Multi-model Ensemble Analysis with Neural Network Gaussian Processes

TL;DR

This paper introduces NN-GPR, a neural network Gaussian process regression method that improves multi-model climate ensemble analysis by preserving spatial details and accurately quantifying uncertainty without needing model rescaling or interpolation.

Contribution

The paper presents NN-GPR, a novel statistical approach that automatically downscales climate model outputs and enhances spatial detail preservation in ensemble projections.

Findings

NN-GPR outperforms traditional methods in surface temperature and precipitation forecasting.

It provides better uncertainty quantification in high-variability regions.

NN-GPR rivals regional climate models using only global model data.

Abstract

Multi-model ensemble analysis integrates information from multiple climate models into a unified projection. However, existing integration approaches based on model averaging can dilute fine-scale spatial information and incur bias from rescaling low-resolution climate models. We propose a statistical approach, called NN-GPR, using Gaussian process regression (GPR) with an infinitely wide deep neural network based covariance function. NN-GPR requires no assumptions about the relationships between models, no interpolation to a common grid, no stationarity assumptions, and automatically downscales as part of its prediction algorithm. Model experiments show that NN-GPR can be highly skillful at surface temperature and precipitation forecasting by preserving geospatial signals at multiple scales and capturing inter-annual variability. Our projections particularly show improved accuracy and uncertainty quantification skill in regions of high variability, which allows us to cheaply assess tail behavior at a 0.44$^\circ$/50 km spatial resolution without a regional climate model (RCM). Evaluations on reanalysis data and SSP245 forced climate models show that NN-GPR produces similar, overall climatologies to the model ensemble while better capturing fine scale spatial patterns. Finally, we compare NN-GPR's regional predictions against two RCMs and show that NN-GPR can rival the performance of RCMs using only global model data as input.