Fig. 2: Cluster feature evaluation. | Nature Communications

Fig. 2: Cluster feature evaluation.

From: Interpretable semi-supervised clustering enables universal detection and intensity assessment of diverse aviation hazardous winds

Fig. 2

a Locations of the selected airports, the red dot and the four blue stars represent the locations of HKIA and the other four airports in mainland China, respectively, the map is created with Cartopy61 and digital elevation model64; b visualization of the cluster features extracted in this work by t-SNE65 method. Source data are provided as a Source Data file.

Back to article page