Reliability of gridded temperature datasets to monitor surface air temperature variability over Bolivia

Six gridded temperature datasets (T-datasets) were evaluated for the first time over the South American continent, through the case study of Bolivia, by comparing them with temperature records acquired from 82 meteorological stations spanning the 1995-2010 period. The comparisons were carried out at the daily time step considering different seasons (annual scale, austral summer and austral winter) and regions (Amazon, La Plata and Altiplano basins). Overall, the climate hazards group infrared temperature with stations (CHIRTS) and the climate prediction centre (CPC) T-datasets provided the most reliable mean daily temperature (T-mean) and also described well the temporal variability of minimum and maximum daily temperature estimates (T-n and T-x). T-mean, T-n and T-x trends were analysed over the 1983-2016 period to observe temperature temporal evolution across the three regions. Despite some general agreements between the trends (T-mean, T-x and T-n), large discrepancies are also observed. It was found that CPC overestimates and CHIRTS underestimates mean temperature trends and that CPC (CHIRTS) was better than CHIRTS (CPC) to estimate T-x (T-n) trends, both in magnitude and space. Furthermore, opposing trends (i.e., warming and cooling) are described by CPC and CHIRTS for some specific regions, which call into question their reliability for such analyses. These findings highlight the need to validate gridded temperature products with reliable ground data for the regions under study, particularly if they have a wide elevation range.