Proceedings of the XXXVth URSI General Assembly and Scientific Symposium – GASS 2023最新文献

筛选

英文中文

A Stacked Machine Learning Model for the vertical Total Electron Content Forecasting 用于垂直总电子含量预测的堆叠式机器学习模型

Proceedings of the XXXVth URSI General Assembly and Scientific Symposium – GASS 2023 Pub Date : 2024-05-01 DOI: 10.46620/ursigass.2023.2291.lamb6866

Eric Nana Asamoah

{"title":"A Stacked Machine Learning Model for the vertical Total Electron Content Forecasting","authors":"Eric Nana Asamoah","doi":"10.46620/ursigass.2023.2291.lamb6866","DOIUrl":"https://doi.org/10.46620/ursigass.2023.2291.lamb6866","url":null,"abstract":"This study focuses on the application of an advance machine learning model (stacked) for forecasting the iono-spheric vertical Total Electron Content (vTEC) from 1 to 24 hours in advance. Data are provided by the Global Navigation Satellite Systems (GNSS) receiver installed at Noto, Italy (NOT1 (lat:36.53, 14.59) data). The stacked model performance is compared with ANN, CNN and ELM. The time series used include vTEC and external drivers (solar and geomagnetic indices) which span from January 1, 2011 to December 31, 2011. The dataset is partition into a training (80%), validation (10%) and test (10%). Proper exter-nal drivers have been selected by ranking their importance of each driver in relation to the vTEC dynamics at different hours of the day. The most important external drivers resulted to be the 10.7 cm solar flux (F10.7) and the Geomag-netic Auroral Electrojet index (AE), used together with the vTEC times series as the input for our model. To measure the performance of the models, we make use of the statistical parameters such as root mean square error (RMSE) and coefficient of determination ( R 2 ) . In the period analyzed, the stacked model showed the best performance on the test dataset","PeriodicalId":514771,"journal":{"name":"Proceedings of the XXXVth URSI General Assembly and Scientific Symposium – GASS 2023","volume":"31 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141056339","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0