Artificial neural network-based storm surge forecast model: Practical application to Sakai Minato,Japan

The present study describes a novel way of a systematic and objective selection procedure for the development of an Artificial Neural Network-based storm Surge Forecast Model (ANN-SFM) with the 5, 12 and 24 h-lead times and its application to Sakai Minato area on the Tottori coast, Japan. The selection procedure guides how to determine the superiority of the best performing model in terms of the appropriate combination of unit number in the hidden layer and parameter in the input layer. In the application of ANN-SFM to Sakai Minato, it is found that the best 5 and 12 h-forecast ANN-SFMs are established with the most suitable set of 70 units (the number of hidden neurons) and the input components of surge level, sea level pressure, the depression rate of sea level pressure, longitude, latitude, central atmospheric pressure and highest wind speed. The best 24 h-forecast ANN-SFM is determined with 160 units and the input parameters of surge level, sea level pressure, the depression rate of sea level pressure, longitude and latitude. The proposed method of the selection procedure is able to be adaptable to other coastal locations for the development of the artificial neural network-based storm surge forecast model as establishing the superiority of the most relevant set combining unit numbers and input parameters.     

ECMWF对不同天气形势下影响浙江台风的路径预报评估

对2012—2016年影响浙江台风进行天气形势场基本分型,依次是:(Ⅰ)东侧副高+浅槽型、(Ⅱ)副高+深槽\低涡型、(Ⅲ)带状副高型、(Ⅳ)副高西伸脊型、(Ⅴ)近海块状副高型、(Ⅵ)其他型。基于此对ECMWF台风路径预报进行评估,包括路径预报距离误差、移向误差和二者的分布特性。结果表明:(1)不同天气型的台风预报:24 h、48 h、72 h的平均距离误差为:57 km,105 km,183 km,其随时效增长增大,以Ⅰ类、Ⅱ类预报效果最差,Ⅲ类和Ⅳ类效果较好,与此对应路径多为登陆浙闽交界或者登陆浙江后西行和登陆台湾二次登陆闽中或登陆闽中转向北上;移向误差绝对值看:24 h、48 h、72 h绝对移向误差分别为5.41°,4.85°,6.46°,从移向偏差看,24 h预报移向总体偏右概率大,而对Ⅰ类预报偏左概率大,Ⅲ类、Ⅳ类预报偏右概率大;Ⅳ、Ⅴ型偏离程度小,Ⅱ型偏离程度大,Ⅰ型、Ⅳ型、Ⅴ型偏离程度随时效增长变化较小,较为稳定,Ⅱ型和Ⅲ型较不稳定;(2)从两种误差的分布可知:影响浙江的台风24 h距离误差主要在100 km内,移向误差范围是-10°～10°;随预报时效增长,离散程度增强,说明移向误差随着距离误差的增大而增大。     

2018年6月青岛近岸一次海雾导致能见度变化的成因分析

2018年6 月5~9日青岛近海发生一次海雾天气过程,为6月9日2018上海合作组织青岛峰会开幕式演出的天气预报服务,特别是能见度精细化预报带来了很大的预报难点。本文分析了此次海雾天气的生消过程,并重点讨论了6月9日能见度变化的主要原因。4~7日边界层内接近接地的强逆温层的建立,有利于海雾的形成与维持。由于白天时段日射增温导致能见度好转,海雾出现日变化。自7日夜间开始地面气压场梯度明显减弱,南风减弱转为偏东风,暖湿气流供应减弱不利于海雾天气的维持。8日之后,边界层内上升运动逐渐增强且混合层高度明显增加,中低层干冷空气的侵入,导致边界层内逆温结构被破坏、近地面湿层消失,使此次海雾过程趋于消散。9日傍晚的能见度条件基本达到演出要求。9日夜间受焰火燃放污染物影响,能见度短时波动。各种海雾客观预报方法预报准确率达到66%左右,主观预报订正准确性高于客观预报。     

Validation of an operational forecasting system of sea dike risk in the southern Zhejiang Province,South China

In this study,an operational forecasting system of sea dike risk in the southern Zhejiang Province,South China was developed based on a coupled storm-surge and wave model.This forecasting system is important because of the high cost of storm-surge damage and the need for rapid emergency planning.A comparison with astronomical tides in 2016 and the validation of storm surges and high water marks of 20 typhoons verified that the forecast system has a good simulation ability.The system can forecast relatively realistic water levels and wave heights as shown under the parametric atmospheric forces simulated in a case study;the sea dikes in credible high risk were mainly located in the estuaries,rivers,and around the islands in the southern Zhejiang.Therefore,the forecast system is applicable in the southern Zhejiang with a support to the effective prevention from typhoon storm-surge damage.     

Application of tank,NAM, ARMA and neural network models to flood forecasting

Two lumped conceptual hydrological models, namely tank and NAM and a neural network model are applied to flood forecasting in two river basins in Thailand, the Wichianburi on the Pasak River and the Tha Wang Pha on the Nan River using the flood forecasting procedure developed in this study. The tank and NAM models were calibrated and verified and found to give similar results. The results were found to improve significantly by coupling stochastic and deterministic models (tank and NAM) for updating forecast output. The neural network (NN) model was compared with the tank and NAM models. The NN model does not require knowledge of catchment characteristics and internal hydrological processes. The training process or calibration is relatively simple and less time consuming compared with the extensive calibration effort required by the tank and NAM models. The NN model gives good forecasts based on available rainfall, evaporation and runoff data. The black‐box nature of the NN model and the need for selecting parameters based on trial and error or rule‐of‐thumb, however, characterizes its inherent weakness. The performance of the three models was evaluated statistically. Copyright © 2000 John Wiley & Sons, Ltd.     

Forecast of Tsunamis from the Japan–Kuril–Kamchatka Source Region

This paper describes an investigation of the subfault distribution along the Japan–Kuril–Kamchatka subduction zone for the implementation of a far-field tsunami forecast algorithm. Analyses of seismic data from 1900 to 2000 define the subduction zone, which in turn is divided into 222 subfaults based on the fault characteristics. For unit slip of the subfaults, a linear long-wave model generates a database of mareograms at water-level stations along the subduction zone and at warning points in the North Pacific. When a tsunami occurs, an inverse algorithm determines the slip distribution from near-source water-level records and predicts the waveforms at the warning points using the pre-computed mareograms. A jackknife resampling scheme uses combinations of input water-level records to provide a series of waveform predictions for the computation of the confidence-interval bounds. The inverse algorithm is applied to hindcast two major tsunamis generated from the Japan–Kuril–Kamchatka source and the computed tsunami heights show good agreement with recorded water-level data.     

上海沿岸海域灾害性大风特征研究与预报检验

选取2011-2017年上海沿岸海域5个浮标站点的风场和海浪数据,分析了大风过程的时间和空间特征;对海浪成长过程进行风向分类,运用滑动相关分析统计了8个风向的海浪滞后时间;计算了大风起风时间的预报提前和滞后量,进行了风速风向的误差和准确率检验。结果表明:越往东部海域,大风时数越多,长江口区东部风速较大;大风极值主要出现在8月份台风过程,出现时段都为傍晚到半夜,大浪极值浪向以东北到东南向为主;秋冬季大风时数多,5-6月大风时数最少;大风风向以西北到东北风为主;海浪成长过程风向分布是东南-西北走向,海浪对风的响应滞后时间平均为3~4 h;大风起风时间预报较实况略有滞后,风速预报的准确率总体在70%以上,预报值较实况值偏小,口外浮标偏小最为明显,偏强率都为0;风向预报准确率低,误差大。     

基于机械学习理论的海冰风险短期预报研究

海冰管理是抵御寒区海洋资源开发海冰威胁的有效手段,海冰风险的准确、快速预测是海冰管理系统的关键组成部分。文中面向海冰管理中的冰情短时预测需求,明确了基于现场监测的海冰风险预测模式,开展了应用机械学习理论的海冰风险短时预测方法研究,并以渤海辽东湾海冰管理为例,讨论了神经网络与小波分解等非线性预测方法在冰情短时预测中的适用性。结果表明,时间序列小波神经网络在短时(6 h)冰厚预测中的预测精度与Elman神经网络相仿,而在24~48 h预测中的精度偏差较大;Elman神经网络在6 h、24 h与48 h的冰厚预测中均能保持较好的预测精度,在冰流速与来冰方向预测中,模型预测精度达到80%左右。     

Annual precipitation gray forecast in disaster year of Chedaren debris flow

The Chedaren ravine belongs to high-prone areas of debris flow in Jilin Province, which threaten the local people＇ s life and security seriously. The authors used the residual correction theory to amend the GM （ 1, 1 ） model and forecast annual precipitation in disaster year of the Chedaren ravine ; it provides scientific foundation for early warning of debris flow disaster in the rainy season based on weather forecast. The prediction resuits show that annual precipitation is 724.7 mm in 2009 ; the region will probably occur large-scale debris flow during the rainy season.     

钻爆法施工条件下城市地下工程建设对环境的影响分析

针对如何使城市地下开挖对周围环境造成的损害最小与损害防治等问题,以钻爆法施工为例,针对开挖设计方法和方案的选取、沉陷预测预报以及损害评价等开展了探索性研究.其目的在于使城市地下开挖施工与周围环境相协调,以确保地下开挖与环境系统达到最优;并以青岛海底隧道青岛接线端隧道开挖对建筑物的影响作为实例,进行了论证和分析,从而确保了受开挖影响的地面建筑物的安全,并且保护了地面环境.