论文信息 - Data Mining for Tropical Cyclone Intensity Prediction

Data Mining for Tropical Cyclone Intensity Prediction

Tropical cyclone (TC) intensity prediction is far more challenging than the corresponding TC track prediction. One of the reasons is the lack of understanding of the coupling relationships of the physical processes controlling TC intensification. Data mining provides potential tools for relationship exploration from the ever-increasing amount of TC data. The data mining tools and algorithms require process-related features from raw observational data such as the TC best track data, TRMM data for 3D rainfall and 2D surface information. The data mining tools and algorithms can search for hidden relationships among the underlying features by means of statistical and logical inferences. In this article, we describe the data, definitions of features from the data, tools for data exploration, and several important results.

Ruixin Yang | Jiang Tang | Menas Kafatos

[1] S. Aberson. The ensemble of tropical cyclone track forecasting models in the north Atlantic basin (1976-2000) , 2001 .

[2] Tomasz Imielinski,et al. Mining association rules between sets of items in large databases , 1993, SIGMOD Conference.

[3] A. Chang,et al. Analyses of 1994 Typhoons in the Taiwan Region using Satellite Data , 1997 .

[4] Mark DeMaria,et al. A Statistical Hurricane Intensity Prediction Scheme (SHIPS) for the Atlantic Basin , 1994 .

[5] Salvatore J. Stolfo,et al. Mining Audit Data to Build Intrusion Detection Models , 1998, KDD.

[6] Xintao Wu,et al. Screening and interpreting multi-item associations based on log-linear modeling , 2003, KDD '03.

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

[8] Mark DeMaria,et al. An Updated Statistical Hurricane Intensity Prediction Scheme (SHIPS) for the Atlantic and Eastern North Pacific Basins , 1999 .

[9] Philip S. Yu,et al. Data mining for path traversal patterns in a web environment , 1996, Proceedings of 16th International Conference on Distributed Computing Systems.

[10] Ramakrishnan Srikant,et al. Mining quantitative association rules in large relational tables , 1996, SIGMOD '96.