卷积神经网络方法在岛礁类海啸波水动力特性演变的应用

doi:10.11978/2023111

热带海洋学报 ›› 2024, Vol. 43 ›› Issue (4): 68-75.doi: 10.11978/2023111CSTR: 32234.14.2023111

卷积神经网络方法在岛礁类海啸波水动力特性演变的应用

高榕泽¹(), 屈科¹^,²^,³(), 任兴月⁴, 王旭¹^,²

1.长沙理工大学水利与环境工程学院, 湖南长沙 410114
2.洞庭湖水环境治理与生态修复湖南省重点实验室, 湖南长沙 410114
3.水沙科学与水灾害防治湖南省重点实验室, 湖南长沙 410114
4.海南大学土木建筑工程学院, 海南海口570228

收稿日期:2023-08-05 修回日期:2023-09-04 出版日期:2024-07-10 发布日期:2024-07-22
作者简介:
高榕泽(1997—), 男, 山东平度人, 硕士研究生, 主要从事深度学习方面的研究。email: grz@stu.csust.edu.cn
基金资助:
国家重点研发计划课题(2022YFC3103601); 国家自然科学基金重点项目(51839002); 湖南省自然科学基金项目(2021JJ20043)

Application of convolutional neural network methods in the evolution of hydrodynamic characteristics of tsunamis like-wave over fringing reef

GAO Rongze¹(), QU Ke¹^,²^,³(), REN Xingyue⁴, WANG Xu¹^,²

1. School of Hydraulic Engineering, Changsha University of Science & Technology, Changsha 410114, China
2. Key Laboratory of Dongting Lake Aquatic Eco-Environmental Control and Restoration of Hunan Province, Changsha 410114, China
3. Key Laboratory of Water-Sediment Sciences and Water Disaster Prevention of Hunan Province, Changsha 410114, China
4. College of Civil Engineering and Architecture, Hainan University, Haikou 570228, China

Received:2023-08-05 Revised:2023-09-04 Online:2024-07-10 Published:2024-07-22
Supported by:
National Key Research and Development Program of China(2022YFC3103601); National Natural Science Foundation of China(51839002); Natural Science Foundation of Hunan Province, China(2021JJ20043)

摘要/Abstract

摘要：

海啸是严重的海洋灾害, 准确的海啸预测对于海洋工程和人民生命财产安全具有重要意义。本文以一维卷积神经网络(1-dimensional convolutional neural network, CONV1D)为基础, 构建岛礁地形的类海啸波水动力特性演变模型。通过输入类海啸波波高时程曲线的观测值, 得到岛礁指定地点的水位淹没时程曲线, 实现时间序列到时间序列的预测, 进行海洋灾害的实时预报, 提前布置防御措施以达到减小损失的目的。结果显示, 预测一组样本所需时间少于一秒, 相对于传统的地震海啸预警系统, 深度学习方法所需计算资源较少, 计算速度更快。对类海啸波到达时间预测的平均相对误差为0.71%, 最大水位高度预测的平均相对误差为6.99%, CONV1D得到的岛礁地形类海啸波水动力特性与数值结果吻合较好。

关键词: 深度学习, 卷积神经网络, 海啸预测, 水动力特性, 时间序列

Abstract:

Tsunami is a serious marine disaster, and accurate tsunami prediction is of great significance to marine engineering and the safety of people’s lives and property. In this paper, based on 1-dimensional convolutional neural network (CONV1D), the evolution model of tsunami-like hydrodynamic characteristics of reef topography is constructed. By inputting observed values of wave heights resembling tsunami waves, the water inundation time series curves for specified locations on islands and reefs are generated. This achieves a prediction from one time series to another, serving the purpose of marine disaster prevention. The results indicate that the average relative error in predicting the arrival time of tsunami-like waves is 0.71%, and the average relative error in predicting maximum water levels is 6.99%. The hydrodynamic characteristics of island and reef terrains resembling tsunami waves obtained through CONV1D exhibit a strong alignment with numerical results.

Key words: deep learning, convolutional neural network, tsunami prediction, hydrodynamic characteristics, times series

高榕泽, 屈科, 任兴月, 王旭. 卷积神经网络方法在岛礁类海啸波水动力特性演变的应用[J]. 热带海洋学报, 2024, 43(4): 68-75.

GAO Rongze, QU Ke, REN Xingyue, WANG Xu. Application of convolutional neural network methods in the evolution of hydrodynamic characteristics of tsunamis like-wave over fringing reef[J]. Journal of Tropical Oceanography, 2024, 43(4): 68-75.

图/表 9

图1

图2

图3

表1

图4

图5

图6

表2

6s观测时长下不同波高的最高水位和到达时间"

H/m	$η ob$ /m	$η p$ /m	$E η$ /%	/s	$t p$ /s	$E t$ /%
0.25	0.0550	0.0527	4.12	13.20	13.40	1.515
0.30	0.0616	0.0592	4.02	12.4	12.6	1.612
0.35	0.0706	0.0629	10.91	11.7	11.9	1.709
0.40	0.0878	0.0751	14.46	11.2	11.3	0.892
0.45	0.0843	0.7066	9.13	10.8	10.8	0
0.50	0.0872	0.0836	4.12	10.4	10.4	0
0.55	0.0897	0.0849	5.35	9.9	10.0	1.010
0.60	0.1018	0.0884	12.34	9.5	9.6	0.105
0.65	0.1046	0.1016	2.86	8.9	8.9	0
0.70	0.1049	0.0991	2.64	8.8	8.8	0
0.75	0.1025	0.0964	5.85	8.6	8.6	0

表2

图7

参考文献 22

[1]	包澄澜, 2005. 海啸灾害及其预警系统[J]. 国际地震动态, (1): 14-18.
	BAO CHENGLAN, 2005. Tsunami disaster and its pre-warning system[J]. Recent Developments in World Seismology, (1): 14-18 (in Chinese with English abstract).
[2]	董杰, 田士政, 武文, 等, 2019. 全球海啸预警系统发展及其对我国的启示[J]. 海洋通报, 38(4): 368-378.
	DONG JIE, TIAN SHIZHENG, WU WEN, et al, 2019. The development of global tsunami warning systems and their enlightenments to China[J]. Marine Science Bulletin, 38(4): 368-378 (in Chinese with English abstract).
[3]	李庆功, 周忠菲, 苏浩, 等, 2014. 中国南海安全的战略思考[J]. 科学决策, (11): 1-51.
	LI QINGGONG, ZHOU ZHONGFEI, SU HAO, et al, 2014. Strategic thinking on China's south sea security[J]. Scientific Decision Making, (11): 1-51 (in Chinese with English abstract).
[4]	刘桦, 赵曦, 王本龙, 等, 2015. 海啸数值模拟与南海海啸预警方法[J]. 力学季刊, 36(3): 351-369.
	LIU HUA, ZHAO XI, WANG BENLONG, et al, 2015. Numerical simulation of tsunami and tsunami warning methods for South China Sea region[J]. Chinese Quarterly of Mechanics, 36(3): 351-369 (in Chinese with English abstract).
[5]	刘铁威, 屈科, 黄竞萱, 等, 2021. 孤立波在透水岸礁上水动力特性数值模拟研究[J]. 水动力学研究与进展(A辑), 36(2): 180-191.
	LIU TEIWEI, QU KE, HUANG JINGXUAN, et al, 2021. Numerical investigation of hydrodynamic characteristics of solitary wave over permeable fringing reef[J]. Chinese Journal of Hydrodynamics, 36(2): 180-191 (in Chinese with English abstract).
[6]	陆继翔, 张琪培, 杨志宏, 等, 2019. 基于CNN-LSTM混合神经网络模型的短期负荷预测方法[J]. 电力系统自动化, 43(8): 131-137.
	LU JIXIANG, ZHANG QIPEI, YANG ZHIHONG, et al, 2019. Short-term load forecasting method based on CNN-LSTM hybrid neural network model[J]. Automation of Electric Power Systems, 43(8): 131-137 (in Chinese with English abstract).
[7]	翁少佳, 蔡锦海, 庞运禧, 等, 2024. 卷积神经网络在近岸表层海温预报中的应用[J]. 热带海洋学报, 43(1): 40-47.
	WENG SHAOJIAO, CAI JINHAI, PANG YUNXI, et al, 2024. Application of convolutional neural network to sea surface temperature prediction in the coastal waters[J]. Journal of Tropical Oceanography, 43(1): 40-47 (in Chinese with English abstract).
[8]	徐志国, 史健宇, 李宏伟, 等, 2022. 南中国海区域海啸预警中心地震监测系统[J]. 地震科学进展, 52(10): 473-481.
	XUE ZHIGUO, SHI JIANYU, LI HONGWEI, et al, 2022. The earthquake monitoring system in the South China Sea Tsunami Advisory Center[J]. Progress in earthquake sciences, 52(10): 473-481 (in Chinese with English abstract).
[9]	姚宇, 2019. 珊瑚礁海岸水动力学问题研究综述[J]. 水科学进展, 30(1): 139-152.
	YAO YU, 2019. A review of the coral reef hydrodynamics[J]. Advances in Water Science, 30(1): 139-152 (in Chinese with English abstract).
[10]	GRAVES A, 2012. Long short-term memory[M]// GRAVESA, Supervised sequence labelling with recurrent neural networks. Berlin: Springer: 37-45.
[11]	HAN ZHONGYANG, ZHAO JUN, LEUNG H, et al, 2021. A review of deep learning models for time series prediction[J]. IEEE Sensors Journal, 21(6): 7833-7848.
[12]	KINGMA D P, BA J, 2014. Adam: a method for stochastic optimization[C/OL]. ICLR, 3rd International Conference on Learning Representations [2023-09-05]. San Diego: ICLR. https://doi.org/10.48550/arXiv.1412.6980.
[13]	KIRANYAZ S, INCE T, HAMILA R, et al, 2015. Convolutional neural networks for patient-specific ECG classification[C]// 2015 37th annual international conference of the IEEE engineering in medicine and biology society (EMBC). Milan: IEEE: 2608-2611.
[14]	KRIZHEVSKY A, SUTSKEVER I, HINTON G E, 2012. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 60(6): 84-90.
[15]	MAAS A L, HANNUN A Y, NG A Y, 2013. Rectifier nonlinearities improve neural network acoustic models[C]// Proceedings of the 30th international conference on machine learning. Atlanta: JMLR.
[16]	MAKINOSHIMA F, OISHI Y, YAMAZAKI T, et al, 2021. Early forecasting of tsunami inundation from tsunami and geodetic observation data with convolutional neural networks[J]. Nature Communications, 12(1): 2253. doi: 10.1038/s41467-021-22348-0 pmid: 33859177
[17]	MOCHIZUKI M, UEHIRA K, KANAZAWA T, et al, 2018. S-net project: performance of a large-scale seafloor observation network for preventing and reducing seismic and tsunami disasters[C]// IEEE, 2018 OCEANS-MTS/IEEE Kobe Techno-Oceans (OTO). Kobe: IEEE, 1-4.
[18]	OISHI Y, IMAMURA F, SUGAWARA D, 2015. Near‐field tsunami inundation forecast using the parallel TUNAMI‐N2 model: Application to the 2011 Tohoku‐Oki earthquake combined with source inversions[J]. Geophysical Research Letters, 42(4): 1083-1091.
[19]	QU KE, REN XINGYUE, KRAATZ S, 2017a. Numerical investigation of tsunami-like wave hydrodynamic characteristics and its comparison with solitary wave[J]. Applied Ocean Research, 63: 36-48.
[20]	QU KE, REN XINGYUE, KRAATZ S, et al, 2017b. Numerical analysis of tsunami-like wave impact on horizontal cylinders[J]. Ocean Engineering, 145: 316-333.
[21]	ROEBER V, CHEUNG K F, 2012. Boussinesq-type model for energetic breaking waves in fringing reef environments[J]. Coastal Engineering, 70: 1-20.
[22]	SRIVASTAVA N, HINTON G, KRIZHEVSKY A, et al, 2014. Dropout: a simple way to prevent neural networks from overfitting[J]. The Journal of Machine Learning Research, 15(1): 1929-1958.

观测时长/s	参数量	预测所用时间/s
5	161110	0.0164
6	186710	0.0175
7	212310	0.0182
8	237910	0.0201
9	263510	0.0175

卷积神经网络方法在岛礁类海啸波水动力特性演变的应用

Application of convolutional neural network methods in the evolution of hydrodynamic characteristics of tsunamis like-wave over fringing reef

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 22

相关文章 7

Metrics

本文评价

推荐阅读 0

[1]	王旭, 屈科, 王梓峻, 杨元平, 王超, 张良斌. 风对波状涌潮海塘越浪水动力特性影响的数值研究[J]. 热带海洋学报, 2024, 43(5): 116-130.
[2]	赵杰, 林延奖, 刘燃, 杜榕. 基于PredRNN++模型对南海中尺度涡旋的预测研究[J]. 热带海洋学报, 2024, 43(1): 16-27.
[3]	翁少佳, 蔡锦海, 庞运禧, 罗荣真. 卷积神经网络在近岸表层海温预报中的应用[J]. 热带海洋学报, 2024, 43(1): 40-47.
[4]	张良斌, 屈科, 黄竞萱, 王旭, 虢磊. 风对聚焦波海堤越浪特性影响的数值模拟研究[J]. 热带海洋学报, 2023, 42(6): 63-73.
[5]	李俊杰, 屈科, 王旭. 采掘坑对孤立波岸礁水动力特性影响的三维数值模拟研究[J]. 热带海洋学报, 2023, 42(6): 42-51.
[6]	刘爽, 经志友, 詹海刚. 基于生成对抗网络模型的热带和亚热带海洋中尺度涡预报研究[J]. 热带海洋学报, 2022, 41(5): 1-16.
[7]	王仁政, 单正垛, 孟思雨, 宫响. 南海北部次表层叶绿素最大值年际变化特征分析^*[J]. 热带海洋学报, 2021, 40(6): 63-75.