Adjusting spatial dependence of climate model outputs with Cycle-Consistent Adversarial Networks&amp;#160;

Bastien François,Mathieu Vrac,Soulivanh Thao

doi:10.5194/egusphere-egu21-8357

Abstract

&lt;p&gt;Climate model outputs are commonly corrected using statistical univariate bias correction methods. Most of the time, those 1d-corrections do not modify the ranks of the time series to be corrected. This implies that biases in the spatial or inter-variable dependences of the simulated variables are not adjusted. Hence, over the last few years, some multivariate bias correction (MBC) methods have been developed to account for inter-variable structures, inter-site ones, or both. As proof-of-concept, we propose to adapt&amp;#160; a computer vision technique used for Image-to-Image translation tasks (CycleGAN) for the adjustment of spatial dependence structures of climate model projections. The proposed algorithm, named MBC-CycleGAN, aims to transfer simulated maps (seen as images) with inappropriate spatial dependence structure from climate model outputs to more realistic images with spatial properties similar to the observed ones. For evaluation purposes, the method is applied to adjust maps of temperature and precipitation from climate simulations through two cross-validation approaches. The first one is designed to assess two different post-processing schemes (Perfect Prognosis and Model Output Statistics). The second one assesses the influence of non-stationary properties of climate simulations on the performance of MBC-CycleGAN to adjust spatial dependences. Results are compared against a popular univariate bias correction method, a &quot;quantile-mapping&quot; method, which ignores inter-site dependencies in the correction procedure, and two state-of-the-art multivariate bias correction algorithms aiming to adjust spatial correlation structure. In comparison with these alternatives, the MBC-CycleGAN algorithm reasonably corrects spatial correlations of climate simulations for both temperature and precipitation, encouraging further research on the improvement of this approach for multivariate bias correction of climate model projections.&lt;/p&gt;

Highlights

With ongoing climate change, mitigation and adaptation strategies have to be anticipated by decision makers in order to reduce potential future consequences of climate change on human societies and activities (IPCC 2014)
We took advantage of this first cross-validation method to compare two postprocessing schemes (PP and model output statistics (MOS)) approaches that differ in the statistical relationships the multivariate bias correction (MBC)-CycleGAN model learns to adjust spatial dependences
The MOS approach that considers biases to refer to systematic distributional differences between references and simulated climate variables was found to be more appropriate for the implementation of the MBC-CycleGAN method and was chosen to be applied for the rest of the study

Summary

Introduction

Mitigation and adaptation strategies have to be anticipated by decision makers in order to reduce potential future consequences of climate change on human societies and activities (IPCC 2014). In the MOS approach, observed and simulated variables are not considered to be synchronized in time, and biases relate to differences in some statistics (such as means or variances) or in distributions between references and modeled climate variables. Potential biases in the spatial dependence structure of modeled variables are not corrected (e.g., Wilcke et al 2013), which can generate corrections with inappropriate multivariate situations and can affect subsequent analyses that depend on spatial characteristics of climate variables (e.g., Zscheischler et al 2019) This can occur with flood risk assessment, that depends on spatial (and temporal) properties of precipitation, soil moisture and river flow (Vorogushyn et al 2018) or with drought-related impacts, that depend on complex interaction of natural and anthropogenic processes (Van Loon et al 2016). It is crucial to provide end users with bias corrections of climate simulations that present relevant 1-dimensional information at each individual site and appropriate spatial representation

Methods

Results

Discussion

Conclusion