scholarly journals A Novel Deep Learning Model by BiGRU with Attention Mechanism for Tropical Cyclone Track Prediction in Northwest Pacific

2021 ◽  
Author(s):  
Tao Song ◽  
Ying Li ◽  
Fan Meng ◽  
Pengfei Xie ◽  
Danya Xu
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Tropical Cyclone ◽  
Attention Mechanism ◽  
Northwest Pacific ◽  
Cyclone Track ◽  
Tropical Cyclone Track ◽  
Deep Learning Model ◽  
Joint Typhoon Warning Center ◽  
Unit Network

Abstract Tropical cyclones are amongst the most powerful and destructive meteorological systems on earth. In this paper, we propose a novel deep learning model for tropical cyclone track prediction method. Specifically, the track task is regarded as a time series predicting challenge, and then a deep learning framework by Bi-directional Gate Recurrent Unit network (BiGRU) with attention mechanism is developed for track prediction. This proposed model can excavate the effective information of the historical track in a deeper and more accurate way. Data exepriments are conducted on tropical cyclone best track data provided by the Joint Typhoon Warning Center (JTWC) from 1988 to 2017 in the Northwest Pacific. As results, our model performs well in tracks of 6h, 12h, 24h, 48h and 72h in the future. The prediction results show that our proposed combined model are superior to state-of-the-art deep learning models, include Recurrent Neural Network (RNN), Long Short-Term Memory neural network (LSTM), Gate Recurrent Unit network (GRU) and BiGRU without the use of attention mechanism. Compared with China Meteorological Administration (CMA), Japan Meteorological Agency (JMA) and Joint Typhoon Warning Center (JTWC), our method has obvious advantage in the mid- to long-term track forecasting, especially in the next 72 hours.

scholarly journals Tropical Cyclone Gale Wind Radii Estimates, Forecasts, and Error Forecasts for the Western North Pacific

2018 ◽  
Vol 33 (4) ◽  
pp. 1081-1092 ◽  
Author(s):  
Charles R. Sampson ◽  
James S. Goerss ◽  
John A. Knaff ◽  
Brian R. Strahl ◽  
Edward M. Fukada ◽  
...  
Keyword(s):  
Tropical Cyclone ◽  
Real Time ◽  
Error Estimates ◽  
Forecast Error ◽  
Operational Reliability ◽  
Cyclone Track ◽  
Tropical Cyclone Track ◽  
Initial Size ◽  
Time Estimates ◽  
Joint Typhoon Warning Center

Abstract In 2016, the Joint Typhoon Warning Center extended forecasts of gale-force and other wind radii to 5 days. That effort and a thrust to perform postseason analysis of gale-force wind radii for the “best tracks” (the quality controlled and documented tropical cyclone track and intensity estimates released after the season) have prompted requirements for new guidance to address the challenges of both. At the same time, operational tools to estimate and predict wind radii continue to evolve, now forming a quality suite of gale-force wind radii analysis and forecasting tools. This work provides an update to real-time estimates of gale-force wind radii (a mean/consensus of gale-force individual wind radii estimates) that includes objective scatterometer-derived estimates. The work also addresses operational gale-force wind radii forecasting in that it provides an update to a gale-force wind radii forecast consensus, which now includes gale-force wind radii forecast error estimates to accompany the gale-force wind radii forecasts. The gale-force wind radii forecast error estimates are computed using predictors readily available in real time (e.g., consensus spread, initial size, and forecast intensity) so that operational reliability and timeliness can be ensured. These updates were all implemented in operations at the Joint Typhoon Warning Center by January 2018, and more updates should be expected in the coming years as new and improved guidance becomes available.

scholarly journals GPCE-AX: An Anisotropic Extension to the Goerss Predicted Consensus Error in Tropical Cyclone Track Forecasts

2011 ◽  
Vol 26 (3) ◽  
pp. 416-422 ◽  
Author(s):  
James A. Hansen ◽  
James S. Goerss ◽  
Charles Sampson
Keyword(s):  
Tropical Cyclone ◽  
Forecast Error ◽  
Cyclone Track ◽  
Tropical Cyclone Track ◽  
Consensus Forecasts ◽  
The Mean ◽  
Along Track ◽  
National Hurricane Center ◽  
Joint Typhoon Warning Center ◽  
Initial Intensity

Abstract A method to predict an anisotropic expected forecast error distribution for consensus forecasts of tropical cyclone (TC) tracks is presented. The method builds upon the Goerss predicted consensus error (GPCE), which predicts the isotropic radius of the 70% isopleth of expected TC track error. Consensus TC track forecasts are computed as the mean of a collection of TC track forecasts from different models and are basin dependent. A novel aspect of GPCE is that it uses not only the uncertainty in the collection of constituent models to predict expected error, but also other features of the predicted storm, including initial intensity, forecast intensity, and storm speed. The new method, called GPCE along–across (GPCE-AX), takes a similar approach but separates the predicted error into across-track and along-track components. GPCE-AX has been applied to consensus TC track forecasts in the Atlantic (CONU/TVCN, where CONU is consensus version U and TVCN is the track variable consensus) and in the western North Pacific (consensus version W, CONW). The results for both basins indicate that GPCE-AX either outperforms or is equal in quality to GPCE in terms of reliability (the fraction of time verification is bound by the 70% uncertainty isopleths) and sharpness (the area bound by the 70% isopleths). GPCE-AX has been implemented at both the National Hurricane Center and at the Joint Typhoon Warning Center for real-time testing and evaluation.

scholarly journals Tropical Cyclone Track Forecasting Using Fused Deep Learning From Aligned Reanalysis Data

2020 ◽  
Vol 3 ◽  
Author(s):  
Sophie Giffard-Roisin ◽  
Mo Yang ◽  
Guillaume Charpiat ◽  
Christina Kumler Bonfanti ◽  
Balázs Kégl ◽  
...  
Keyword(s):  
Deep Learning ◽  
Tropical Cyclone ◽  
Reanalysis Data ◽  
Cyclone Track ◽  
Tropical Cyclone Track

scholarly journals A Novel Deep Learning Approach for Tropical Cyclone Track Prediction Based on Auto-Encoder and Gated Recurrent Unit Networks

2020 ◽  
Vol 10 (11) ◽  
pp. 3965 ◽  
Author(s):  
Jie Lian ◽  
Pingping Dong ◽  
Yuping Zhang ◽  
Jianguo Pan
Keyword(s):  
Deep Learning ◽  
Tropical Cyclone ◽  
Weather Prediction ◽  
Human Society ◽  
Complex Data ◽  
Strong Wind ◽  
Cyclone Track ◽  
Tropical Cyclone Track ◽  
Gated Recurrent Unit ◽  
Better Than

Under global climate change, the frequency of typhoons and their strong wind, heavy rain, and storm surge increase, seriously threatening the life and property of human society. However, traditional tropical cyclone track prediction methods have difficulties in processing large amounts of complex data in terms of prediction efficiency and accuracy. Recently, deep learning methods have shown a potential capability to process complex data efficiently and accurately. In this paper, we propose a novel data-driven approach based on auto-encoder (AE) and gated recurrent unit (GRU) models to forecast tropical cyclone landing locations using the historical tropical cyclone tracks and various meteorological attributes. This approach fuses a data preprocessing layer, an AE layer, and a GRU layer with a customized batch process. The model is trained on a real-world tropical cyclone dataset from the years 1945–2017. Through a comparison with existing forecasting methods, the results verified that our proposed model performed around 15%, 42%, and 56% better than the Numerical Weather Prediction model (NWP) in 24, 48, and 72 h forecasts, and 27%, 13%, 17%, and 17% better than RNN, AE-RNN, GRU, and LSTM, respectively, in 24 h forecasts, using the absolute position error. In addition, a comparison of the meteorological variables indicated that the variable maximum sustained wind speed had the most significant effect on tropical cyclone track prediction.

Experiments With a Self-Adaptive Multigrid Barotropic Tropical Cyclone Track Model

1999 ◽  
Author(s):  
Scott R. Fulton ◽  
Nicole M. Burgess ◽  
Brittany L. Mitchell
Keyword(s):  
Tropical Cyclone ◽  
Cyclone Track ◽  
Tropical Cyclone Track ◽  
Self Adaptive

Improving Sentiment Analysis using Hybrid Deep Learning Model

2020 ◽  
Vol 13 (4) ◽  
pp. 627-640 ◽  
Author(s):  
Avinash Chandra Pandey ◽  
Dharmveer Singh Rajpoot
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Sentiment Analysis ◽  
Classification Accuracy ◽  
Short Term Memory ◽  
Computational Cost ◽  
Extraction Process ◽  
Learning Model ◽  
Sentiment Classification ◽  
Deep Learning Model

Background: Sentiment analysis is a contextual mining of text which determines viewpoint of users with respect to some sentimental topics commonly present at social networking websites. Twitter is one of the social sites where people express their opinion about any topic in the form of tweets. These tweets can be examined using various sentiment classification methods to find the opinion of users. Traditional sentiment analysis methods use manually extracted features for opinion classification. The manual feature extraction process is a complicated task since it requires predefined sentiment lexicons. On the other hand, deep learning methods automatically extract relevant features from data hence; they provide better performance and richer representation competency than the traditional methods. Objective: The main aim of this paper is to enhance the sentiment classification accuracy and to reduce the computational cost. Method: To achieve the objective, a hybrid deep learning model, based on convolution neural network and bi-directional long-short term memory neural network has been introduced. Results: The proposed sentiment classification method achieves the highest accuracy for the most of the datasets. Further, from the statistical analysis efficacy of the proposed method has been validated. Conclusion: Sentiment classification accuracy can be improved by creating veracious hybrid models. Moreover, performance can also be enhanced by tuning the hyper parameters of deep leaning models.

Sign in / Sign up

Export Citation Format

Share Document