Understanding the complex interplay of atmospheric processes is one of the biggest challenges in climate science. A new study, co-authored by our colleague Fernando Iglesias-Suarez, brings forward promising advances in this direction by using machine learning (ML) to represent uncertainty in atmospheric processes — a critical yet often overlooked element in climate modeling.
The study, “Simulating Atmospheric Processes in Earth System Models and Quantifying Uncertainties With Deep Learning Multi‐Member and Stochastic Parameterizations” (Behrens et al., 2025), introduces novel ML approaches to better represent processes like convection and turbulence, which occur at scales too small to be resolved by conventional climate models.
Why Stochasticity Matters in Climate Models
Most current ML-driven climate model components provide deterministic predictions — that is, a single output for a given input. However, many atmospheric processes are inherently stochastic, meaning they can behave differently even under similar conditions. Ignoring this randomness limits the realism and accuracy of simulations.
To address this, the authors developed and tested stochastic ML-based parameterizations, allowing the model to generate a range of plausible outcomes rather than a single prediction. This ensemble approach improves both the representation of physical processes and the quantification of uncertainty — crucial for robust climate projections.
Three Paths to Smarter ML Parameterizations
The team explored three different ways to introduce stochasticity (see Fig. 1):
1. Monte Carlo Dropout – Adding noise during inference to simulate uncertainty.
2. Multi-member Ensembles – Using multiple independently trained neural networks to capture a range of predictions.
3. Latent Space Perturbations – Leveraging a variational encoder-decoder to introduce controlled randomness in the model’s internal representations.
Among these, the multi-member ensemble approach showed particularly promising results in capturing the complex behavior of atmospheric convection and improved the simulation of tropical extreme precipitation.
Testing in the Real World (or as Close as it Gets)
The researchers embedded these new parameterizations in a state-of-the-art climate model using a so-called “superparameterization” framework. While full model integration remains challenging — with some hybrid simulations crashing early — a partial coupling strategy enabled stable runs over several months. Importantly, this still allowed for significant improvements in specific areas, such as the global precipitation diurnal cycle (Fig. 2), compared to traditional schemes.
Our Commitment to Climate Innovation
At Predictia, this kind of work resonates strongly with our mission: translating cutting-edge scientific advances into practical, usable weather and climate solutions. By incorporating AI models that don’t just predict—but also represent uncertainty in those predictions—we’re one step closer to making climate information more reliable and actionable.
Stochastic AI parameterizations are a step toward a new generation of Earth system models that better reflect the chaotic nature of the atmosphere. This is not only a scientific achievement but also a meaningful contribution to more trustworthy climate services for decision-makers.
Should you need more information, don’t hesitate to contact us at predictia@predictia.es.