A Deep Neural Network Model of Global Topside Electron Temperature Using Incoherent Scatter Radars and Its Application to GNSS Radio Occultation

The goal of this study is to present a new model for global topside electron temperature ( urn:x-wiley:jgra:media:jgra55532:jgra55532-math-0001) using a deep neural network (DNN) that is trained using measurements from incoherent scatter radars (ISRs). This study is also an investigation into whether this model can be used to generate the electron temperature in the topside ionosphere using GNSS ionospheric radio occultation (GNSS‐IRO) data as the input. ISR is one of the most reliable and long‐term sources to measure topside ionospheric electron density and plasma temperature information simultaneously. However, a drawback of ISR databases is the relatively poor spatial coverage due to the low number of ISR stations around the world. In contrast, GNSS‐IRO can be used to measure the global distributed electron density, but urn:x-wiley:jgra:media:jgra55532:jgra55532-math-0002 information is not directly detected. The relationship between the electron density and the electron temperature has been investigated by many researchers, but these studies have not explicitly considered the parameters that are known to influence the electron temperature, such as solar and geomagnetic activity level, and the features of electron density profile ( urn:x-wiley:jgra:media:jgra55532:jgra55532-math-0003, urn:x-wiley:jgra:media:jgra55532:jgra55532-math-0004, and scale height). This study uses a DNN technique to create a new global topside electron temperature model from three submodels that have been trained using data from three ISR stations: Arecibo (low latitude), Millstone Hill (midlatitude), and Poker Flat (high latitude). This global model is trained using electron density profile information (e.g., vertical scale height [VSH], urn:x-wiley:jgra:media:jgra55532:jgra55532-math-00052, and urn:x-wiley:jgra:media:jgra55532:jgra55532-math-00062) and solar and geomagnetic activity ( urn:x-wiley:jgra:media:jgra55532:jgra55532-math-0007 and urn:x-wiley:jgra:media:jgra55532:jgra55532-mat