A tropical cyclone similarity search algorithm based on deep learning method

Abstract The tropical cyclone (TC) track forecast is still a challenging problem. For operational TC forecasts, it is useful for forecasters to find the similar TC in history and reference its data to improve TC forecasting. Considering the vast number of historical TC cases, it is necessary to design a suitable search algorithm to help forecasters find similar TC cases. A historical TC similarity search algorithm (named as SA_DBN) used deep learning approaches based on 500-hPa weather patterns was proposed in this study. Various weather features were automatically extracted by a deep belief network (DBN) without subjective influences. The Chebyshev distance was used to measure the similarity between two TCs. In order to show that similar-TCs retrieved by SA_DBN are helpful for forecasting, a modified WPCLPR method based on the standard WPCLPR and similar-TC track is designed. The modified WPCLPR improved the forecast result (at 85% confidence level) when the lead time was 54H, 60H or 66H. These results showed that the proposed algorithm could effectively retrieve similar TCs and be helpful to forecasters.

[1]  Liang Zou,et al.  Fast prediction of typhoon tracks based on a similarity method and GIS , 2013 .

[2]  Rita Kovordanyi,et al.  Tropical cyclone track forecasting techniques ― A review , 2012 .

[3]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[4]  Christian Igel,et al.  Training restricted Boltzmann machines: An introduction , 2014, Pattern Recognit..

[5]  P. Passalacqua,et al.  Multiresolution analysis of characteristic length scales with high‐resolution topographic data , 2017 .

[6]  Charles R. Sampson,et al.  A History of Western North Pacific Tropical Cyclone Track Forecast Skill , 2004 .

[7]  Lester E. Carr,et al.  Dynamical Tropical Cyclone Track Forecast Errors. Part II: Midlatitude Circulation Influences , 2000 .

[8]  C. J. Neumann.  An alternate to the HURRAN (Hurricane Analog) tropical cyclone forecast system , 1972 .

[9]  Lei Han,et al.  3D Convective Storm Identification, Tracking, and Forecasting—An Enhanced TITAN Algorithm , 2009 .

[10]  Christoph Beck,et al.  Development and comparison of circulation type classifications using the COST 733 dataset and software , 2016 .

[11]  M. Dixon,et al.  TITAN: Thunderstorm Identification, Tracking, Analysis, and Nowcasting—A Radar-based Methodology , 1993 .

[12]  James Nga-Kwok Liu,et al.  Similarity Retrieval from Time-Series Tropical Cyclone Observations Using a Neural Weighting Generator for Forecasting Modeling , 2005, KES.

[13]  Xing Zhao,et al.  Spectral–Spatial Classification of Hyperspectral Data Based on Deep Belief Network , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[14]  Tim Appelhans,et al.  Comparison of four machine learning algorithms for their applicability in satellite-based optical rainfall retrievals , 2015 .

[15]  Soltane Ameur,et al.  Combination of support vector machine, artificial neural network and random forest for improving the classification of convective and stratiform rain using spectral features of SEVIRI data , 2018 .

[16]  Andreas Philipp,et al.  Classifications of Atmospheric Circulation Patterns , 2008, Annals of the New York Academy of Sciences.

[17]  K. P. Moustris,et al.  Rain intensity forecast using Artificial Neural Networks in Athens, Greece , 2010 .

[18]  Geoffrey E. Hinton.  A Practical Guide to Training Restricted Boltzmann Machines , 2012, Neural Networks: Tricks of the Trade.

[19]  J. Thepaut,et al.  The ERA‐Interim reanalysis: configuration and performance of the data assimilation system , 2011 .

[20]  M. Casado,et al.  Circulation types and winter precipitation in Spain , 2016 .

[21]  D. Struppa,et al.  Application of Recurrent Neural Networks for Drought Projections in California , 2017 .

[22]  Andreas Philipp,et al.  The COST733 circulation type classification software: an example for surface ozone concentrations in Central Europe , 2011 .

[23]  Charles J. Neumann,et al.  A statistical model for the prediction of Western North Pacific tropical cyclone motion (WPCLPR) , 1985 .

[24]  K. Fraedrich,et al.  Estimates of cyclone track predictability. I: Tropical cyclones in the Australian region , 1989 .

[25]  Zhiguo Cao,et al.  mCLOUD: A Multiview Visual Feature Extraction Mechanism for Ground-Based Cloud Image Categorization , 2016 .

[26]  Steven A. Ackerman,et al.  Cloud Classification of Satellite Radiance Data by Multicategory Support Vector Machines , 2004, Journal of Atmospheric and Oceanic Technology.

[27]  B. Brown,et al.  A New Verification Measure for Tropical Cyclone Track Forecasts and its Experimental Application , 2013 .

[28]  Xiaogang Huang,et al.  Evaluation and Error Analysis of Official Forecasts of Tropical Cyclones during 2005–14 over the Western North Pacific. Part I: Storm Tracks , 2017 .

[29]  Russell L. Elsberry,et al.  Advances in research and forecasting of tropical cyclones from 1963–2013 , 2013, Asia-Pacific Journal of Atmospheric Sciences.

[30]  Nikos Pelekis,et al.  Similarity Search in Trajectory Databases , 2007, 14th International Symposium on Temporal Representation and Reasoning (TIME'07).

[31]  Miguel Á. Carreira-Perpiñán,et al.  On Contrastive Divergence Learning , 2005, AISTATS.

[32]  Lawrence D. Jackel,et al.  Handwritten Digit Recognition with a Back-Propagation Network , 1989, NIPS.

[33]  Helmut Alt,et al.  Comparison of Distance Measures for Planar Curves , 2003, Algorithmica.

[34]  Geoffrey E. Hinton.  Deep belief networks , 2009, Scholarpedia.

[35]  Chandan Roy,et al.  Cyclone track forecasting based on satellite images using artificial neural networks , 2009 .

[36]  J. Abbot,et al.  Skilful rainfall forecasts from artificial neural networks with long duration series and single-month optimization , 2017 .

[37]  Athanasios G. Paliatsos,et al.  Artificial neural networks modeling for forecasting the maximum daily total precipitation at Athens, Greece , 2014 .

[38]  Wei Zhang,et al.  An Overview of the China Meteorological Administration Tropical Cyclone Database , 2014 .

[39]  J. Abbot,et al.  Input selection and optimisation for monthly rainfall forecasting in Queensland, Australia, using artificial neural networks , 2014 .

[40]  Zhiguo Cao,et al.  Cloud Classification of Ground-Based Images Using Texture–Structure Features , 2014 .

[41]  Ilya Sutskever,et al.  On the Convergence Properties of Contrastive Divergence , 2010, AISTATS.

[42]  A. Ihler,et al.  A Deep Neural Network Modeling Framework to Reduce Bias in Satellite Precipitation Products , 2016 .

[43]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[44]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[45]  R. Torn,et al.  An Ensemble Approach to Investigate Tropical Cyclone Intensification in Sheared Environments. Part I: Katia (2011) , 2016 .

[46]  Ole Winther,et al.  Autoencoding beyond pixels using a learned similarity metric , 2015, ICML.