A Differentiable Framework for Global Circulation Model Precipitation Bias Correction
For climate scientists and regional planners, this provides a physically informed, scalable, and computationally efficient bias correction method that addresses limitations of traditional statistical and black-box machine learning approaches.
The paper introduces δCLIMBA, a differentiable framework for bias correction of Global Circulation Model precipitation outputs, which learns spatiotemporally adaptive parametric adjustments. It accurately corrects extreme storm events and reproduces quantile distributions across U.S. cities, with performance comparable to LOCA2, while preserving future trends and reducing biases in unseen regions.
Systematic biases in Global Circulation Model (GCM) outputs limit their direct applicability in regional planning, necessitating bias correction. Correcting precipitation is particularly challenging due to its non-Gaussian distribution, intermittent nature, and non-linear extremes. However, traditional statistical methods cannot learn from big data and easily address systematic biases in the GCMs, and while machine learning does provide this flexibility, their black-box type functionality hinders us from understanding these biases completely which also further prevents generalization across different GCMs and locations, especially for precipitation. In this study, we propose a differentiable bias adjustment framework called δCLIMBA (or dCLIMBA), that learns a spatiotemporally adaptive parametric bias adjustment procedure between historical CMIP6 model outputs and reference reanalysis datasets (Livneh). Results demonstrate that the proposed method accurately corrects both the magnitude and distribution of extreme storm events, with particularly strong performance in capturing extremes. The quantile distribution of precipitation is well reproduced across diverse U.S. cities, and spatial patterns perform comparably to the widely used LOCA2 statistical downscaling technique. In addition, the framework showed future trend preservation unlike pure quantile based methods and LOCA2; and results from bias correction over unseen regions showed that the marginal biases were attenuated. This work presents a modular, computationally efficient and extensible bias correction approach that is physically informed, scalable, and compatible with both historical and future applications. Its flexibility makes it suitable for integration into Earth system post-processing pipelines and impact workflows.