GloUTCI-M: a global monthly 1 km Universal Thermal Climate Index dataset from 2000 to 2022

Abstract

Abstract. Climate change has precipitated recurrent extreme events and emerged as an imposing global challenge, exerting profound and far-reaching impacts on both the environment and human existence. The Universal Thermal Climate Index (UTCI), serving as an important approach to human comfort assessment, plays a pivotal role in gauging how humans adapt to meteorological conditions and copes with thermal and cold stress. However, the existing UTCI datasets still grapple with limitations in terms of data availability, hindering their effective application across diverse domains. We have produced GloUTCI-M, a monthly UTCI dataset boasting global coverage and an extensive time series spanning March 2000 to October 2022, with a high spatial resolution of 1 km. This dataset is the product of a comprehensive approach leveraging multiple data sources and advanced machine learning models. Our findings underscored the superior predictive capabilities of CatBoost in forecasting the UTCI (mean absolute error, MAE = 0.747 °C; root mean square error, RMSE = 0.943 °C; and coefficient of determination, R2=0.994) when compared to machine learning models such as XGBoost and LightGBM. Utilizing GloUTCI-M, the geographical boundaries of cold stress and thermal stress areas at global scale were effectively delineated. Spanning 2001–2021, the mean annual global UTCI was recorded at 17.24 °C, with a pronounced upward trend. Countries like Russia and Brazil emerged as key contributors to the mean annual global UTCI increasing, while countries like China and India exerted a more inhibitory influence on this trend. Furthermore, in contrast to existing UTCI datasets, GloUTCI-M excelled at portraying UTCI distribution at finer spatial resolutions, augmenting data accuracy. This dataset can enhance our capacity to evaluate thermal stress experienced by humans, offering substantial prospects across a wide array of applications. GloUTCI-M is publicly available at https://doi.org/10.5281/zenodo.8310513 (Yang et al., 2023).