent Engineering Informatics, 2(2-3), 166-180.
[10] Zaytar, M. A., and El Amrani, C. 2016. Sequence to Sequence Weather Forecasting with Long Short-Term Memory Recurrent Neural Networks. International Journal of Computer Applications, 143(11), 7-11.
[11] Qing, X., and Niu, Y. 2018. Hourly Day-ahead Solar Irradiance Prediction Using Weather Forecasts by LSTM. Energy, 148, 461-468.
[12] Yu, Y., Cao, J., and Zhu, J. 2019. An LSTM Short-term Solar Irradiance Forecasting Under Complicated Weather Conditions. IEEE Access, 7, 145651-145666.
[13] Liu, Z., and Sullivan, C. J. 2019. Prediction of Weather Induced Background Radiation Fluctuation with Recurrent Neural Networks. Radiation Physics and Chemistry, 155, 275-280.
[14] Guan, Y., Zhang, B., and Yan, X. 2019. Accurate Short-term Forecasting for Photovoltaic Power Method Using RBM Combined LSTM-RNN Structure with Weather Factors Quantification. IEEE Sustainable Power and Energy Conference, 797-802.
[15] Gao, M., Li, J., Hong, F., and Long, D. 2019. Day-Ahead Power Forecasting in a Large-Scale Photovoltaic Plant Based on Weather Classification Using LSTM. Energy, 187, 115838.
[16] Karevan, Z., and Suykens, J. A. 2020. Transductive LSTM for Time-Series Prediction: An Application to Weather Forecasting. Neural Networks, 125, 1-9.
[17] Kim, K. S., Lee, J. B., Roh, M. I., Han, K. M., and Lee, G. H. 2020. Prediction of Ocean Weather Based on Denoising Autoencoder and Convolutional LSTM. Journal of Marine Science and Engineering, 8(10), 805.
[18] Hossain, M. S., and Mahmood, H. 2020. Short-term Photovoltaic Power Forecasting Using an LSTM Neural Network and Synthetic Weather Forecast. IEEE Access, 8, 172524-172533.
[19] Tukymbekov, D., Saymbetov, A., Nurgaliyev, M., Kuttybay, N., Dosymbetova, G., and Svanbayev, Y. 2021. Intelligent Autonomous Street Lighting System Based on Weather Forecast Using LSTM. Energy, 231, 120902.
[20] Zhu, Z., Zhuo, L., Qu, P., Zhou, K., and Zhang, J. 2016. Extreme Weather Recognition Using Convolutional Neural Networks. IEEE International Symposium on Multimedia, 621-625.
[21] Liu, Y., Racah, E., Correa, J., Khosrowshahi, A., Lavers, D., Kunkel, K., Collins, W. and Wehner, M. 2016. Application of Deep Convolutional Neural Networks for Detecting Extreme Weather in Climate Datasets. Computer Vision and Pattern Recognition, 81–88.
[22] Chen, B., Chen, B. F., and Lin, H. T. 2018. Rotation-Blended CNNs on a New Open Dataset for Tropical Cyclone Image-to-Intensity Regression. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 90-99.
[23] Tian, W., Huang, W., Yi, L., Wu, L., and Wang, C. 2020. A CNN-based Hybrid Model for Tropical Cyclone Intensity Estimation in Meteorological Industry. IEEE Access, 8, 59158-59168.
[24] Wang, C., Zheng, G., Li, X., Xu, Q., Liu, B., and Zhang, J. 2021. Tropical Cyclone Intensity Estimation from Geostationary Satellite Imagery Using Deep Convolutional Neural Networks. IEEE Transactions on Geoscience and Remote Sensing, 60, pp. 1-16.
[25] Wang, Q., Huang, J., Liu, R., Men, C., Guo, L., Miao, Y., Jiao, L., Wang, Y., Shoaib, M., and Xia, X. 2020. Sequence-based Statistical Downscaling and its Application to Hydrologic Simulations Based on Machine Learning and Big Data. Journal of Hydrology, 586, 124875.
[26] Zhou, Y., Guo, S., Xu, C. Y., Chang, F. J., and Yin, J. 2020. Improving the Reliability of Probabilistic Multi-Step-Ahead Flood Forecasting by Fusing Unscented Kalman Filter with Recurrent Neural Network. Water, 12(2), 578.
[27] Kao, I. F., Liou, J. Y., Lee, M. H., and Chang, F. J. 2021. Fusing Stacked Autoencoder and Long Short-Term Memory for Regional Multistep-Shead Flood Inundation Forecasts. Journal of Hydrology, 598, 126371.
[28] Gao, S., Zhao, P., Pan, B., Li, Y., Zhou, M., Xu, J. L., Zhong, S., and Shi, Z. W. 2018. A Nowcasting Model for the Prediction of Typhoon Tracks Based on a Long Short-Term Memory Neural Network. Acta Oceanologica Sinica, 37(5), 8–12.
[29] Chen, R., Wang, X., Zhang, W., Zhu, X., Li, A., and Yang, C. 2019. A Hybrid CNN-LSTM Model for Typhoon Formation Forecasting. GeoInformatica, 23(3), 375-396.
[30] Yuan, S., Wang, C., Mu, B., Zhou, F., and Duan, W. 2021. Typhoon Intensity Forecasting Based on LSTM Using the Rolling Forecast Method. Algorithms, 14(3), 83.
[31] Li, W., Kiaghadi, A., and Dawson, C. 2021. Exploring the Best Sequence LSTM Modeling Architecture for Flood Prediction. Neural Computing and Applications, 33(11), 5571-5580.
[32] Chen, K., Kuang, C., Wang, L., Chen, K., Han, X., and Fan, J. 2021. Storm Surge Prediction Based on Long Short-Term Memory Neural Network in the East China Sea. Applied Sciences, 12(1), 181.
[33] Wei, C. C. 2021. Collapse Warning System Using LSTM Neural Networks for Construction Disaster Prevention in Extreme Wind Weather. Journal of Civil Engineering and Management, 27(4), 230-245.
[34] Caseri, A. N., Santos, L. B. L., and Stephany, S. 2022. A Convolutional Recurrent Neural Network for Strong Convective Rainfall Nowcasting Using Weather Radar Data in Southeastern Brazil. Artificial Intelligence in Geosciences, 3, 8-13.
[35] Li, P., Zhang, J., and Krebs, P. 2022. Prediction of Flow Based on a CNN-LSTM Combined Deep Learning Approach. Water, 14(6), 993.
[36] Zhou, G., Xu, J., Qian, Q., Xu, Y., and Xu, Y. 2022. Discriminating Technique of Typhoon Rapid Intensification Trend Based on Artificial Intelligence. Atmosphere, 13(3), 448.
[37] Lamraoui, M., Barakat, M., Thomas, M., and Badaoui, M. E. 2015. Chatter Detection in Milling Machines by Neural Network Classification and Feature Selection. Journal of Vibration and Control, 21(7), 1251-1266.
[38] Efitorov, A., Burikov, S., Dolenko, T., Laptinskiy, K., and Dolenko, S. 2015. Significant Feature Selection in Neural Network Solution of an Inverse Problem in Spectroscopy. Procedia Computer Science, 66, 93-102.
[39] Cruz, F. C., Simas Filho, E. F., Albuquerque, M. C. S., Silva, I. C., Farias, C. T. T., and Gouvêa, L. L. 2017. Efficient Feature Selection for Neural Network Based Detection of Flaws in Steel Welded Joints Using Ultrasound Testing. Ultrasonics, 73, 1-8.
[40] Zhang, H., Wang, J., Sun, Z., Zurada, J. M., and Pal, N. R. 2019. Feature Selection for Neural Networks Using Group Lasso Regularization. IEEE Transactions on Knowledge and Data Engineering, 32(4), 659-673.
[41] Toğaçar, M., Ergen, B., and Cömert, Z. 2020. Waste Classification Using Autoencoder Network with Integrated Feature Selection Method in Convolutional Neural Network Models. Measurement, 153, 107459.
[42] Toğaçar, M., Ergen, B., and Cömert, Z. 2020. Classification of Flower Species by Using Features Extracted from The Intersection of Feature Selection Methods in Convolutional Neural Network Models. Measurement, 158, 107703.
[43] Pham, T. N., Van Tran, L., and Dao, S. V. T. 2020. Early Disease Classification of Mango Leaves Using Feed-Forward Neural Network and Hybrid Metaheuristic Feature Selection. IEEE Access, 8, 189960-189973.
[44] Chen, Z., Pang, M., Zhao, Z., Li, S., Miao, R., Zhang, Y., Feng, X., Feng, X., Zhang, Y., Duan, M., Huang, L., and Zhou, F. 2020. Feature Selection May Improve Deep Neural Networks for the Bioinformatics Problems. Bioinformatics, 36(5), 1542-1552.
[45] Li, S., Wang, P., and Goel, L. 2015. Wind Power Forecasting Using Neural Network Ensembles with Feature Selection. IEEE Transactions on Sustainable Energy, 6(4), 1447-1456.
[46] Zhao, C., van Heeswijk, M., and Karhunen, J. 2016. Air Quality Forecasting Using Neural Networks. IEEE Symposium Series on Computational Intelligence, 1-7.
[47] Wolff, B., Kramer, O., and Heinemann, D. 2017. Selection of Numerical Weather Forecast Features for PV Power Predictions with Random Forests. International Workshop on Data Analytics for Renewable Energy Integration, 78-91.
[48] Das, B., Nair, B., Reddy, V. K., and Venkatesh, P. 2018. Evaluation of Multiple Linear, Neural Network and Penalised Regression Models for Prediction of Rice Yield Based on Weather Parameters for West Coast of India. International Journal of Biometeorology, 62(10), 1809-1822.
[49] Yin, Y., Yang, P., Zhang, Y., Chen, H., and Fu, S. 2020. Feature Selection and Processing of Turbulence Modeling Based on an Artificial Neural Network. Physics of Fluids, 32(10), 105117.
[50] Chen, H., and Chang, X. 2021. Photovoltaic Power Prediction of LSTM Model Based on Pearson Feature Selection. Energy Reports, 7, 1047-1054.
[51] Ren, J., Xu, N., and Cui, Y. 2022. Typhoon Track Prediction Based on Deep Learning. Applied Sciences, 12(16), 8028.
[52] Yildirim, M., Çinar, A., and Cengil, E. 2022. Classification of the Weather Images with the Proposed Hybrid Model Using Deep Learning, SVM classifier, and mRMR Feature Selection Methods. Geocarto International, 1-11.
[53] Tao, H., Awadh, S. M., Salih, S. Q., Shafik, S. S., and Yaseen, Z. M. 2022. Integration of Extreme Gradient Boosting Feature Selection Approach with Machine Learning Models: Application of Weather Relative Humidity Prediction. Neural Computing and Applications, 34(1), 515-533.
[54] Pascanu, R., Mikolov, T., and Bengio, Y. 2013. On the Difficulty of Training Recurrent Neural Networks. International Conference on Machine Learning, 1310-1318.
[55] Graves, A. 2012. Long Short-Term Memory. Supervised Sequence Labelling with Recurrent Neural Networks, 37-45.
[56] Greenwood, P. E., and Nikulin, M. S. 1996. A Guide to Chi-Squared Testing. John Wiley & Sons. 280, 160-226.
[57] Spearman, C. 1904. The Proof and Measurement of Association between Two Things. The American Journal of Psychology, 15(1), 72-101.
[58] Pearson, K. 1895. Note on Regression and Inheritance in the Case of Two Parents. Proceedings of the Royal Society of London, 58, 240-242.
[59] Mao, K. Z. 2004. Orthogonal Forward Selection and Backward Elimination Algorithms for Feature Subset Selection. IEEE Transactions on Systems, 34(1), 629-634.
[60] Chen, X. W., and Jeong, J. C. 2007. Enhanced Recursive Feature Elimination. Sixth International Conference on Machine Learning and Applications, 429-435.
[61] Cortes, C., and Vapnik, V. 1995. Support-Vector Networks. Machine Learning, 20(3), 273-297.
[62] Smola, A. J., and Schölkopf, B. 2004. A Tutorial on Support Vector Regression. Statistics and Computing, 14(3), 199-222.
[63] Hoerl, A. E., and Kennard, R. W. 1970. Ridge Regression: Biased Estimation for Nonorthogonal Problems. Technometrics, 12(1), 55-67.
[64] Breiman, L. 2001. Random Forests. Machine Learning, 45(1), 5-32.
[65] Lewis, C. D. 1982. Industrial and Business Forecasting Methods: A Practical Guide to Exponential Smoothing and Curve Fitting, Butterworth Scientific.
[66] Kingma, D. P., and Ba, J. L. 2015. ADAM: A Method for Stochastic Optimization. International Conference on Learning Representations, 13.
[67] Robbins, H., and Monro, S. 1951. A stochastic Approximation Method. The Annals of Mathematical Statistics, 400-407.
[68] The Civil Aeronautics Administration. 2021. Aviation Meteorological Regulations (110-TS-3(8)). 91.
[69] Cohen, J. 2013. Statistical Power Analysis for the Behavioral Sciences. Academic Press.