Abstract
The multi-model ensemble approach is generally considered as the best way to explore the advantage and to avoid the weakness of each individual model, and ultimately to achieve the best climate projection. But the design of an optimal strategy and its practical implementation still constitutes a challenge. Here we use the random forest (RF) algorithm (from the category of machine learning) to explore the information offered by the multi-model ensemble simulations within the Coupled Model Intercomparison Project Phase 6. Our objective is to achieve a more reliable climate projection (mean climate and extremes) over China. RF is furthermore compared to two other ensemble-processing strategies of different nature, one is the basic arithmetic mean (AM), and another is the linear regression across the ensemble members. Our results indicate that RF effectively enhances the capability in capturing spatial climate characteristics. Regions with complex topography, such as the Tibetan Plateau and its periphery, show the most significant improvements. RF projects less future warming but enhanced wet conditions across China. It also produces larger spatial variability and more small-scale features. The most obvious increase of precipitation is in the northern part and the periphery of the Tibetan Plateau. The projected changes in RF for strong precipitation are almost twice higher than in AM, while in the northwestern area, weaker increases of precipitation are projected by RF, which indicates larger spatial inhomogeneity of its projection.
Highlights
Global warming has altered the mean and extreme climate in many regions of the world, and this warming trend will undoubtedly continue (Hulme 2016)
To assess the ability of our three schemes dealing with the multi-model ensemble simulations, the spatial patterns and corresponding distribution boxplots for biases of all indices against observations across China during the validation period are examined
Compared with arithmetic mean (AM), biases from linear regression (LR) and Random Forest (RF) are reduced across almost the whole domain
Summary
Global warming has altered the mean and extreme climate in many regions of the world, and this warming trend will undoubtedly continue (Hulme 2016). More complex statistical methods such as the Bayesian methods (Robertson et al 2004; Tan et al 2016) or weighted averages, which consider the simulation skills and model inter-dependence, have been developed (Xu et al 2010; Jiang et al 2015; Knutti et al 2017; Brunner et al 2020). These methods allow tuning particular parameters or weights and constraining uncertainties with historical observations. Most of these strategies or methods, rely on the concept of linear regression based on some specific relationships or indices, potentially neglecting useful information
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
