# Earth System Modeling 2.0: A Blueprint for Models That Learn From Observations and Targeted High-Resolution Simulations Source: [Earth System Modeling 2.0: A Blueprint for Models That Learn From Observations and Targeted High-Resolution Simulations]() Collection index: [llms.txt]() Data updated: 2025-10-24T22:14:41.429Z Authors: Tapio Schneider, Shiwei Lan, Andrew Stuart, Jo\\~ao Teixeira Published: 2017-08-31T18:45:40.000Z ## Abstract Climate projections continue to be marred by large uncertainties, which originate in processes that need to be parameterized, such as clouds, convection, and ecosystems. But rapid progress is now within reach. New computational tools and methods from data assimilation and machine learning make it possible to integrate global observations and local high-resolution simulations in an Earth system model (ESM) that systematically learns from both. Here we propose a blueprint for such an ESM. We outline how parameterization schemes can learn from global observations and targeted high-resolution simulations, for example, of clouds and convection, through matching low-order statistics between ESMs, observations, and high-resolution simulations. We illustrate learning algorithms for ESMs with a simple dynamical system that shares characteristics of the climate system; and we discuss the opportunities the proposed framework presents and the challenges that remain to realize it. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Parameter Estimation on Kuramoto-Sivashinsky Equation (KSE) (test)](): Parameter Estimation; Kuramoto-Sivashinsky Equation (KSE) (test); MAPE (lambda\_2): 0.3473. - [Uncertainty Quantification on Kuramoto-Sivashinsky (KS) equation 100 instances (test)](): Uncertainty Quantification; Kuramoto-Sivashinsky (KS) equation 100 instances (test); CRPS (λ\_s): 1.14. - [Parameter Estimation on Multiscale Lorenz-96 (test)](): Parameter Estimation; Multiscale Lorenz-96 (test); Mean AP Error (F): 15.48. - [Continuous Ranked Probability Score (CRPS) Estimation on Lorenz-96 200 samples (test)](): Continuous Ranked Probability Score (CRPS) Estimation; Lorenz-96 200 samples (test); CRPS Component F: 0.91. ## Original sources and implementation [Original paper]() [PDF]()