Multimodel ensemble analysis with neural network Gaussian processes

DOI10.1214/23-AOAS1768MaRDI QIDQ6138650zbMATH OpenOpenAlexFDO

Authors Bo Li, Ryan Sriver

Publication date 16 January 2024

Published in The Annals of Applied Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2202.04152

zbMATH Keywords

deep learningGaussian process regressionclimate model integrationmultimodel ensembles

Mathematics Subject Classification ID

Applications of statistics (62Pxx)

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${}^{c}irc$/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.

Cites work

• Bayesian modeling of uncertainty in ensembles of climate models
• Climate projections using Bayesian model averaging and space-time dependence
• Deep learning
• Deep learning: a Bayesian perspective
• Exploiting strength, discounting weakness: combining information from multiple climate simulators
• Gaussian processes for machine learning.
• Improving predictive inference under covariate shift by weighting the log-likelihood function
• Information rates of nonparametric Gaussian process methods
• Modeling Nonstationarity in Space and Time
• Modeling nonstationary processes through dimension expansion
• On constraining projections of future climate using observations and simulations from multiple climate models
• Probabilistic Forecasts, Calibration and Sharpness
• Second-Order Exchangeability Analysis for Multimodel Ensembles
• Strictly Proper Scoring Rules, Prediction, and Estimation

This page was built for publication: Multimodel ensemble analysis with neural network Gaussian processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6138650)