부산대학교 도서관

Weather radar holds the capability to monitor the extensive migration of bird and insect species. In particular, polarimetric weather radar can enhance aerial ecological monitoring by quantifying target shape through the measurement of polarization moments. This article introduces an intelligent algorithm to classify bird and insect migration using polarimetric weather radar data. A radar image dataset was formed by intentionally curating typical migratory data of birds and insects captured by the polarimetric weather radar. Next, point features and spatial texture features were extracted from the radar images in the dataset for training a classifier using a supervised learning approach, resulting in a classification accuracy of 93.56%. Furthermore, the importance of the features was analyzed, uncovering that the most influential attribute was the reflectivity factor at 33.83%, surpassing the cumulative influence of other dual-polarization moments. In addition, spatial textures also played an essential role for the classifier, collectively weighing 35.65%. Lastly, the proposed method was validated with bird radar data, attaining an accuracy level of 95.36%.