Abstract

Global climate change leads to distinct regional impacts. Future climate projections are available through global model outputs but they lack the spatial detail needed to inform local decision making for adaptation. Regional-and local-scale climate information can be generated by "downscaling" these global model outputs through regional climate model simulations which require enormous supercomputing resources thereby limiting the availability of local-scale projections especially in underdeveloped regions. Here, we build and test four different computationally-efficient machine learning models as an alternative to regional climate models for downscaling daily temperature data over India. We progressively improve our model design by utilising spatial learning and then including temporal learning and optimising the target region for downscaling. We systematically evaluate all the four models and select the best variant to project daily temperatures over India for 2030. We present seasonal maps, frequency distributions as well as city-specific time-series of daily temperatures for the downscaled data visa -vis the original global model data. We find a slight overall increase in the annual averaged downscaled temperatures (0.29 o C) and an even larger increase in the most frequent (modal) temperature (1.05 o C) but also a decrease over certain regions, particularly in the Indo-Gangetic plain, in summer and monsoon as compared to the coarse-scale temperatures in the global model data. Our machine learning model compares favourably with reference data from the ERA5 reanalyses and runs much faster, with much lesser computational resources than a typical physics-based regional climate model and therefore opens up the possibility of democratising the field of climate downscaling.