:::
2022/11/22 14:00 Mr. Chien-Han Tseng（Research and Development Division, Central Weather Bureau）
Seminar
Poster： ╱ Post date：2022-11-16NCU IHOS Seminar Announcement
Speaker：Mr. Chien-Han Tseng
Place：S-325, Science Building 1
Abstract：
Title：The Sea Surface Temperature Classification/Clustering and East Asia Precipitation Seasonal Forecast based on an ISOMAP analysis
Speaker：Mr. Chien-Han Tseng
Research and Development Division, Central Weather Bureau
Time：11/22（Tue.）14：00
Place：S-325, Science Building 1
Abstract：
Isometric feature mapping (ISOMAP) is a nonlinear dimensionality reduction method used for extracting features from spatiotemporal data. The traditional principal component analysis (PCA), a linear dimensionality reduction method, measures the distance between two data points based on the Euclidean distance (line segment), which cannot reflect the actual distance between the data points in a nonlinear space. By contrast, the ISOMAP measures the distance between two data points based on the geodesic distance, which more closely reflects the actual distance by the view of tracing along the local linearity in the original nonlinear structure. Thus, ISOMAP-reconstructed data points can reflect the features of real structures and can be classified more accurately than traditional PCA-reconstructed data points. In this report, sea surface temperature (SST) and the global precipitation classification/clustering were diagnosed by the ISOMAP. The leading components, the low-dimensional components, of ISOMAP are the orthogonal basis sets, and trajectories exhibit meaningful orbits that machine algorithms can learn. The SST trajectories were similar to the Lorenz 63 model on a phase space figure, and the precipitation trajectories showed the non-random behaviors interannually. The low-dimensionality implies that it does not need to use many data points to predict the future. Preliminary seasonal prediction of the SST in Pacific Ocean or precipitation in East Asia from the low-dimensional components of ISOMAP was done by support vector regression. Moreover, these ISOMAP-reconstructed data points can be used for cluster analysis by emphasizing the differences among the points more than those by the traditional PCA. In this report, sea surface temperature (SST)/East Asia precipitation data points reconstructed using the ISOMAP were compared. The classification/clustering based on these reconstructed SST/precipitation points were tested using the Niño 3.4 index, which labels El Niño, La Niña, or normal events. The ISOMAP not only helped differentiate the points in two different events but also provided better difference measurement of the points belonging to the same class (e.g., 82/83 and 97/98 El Niño events).
Keywords: El Niño; EOF; ISOMAP; La Niña; Niño 3.4; PCA; SST
Last modification time：2022-11-16 AM 11:08
