Spatiotemporal Gaussian Process Regression Advances Early Detection of Precipitation Emergence

Detecting long-term precipitation trends is difficult because internal variability often obscures externally forced signals. Conventional methods, such as multimodel ensemble means (MMM), often suppress regional signals and overestimate future uncertainties. Here, we develop and compare Bayesian frameworks based on Gaussian Process Regression (GPR) that predict precipitation anomalies by combining observational records with priors derived from Coupled Model Intercomparison Project Phase 6 (CMIP6) Global Climate Models (GCMs). We test three variants: a univariate GPR (UGPR) using only temporal covariances, a circulation-aware GPR (CGPR) incorporating circulation variability, and a spatio-temporal GPR (SGPR) that exploits spatial and temporal covariances. Using leave-one-out cross-validation across 33 CMIP6 models conditioned on data up to 2020, we compare the predictive skill, uncertainty reduction, and signal emergence characteristics of all four approaches. All three GPR frameworks substantially outperform the CMIP6 MMM, reducing global predictive errors by approximately 60% and narrowing uncertainty by about 12%, with broadly comparable global-mean performance among the GPR methods. Differences between GPR variants emerge primarily at regional scales. In particular, SGPR advances the detection of forced precipitation changes by up to 15 years relative to UGPR in regions including the Middle East, northwestern Africa, Eastern Europe, Japan, and parts of South America, while CGPR yields more limited and regionally heterogeneous improvements. These results demonstrate that while Bayesian GPR methods generally provide robust improvements over conventional ensemble approaches, explicitly accounting for spatiotemporal covariances enhances the timing and spatial extent of precipitation signal emergence in selected regions. Our findings highlight the importance of regional covariance structure for early detection and underscore the value of flexible Bayesian frameworks for dynamically integrating observations into climate change detection and prediction.