Study on Wind Simulations Using Deep Learning Techniques during Typhoons: A Case Study of Northern Taiwan

Abstract

A scheme for wind-speed simulation during typhoons in Taiwan is highly desirable, considering the effects of the powerful winds accompanying the severe typhoons. The developed combination of deep learning (DL) algorithms with a weather-forecasting numerical model can be used to determine wind speed in a rapid simulation process. Here, the Weather Research and Forecasting (WRF) numerical model was employed as the numerical simulation-based model for precomputing solutions to determine the wind velocity at arbitrary positions where the wind cannot be measured. The deep neural network (DNN) was used for constructing the DL-based wind-velocity simulation model. The experimental area of Northern Taiwan was used for the simulation. Regarding the complex typhoon system, the collected data comprised the typhoon tracks, FNL (Final) Operational Global Analysis Data for the WRF model, typhoon characteristics, and ground weather data. This study included 47 typhoon events that occurred over 2000–2017. Three measures were used to analyze the models for identifying optimal performance levels: Mean absolute error, root mean squared error, and correlation coefficient. This study compared observations with the WRF numerical model and DNN model. The results revealed that (1) simulations by using the WRF-based models were satisfactorily consistent with the observed data and (2) simulations by using the DNN model were considerably consistent with those of the WRF-based model. Consequently, the proposed DNN combined with WRF model can be effectively used in simulations of wind velocity at arbitrary positions of study area.

Forecasting of Typhoon-Induced Wind-Wave by Using Convolutional Deep Learning on Fused Data of Remote Sensing and Ground Measurements

“…In summary, Table 2 lists all the designed model cases for wind speed (i.e., WIND-1 and WIND-2) and wave height (i.e., WAVE-1 to WAVE-4) and their corresponding algorithms and data used. Here, our proposed cases were WIND-2, WAVE-3, and WAVE-4, and the other cases using past studies were WIND-1 [ 21 , 23 , 29 ], WAVE-1 [ 32 ], and WAVE-2 [ 32 ]. The network architectures of these model cases were described in the following sections.…”

“…The influence of wind fields and terrain effects could be considered for more detail. For example, Wei [ 21 ] used the National Center for Environmental Prediction final reanalysis data on 1-degree by 1-degree resolution as the initial field and boundary conditions for simulating a WRF model and suggested that the interpolation method could be used to obtain the spatiotemporal sequences of the wind field effectively. Second, as mentioned earlier, this work collected radar reflectivity images with a sample time of one hour.…”

“…With the development of artificial intelligence, numerous machine learning algorithms, such as decision trees, support vector machines, and deep neural networks, such as multilayer perceptrons (MLPs) and convolutional neural networks (CNNs), have been applied to the field of natural science. The advantages of machine learning methods are that they effectively identify and learn correlated patterns between input datasets and the corresponding target values [ 20 , 21 ]. However, they are less subject to the constraints of physical mechanisms [ 22 , 23 ].…”

Wind Features Extracted from Weather Simulations for Wind-Wave Prediction Using High-Resolution Neural Networks

“…The WRF model provides various options for physical parameters, such as weather patterns, geographic locations, and simulation scenarios. We referred to [17,[67][68][69] in selecting the physical parameters. These researchers studied the typhoon track, rainfall, and wind forecasts for WRF model simulations using reasonable physical parameters for typhoons approaching Taiwan.…”

Collapse Warning System Using LSTM Neural Networks for Construction Disaster Prevention in Extreme Wind Weather

“…This study reviewed the relevant literature on wind velocity prediction models using DL-based and MLbased approaches, because they exhibit high calculation efficiency and accurate prediction ability (Dongmei et al, 2017;Mallick et al, 2020;Panapakidis et al, 2019;Sheela & Deepa, 2013;Wei, 2014Wei, , 2015. In addition, several popular approaches are investigated such as autoregressive integrated moving average (Cadenas & Rivera, 2010;Cadenas et al, 2016), support vector machine (Chou et al, 2020;Wei, 2017), random forest (Kim et al, 2019), radial basis function (Noorollahi et al, 2016), and neural networks (Chen et al, 2018;Huang et al, 2018a;Hu et al, 2016;Wei, 2019). A recurrent neural network (RNN) is an extension of a conventional feedforward neural network that can handle a variable-length sequence input (Chung et al, 2014;Graves, 2013).…”