Snow identification from unattended automatic weather stations images using DANet

Frontiers in Earth Science

Earth Science

Jie Gong¹  Min Liu²  Yonghua Wang³  Fan Deng⁴ 

[1] Institute of Geological Survey, China University of Geosciences, Wuhan, China;Wuhan Huaxin Lianchuang Technology Engineering Co., Ltd., Wuhan, China;Institute of Geological Survey, China University of Geosciences, Wuhan, China;Wuhan Natural Resources and Planning Information Center, Wuhan, China;Wuhan Huaxin Lianchuang Technology Engineering Co., Ltd., Wuhan, China;Wuhan Huaxin Lianchuang Technology Engineering Co., Ltd., Wuhan, China;School of Geosciences, Yangtze University, Wuhan, China;

关键词: snow identification;    automatic weather station (AWS);    attention mechanism;    DANet model;    weather monitoring;   

DOI  :  10.3389/feart.2023.1226451

 received in 2023-05-21, accepted in 2023-06-26,  发布年份 2023

来源: Frontiers

【 摘 要 】

Identifying snow phenomena in images from automatic weather station (AWS) is crucial for live weather monitoring. In this paper, we propose a convolutional neural network (CNN) based model for snow identification using images from AWS cameras. The model combines the attention mechanism of the DANet model with the classical residual network ResNet-34 to better extract the features of snow cover in camera images. To improve the generalizability of the model, we also use images from public datasets in addition to images taken by cameras from unmanned weather stations. Our results show that the proposed model achieved a POD of 91.65%, a FAR of 7.34% and a TS score of 85.45%, demonstrating its effectiveness in snow identification. This study has the potential to facilitate more efficient and effective weather monitoring in a variety of locations.

【 授权许可】

Unknown   
Copyright © 2023 Gong, Wang, Liu and Deng.