Hybrid statistical–dynamical approaches have emerged as a promising avenue to improve our understanding of the climate system and to better simulate and predict its variability on multiple timescales. They combine the strengths of dynamical and statistical models, preserving the physical consistency of numerical models, while benefiting from statistical and data-driven methodologies to address key model deficiencies (e.g., low signal-to-noise ratio, biases in spatio-temporal variability, unresolved sub-grid processes, and limited resolution) and mitigate computational costs.

This session aims to bring together the latest advances in the hybrid approaches to (i) improve our understanding and ability to simulate the climate system and its variability, (ii) enhance climate predictions on multiple timescales, and (iii) translate these advances into more reliable climate services for diverse users (e.g., health, energy, agriculture, water).

With these objectives in mind, we welcome contributions on, but not limited to: subsampling and filtering strategies to enhance predictions of climate variability and extremes on different timescales (including process-constrained projections); advanced machine learning (ML) and causal discovery techniques for validation, bias-correction and downscaling of dynamical model outputs; hybrid multimodel ensemble approaches to improve climate model simulations; transfer learning to leverage climate model outputs and expand ML training datasets; physics-informed ML parametrization of sub-grid processes; hybrid surrogate models that emulate or correct specific components of dynamical models; and impact/service oriented studies that deploy hybrid pipelines to support decision-making, such as hybrid seasonal forecasts and early warning systems based on ML or causal discovery techniques.