Special issue  

Modelling potential natural biome distribution is one of the most classical issues in biogeoscience. This study shows how accurate models can be constructed without simplifying climate data by employing machine-learning techniques. While extreme climate data enhance predictions, their inclusion can significantly reduce model reliability. With the convolutional neural network algorithm emerging as the preferred choice, this research paves the way for more robust global-scale biome predictions.

In this study, ecosystem COS fluxes data were employed to optimize GPP estimation across various ecosystems with the Boreal Ecosystem Productivity Simulator (BEPS), which was further developed for simulating the leaf COS uptake under its state-of-the-art ‘two-leaf’ framework. our results showcased the efficacy of COS in enhancing model prediction and reducing prediction uncertainty of GPP, and deepened insights into the sensitivity, identifiability, and interactions of parameters related to COS.

We assess the representation of the plant' response to surface water in a global atmospheric chemistry model. This sensitivity is crucial for the return of precipitation back to the atmosphere and thus significantly impacts the representation of weather as well as air quality. The newly implemented response function reduces this process towards a better comparison with satellite observations. This yields a higher intensity of unusual warm periods and a higher production of air pollutants.