Background: With the increasing adoption of fifth generation (5G) networks, there is a growing concern about the environmental impact of these networks. The radio frequency (RF) electromagnetic field (EMF) exposure is raising more and more public concerns. Thus, the simulation of RF-EMF exposure is a key point in the developing of future technologies. Due to the complexity in simulating such systems, the build of predictive model are perfectly suited to compare the estimates of EMF levels to guidelines made by organizations like ICNIRP.
Objectives: The aim of this internship is to explore the use of gradient-boosting methods for estimating
field values in the case of 4G/5G networks based on simulation data and sensor data. Boosting methods have recently been popularized thanks to the XGBoost algorithm (Extreme Gradient Boosting) algorithm [1], which has won many AI competitions in recent years. Using data from various sensors installed in urban environment in France [2], surrogate models for predicting RF-EMF exposure can be used for uncertainty quantification or solving optimization problems at a low computational cost. These algorithms have been optimized for speed and performance and support parallel and distributed computing. Thanks to their combination with regression trees, these gradient boosting methods are therefore perfectly suited for handling large data sets.
In this internship, you will:
1) Get acquainted with boosting algorithms using first experimental data from monitoring sensors [2] to
predict both spatial and temporal variation of RF-EMF exposure.
2) Enhance the surrogate models based on simulation data from Cartoradio [3] in the scope of analyzing
the environmental complexity and its influence on the RF-EMF exposure.
3) Compare the performance of the developed surrogate models to the Neural-network based model developed earlier in the team [4] along with various surrogate techniques available in the literature.
Requirements:
1) Background in wave propagation, electromagnetics
2) Good in probability, mathematics, experience in Matlab/Python
3) Good English and team working.
Practical Information: The duration of internship is 6 months between Feb. and Oct. 2026. Location is
at Telecom Paris, 19 place Marguerite Perey, 91120 Palaiseau. For the application, please send your CV and Transcripts from last 3 years to:
Paul Lagouanelle (paul.lagouanelle@telecom-paris.fr) & Shanshan Wang (shanshan.wang@telecom-paris.fr)
References
[1] T. Chen and C. Guestrin, “Xgboost: A scalable tree boosting system,” in Proceedings of the 22nd acm
sigkdd international conference on knowledge discovery and data mining, pp. 785–794, 2016.
[2] O. Jawad, E. Conil, J.-B. Agnani, S. Wang, and J. Wiart, “Monitoring of the exposure to electromagnetic fields with autonomous probes installed outdoors in france,” Comptes Rendus. Physique, vol. 25, no. S1, pp. 1–21, 2024.
[3] Agence Nationale des Frequences, “Cartoradio,” 2021.
[4] Y. Zhang, S. Wang, and J. Wiart, “Exposnet: A deep learning framework for emf exposure prediction in complex urban environments,” arXiv preprint arXiv:2503.02966, 2025.
