In this paper, we investigated performance indicators of the climate model ICON (ICOsahedral Nonhydrostatic) on different compute architectures to answer the question of how to generate high-resolution climate simulations. Evidently, it is not enough to use more computing units of the conventionally used architectures; higher memory throughput is the most promising approach. More potential can be gained from single-node optimization rather than simply increasing the number of compute nodes.

We compared spatiotemporal forecasts of three machine learning models that learned water and energy
states on the land surface from a physical model scheme. The forecasting models were developed with reanalysis data and simulations on a European scale and transferred to the globe. We found that all approaches deliver highly accurate approximations of the physical dynamic at long time horizons, implying their usefulness to advance land surface forecasting with synthetic data. 

In this work, we develop two automated workflows for identifying fold structures on geological maps using machine learning. In one method, we identify map patterns suggestive of folding based on pre-defined rules and apply a clustering algorithm to group those from the same fold together. In the other, we train a convolutional neural network to identify folds based on a set of training examples. We apply both methods to a set of synthetic maps and to real-world maps from two locations in France.

A metrics package designed for easy analysis of atmospheric river (AR) characteristics and statistics is presented. The tool is efficient for diagnosing systematic AR bias in climate models and useful for evaluating new AR characteristics in model simulations. In climate models, landfalling AR precipitation shows dry biases globally, and AR tracks are farther poleward (equatorward) in the North and South Atlantic (South Pacific and Indian Ocean).

Many biogeochemistry models assume all material reaching the seafloor is remineralized and returned to solution, which is sufficient for studies on short-term climate change. Under long-term climate change, the carbon storage in sediments slows down carbon cycling and influences feedbacks in the atmosphere–ocean–sediment system. This paper describes the coupling of a sediment model to an ocean biogeochemistry model and presents results under the pre-industrial climate and under CO₂ perturbation.