Spatially Adaptive Ensemble Learning with Calibrated Predictive Uncertainty

Abstract

Air pollution exposure assessment often uses ensembles of spatio-temporal models, but a critical limitation is that conventional methods use deterministic weights and fail to quantify the uncertainty of their predictions. This yields suboptimal results and prevents the assessment of prediction reliability in health effects studies. We developed a new $\text{Bayesian nonparametric ensemble framework}$ that addresses these issues. Our method employs a dependent random measure to adaptively combine models based on their performance in specific feature sub-regions. It also nonparametrically models the ensemble's predictive cumulative density function (CDF), providing a data-consistent measure of uncertainty. We show that our method is asymptotically consistent and improves predictive accuracy for complex data distributions. The framework is demonstrated on simulated data and applied to generate a spatial prediction model for fine particle ($P{M}_{2.5}$) levels in Eastern New England, USA.

References in corpus (2)

• Adaptive Bayesian estimation using a Gaussian random field with inverse Gamma bandwidth
• Estimating Uncertainty Online Against an Adversary