Decision-Tree-Based Classification of Lifetime Maximum Intensity of Tropical Cyclones in the Tropical Western North Pacific

The National Typhoon Center of the Korea Meteorological Administration developed a statistical–dynamical typhoon intensity prediction model for western North Pacific, CSTIPS-DAT, using track-pattern clustering technique. led to significant improvements in tropical cyclones (TCs). However, relatively large errors have been found cluster located Pacific (TWNP), mainly because predictand variance. In this study, decision-tree algorithm was employed reduce variance TCs TWNP. tree predicts likelihood TC reaching maximum lifetime greater than 70 knots at its genesis. four rules suggest that pre-existing ocean thermal structures along track and latitude TC’s position play roles determination intensity. classification exhibited 90.0% 80.5% accuracy training test periods, respectively. These results with CSTIPS-DAT can be further improved by developing independent statistical models groups classified present algorithm.