As telecommunications networks evolve to cope with ever-increasing user demands, so does our exposure induced by radiofrequency (RF) electromagnetic fields (EMF). This research proposal aims at keeping pace with the ongoing evolution in wireless telecommunications, such as the introduction in of Massive MIMO (Multiple-Input Multiple-Output) and beamforming in the fourth generation (4G) technology Long Term Evolution (LTE), and their anticipated widespread use in 5G New Radio (NR). As RF-EMF exposure becomes more user-dependent, current measurement methods are too static, too short, and/or ignore the user dimension. The first two concerns (static and short-term) will be mitigated by designing extensive, static as well as mobile, sensor networks that continuously monitor environmental RF-EMF. The third issue (user dimension) is expected to become a dominant factor with the introduction of 5G NR. Hence, new measurement methods are required depending on technological advances and possible novel use cases introduced with subsequent releases of 5G NR. Moreover, as the collected measurement data are expected to be numerous (millions of data points) and of heterogeneous origin (different measurement devices), artificial intelligence (AI) machine learning techniques and stochastic methods will be explored. The combined objectives of this proposal will lead to a better characterization and a better understanding of our current and future exposures to RF-EMF in the urban environment.