{"title":"利用商用微波链路衰减和温度改进的水汽密度估计","authors":"Itay Bragin, Y. Rubin, P. Alpert, J. Ostrometzky","doi":"10.1109/ICASSPW59220.2023.10193740","DOIUrl":null,"url":null,"abstract":"Water vapor measurement is beneficial for weather models. A machine learning support vector machine model for estimating water vapor density at a reference weather station location using measurements of the received signal level from commercial microwave link and trained with data from the reference weather station has already been proposed. In this paper, we propose an enhanced machine learning model that utilizes three commercial microwave links inside a given area, as well as additional temperature observations. This model can achieve higher accuracy of water vapor estimation (when compared to the weather station as ground truth). Specifically, we present preliminary results, and show that although certain uncertainties exist, the root mean square error achieved by the presented approach was more than twice as small as the error achieved when utilizing a model using a single commercial microwave link.","PeriodicalId":158726,"journal":{"name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","volume":"353 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Improved Water Vapor Density Estimation With Commercial Microwave Links Attenuation And Temperature\",\"authors\":\"Itay Bragin, Y. Rubin, P. Alpert, J. Ostrometzky\",\"doi\":\"10.1109/ICASSPW59220.2023.10193740\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Water vapor measurement is beneficial for weather models. A machine learning support vector machine model for estimating water vapor density at a reference weather station location using measurements of the received signal level from commercial microwave link and trained with data from the reference weather station has already been proposed. In this paper, we propose an enhanced machine learning model that utilizes three commercial microwave links inside a given area, as well as additional temperature observations. This model can achieve higher accuracy of water vapor estimation (when compared to the weather station as ground truth). Specifically, we present preliminary results, and show that although certain uncertainties exist, the root mean square error achieved by the presented approach was more than twice as small as the error achieved when utilizing a model using a single commercial microwave link.\",\"PeriodicalId\":158726,\"journal\":{\"name\":\"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)\",\"volume\":\"353 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-06-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICASSPW59220.2023.10193740\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICASSPW59220.2023.10193740","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Improved Water Vapor Density Estimation With Commercial Microwave Links Attenuation And Temperature
Water vapor measurement is beneficial for weather models. A machine learning support vector machine model for estimating water vapor density at a reference weather station location using measurements of the received signal level from commercial microwave link and trained with data from the reference weather station has already been proposed. In this paper, we propose an enhanced machine learning model that utilizes three commercial microwave links inside a given area, as well as additional temperature observations. This model can achieve higher accuracy of water vapor estimation (when compared to the weather station as ground truth). Specifically, we present preliminary results, and show that although certain uncertainties exist, the root mean square error achieved by the presented approach was more than twice as small as the error achieved when utilizing a model using a single commercial microwave link.