Creating Air Temperature Models for High-Elevation Desert Areas Using Machine Learning

The standard way to measure the air temperature (Ta) as the key variable in climate change studies is at 2m height above the surface at a fixed location (weather station). In contrast, the surface temperature (Ts) can be measured by satellites over large areas. Estimation of Ta from Ts is one potential way of overcoming shortages due to uneven or irregular distributions of weather stations. However, whether this is successful has not been assessed in high-elevation regions. This is particularly important in high-elevation regions. In this study, we estimate Ta in the high-elevation desert zone of Kilimanjaro (>4500m) using four models (five models including the benchmark model) with unique sets of inputs using five machine learning (ML) algorithms. Note that different combinations of Ta and Ts were tested as inputs to evaluate the potential of Ts as a proxy for Ta. The Root Mean Square Error (RMSE) for each model was compared with a benchmark model and ranked according to their RMSE. Similarly, models and algorithms were ranked in terms of reliability and consistency. Correspondingly, results were compared with the benchmark model. Three models out of four outperformed the benchmark model in the consistency ranking, while two out of four models outperformed the benchmark model in the reliability ranking. Therefore, ML algorithms are efficient tools for estimating Ta from Ts in this high-elevation desert environment. However, models using Ts only as inputs were not as accurate as models that used Ta from an earlier time period as one of the inputs. This highlights the amount of de-coupling between Ta and TS at high elevations, which provides a challenge for using Ts alone as a proxy for Ta in this zone