Modeling troposherical phenomena in extreme long distance LPWAN communication
In LoRaWAN networks such as The Things Network, long distance transmissions, well beyond the limitations of line of sight in terrestrial geometry, are frequently observed. Tropospheric effects are seen as responsible for bending or guiding radio waves around the earth curvature. As an example, under the right weather conditions, the LoRaWAN gateway at ITU may collect packets from northern Germany, and nodes from Copenhagen may send data to Sweden and Germany. An understanding and prediction of such occurences is of relevance to applications in e.g. logistics and maritime networking, and more so where LPWANs are directly utilized for location tracking. We propose to collect and correlate LoRaWAN link data with publicly available weather and satellite data, and apply ML techniques to work towards models and predictions for these phenomena.