<p>Knowledge of the ionospheric electron density is essential for a wide range of applications, e.g., telecommunications, satellite positioning and navigation, and Earth observation from space. Therefore, considerable efforts have been concentrated on modeling this ionospheric parameter of interest. Ionospheric electron density is characterized by high complexity and is space&#8722;and time&#8722;varying, as it is highly dependent on local time, latitude, longitude, season, solar cycle and activity, and geomagnetic conditions. Daytime disturbances cause periodic changes in total electron content (diurnal variation) and additionally, there are multi-day periodicities, seasonal variations, latitudinal variations, or even ionospheric perturbations that cause fluctuations in signal transmission.</p><p>Because of its multiple band frequencies, the current Global Navigation Satellite Systems (GNSS) offer an excellent example of how we can infer ionosphere conditions from its effect on the radiosignals from different GNSS band frequencies. Thus, GNSS techniques provide a way of directly measuring the electron density in the ionosphere. The main advantage of such techniques is the provision of the integrated electron content measurements along the satellite-to-receiver line-of-sight at a large number of sites over a large geographic area.</p><p>Deep learning techniques are essential to reveal accurate ionospheric conditions and create representations at high levels of abstraction. These methods can successfully deal with non-linearity and complexity and are capable of identifying complex data patterns, achieving accurate ionosphere modeling. One application that has recently attracted considerable attention within the geodetic community is the possibility of applying these techniques in order to model the ionosphere delays based on GNSS satellite signals.</p><p>This paper deals with a modeling approach suitable for predicting the ionosphere delay at different locations of the IGS network stations using an adaptive Convolutional Neural Network (CNN). As experimental data we used actual GNSS observations from selected stations of the global IGS network which were participating in the still-ongoing MGEX project that provides various satellite signals from the currently available multiple navigation satellite systems. Slant TEC data (STEC) were obtained using the undifferenced and unconstrained PPP technique. The STEC data were provided by GAMP software and converted to VTEC data values. The proposed CNN uses the following basic information: GNSS signal azimuth and elevation angle, GNSS satellite position (x and y). Then, the adaptive CNN utilizes these data inputs along with the predicted VTEC values of the first CNN for the previous observation epochs. Topics to be discussed in the paper include the design of the CNN network structure, training strategy, data analysis, as well as preliminary testing results of the ionospheric delays predictions as compared with the IGS ionosphere products. &#160;&#160;</p>
Automated Identification of Wood Veneer Surface Defects Using Faster Region-Based Convolutional Neural Network with Data Augmentation and Transfer Learning
