The thermal subsystem of the Mars Express (MEX) orbiter keeps the on-board equipment within its predefined operating temperatures range. To plan and optimize the scientific operations of MEX, its operators need to estimate in advance, as accurately as possible, the power consumption of the thermal subsystem. The residual power can then be allocated for scientific purposes. We present a machine learning-based pipeline for the prediction of MEX’s thermal power consumption. We show that the proposed pipeline is superior in accuracy to the models currently used by MEX’s operators. We also demonstrate that machine learning can provide the operators with insight about the orbiter’s thermal behavior. Better understanding of the thermal subsystem and improved predictive accuracy of the thermal power consumption could help operators to improve science return and to prolong the operating life of MEX