Ziliang Wei, Jiajing Wu, Bo Yin, Dongning Jia, Jiali Xu
{"title":"Atmospheric duct propagation loss prediction based on time convolution network (TCN)","authors":"Ziliang Wei, Jiajing Wu, Bo Yin, Dongning Jia, Jiali Xu","doi":"10.1109/WCEEA56458.2022.00039","DOIUrl":null,"url":null,"abstract":"The accurate prediction of propagation loss of radio waves in atmospheric duct environment is a hot issue in radar signal transmission and target detection research. Deep learning has achieved good results in many fields, and there are corresponding applications in the accurate prediction of propagation loss prediction. In this paper, we use the time- series convolutional network (TCN) model to predict the data of evaporative duct and surface duct over-the-horizon propagation loss time series and compare the prediction effect with the current state-of-the-art time-series prediction network models LSTM and GRU. The RMSE is used as the evaluation index to calculate their accuracy, and the experiments prove that the TCN model has the best prediction effect than the most advanced LSTM and GRU models, both in the evaporative duct and surface duct environments.","PeriodicalId":143024,"journal":{"name":"2022 International Conference on Wireless Communications, Electrical Engineering and Automation (WCEEA)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 International Conference on Wireless Communications, Electrical Engineering and Automation (WCEEA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/WCEEA56458.2022.00039","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
The accurate prediction of propagation loss of radio waves in atmospheric duct environment is a hot issue in radar signal transmission and target detection research. Deep learning has achieved good results in many fields, and there are corresponding applications in the accurate prediction of propagation loss prediction. In this paper, we use the time- series convolutional network (TCN) model to predict the data of evaporative duct and surface duct over-the-horizon propagation loss time series and compare the prediction effect with the current state-of-the-art time-series prediction network models LSTM and GRU. The RMSE is used as the evaluation index to calculate their accuracy, and the experiments prove that the TCN model has the best prediction effect than the most advanced LSTM and GRU models, both in the evaporative duct and surface duct environments.