Directory of Experts
Back to search results

Research project title

Characterizing open loop geothermal systems with artificial intelligence and geophysics

Education level

Master or doctorate


Director: Gabriel Fabien-Ouellet

End of display

November 9, 2022

Areas of expertise


Mining and mineral processing


Artificial intelligence

Earth science

Geothermal energy


Unit(s) and department(s)

Department of Civil, Geological and Mining Engineering


Applicants from physics, computer sciences, applied mathematics or earth sciences are favored, but anyone interested in the topic is encouraged to apply.

Detailed description

Open loop geothermal systems have the potential to significantly reduce heating and air-conditioning costs. Geothermal systems use the ground, and more precisely the aquifer, as a heat reservoir. Thus, the aquifer intrinsic properties, most notably its heat and hydraulic conductivity, affect directly the energy that can be stored and extracted from the ground. The spatial variability of those properties is particularly important, as it can greatly influence water and heat flow. Therefore, characterizing the spatial variability of aquifers at the geothermal scale is necessary for designing and exploiting such systems, and would help to better understand the interaction between adjacent geothermal wells.


This PhD or master’s project aims to develop an approach for characterizing open loop geothermal systems based on artificial intelligence and geophysical monitoring. New characterization tools are needed to address important issues, such as: what are the flow patterns of water and heat around injection wells, do preferential pathways exist and what are their impacts on heat flow? Answering those questions is challenging both scientifically and technically, and requires a multidisciplinary effort. Consequently, the characterization approach will include different field measurements: seismic, electrical and radar cross-well tomography, as well as thermal and pumping tests. Fieldwork will take place at the experimental site of Varennes and at the demonstration site of the NSERC Industrial Chair in Geothermal Energy for Geothermal Standing Column Wells in Industrial Buildings. The integration of geophysical and thermal data will be based on deep learning: deep neural networks will be trained to detect permeable horizons from seismic and electrical surveys. Training will be based on coupled simulations of ground water flow, heat exchange and electrical resistivity measurements. The new insights obtained from methodological developments and their application in real-world conditions will advance the design, the exploitation and the environmental impact assessment of geothermal systems.

Financing possibility

Financial support is provided for the duration of the project

Gabriel Fabien-Ouellet

Gabriel Fabien-Ouellet

Assistant Professor

Main profile