In this work we study the potentialities of machine learning models in reconstructing the solar wind speed observations gathered in the first Lagrangian point by the ACE satellite in 2016–2017. We leverage a supervised model trained with the ACE observations and the galactic cosmic-ray flux variation data measured with particle detectors hosted on board the LISA Pathfinder mission also orbiting around L1 during the same years. Missing data in galactic cosmic-ray time series have been filled with the benefit of other machine learning models developed in previous work. The model presented here will be used for the European Space Agency Laser Interferometer Space Antenna (LISA) after its launch in 2035 to estimate the solar wind speed, that will not be measured on board, with the only benefit of galactic cosmic-ray variation measurements. We show that ensemble models composed of heterogeneous weak regressors are able to outperform weak regressors in terms of predictive accuracy. Machine learning and other powerful predictive algorithms open a window on the possibility of substituting dedicated instrumentation with software models acting as surrogates for diagnostics of space missions such as the LISA mission and space weather science.