An ensemble approach to downscale climatological variables via screening of clustered ANNs

ABSTRACT The statistical downscaling of global circulation models presents a significant challenge in selecting appropriate input variables from a vast pool of predictors. To address the issue, we developed ensemble approach based on the Combining Multiple Clusters via Similarity Graph (COMUSA), which integrates k-means and self-organizing maps (SOMs) methods with the mutual information (MI)-random sampling approach. This innovative feature extraction technique demonstrated a 21% improvement in the classification efficacy of large-scale climatic variables. When comparing feature extraction methods, the combination of MI-random sampling and ensemble clustering yielded more accurate results than SOM clustering alone. The most efficient artificial neural networks (ANNs)-based downscaling model was employed to project near- and mid-future precipitation and temperature (2025–2035, 2035–2045), revealing varied outcomes under different scenarios (SSP3-7.0 and SSP5-8.5). Under SSP3-7.0 and SSP5-8.5, annual mean precipitation values are projected to decrease by 2–3 and by 4–5%. Also, projected annual mean temperature values indicate an increase in 21-27 and 29-35% under SSP3-7.0 and SSP5-8.5 scenarios. Integrating COMUSA ensemble clustering with MI-random sampling enhances the estimation accuracy of the ANN downscaling model, contributing to accurate projections of future precipitation and temperature values.