Agent-Based Cluster Analysis of Tropical Cyclone Tracks in the Western North Pacific

The clustering model integrating Finite Mixture Model (FMM) and classical Expectation-Maximum (EM) algorithm has been applied to tropical cyclone (TC) tracks during the last decade. However, the efficiency of classical EM algorithm is insufficiently good and the robustness of the model is not verified. Besides, it is inconvenient for users to manually choose the parameters for the cluster analysis. In order to improve the efficiency of classical EM algorithm, the "Lazy-Ψα 2" EM is proposed by integrating Lazy EM algorithm and Ψα 2 algorithm. Sensitivity analysis is conducted to ensure the insensitivity of the clustering model to the amount of data set. The cluster analysis is implemented on an agent-based framework by which the tool can automatically choose the parameters by evaluating the clustering performance. TC tracks in western North Pacific from 1949 to 2006 are classified into 12 clusters by the probabilistic clustering model that is solved by "Lazy-Ψα 2" EM algorithm. The log-likelihood is taken as the performance indicator. Elaborate comparisons are made between the present cluster analysis and other cluster analyses related to TC tracks.

[1]  Kenneth J. Berry,et al.  Predicting Atlantic Basin Seasonal Tropical Cyclone Activity by 1 August , 1993 .

[2]  Michael Luck,et al.  A Manifesto for Agent Technology: Towards Next Generation Computing , 2004, Autonomous Agents and Multi-Agent Systems.

[3]  Michael Luck,et al.  Agent technology: Enabling next generation computing , 2003 .

[4]  D. Rubin,et al.  Parameter expansion to accelerate EM: The PX-EM algorithm , 1998 .

[5]  R. Blender,et al.  Identification of cyclone‐track regimes in the North Atlantic , 1997 .

[6]  Padhraic Smyth,et al.  Trajectory clustering with mixtures of regression models , 1999, KDD '99.

[7]  François Bousquet,et al.  Multi-agent simulations and ecosystem management: a review , 2004 .

[8]  Richard A. Anthes,et al.  Tropical Cyclones: Their Evolution, Structure and Effects , 1982 .

[9]  Saltelli Andrea,et al.  Global Sensitivity Analysis: The Primer , 2008 .

[10]  Geoffrey J. McLachlan,et al.  Finite Mixture Models , 2019, Annual Review of Statistics and Its Application.

[11]  Geoffrey E. Hinton,et al.  A View of the Em Algorithm that Justifies Incremental, Sparse, and other Variants , 1998, Learning in Graphical Models.

[12]  R. Elsberry,et al.  Large-Scale Circulation Variability over the Tropical Western North Pacific. Part I: Spatial Patterns and Tropical Cyclone Characteristics , 1995 .

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

[14]  Padhraic Smyth,et al.  Probabilistic clustering of extratropical cyclones using regression mixture models , 2007 .

[15]  Ana L. C. Bazzan,et al.  Anticipatory Traffic Forecast Using Multi-Agent Techniques , 2000 .

[16]  Gerhard Weiss,et al.  Multiagent systems: a modern approach to distributed artificial intelligence , 1999 .

[17]  Chun‐Chieh Wu,et al.  Current understanding of tropical cyclone structure and intensity changes – a review , 2004 .

[18]  Lester E. Carr,et al.  Dynamical Tropical Cyclone Track Forecast Errors. Part I: Tropical Region Error Sources , 2000 .

[19]  Ana L. C. Bazzan,et al.  Agents in Traffic Modelling - From Reactive to Social Behaviour , 1999, KI.

[20]  Jiawei Han,et al.  Data Mining: Concepts and Techniques , 2000 .

[21]  Padhraic Smyth,et al.  Probabilistic curve-aligned clustering and prediction with regression mixture models , 2004 .

[22]  Padhraic Smyth,et al.  Cluster Analysis of Typhoon Tracks. Part II: Large-Scale Circulation and ENSO , 2007 .

[23]  Ch. Roland,et al.  Acceleration schemes with application to the EM algorithm , 2007, Comput. Stat. Data Anal..

[24]  Padhraic Smyth,et al.  Cluster Analysis of Typhoon Tracks. Part I: General Properties , 2007 .

[25]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[26]  Shuangzhe Liu,et al.  Global Sensitivity Analysis: The Primer by Andrea Saltelli, Marco Ratto, Terry Andres, Francesca Campolongo, Jessica Cariboni, Debora Gatelli, Michaela Saisana, Stefano Tarantola , 2008 .

[27]  James S. Goerss,et al.  Prediction of Consensus Tropical Cyclone Track Forecast Error , 2007 .

[28]  Gerhard Weiss,et al.  Multi-Agent Systems , 2013 .

[29]  B. Everitt,et al.  Finite Mixture Distributions , 1981 .

[30]  Geoffrey J. McLachlan,et al.  Mixture models : inference and applications to clustering , 1989 .

[31]  Russell L. Elsberry,et al.  Consensus of Dynamical Tropical Cyclone Track Forecasts—Errors versus Spread , 2000 .

[32]  G. McLachlan,et al.  The EM algorithm and extensions , 1996 .

[33]  Jae-Gil Lee,et al.  Trajectory clustering: a partition-and-group framework , 2007, SIGMOD '07.

[34]  James B. Elsner,et al.  Examining the ENSO-typhoon hypothesis , 2003 .

[35]  Wolfram Burgard,et al.  KI-99: Advances in Artificial Intelligence , 2003, Lecture Notes in Computer Science.

[36]  Longbing Cao,et al.  Agent Mining: The Synergy of Agents and Data Mining , 2009, IEEE Intelligent Systems.

[37]  Jacques Ferber,et al.  Multi-agent systems - an introduction to distributed artificial intelligence , 1999 .

[38]  M. Janssen,et al.  Multi-Agent Systems for the Simulation of Land-Use and Land-Cover Change: A Review , 2003 .

[39]  A. Barnston,et al.  Clustering of eastern North Pacific tropical cyclone tracks: ENSO and MJO effects , 2008 .

[40]  Michael Luck,et al.  Understanding Agent Systems , 2001, Springer Series on Agent Technology.

[41]  Afsaneh Haddadi,et al.  Application of multi-agent systems in traffic and transportation , 1997, IEE Proc. Softw. Eng..

[42]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[43]  R. Simpson,et al.  The hurricane and its impact , 1981 .

[44]  Victor Lesser.  Multi-agent systems , 2003 .

[45]  Michael Luck,et al.  Agent technology: Enabling next generation computing , 2003 .