Roberto Castello

roberto.castello@epfl.ch +41 21 693 87 94

EPFL SDSC
INN 218 (Bâtiment INN)
Station 14
1015 Lausanne

+41 21 693 87 94
Office: INN 218
EPFL › VPA › VPA-AVP-CP › SDSC › SDSC-GE

Expertise

Applied Machine Learning and AI for the built environment and renewable energies, Building Physics, Statistical methods, Geographic Information Systems

Biography Publications

Roberto holds an M.Sc. and a Ph.D. in Particle Physics from the University of Torino, Italy. He worked as a Research Fellow for the Belgian National Fund for Scientific Research (FNRS) and later at the CERN Experimental Physics division as a Senior Research Fellow and Data Scientist. In 2018, he joined the EPFL Solar Energy and Building Physics Laboratory (LESO-PB) as a Senior Scientist and group leader to work on data mining and Machine Learning for the built environment and renewable energy. He has started and led multiple collaborations with academic and industrial partners in the energy domain.
Roberto joined the EPFL-ETHZ Swiss Data Science Center (SDSC) in September 2021 as a Principal Data Scientist with the mission of accompanying industries, the public sector, and NGOs through their data science journey.

Show less

Real-time estimates of Swiss electricity savings using streamed smart meter data

A. Mari; C. Remlinger; R. Castello; M. Galus; G. Obozinski et al.

Applied Energy. 2025. DOI : 10.1016/j.apenergy.2024.124537.

Roberto Castello

Expertise

Real-time estimates of Swiss electricity savings using streamed smart meter data

Explainable machine learning prediction of edema adverse events in patients treated with tepotinib

Impact of the COVID-19 pandemic on the energy performance of residential neighborhoods and their occupancy behavior

Large-scale evaluation of the suitability of buildings for photovoltaic integration: Case study in Greater Geneva

Using Machine Learning to estimate the technical potential of shallow ground-source heat pumps with thermal interference

Dimensionality reduction and clustering of time series for anomaly detection in a supermarket heating system

Quantification of the suitable rooftop area for solar panel installation from overhead imagery using Convolutional Neural Networks

Quantification of existing rooftop PV hourly generation capacity and validation against measurement data

A machine learning-assisted building electricity consumption profiling for anomaly detection

Detecting solar rooftop photovoltaic panels in aerial images using neural networks: a transfer learning approach

Big data mining for the estimation of hourly rooftop photovoltaic potential and its uncertainty

Spatio-Temporal Relationship between Land Cover and Land Surface Temperature in Urban Areas: A Case Study in Geneva and Paris

A fast machine learning model for large-scale estimation of annual solar irradiation on rooftops

Wind profile prediction in an urban canyon: a machine learning approach

Deep learning in the built environment: automatic detection of rooftop solar panels using Convolutional Neural Networks

Geospatial analysis and optimization of the incoming and stored CO2 emissions within the EPFL campus

Topology classification with deep learning to improve real-time event selection at the LHC

Spatio-temporal modelling and uncertainty estimation of hourly global solar irradiance using Extreme Learning Machines

From a Vegetation Index to a Sustainable Development Goal Indicator: Forest Trend Monitoring Using Three Decades of Earth Observations across Switzerland