Application of artificial neural networks in tide-forecasting

An accurate tidal forecast is an important task in determining constructions and human activities in ocean environments. Conventional tidal forecasting has been based on harmonic analysis using the least squares method to determine harmonic parameters. However, a large number of parameters are required for the prediction of a long-term tidal level with harmonic analysis. Unlike conventional harmonic analysis, this paper presents an artificial neural network (ANN) model for forecasting the tidal-level using the short term measuring data. The ANN model can easily decide the unknown parameters by learning the input–output interrelation of the short-term tidal records. Three field data with three types of tides will be used to test the performance of the proposed ANN model. The numerical results indicate that the hourly tidal levels over a long duration can be predicted using a short-term hourly tidal record.     

Study of tide prediction method influenced by nonperiodic factors based on support vector machines

Harmonic analysis, the traditional tidal forecasting method, cannot take into account the impact of noncyclical factors, and is also based on the BP neural network tidal prediction model which is easily limited by the amount of data. According to the movement of celestial bodies, and considering the insufficient tidal characteristics of historical data which are impacted by the nonperiodic weather, a tidal prediction method is designed based on support vector machine (SVM) to carry out the simulation experiment by using tidal data from Xiamen Tide Gauge, Luchaogang Tide Gauge and Weifang Tide Gauge individually. And the results show that the model satisfactorily carries out the tide prediction which is influenced by noncyclical factors. At the same time, it also proves that the proposed prediction method, which when compared with harmonic analysis method and the BP neural network method, has faster modeling speed, higher prediction precision and stronger generalization ability.     

基于非稳态调和分析和长短时记忆神经网络的河口潮位短期预报混合模型

河口潮汐过程受上游径流、外海潮波等因素影响,动力机制复杂,潮位预报难度大。本文提出了一种基于非稳态调和分析（NS＿TIDE）和长短时记忆（LSTM）神经网络的混合模型,对河口潮位进行12～48 h短期预报。该模型首先对河口实测潮汐数据进行非稳态调和分析,通过与实测资料对比得到分析误差的时序序列,并以此作为LSTM神经网络的输入数据,通过网络学习并预测未来12～48 h潮位预报误差,据此对NS＿TIDE的预测结果进行实时校正。利用该模型对2020年长江口潮位过程进行了预报检验,结果表明混合模型12 h、24 h、36 h和48 h短期水位预报的均方根误差（RMSE）相比NS＿TIDE模型至多分别降低了0.16 m、0.15 m、0.14 m和0.12 m;针对2020年南京站最高水位预测,NS＿TIDE模型预报误差为0.64 m,而混合模型预报误差仅为0.10 m。     

基于调和分析法与ANFIS系统的综合潮汐预报模型

港口沿岸地区以及河流入海口等地区的精确潮汐预报对于各种海洋工程作业有着非常重要的意义。潮汐水位的变化受到众多复杂因素的影响,而且这些复杂的因素往往有着较强的实变性和非线性。为了进一步提高沿岸港口码头等水域的潮汐水位的预测精度,本文提出了一种基于调和分析模型与自适应神经模糊推理系统相结合的模块化潮汐水位预测模型;并采用相关分析确定整个预测模型的输入维数;模块化将潮汐分解为两部分：由天体引潮力形成的天文潮部分和由各种天气以及环境因素引起非天文潮部分。其中调和分析法用于天文潮部分的预测,ANFIS用于预测具有较强非线性的非文潮部分。模块化综合了两种方法的优势,即调和分析法能够实现长期、稳定的天文潮预报,ANFIS能够以较高的精度实现潮汐非线性拟合与预测。模型使用ANFIS模型和调和分析模型分别对潮汐的非天文潮和天文潮部分进行仿真预测,然后将两部分的预测结果综合形成最终的潮汐预测值。此外,本文选用三种不同的模糊规则生成方法（grid partition （GP）,fuzzy c-means （FCM） and sub-clustering （SC））生成完整的ANFIS系统,并使用实测数据进行验证用以选取最优的ANFIS预测模型。最后将最优的ANFIS模型与调和分析模型相结合进行潮汐水位的最终预报。仿真实验选用Fort Pulaski潮汐观测站的实测潮汐值数据进行预报的仿真实验,仿真结果验证了该模型的可行性与有效性并取得了良好的效果,具有较高的预报精度。     

Development of wavelet network model for accurate water levels prediction with meteorological effects

Accurate water levels modeling and prediction is essential for safety of coastal navigation and other maritime applications. Water levels modeling and prediction is traditionally developed using the least-squares-based harmonic analysis method that estimates the harmonic constituents from the measured water levels. If long water level measurements are not obtained from the tide gauge, accurate water levels prediction cannot be estimated. To overcome the above limitations, the current state-of-the-art artificial neural network has recently been developed for water levels prediction from short water level measurements. However, a highly nonlinear and efficient wavelet network model is proposed and developed in this paper for water levels modeling and prediction using short water level measurements. Water level measurements (about one month and a week) from six different tide gauges are employed to develop the proposed model and investigate the atmospheric changes effect. It is shown that the majority of error values, the differences between water level measurements and the modeled and predicted values, fall within the −5 cm and +5 cm range and root-mean-squared (RMS) errors fall within 1–6 cm range. A comparison between the developed highly nonlinear wavelet network model and the harmonic analysis method and the artificial neural networks shows that the RMS of the developed wavelet network model when compared with the RMS of the harmonic analysis method is reduced by about 70% and when compared with the RMS of the artificial neural networks is reduced by about 22%. It is also worth noting that if the atmospheric changes effect (meteorological effect) of the air pressure, the air temperature, the relative humidity, wind speed and wind direction are considered, the performance accuracy of the developed wavelet network model is improved by about 20% (based on the estimated RMS values).     

潮汐调和分析与应用研究

基于长江口外鸡骨礁、绿华山潮位站多年实测潮汐资料,开展潮汐调和分析与应用研究。采用最小二乘法计算调和常数,研究不同分潮组合及不同资料长度对调和分析结果的影响。采用规范法及直接预报法计算深度基准面,并分析计算结果。采用余水位订正方法推算潮位,并进行精度验证。结果表明:调和分析精度随分潮个数的增加而提高;采用年实测潮汐资料调和分析的精度总体高于采用多年实测潮汐资料调和分析的精度;采用预报年份相邻的年实测潮汐资料进行潮汐预报精度较高;理论最低潮面计算值,规范法较直接预报法偏小。基于绿华山站与鸡骨礁站实测资料进行余水位推算验证,精度基本满足实用要求。     

Tidal Correction of Altimetric Data in the Japan Sea

Satellite altimetric data have been very useful in the study of variation in the eddy field of the ocean. In order to investigate the variation in the eddy field, we have to remove tidal signals from altimetric data. However, global tidal models do not have sufficient accuracy in marginal seas such as the Japan Sea. In this study, we carried out harmonic analysis of temporal fluctuations of sea surface height data in the Japan Sea measured by TOPEX/POSEIDON. We could eliminate the tidal signals from altimetric data of TOPEX/POSEIDON and also from ERS-2 altimetric data with use of the harmonic constants derived from TOPEX/POSEIDON and tide gauge data along the coast. We draw co-tidal and co-range charts in the Japan Sea using the result of the harmonic analysis of TOPEX/POSEIDON altimetric data and tide gauge data along the coast. The results obtained turn out to be very useful for the tidal correction of altimetric data from satellite in the Japan Sea.     

东海北部1个潜标连续观测站的潮流垂向特征分析

采用调和分析方法对东海北部海区1个坐底式潜标连续观测的近两个半月的海流数据进行分析,研究了该站点的潮流空间结构特征以及余流信息。调和分析结果表明,该点以半日潮流为主,潮流类型在40 m以上属不规则半日潮流,40 m以下则属规则半日潮流;该海区的潮流以顺时针旋转为主,潮流量值占海流的比率随深度递增,潮流椭圆要素存在明显的垂向变化。本文研究有助于了解该站点潮流的垂直变化特点,并为潮流数值模拟提供校验依据。     

中国沿海GPS站用于潮波系数提取分析

首先给出了基于GNSS-MR技术提取潮波系数的原理与方法,然后利用布设在浙江省石浦港验潮室屋顶的GPS站DSPU实测数据对潮波系数进行了提取,并与验潮站实测潮位调和分析结果进行了对比分析。实验结果表明GPS-MR反演潮位与验潮站实测潮位值吻合较好,相关系数优于0.97;GPS-MR反演潮位与验潮站实测潮位获取的潮波系数基本一致,除M2、S2外其它差异较小。两者获取的潮波系数差异主要因为DSPU测站观测环境极大地影响了GPS-MR提取潮位精度。沿海GNSS站用于潮位监测和潮波系数提取,将进一步拓展沿海GNSS监测站的应用领域,在一定程度上可弥补验潮站的不足。     

基于潮汐表数据同化的天文潮数值预报模型及其模拟预报效果

潮汐表是利用长期潮汐观测结果经调和分析实现的主要港湾潮汐预报结果,具有较高的预报精度,而通常的天文潮数值预报目前还难以达到潮汐表的预报精度.本研究在建立常规天文潮数值预报模型的基础上,建立了基于潮汐表数据同化的天文潮数值预报模型,并分别采用这2种模型预报福建沿岸海域的天文潮.其结果表明同化模型的预报结果无论是在潮时还是在潮高均明显优于常规模型;同化模型能显著地改善所研究的沿岸海域90个水位点中至少45个水位点的潮汐预报结果,而其他水位点的预报结果也有不同程度地改善.     

Evaluation of tidal error in altimetry data in the Asian marginal seas

The magnitude and geographical distribution of the error in the Archiving, Validation and Interpretation of Satellite Oceanographic data (AVISO) altimetry data associated with tidal correction around Asian marginal seas has been revealed. The errors were evaluated by harmonic analysis of the AVISO corrected sea surface heights data (CorSSH). Errors of more than 15 cm of tidal correction were recognized in the western and northern parts of the Yellow Sea, Celebes Sea, Kuril Islands, and the northwestern part of the Okhotsk Sea. It was found that the CorSSH and sea level anomaly (SLA) data downloaded from the AVISO are not available for direct use in those marginal seas. To reduce the tidal correction error, the harmonic constants calculated from the latest tide model and regional tide model were applied as the tidal correction of the Altimetry data. The tidal errors in the Yellow Sea and the northwestern part of the Okhotsk Sea were reduced by approximately 20 cm and 10 cm, respectively. Root mean square differences between the harmonic constants derived from tide models and those derived from altimetry data were calculated. The root mean square differences were large in the Yellow and the Okhotsk Seas. Root sum squares for four principal tidal constituents in the Yellow and East China Seas and Okhotsk Sea were 7.72 cm and 8.36 cm, respectively.     

舟山本岛南部附近海域潮汐潮流特征分析

文章基于沈家门长期潮位站、长峙岛临时潮位站的观测资料和对舟山本岛南部海域多个站位实测的潮流基础数据,采用调和分析法对潮汐潮流进行特征分析。舟山本岛南部附近海域潮汐类型属于规则半日潮,潮差变化和日不等现象明显,有一定的潮汐浅海作用。潮流类型属于以往复流为主的规则半日浅海潮流,实测潮流中涨落潮流速不等、历时不等现象显著,最大流速、平均流速均是大潮大于小潮,涨潮流历时长于落潮流历时,潮流变化主要受协振波所控制,流向在涨落潮方向波动。     

基于余水位订正的海洋潮位推算关键技术研究

从分潮数目选择、调和常数稳定性优化两个关键环节入手,选择11个主要分潮用于潮位推算,并利用邻近长期站对中短期验潮站调和常数做差比订正,显著提高了中短期验潮站的潮位推算精度。     

渤黄海潮汐潮流精细化数值模拟及可视化预报系统

利用有限元海洋模式ADCIRC (Advanced Circulation Model),建立了高分辨率的渤黄海二维潮汐潮流数值模型,该模型以M2,S2,K1,O1等8个分潮的水位作为驱动,模拟出了该8个分潮的潮汐潮流调和常数;利用该调和常数预报的潮位和二维平均潮流与实测资料相比,符合较好;利用模拟得到的潮汐潮流调和常...     

南海北部沿岸海域潮汐的调和分析

采用t_tide潮汐分析工具对南海北部的5个验潮站2009年全年的逐时潮高资料进行调和分析,计算出各站的调和常数,评估调和常数的准确性、稳定性,并总结了广东沿岸海域潮汐特征.利用对2009年逐时潮高的调和分析结果对2010年全年的潮高进行预测,将各站预测结果与同时间的实测数据进行全年和分季节进行比较,对预测结果与实测数据的残差进行统计分析.通过对残差的散点分布、概率分布、置信区间等统计结果进行分析,检验预测结果的准确性、稳定性和可靠性.结果表明：广东沿岸海域潮汐是以M2分潮为主,K1、O1、S2为次结合的潮汐机制,采用t_tide潮汐分析工具对南海北部潮高的预测结果与实测数据拟合较好,相位预测准确,潮高预测除在时间序列尾部（年尾）有些许较大的误差外,t_tide工具在南海北部潮汐预报中具有较高的准确性和稳定性.预测残差的整体服从正态分布,残差均值小于10-2m量级,方差最大为0.229 4,最小为0.173 2,95%置信区间长度小于10-2.各站季节分析主要分潮的离散度小于0.04的结果充分证明不同季节的分析区别不明显,3个月资料与整年资料的调和分析结果几乎一致,与所选取的季节资料几乎无关.虽然在预测值中,有极个别的残差将近1 m,但并不足以影响到预测的准确性.     

数据融合下的短期潮位预报测试及分析

针对短期验潮数据分析难度大、预报精度低的问题,设计了一种基于数据融合技术的短期潮位预报方法,利用扩展卡尔曼滤波(EKF),将通用的潮汐模型计算水位融合到调和预报模型之中,生成精度更高的融合预报值.数据测试表明,对于3天的验潮数据,EKF方法至少对向后5天的预报有效,融合值较两种源数据的平均优化度分别为33％和60％;对...     

台风对钱塘江涌潮影响研究

钱塘江年最大涌潮几乎都发生在台风期间。基于实测潮汐资料,结合天文潮调和分析,研究台风对钱塘江河口涌潮起潮点下游河段潮汐的影响,探讨因潮汐变化间接引起的钱塘江涌潮变化。结果表明:台风引起低潮位、潮差、潮到时间、涨潮历时等变化,间接影响涌潮,造成涌潮高度、陡度、传播速度、到达时间和涌潮流速等变化。总体而言,台风期间盐官涌潮高度平均增大0.18 m,到达时间平均提早37 min;澉浦至盐官段涌潮传播速度平均增大8.9%,陡度变陡,流速有增有减,但单宽流量增大。     

基于高频地波雷达观测的粤西近海潮流潮能分析

利用粤西海域高频地波雷达观测得到的表层海流资料进行潮流调和分析。结果表明: 粤西近海主要属于不正规半日分潮, 浅水分潮较强。以M₂分潮为例, 潮流运动形式主要为逆时针的往复流为主, 方向沿西北—东南方向。粤西近海的潮能主要由东部陆架输送进来, 潮能自东向西传播, 在大潮期间, 粤西的潮能出现向岸方向分量, 表现为从东南向西北方向传播, 在近岸区域潮能通量传播的方向会发生一个向岸的偏转。通过潮能收支方程计算潮能耗散, 发现粤西近海潮能耗散的高值区在西部岛屿密集区域, 与琼州海峡的存在和琼州海峡东北处地形变化存在明显的相关关系。     

Assessment of SARAL-ALTIKA Tidal Corrections in the Coastal Oceans Around India

The present tidal correction of sea level records of Satellite with ARgoes and ALtimeter (SARAL) is based on the finite element solution (FES) of global tide model FES2012 tidal solution. In this study, we examined the validity of the tidal corrections in the coastal oceans around India using tide gauge measurements and a regional tidal model. Our regional model is based on the barotropic version of the Princeton Ocean Model that is forced by the time-varying tidal levels at the open ocean end based on the global FES99 tidal solution. Tide charts prepared from the simulated tidal levels are very similar to the FES tidal solutions. Comparison with the tide gauge measurement shows close agreement with the regional tidal solutions. On the other hand, the agreement with the FES tide models differ significantly in the Gulf of Khambhat and the Gulf of Kutch on the northwest, and in the Hooghly estuary on the northeast continental shelf. However, the agreement is exceptional in other parts of the study domain. These tidal solutions are used in the SARAL-ALTIKA X-track data to assess the FES tidal correction and to draw some inferences associated with the coastal processes. It is revealed that these corrections are reasonably accurate for the coastal oceans around India except the aforementioned converging channels.     

海道测量中跳变水位和缺失水位的补救方法

基于余水位的配置模型,通过潮汐调和分析,利用已知长期验潮站余水位结合临近短期验潮站天文潮位来恢复短期站的实际水位,并对其进行误差分析,证明基于余水位进行推算未知验潮站潮位的可行性与实用性。为了保证验潮仪采集数据的精确度,基于日(月)平均海面在较大的空间尺度内有较强的相关性这一原理,对短期验潮站验潮仪零点漂移进行检测,并对其进行误差分析。