蜜臀AV在线观看,五十六十老熟女HD60,欧美又粗又大AAA片

基于CNN-LSTM的珠江河口臺(tái)風(fēng)過(guò)程實(shí)時(shí)滾動(dòng)修正預(yù)報(bào)

單位：1. 中山大學(xué) 土木工程學(xué)院, 廣東珠海 519085;
2. 中山大學(xué)水資源與環(huán)境研究中心, 廣東廣州 510275;
3. 廣州市水務(wù)科學(xué)研究所, 廣東廣州 510220

關(guān)鍵詞：實(shí)時(shí)滾動(dòng)預(yù)報(bào) 臺(tái)風(fēng) 珠江河口深度學(xué)習(xí) 誤差校正

分類號(hào)：P457.8

出版年·卷·期（頁(yè)碼）：2024·41·第一期（94-103）

摘要：

為改善臺(tái)風(fēng)預(yù)報(bào)精度，基于實(shí)時(shí)滾動(dòng)修正預(yù)報(bào)思路，利用卷積神經(jīng)網(wǎng)絡(luò)嵌套長(zhǎng)短期記憶神經(jīng)網(wǎng)絡(luò)（CNN-LSTM）和誤差校正（EC）技術(shù)，搭建了珠江河口臺(tái)風(fēng)實(shí)時(shí)預(yù)報(bào)模型。研究結(jié)果表明：“滾動(dòng)預(yù)報(bào)”比單次預(yù)報(bào)有更好的路徑和強(qiáng)度預(yù)報(bào)效果，隨著模型滾動(dòng)時(shí)間的延長(zhǎng)，預(yù)報(bào)整體精度有逐漸改善的趨勢(shì)。路徑預(yù)報(bào)結(jié)果的均方根誤差比單次預(yù)報(bào)減小了25.67%，強(qiáng)度預(yù)報(bào)結(jié)果的平均絕對(duì)誤差比單次預(yù)報(bào)減小了65.04%；考慮誤差校正的CNN-LSTM-EC的路徑、強(qiáng)度“滾動(dòng)預(yù)報(bào)”效果均優(yōu)于CNN-LSTM，前者的路徑預(yù)報(bào)誤差較后者減小了22.57%，強(qiáng)度預(yù)報(bào)誤差減小2.5%。

In order to improve the accuracy of typhoon forecasting, this paper introduces a real-time rolling corrected typhoon forecasting model in the Pearl River Estuary utilizing Convolutional Neural Network Long Short-Term Memory (CNN-LSTM) neural network and Error Correction (EC) method. The results show that the rolling forecasts have better performances on typhoon's track and intensity than the single-time forecasts. The overall accuracy of the rolling forecasts increases gradually along with the prolong of the rolling time of the model. In comparison with the single-time forecasts, the root mean squared error of typhoon's track rolling forecasts decreases by 25.67% and the mean absolute error of typhoon's intensity rolling forecasts decreases by 65.04%. The real-time rolling corrected forecasts of typhoon's track and intensity based on CNN-LSTM-EC are better than those based on CNN-LSTM. Compared with the latter, the forecasting error of the former decreases by 22.57% on the typhoon's track and by 2.5% on the typhoon's intensity.

參考文獻(xiàn)：

[1] EMANUEL K. Increasing destructiveness of tropical cyclones over the past 30 years[J]. Nature, 2005, 436(7051): 686-688.
[2] HOYOS C D, AGUDELO P A, WEBSTER P J, et al. Deconvolution of the factors contributing to the increase in global hurricane intensity[J]. Science, 2006, 312(5770): 94-97.
[3] WEBSTER P J, HOLLAND G J, CURRY J A, et al. Changes in tropical cyclone number, duration, and intensity in a warming environment[J]. Science, 2005, 309(5742): 1844-1846.
[4] 王潔, 楊奕杰, 王杰, 等. 基于近20a歷史數(shù)據(jù)的中國(guó)沿海城市臺(tái)風(fēng)災(zāi)害風(fēng)險(xiǎn)評(píng)估[J]. 海洋預(yù)報(bào), 2021, 38(5): 24-30. WANG J, YANG Y J, WANG J, et al. Typhoon disaster risk assessment of coastal cities in China based on historical data over the past 20 years[J]. Marine Forecasts, 2021, 38(5): 24-30.
[5] 陳煜, 楊劍, 段忠東, 等. 粵港澳大灣區(qū)臺(tái)風(fēng)危險(xiǎn)性分析[J]. 自然災(zāi)害學(xué)報(bào), 2022, 31(2): 26-38. CHEN Y, YANG J, DUAN Z D, et al. Typhoon hazard analysis of the Guangdong-Hong Kong-Macao Greater Bay Area[J]. Journal of Natural Disasters, 2022, 31(2): 26-38.
[6] CHEN R, ZHANG W M, WANG X. Machine learning in tropical cyclone forecast modeling: a review[J]. Atmosphere, 2020, 11(7): 676.
[7] 曹祥村, 邵利民. 一種利用BP網(wǎng)絡(luò)預(yù)報(bào)臺(tái)風(fēng)路徑的新方法[J]. 海洋預(yù)報(bào), 2007, 24(3): 75-82. CAO X C, SHAO L M. A new method of forecasting typhoon paths using BP Network[J]. Marine Forecasts, 2007, 24(3): 75-82.
[8] ALI M M, KISHTAWAL C M, JAIN S. Predicting cyclone tracks in the north Indian Ocean: an artificial neural network approach[J]. Geophysical Research Letters, 2007, 34(4): L04603.
[9] ALEMANY S, BELTRAN J, PEREZ A, et al. Predicting hurricane trajectories using a recurrent neural network[C]//Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence and Thirty-First Innovative Applications of Artificial Intelligence Conference and Ninth AAAI Symposium on Educational Advances in Artificial Intelligence. Honolulu: AAAI, 2019: 58.
[10] KORDMAHALLEH M M, SEFIDMAZGI M G, HOMA-IFAR A. A sparse recurrent neural network for trajectory prediction of Atlantic hurricanes[C]//Proceedings of Genetic and Evolutionary Computation Conference 2016. Denver: ACM, 2016: 957-964.
[11] PAN B, XU X, SHI Z W. Tropical cyclone intensity prediction based on recurrent neural networks[J]. Electronics Letters, 2019, 55(7): 413-415.
[12] GUO R, QI L B, GE Q Q, et al. A study on the ensemble forecast real-time correction method[J]. Journal of Tropical Meteorology, 2018, 24(1): 42-48.
[13] LIN I I, CHEN C H, PUN I F, et al. Warm ocean anomaly, air sea fluxes, and the rapid intensification of tropical cyclone Nargis (2008)[J]. Geophysical Research Letters, 2009, 36(3): L03817.
[14] SANDERY P A, BRASSINGTON G B, CRAIG A, et al. Impacts of ocean-atmosphere coupling on tropical cyclone intensity change and ocean prediction in the Australian region[J]. Monthly Weather Review, 2010, 138(6): 2074-2091.
[15] LIU Y, WANG H, LEI X H, et al. Real-time forecasting of river water level in urban based on radar rainfall: A case study in Fuzhou City[J]. Journal of Hydrology, 2021, 603: 126820.
[16] LIU Y, WANG H, FENG W W, et al. Short term real-time rolling forecast of urban river water levels based on LSTM: a case study in Fuzhou city, China[J]. International Journal of Environmental Research and Public Health, 2021, 18(17): 9287.
[17] YANG R Y, MU J L, WANG S D, et al. Hourly rolling correction of precipitation forecast via convolutional and long short-term memory networks[J]. Atmospheric Science Letters, 2022, 23(10):e1100.
[18] ALASALI F, TAWALBEH R, GHANEM Z, et al. A sustainable early warning system using rolling forecasts based on ANN and golden ratio optimization methods to accurately predict real-time water levels and flash flood[J]. Sensors, 2021, 21(13): 4598.
[19] 劉天紹, 劉孫俊, 楊璽, 等. 1951—2015影響廣東沿海臺(tái)風(fēng)的統(tǒng)計(jì)分析[J]. 海洋預(yù)報(bào), 2018, 35(4): 68-74. LIU T S, LIU S J, YANG X, et al. Statistical analysis of the typhoon influencing Guangdong province during 1951-2015[J]. Marine Forecasts, 2018, 35(4): 68-74.
[20] 葉榮輝, 戈軍, 張文明, 等. 影響粵港澳大灣區(qū)的熱帶氣旋統(tǒng)計(jì)分析[J]. 水利水電技術(shù), 2020, 51(S1): 37-43. YE R H, GE J, ZHANG W M, et al. Statistical analysis on impact from tropical cyclone on Guangdong-HongKong-Macao Greater Bay Area[J]. Water Resources and Hydropower Engineering, 2020, 51(S1): 37-43.
[21] LECUN Y, BOSER B, DENKER J S, et al. Backpropagation applied to handwritten zip code recognition[J]. Neural Computation, 1989, 1(4): 541-551.
[22] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[23] HOCHREITER S, SCHMIDHUBER J. Long short-term memory [J]. Neural Computation, 1997, 9(8): 1735-1780.
[24] 周夢(mèng), 陳華, 郭富強(qiáng), 等. 洪水預(yù)報(bào)實(shí)時(shí)校正技術(shù)比較及應(yīng)用研究[J]. 中國(guó)農(nóng)村水利水電, 2018(7): 90-95. ZHOU M, CHEN H, GUO F Q, et al. The application of real-time correction techniques for flood forecasting[J]. China Rural Water and Hydropower, 2018(7): 90-95.

服務(wù)與反饋：

【文章下載】【發(fā)表評(píng)論】【查看評(píng)論】【加入收藏】