Abstract:

Aiming at the complexity of traditional methods for feature extraction about satellite cloud images, and the difficulty of developing deep convolutional neural network from scratch, a parameter-based transfer learning method for classifying typhoon intensity is proposed. Take typhoon satellite cloud images published by Japan Meteorological Agency, which includes 10 000 scenes among nearly 40 years to construct training and test typhoon datasets. Three deep convolutional neural networks, VGG16, InceptionV3 and ResNet50 are trained as source models on the large-scale ImageNet datasets. Considering the discrepancy between low-level features and high-level semantic features of typhoon cloud images, adapt the optimal number of transferable layers in neural networks and freeze weights of low-level network. Meanwhile, fine-tune surplus weights on typhoon dataset adaptively. Finally, a transferred prediction model which is suitable for small sample typhoon datasets, called T-typCNNs is proposed. Experimental results show that the T-typCNNs can achieve training accuracy of 95.081% and testing accuracy of 91.134%, 18.571% higher than using shallow convolutional neural network, 9.819% higher than training with source models from scratch.

Key words: Typhoon grade, Transfer learning, Deep convolutional neural network, Number of transferable layers, Adaptive fine-tuning

鎽樿锛�

閽堝浼犵粺鍗槦浜戝浘鐗瑰緛鎻愬彇鏂规硶澶嶆潅涓旀繁搴﹀嵎绉缁忕綉缁滐紙Deep Convolutional Neural Network, DCNN锛夋ā鍨嬪紑鍙戝洶闅剧殑闂锛屾彁鍑轰竴绉嶅熀浜庡弬鏁拌縼绉荤殑鍙伴绛夌骇鍒嗙被鏂规硶銆傚埄鐢ㄦ棩鏈皵璞″巺鍙戝竷鐨勮繎40 a 10 000澶氭櫙鍙伴浜戝浘鏁版嵁锛屾瀯寤轰簡閫傚簲浜庤縼绉诲涔犵殑鍙伴浜戝浘璁粌闆嗗拰娴嬭瘯闆嗐�傚湪澶ц妯mageNet婧愭暟鎹泦涓婅缁冨嚭3绉嶆簮妯″瀷VGG16锛孖nceptionV3鍜孯esNet50锛屼緷鎹彴椋庝簯鍥句綆灞傜壒寰佷笌楂樺眰璇箟鐗瑰緛鐨勫樊寮傦紝閫傞厤缃戠粶鏈�浣宠縼绉诲眰鏁板苟鍐荤粨浣庡眰鏉冮噸锛岄珮灞傛潈閲嶉噰鐢ㄨ嚜閫傚簲寰皟绛栫暐锛屾瀯寤哄嚭浜嗛�傜敤浜庡彴椋庡皬鏍锋湰鏁版嵁闆嗙殑杩佺Щ棰勬姤妯″瀷T-typCNNs銆傚疄楠岀粨鏋滆〃鏄�:T-typCNNs妯″瀷鍦ㄨ嚜寤哄彴椋庢暟鎹泦涓婄殑璁粌绮惧害涓�95.081%锛岄獙璇佺簿搴﹀彲杈�91.134%锛屾瘮鍒╃敤娴呭眰鍗风Н绁炵粡缃戠粶璁粌鍑虹殑绮惧害楂�18.571%锛岀浉姣斾簬鐩存帴鐢ㄦ簮妯″瀷璁粌鏈�澶氭彁楂�9.819%銆�

鍏抽敭璇�: 鍙伴绛夌骇, 杩佺Щ瀛︿範, 娣卞害鍗风Н绁炵粡缃戠粶, 杩佺Щ灞傛暟, 鑷�傚簲寰皟