|
摘要：
|
| 澳门地区由于地理位置特殊、气候湿润以及高度城市化的特点，在台风风暴潮期间频繁遭受由降水、河道洪水、倒灌海水等多因素叠加引发的复合型洪涝事件。为了精准分析这类灾害下的城市淹没水位的变化规律，提出一种基于变分模态分解（VMD）、卷积神经网络（CNN）、双向门控循环单元（BiGRU）和注意力机制的城市淹没水位预测模型。首先，采用 VMD对历史城市淹没水位数据进行分解，得到一系列相对平稳的子序列；然后，将CNN用于对多环境因素数据进行特征提取；特征提取完成后，使用BiGRU网络进行双向循环训练；最后，通过注意力机制为BiGRU输出分配相应权重，并加权求和得到最终的城市淹没水位预测结果。实验结果表明，该模型在城市淹没水位变化预测中表现优异。 |
| Due to its geographical location, humid climate and high degree of urbanization, the Macao region frequently suffers from compound flooding events caused by the superposition of multiple factors such as precipitation, river floods and backflow of seawater during typhoon storm surges. To accurately analyze the changes in urban inundation water levels under such disasters, a prediction model for urban inundation water levels based on Variational Mode Decomposition (VMD), Convolutional Neural Networks (CNN), Bidirectional Gated Recurrent Unit (BiGRU) and attention mechanism is proposed. Firstly, the VMD is used to decompose historical urban inundation water level data to obtain a series of relatively stable sub-sequences. Then, the CNN is used to extract features from multi-environmental factor data. After feature extraction, the BiGRU network is used for bidirectional recurrent training. Finally, the attention mechanism assigns corresponding weights to the BiGRU and performs weighted summation to obtain the final prediction result of urban inundation water levels. Experimental results show that this model performs well in predicting changes in urban inundation water levels. |
|
参考文献：
|
[1] 张云霞, 闪淳昌, 秦绪坤. 澳门“天鸽”台风灾害现场调查评估的实践与思考[J]. 中国减灾, 2021(19): 40-45. ZHANG Y X, SHAN C C, QIN X K. Practice and reflections on on-site investigation and assessment of typhoon Hato disaster in Macao[J]. Disaster Reduction in China, 2021(19): 40-45.
[2] 罗志发, 黄本胜, 邱静, 等. 粤港澳大湾区风暴潮时空分布特征及影响因素[J]. 水资源保护, 2022, 38(3): 72-79. LUO Z F, HUANG B S, QIU J, et al. Spatio-temporal distribution characteristics and influencing mechanisms of storm surge in Guangdong, Hong Kong and Macao Greater Bay Area[J]. Water Resources Protection, 2022, 38(3): 72-79.
[3] 蒋昌波, 赵兵兵, 邓斌, 等. 北部湾台风风暴潮数值模拟及重点区域风险分析[J]. 海洋预报, 2017, 34(3): 32-40. JIANG C B, ZHAO B B, DENG B, et al. Numerical simulation of typhoon storm surge in the Beibu Gulf and hazardous analysis at key areas[J]. Marine Forecasts, 2017, 34(3): 32-40.
[4] 傅赐福, 于福江, 董剑希, 等. 基于数值模拟的2024年10月渤海和黄海沿岸海水倒灌事件成因分析[J]. 海洋预报, 2025, 42(1): 1-10. FU C F, YU F J, DONG J X, et al. Causal analysis of the October 2024 seawater backflow event along the coasts of the Bohai Sea and the Yellow Sea based on numerical simulation[J]. Marine Forecasts, 2025, 42(1): 1-10.
[5] 付慧卿, 吴伦宇, 季轩梁, 等. 基于SCHISM的中国近海潮汐二维数值模拟[J]. 海洋预报, 2024, 41(5): 1-14. FU H Q, WU L Y, JI X L, et al. Two-dimensional numerical simulation of tides in the coastal waters of China based on SCHISM[J]. Marine Forecasts, 2024, 41(5): 1-14.
[6] 马荣华, 陈海韵, 罗阳, 等. 广州海域精细化海洋灾害数值预警报系统的构建与应用[J]. 海洋预报, 2025, 42(3): 103-113. MA R H, CHEN H Y, LUO Y, et al. Construction and application of fine-resolution marine disaster numerical forecasting system in the Guangzhou coastal area[J]. Marine Forecasts, 2025, 42(3): 103-113.
[7] 刘媛媛, 张丽, 李磊, 等. 基于多变量LSTM神经网络模型的风暴潮临近预报[J]. 海洋通报, 2020, 39(6): 689-694. LIU Y Y, ZHANG L, LI L, et al. Storm surge nowcasting based on multivariable LSTM neural network model[J]. Marine Science Bulletin, 2020, 39(6): 689-694.
[8] 苗庆生, 徐珊珊, 杨锦坤, 等. 长短期记忆神经网络在厦门风暴潮预报中的应用[J]. 中国海洋大学学报, 2022, 52(9): 10-19. MIAO Q S, XU S S, YANG J K, et al. Application of long shortterm memory neural network in Xiamen storm surge forecast[J]. Periodical of Ocean University of China, 2022, 52(9): 10-19.
[9] 徐楚天, 沈良朵, 班文超, 等. 基于CEEMDAN-LSTM风暴潮潮位预测分析研究[J]. 太阳能学报, 2024, 45(11): 578-585. XU C T, SHEN L D, BAN W C, et al. Research on prediction and analysis of storm surge level based on CEEMDAN-LSTM[J]. Acta Energiae Solaris Sinica, 2024, 45(11): 578-585.
[10] 谢文鸿, 徐广珺, 董昌明. 基于ConvLSTM机器学习的风暴潮漫滩预报研究[J]. 大气科学学报, 2022, 45(5): 674-687. XIE W H, XU G J, DONG C M. Research on storm surge floodplain prediction based on ConvLSTM machine learning[J]. Transactions of Atmospheric Sciences, 2022, 45(5): 674-687.
[11] 王甜甜, 鲁云蒙, 刘铁忠. 基于VMD-CNN-LSTM模型和迁移学习框架的风暴潮预测研究[J]. 灾害学, 2023, 38(4): 195-202. WANG T T, LU Y M, LIU T Z. Storm surge prediction based on VMD-CNN-LSTM model and transfer learning framework[J]. Journal of Catastrophology, 2023, 38(4): 195-202.
[12] 苑希民, 黄玉啟, 田福昌, 等. 基于LSTM-GM神经网络模型的风暴潮增水预报方法[J]. 水资源保护, 2023, 39(6): 8-15. YUAN X M, HUANG Y Q, TIAN F C, et al. Research on forecasting method of storm surge based on LSTM-GM neural network model[J]. Water Resources Protection, 2023, 39(6): 8-15.
[13] HUANG Y P, YAN L, CHENG Y, et al. Coal thickness prediction method based on VMD and LSTM[J]. Electronics, 2022, 11(2): 232.
[14] LEI Z F, SU W B. Mold level predict of continuous casting using hybrid EMD-SVR-GA algorithm[J]. Processes, 2019, 7(3): 177.
[15] 邹智, 吴铁洲, 张晓星, 等. 基于贝叶斯优化CNN-BiGRU混合神经网络的短期负荷预测[J]. 高电压技术, 2022, 48(10): 3935-3945. ZOU Z, WU T Z, ZHANG X X, et al. Short-term load forecast based on Bayesian optimized CNN-BiGRU hybrid neural networks[J]. High Voltage Engineering, 2022, 48(10): 3935-3945.
[16] LIU B, GAN H B, CHEN D, et al. Research on fault early warning of marine diesel engine based on CNN-BiGRU[J]. Journal of Marine Science and Engineering, 2022, 11(1): 56.
[17] JIN Y, WANG X, ZHANG D P, et al. Remaining useful life prediction method of offshore equipment bearings based on convolutional neural network-bidirectional gated recurrent unitsqueeze and excitation[J]. Journal of Nanoelectronics and Optoelectronics, 2022, 17(10): 1343-1353.
[18] NIU D X, YU M, SUN L J, et al. Short-term multi-energy load forecasting for integrated energy systems based on CNN-BiGRU optimized by attention mechanism[J]. Applied Energy, 2022, 313: 118801.
[19] 邵必林, 纪丹阳. 基于VMD-SE的电力负荷分量的多特征短期预测[J]. 中国电力, 2024, 57(4): 162-170. SHAO B L, JI D Y. Multi-feature short-term prediction of power load components based on VMD-SE[J]. Electric Power, 2024, 57(4): 162-170.
[20] HU R W, XIANG S J. CNN prediction based reversible data hiding[J]. IEEE Signal Processing Letters, 2021, 28: 464-468.
[21] 龚飘怡, 罗云峰, 方哲梅, 等. 基于Attention-BiLSTM-LSTM神经网络的短期电力负荷预测方法[J]. 计算机应用, 2021, 41(S1): 81-86. GONG P Y, LUO Y F, FANG Z M, et al. Short-term power load forecasting method based on Attention-BiLSTM-LSTM neural network[J]. Journal of Computer Applications, 2021, 41(S1): 81-86.
[22] TUTZ G, RAMZAN S. Improved methods for the imputation of missing data by nearest neighbor methods[J]. Computational Statistics & Data Analysis, 2015, 90: 84-99. |
|
服务与反馈：
|
|
【文章下载】【发表评论】【查看评论】【加入收藏】
|
|
|
