Résumé
Due to its sensitivity to topographic and land use land cover features, air temperature (maximum, minimum, and mean-Tx, Tn, and Tmean) is extremely variable in space and time. The sparse and unevenly distributed meteorological stations observed across remote regions cannot monitor such variability. Freely available, gridded temperature datasets (T-datasets) are positioned as an opportunity to overcome this issue. Still, their coarse spatial resolution (i.e., >= 5 km) does not allow for the observation of air temperature variations on a fine spatial scale. In this context, a set of variables that have a close relationship with daily air temperature (MODIS maximum, minimum, and mean Land Surface Temperature-LSTx, LSTn, and LSTmean; MODIS NDVI; SRTM topographic features-elevation, slope, and aspect) are integrated in three regression machine-learning models (Random Forest-RF, eXtreme Gradient Boosting-XGB, Multiple Linear Regression-MLR) to propose a T-dataset estimates (Tx, Tn, and Tmean) spatial resolution downscaling framework. The approach consists of two main steps: firstly, the machine-learning models are trained at the native 5 km spatial resolution of the studied T-dataset (i.e., CHIRTS); secondly, the application of the trained machine-learning models at a 1 km spatial resolution to downscale CHIRTS from 5 km to 1 km. The results show that the method not only improves the spatial resolution of the CHIRTS dataset, but also its accuracy, with higher improvements for Tn than for Tx and Tmean. Among the considered models, RF performs the best, with an R2, RMSE, and MAE improvement of 2.6% (0%), 47.1% (6.1%), and 55.3% (7%) for Tn (Tx). These results will support air temperature monitoring and related extreme events such as heat and cold waves, which are of prime importance in the actual climate change context.